System

Abstract

A system is provided.SOLUTION: A system, comprising: means for users to send a request to initiate a consultation via terminals; means for a server to receive the request and send a request to a generative AI model to generate an initial greeting message; means for the generative AI model to generate the initial greeting message based on the request; and means for displaying the initial greeting message on the terminals of the users.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] When operating mentoring programs within companies, problems such as inappropriate matching, unclear roles, lack of resources, and insufficient feedback exist, hindering employee growth and motivation. Furthermore, while many employees want to seek advice on new projects or daily work, there are not always experts available to respond appropriately, and communication between employees can be difficult. Given these circumstances, there is a need to provide an environment where employees can easily receive advice and support at any time, but new technological solutions are needed to achieve this. [Means for solving the problem]

[0005] The present invention aims to solve the above problem by providing a system that includes a means for a user to send a request to start a consultation via a terminal, a means for a server to receive the request and send a request to a generative AI model to generate an initial greeting message, a means for the generative AI model to generate the initial greeting message based on the request, and a means for displaying the initial greeting message on the user's terminal.

[0006] Furthermore, the present invention includes a means for a user to input consulting details, a means for the server to send the input to the generative AI model and a request to generate an appropriate response, a means for the generative AI model to generate a response based on the request, and a means for displaying the response on the user's terminal. This creates an environment where employees can easily consult at any time, enabling efficient responses.

[0007] The present invention also includes a means for a user to send a request for goal setting consultation, a means for a server to send the request to a generative AI model and send a request to generate questions about goal setting, a means for the generative AI model to generate questions about goal setting based on the request, a means for displaying the questions on the user's terminal, a means for the user to input information to answer the questions, a means for the server to receive the input and send it to the generative AI model, a means for the generative AI model to generate an outline of goal setting based on the input, and a means for displaying the outline on the user's terminal. This allows employees to clarify their own goal setting and efficiently manage their progress toward those goals.

[0008] By taking the above measures, it is possible to resolve various issues associated with mentoring systems and provide a new environment that supports employee growth and efficient work performance.

[0009] "User" refers to an individual or user who uses the Buddy AI system via a terminal to seek advice or set goals.

[0010] A "terminal" is an electronic device such as a PC or smartphone that a user uses to access the Buddy AI system and input and receive information.

[0011] The "server" is a computer that plays a central role in the Buddy AI system, receiving and sending requests, managing the database, and coordinating with the generative AI model.

[0012] A "generative AI model" is an artificial intelligence model that generates appropriate responses to user requests based on machine learning algorithms.

[0013] A "request" is information requested by a user via their terminal to the Buddy AI system, such as for consultation, goal setting, or progress report.

[0014] The "initial greeting message" is the first message generated by the generative AI model when a user starts a consultation, guiding the user to the start of the consultation and encouraging them to ask questions.

[0015] "Consulting content" refers to the specific matters or questions that the user would like to discuss with the Buddy AI system.

[0016] A "response" is an answer or advice that the generative AI model generates based on the user's consulting content.

[0017] "Goal setting" is the process by which users clarify the goals they want to achieve with the Buddy AI system.

[0018] "Questions" are questions generated by the generative AI model to assist users in setting goals, with the aim of clarifying the goals.

[0019] An "outline" is a goal-setting summary or plan that the generative AI model generates based on the answers it receives from the user.

[0020] "Feedback" refers to advice and evaluations provided by the generative AI model based on the user's progress and reports, including progress management and improvement suggestions. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] This invention provides a system called "Buddy AI" that uses generative AI to solve the problems of in-house mentoring programs. This system allows users to start a consultation via their device, and the server uses a generative AI model to provide appropriate responses and feedback, creating an environment where users can easily receive consultation and support at any time.

[0043] The system configuration of the present invention is as follows.

[0044] 1. User Registration

[0045] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration.

[0046] 2. Starting a consultation

[0047] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device. For example, a message such as "Hello! What would you like to consult about today?" is displayed.

[0048] 3. Dialogue Progress

[0049] The user inputs and sends the inquiry. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the device. For example, in response to a question such as, "I'm having trouble managing the schedule for a new project. Do you have any advice?" the generative AI model provides specific advice.

[0050] 4. Goal setting and progress management

[0051] When a user requests a consultation on goal setting, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. The generative AI model creates an outline for goal setting, and the server displays it on the device. For example, the model might provide content such as, "To efficiently manage the schedule of a new project, we propose the following plan..."

[0052] 5. Providing Feedback

[0053] The user enters progress updates on the device. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, which the server displays on the device. For example, feedback might be provided such as, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[0054] 6. Usage history learning and personalization

[0055] The server periodically sends the user's usage history to the generative AI model as learning data. The generative AI model learns from that data and provides the user with more personalized feedback. For example, personalized feedback such as "Based on your past consultation history, we will narrow down and suggest important points for schedule management for your new project..." is provided.

[0056] In this way, this invention is a system that uses generative AI to provide an environment where employees can easily consult and receive feedback at any time, solving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] The user accesses the Buddy AI system website via their device and opens the registration page.

[0060] Step 2:

[0061] The user enters the required information (name, email address, job title, department, etc.) into the registration form.

[0062] Step 3:

[0063] The user clicks the "Register" button and submits the registration information.

[0064] Step 4:

[0065] The server receives the user's input and stores it in a database.

[0066] Step 5:

[0067] The server will send the user an email notifying them of the completion of registration.

[0068] Step 6:

[0069] The user logs into the Buddy AI system from their device and goes to the dashboard screen.

[0070] Step 7:

[0071] The user clicks the "Start Consultation" button.

[0072] Step 8:

[0073] The server receives the user's consultation request and sends a request to the generative AI model to start a session.

[0074] Step 9:

[0075] The generative AI model creates an initial greeting message and returns it to the server.

[0076] Step 10:

[0077] The server displays an initial greeting message on the user's terminal.

[0078] For example: "Hello! What would you like to discuss today?"

[0079] Step 11:

[0080] The user enters the consultation content in the chat box and clicks the "Send" button.

[0081] Step 12:

[0082] The server receives user input and sends it to the generative AI model.

[0083] Step 13:

[0084] The generative AI model generates a response based on the user's inquiry.

[0085] Step 14:

[0086] The server receives the generated response and displays it on the user's terminal.

[0087] Step 15:

[0088] If the user wishes to continue the dialogue or set a goal, they input a request for goal setting.

[0089] Step 16:

[0090] The server sends a goal setting request to the generative AI model.

[0091] Step 17:

[0092] The generative AI model generates questions to assist with goal setting and returns them to the server.

[0093] Step 18:

[0094] The server displays the generated question on the user's terminal.

[0095] Step 19:

[0096] The user answers the question and submits the answer in the chat box.

[0097] Step 20:

[0098] The server receives the user's answers and sends them to the generative AI model.

[0099] Step 21:

[0100] A generative AI model generates a goal setting outline based on the user's answers.

[0101] Step 22:

[0102] The server displays the generated outline on the user's terminal.

[0103] Step 23:

[0104] After setting a goal, if the user wishes to report progress, they can enter and submit updated information from their device.

[0105] Step 24:

[0106] The server receives the user's updated information and stores it in a database.

[0107] Step 25:

[0108] The server sends updates to the generative AI model.

[0109] Step 26:

[0110] The generative AI model generates feedback based on the updated information and returns it to the server.

[0111] Step 27:

[0112] The server displays the generated feedback on the user's terminal.

[0113] Step 28:

[0114] The server periodically generates the user's usage history and sends it to the AI ​​model as learning data.

[0115] Step 29:

[0116] A generative AI model learns from users' usage history and generates increasingly personalized feedback.

[0117] Step 30:

[0118] The server displays the personalized feedback on the user's terminal.

[0119] In this way, users can use "Buddy AI" to receive individual consultations, set goals, monitor progress, and receive feedback.

[0120] Example 1

[0121] 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."

[0122] Traditional in-company mentoring systems have many restrictions on the timing and content of consultations, making it difficult to receive appropriate feedback quickly. Furthermore, some employees may become overly reliant on specific mentors, making it difficult to receive personalized advice. This can lead to ineffective goal setting and progress management for employees, hindering work efficiency and growth.

[0123] 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.

[0124] In this invention, the server includes a means for a user to send a request to start a consultation via a terminal, a means for sending a request to the generative AI model to generate an initial greeting message, and a means for the generative AI model to receive a request to start a session including the user's basic information. This enables the generative AI model to provide specific advice based on the user's input. The generative AI model also generates a response based on user information stored in a database, allowing for more personalized feedback to the user. This provides an environment where employees can easily receive consultation and support at any time, enabling effective goal setting and progress management.

[0125] "User" refers to an individual who uses the system to receive consultation and feedback.

[0126] "Terminal" refers to a device, such as a PC or smartphone, that a user uses to access the system.

[0127] A "request" refers to an action or request made by a user to a server.

[0128] "Server" refers to a computer that receives a user's request, communicates with a generative AI model to generate an appropriate response, and returns it to the user.

[0129] A "generative AI model" refers to software that uses artificial intelligence to generate appropriate responses to user input.

[0130] "Initial greeting message" refers to a message containing a welcome message or question that a generative AI model generates during its first interaction with a user.

[0131] A "session" refers to a series of interactions between a user and a generative AI model.

[0132] "Personalized feedback" refers to tailored feedback provided based on a user's past usage history and specific needs.

[0133] "Response" refers to the reply or advice that a generative AI model generates based on a user's request.

[0134] "Goal setting" refers to the process of defining the objectives or goals that users want to achieve.

[0135] "Progress management" refers to the process of monitoring a user's progress toward achieving their goals and providing appropriate advice or corrections.

[0136] This invention provides a system called "Buddy AI" that uses a generative AI model to solve the problems of in-house mentoring programs. This system allows users to start a consultation via their device, and the server uses a generative AI model to provide appropriate responses and feedback, creating an environment where users can easily receive consultation and support at any time.

[0137] System Configuration

[0138] 1. User Registration

[0139] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration. Specifically, the user enters information such as name, email address, and department into the registration form, and the server stores that information in a database.

[0140] 2. Starting a consultation

[0141] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device. For example, a message such as "Hello! What would you like to consult about today?" is displayed.

[0142] 3. Dialogue Progress

[0143] The user inputs and submits the content of their inquiry. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the device. For example, if a user asks, "I'm having trouble managing the schedule for a new project. Do you have any advice?" the generative AI model will provide specific advice.

[0144] 4. Goal setting and progress management

[0145] When a user requests a consultation on goal setting, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. For example, the service might provide content such as, "To efficiently manage the schedule of a new project, we propose the following plan..."

[0146] 5. Providing Feedback

[0147] The user enters progress updates on the device. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, which the server displays on the device. For example, the feedback might be, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[0148] 6. Usage history learning and personalization

[0149] The server periodically sends the user's usage history to the generative AI model as learning data. The generative AI model learns from that data and provides the user with more personalized feedback. For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest important points for schedule management for your new project..." is provided.

[0150] In this way, the present invention is a system that uses a generative AI model to provide an environment where employees can easily consult with or receive feedback at any time, thereby resolving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[0151] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0152] Step 1:

[0153] A user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information in the new registration form. The input data includes name, email address, department, etc. This data is sent to the server. Specifically, the user opens a browser, enters the system's URL, enters the required information in the form, and clicks the submit button.

[0154] Step 2:

[0155] The server receives the user's input information and saves the data in a database. The received data includes the user name, email address, department, etc., and performs data validation to ensure that it is saved accurately in the database. As a concrete example, the server issues an insert query to the database and saves the data. If the save is successful, the result is confirmed.

[0156] Step 3:

[0157] The server sends the user an email to notify them that registration is complete. The email contains a message informing them that registration is complete and instructions for the next step. The server uses the user's email address as input data and uses the email sending API to send a confirmation email for registration completion.

[0158] Step 4:

[0159] A user logs in to the system from a terminal. An email address and password are required as input data. The server uses this input data to authenticate the user, and if authentication is successful, the dashboard screen is displayed on the terminal. Specifically, the user opens the login page in a browser, enters their email address and password, and clicks the login button.

[0160] Step 5:

[0161] The user clicks the "Start Consultation" button. The server sends a session start request to the generative AI model, including the user's basic information. The user's basic information is used as input data, and an initial greeting message is generated as output. The generative AI model receives this request and generates a prompt message such as "Hello! What would you like to consult about today?", which is then displayed on the device.

[0162] Step 6:

[0163] The user inputs and sends the consultation content. The input data is the consulting content, such as "I'm having trouble managing the schedule of a new project. Do you have any advice?" The server receives this input data, sends it to the generative AI model, and generates an appropriate response. The generative AI model creates an answer based on the user's input and generates advice as output data. The generated response is displayed on the device.

[0164] Step 7:

[0165] A user requests advice on goal setting. The server sends the request to the generative AI model. The input data is the user's request regarding their goal. The generative AI model generates a question to clarify the user's goal, and the server displays the question on the device. Specifically, the generative AI model generates the question, "What kind of goal do you want to set?"

[0166] Step 8:

[0167] The user answers questions, and the server saves the answers and sends them to the generative AI model. The input data are the answers about the user's goals. The server saves the data in a database, and the generative AI model receives the data and creates an outline for goal setting. Once the outline is generated, the server displays it on the user's device. For example, an outline such as "We propose the following plan to efficiently manage the schedule of a new project..." may be displayed.

[0168] Step 9:

[0169] The user inputs progress updates on their device. The input data includes their current progress and achievements. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, and the server displays the feedback on the device. For example, the feedback might read, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[0170] Step 10:

[0171] The server periodically sends the user's usage history to the generative AI model as learning data. The input data includes past consultation details and progress data. The generative AI model learns from this data and provides personalized feedback to the user. The output data is feedback tailored to the user's specific needs. For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest key points for schedule management for your new project..." is generated.

[0172] (Application example 1)

[0173] 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."

[0174] Currently, factories lack an environment where workers can receive real-time advice on robot and machine operation. As a result, there are problems with efficient work flows and machine maintenance. There is also a lack of systems that effectively support goal setting and progress management, which is a factor that reduces production efficiency. Therefore, it is necessary to provide an environment where real-time support and consultation can be provided between robots and machines and workers on factory floors.

[0175] 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.

[0176] In this invention, the server includes a means for a user to send a request to start a consultation via a terminal, a means for the server to receive the request and send a request to the generative AI model to generate an initial greeting message, a means for the generative AI model to generate the initial greeting message based on the request, a means for displaying the initial greeting message on the user's terminal, a means for sending a request for assistance with physical work, a means for generating a work procedure based on the request, and a means for displaying the work procedure on the user's terminal. This enables workers to receive real-time assistance and consultation regarding the operation and maintenance of robots and machines. It also enhances support for goal setting and progress management.

[0177] A "user" is a person who starts a consultation via a terminal and uses the functions provided by the system.

[0178] A "terminal" is an electronic device used by a user to access the system, including a PC or smartphone.

[0179] A "server" is a central computer that manages the entire system and receives and processes various requests.

[0180] A "generative AI model" is an artificial intelligence technology that generates initial greeting messages, responses, goal setting outlines, and more based on user requests.

[0181] A "request" is an operation request or consultation content that a user sends to a server via a terminal.

[0182] The "initial greeting message" is the greeting that the generative AI model first generates upon receiving a user request.

[0183] "Consulting content" refers to the specific consultation matters and questions that users ask about through the system.

[0184] A "response" is a reply or advice generated by the generative AI model based on the consulting content.

[0185] "Goal setting" is the process of clarifying the specific goals that users want to achieve.

[0186] "Progress" refers to the status or report of how far you have progressed toward your goal.

[0187] "Feedback" is advice and suggestions for improvement generated by the generative AI model based on its progress.

[0188] A "work procedure" is a specific work procedure or manual that a generative AI model generates to assist with physical work.

[0189] In a system embodying this invention, a "Robo Buddy AI" is installed in a robot working in a factory, and real-time support and consultation is provided between the factory worker and the robot. Specific embodiments are described below.

[0190] Hardware and Software

[0191] 1. Hardware:

[0192] Factory robot control terminals (PCs, smartphones, etc.)

[0193] Server equipment (a central computer for database and AI model processing)

[0194] 2. Software:

[0195] Python

[0196] Flask

[0197] OpenAI API (generative AI model)

[0198] System Operation

[0199] 1. User Registration

[0200] The user accesses the system via a terminal and applies for registration by entering the required information in the new registration form. The server receives this information and stores it in a database. The server then sends the user a notification that registration is complete. With this operation, the user is ready to begin consultations and support.

[0201] 2. Starting a consultation

[0202] The user logs in to the system from their device and clicks the "Start Consultation" button. The server sends the consultation request to the AI ​​model and generates an initial greeting message. The initial greeting message might be something like "Hello! What would you like to consult about today?"

[0203] 3. Dialogue Progress

[0204] The user inputs the content of their inquiry and sends it to the server. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the user's device. For example, if a user inputs, "Please tell me how to maintain this machine," the generative AI model generates detailed instructions such as, "To maintain this machine, follow these steps..."

[0205] 4. Goal setting and progress management

[0206] When a user requests a consultation on goal setting, the server sends the request to the generative AI model, which then generates a question about goal setting. The server displays the question on the user's device, and the user answers by entering information. The server then sends the input to the generative AI model, which generates an outline of goal setting. This operation allows the user to clarify their goals and effectively manage their progress.

[0207] 5. Providing Feedback

[0208] When a user inputs progress updates on their device, the server stores the updates in a database and sends them to the generative AI model, which generates feedback based on the updates and displays it on the user's device, allowing them to receive specific advice on next steps.

[0209] Specific prompt examples

[0210] Example 1:

[0211] User: How do I maintain this machine?

[0212] Buddy AI:

[0213] Example 2:

[0214] User: I'm having trouble managing the schedule for a new project. Any advice?

[0215] Buddy AI:

[0216] In this way, RoboBuddy AI can be applied to factory robots, enabling real-time support and consultation between workers and robots, improving work efficiency and maintenance quality.

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

[0218] Step 1:

[0219] The user accesses the system via a terminal and applies for registration by entering the required information in the new registration form. The input data includes the user's personal information and authentication information. The server receives this information and stores it in a database. The server then sends a notification to the user that registration is complete. Based on the input, the user information is stored in the database and a registration completion notification is generated.

[0220] Step 2:

[0221] The user logs in to the system from their device and clicks the "Start Consultation" button. The server sends the consultation request to the generation AI model and requests it to generate an initial greeting message. The generation AI model receives the request and generates the initial greeting message. The initial greeting message is chosen to be something like "Hello! What would you like to consult about today?" The server displays the generated greeting message on the user's device. The initial greeting message is generated based on the request and displayed on the user's device.

[0222] Step 3:

[0223] The user inputs the consultation content and sends it to the server. For example, "Please tell me how to maintain this machine." The server sends the input content to the generative AI model and sends a request to generate an appropriate response. The generative AI model receives the consulting request and generates a response based on the content. A response such as "The maintenance of this machine will be carried out using the following steps..." is generated. The server displays the generated response on the user's device. Based on the input of the consultation content, specific operating procedures are generated and displayed on the user's device.

[0224] Step 4:

[0225] When a user wishes to consult about goal setting, they send a dedicated request. The server sends the goal setting request to the generative AI model, which then sends a request to generate a question related to goal setting. The generative AI model receives the request and generates a question related to goal setting. The question might be something like, "What should you aim for in order to efficiently manage the schedule of a new project?" This is then displayed on the user's device. The user enters information to answer the question and sends it to the server. The input is sent to the generative AI model, which generates a goal setting outline. The outline is generated and displayed on the user's device. Specific goal setting questions and their outlines are generated based on the input and displayed on the user's device.

[0226] Step 5:

[0227] The user inputs update information from their device to report their progress and sends it to the server. The server stores this update information in a database and sends it to the generative AI model. The generative AI model generates feedback based on the update information. Feedback such as "Thank you for reporting on your progress last week. To keep up the good work, let's focus on the following task as your next step..." is generated. The server displays the generated feedback on the user's device. Specific feedback is generated based on the progress input and displayed on the user's device.

[0228] 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.

[0229] This invention provides a system called "Buddy AI" that combines generative AI and an emotion engine to solve the challenges of in-company mentoring programs. With this system, users start consultations via their devices, and the server uses a generative AI model to provide appropriate responses and feedback. Furthermore, the emotion engine recognizes the user's emotions and provides personalized responses based on these, creating an environment where users can easily receive consultations and support at any time.

[0230] The system configuration of the present invention is as follows.

[0231] 1. User Registration

[0232] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration.

[0233] 2. Starting a consultation

[0234] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device.

[0235] For example, a message might say, "Hello! What would you like to talk about today?"

[0236] 3. Dialogue Progress

[0237] The user inputs and submits the consultation content. The server sends the input content to the emotion engine, which analyzes the text entered by the user and generates emotion data. The emotion data includes information about the user's emotional state (joy, sadness, anger, etc.).

[0238] 4. Use of Emotional Data

[0239] The server sends the emotional data and the content of the consultation to the generative AI model, which then generates a response based on this information. The response is tailored to take into account the user's emotional state.

[0240] For example, if a user inputs, "I'm having trouble managing the schedule for a new project," and the emotional data indicates "stress," the generative AI model will generate a response such as, "Project management is certainly difficult, but if you take it one step at a time, you can definitely achieve it. Let's think together about the next step."

[0241] 5. Providing a Response

[0242] The server receives the generated response and displays it on the user's terminal. The user can continue the dialogue or, if they wish to set a goal, enter a request for goal setting.

[0243] 6. Goal setting and progress management

[0244] When a user requests a goal setting consultation, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. The generative AI model creates a goal setting outline, which the server displays on the device.

[0245] For example, you might receive something like, "We propose the following plan to efficiently manage the schedule of your new project..."

[0246] 7. Providing Feedback

[0247] The user inputs update information from the device to report progress. The server stores the update information in a database and sends it to the emotion engine. The emotion engine analyzes the update information and generates emotion data. The server sends the emotion data and update information to the generative AI model, which then generates feedback based on it and the server displays it on the device.

[0248] For example, feedback might be provided such as, "Thank you for your progress report last week. To keep up, let's focus on the following tasks as next steps..."

[0249] 8. Usage learning and personalization

[0250] The server periodically sends the user's usage history to the generative AI model and emotion engine as learning data, which the generative AI model and emotion engine then use to learn from the data and provide the user with more personalized feedback.

[0251] For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest key points for schedule management for your new project..." is provided.

[0252] In this way, this invention is a system that uses generative AI and an emotion engine to provide an environment where employees can easily consult with or receive feedback at any time, solving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[0253] The processing flow will be explained below.

[0254] Step 1:

[0255] The user accesses the Buddy AI system website via their device and opens the new registration page.

[0256] Step 2:

[0257] The user enters the required information (name, email address, job title, department, etc.) into the registration form.

[0258] Step 3:

[0259] The user clicks the "Register" button and submits the registration information.

[0260] Step 4:

[0261] The server receives the user's registration information and stores it in a database.

[0262] Step 5:

[0263] The server will send the user an email notifying them of the completion of registration.

[0264] Step 6:

[0265] The user logs into the Buddy AI system from their device and goes to the dashboard screen.

[0266] Step 7:

[0267] The user clicks the "Start Consultation" button.

[0268] Step 8:

[0269] The server receives the user's consultation request and sends a request to the generative AI model to start a session.

[0270] Step 9:

[0271] The generative AI model creates an initial greeting message and returns it to the server.

[0272] For example, "Hello! What would you like to discuss today?"

[0273] Step 10:

[0274] The server displays an initial greeting message on the user's terminal.

[0275] Step 11:

[0276] The user enters the consultation content in the chat box and clicks the "Send" button.

[0277] Step 12:

[0278] The server receives the user's input and sends it to the emotion engine.

[0279] Step 13:

[0280] The emotion engine analyzes the user's input text and generates emotion data.

[0281] Example: Detecting emotions such as "stress" or "anxiety" from text.

[0282] Step 14:

[0283] The server sends the user's consultation details, including emotional data, to the generative AI model.

[0284] Step 15:

[0285] A generative AI model generates a response based on emotional data and the content of the consultation.

[0286] For example: "Project management can be challenging, but it can be achieved if you take it one step at a time. Let's figure out next steps together."

[0287] Step 16:

[0288] The server receives the generated response and displays it on the user's terminal.

[0289] Step 17:

[0290] If the user wishes to continue the dialogue or set a goal, they input a request for goal setting.

[0291] Step 18:

[0292] The server sends a goal setting request to the generative AI model.

[0293] Step 19:

[0294] The generative AI model generates questions to clarify the user's goals and returns them to the server.

[0295] Step 20:

[0296] The server displays the generated question on the user's terminal.

[0297] Step 21:

[0298] The user answers the question and submits the answer in the chat box.

[0299] Step 22:

[0300] The server receives the user's answers and sends them to the generative AI model.

[0301] Step 23:

[0302] A generative AI model generates a goal setting outline based on the user's answers.

[0303] Step 24:

[0304] The server displays the generated outline on the user's terminal.

[0305] For example: "To efficiently manage the schedule for the new project, we propose the following plan..."

[0306] Step 25:

[0307] After setting a goal, if the user wishes to report progress, they can enter and submit updated information from their device.

[0308] Step 26:

[0309] The server receives the user's updated information and stores it in a database.

[0310] Step 27:

[0311] The server sends updates to the emotion engine.

[0312] Step 28:

[0313] The emotion engine analyzes the updated information and generates emotion data.

[0314] Step 29:

[0315] The server sends the emotion data and updates to the generative AI model.

[0316] Step 30:

[0317] A generative AI model generates feedback based on emotional data and updates.

[0318] Step 31:

[0319] The server displays the generated feedback on the user's terminal.

[0320] For example: "Thank you for your progress report last week. To keep up, let's focus on these next tasks..."

[0321] Step 32:

[0322] The server periodically generates user usage history and sends it to the AI ​​model and emotion engine as learning data.

[0323] Step 33:

[0324] Generative AI models and emotion engines learn from usage history and generate personalized feedback.

[0325] Step 34:

[0326] The server displays the personalized feedback on the user's terminal.

[0327] Example: "Based on past consultation history, we will narrow down and propose key points for schedule management for the new project..."

[0328] In this way, users can use "Buddy AI" to receive individual consultations, goal setting, progress management, and feedback. Furthermore, by combining it with an emotion engine, the system can provide personalized responses that take into account the user's emotional state, resolving various issues in mentoring programs.

[0329] Example 2

[0330] 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."

[0331] Traditional mentoring systems have struggled to provide personalized feedback and consultation to individual employees, particularly in providing emotional support and appropriate responses in a timely manner. This can lead to a risk of lowering employee motivation and efficiency, potentially negatively impacting corporate performance. Furthermore, it has been difficult to balance consistency and individual attention when it comes to employee progress management and goal setting.

[0332] 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.

[0333] In this invention, the server includes: means for the user to send a request to start a consultation via a terminal; means for the server to receive the request and send a request to the generative AI model to generate an initial greeting message; means for the generative AI model to generate the initial greeting message based on the request; means for the server to display the initial greeting message on the user's terminal; means for the server to send the user's input to the emotion engine and send a request to generate emotion data; means for the emotion engine to generate emotion data based on the request; means for the server to send the emotion data and the user's input to the generative AI model and send a request to generate a response; means for the generative AI model to generate a response based on the request and taking the emotion data into consideration; means for displaying the response on the user's terminal; means for periodically sending the user's usage history to the generative AI model and the emotion engine as learning data and using it for personalization; means for the server to store the user's progress in a database, send update information to the emotion engine to generate emotion data, and means for generating a response based on the emotion data and displaying it on the user's terminal. This enables personalized responses and feedback to be provided to individual employees, improving employee motivation and efficiency and contributing to improved corporate performance.

[0334] "User" refers to an individual who uses the system to provide consultation and feedback.

[0335] A "terminal" is a device used by a user to access the system, including a PC, smartphone, etc.

[0336] "Request" refers to a command or request for information sent by a user or system to a generative AI model or emotion engine.

[0337] A "server" is a computer system that is the central part of the system and manages data storage, processing, and communication with other components.

[0338] A "generative AI model" refers to an artificial intelligence model that uses natural language processing techniques to generate appropriate responses or feedback in response to user input.

[0339] An "initial greeting message" refers to the first message sent by the generative AI model when a user begins a consultation.

[0340] "Emotion engine" refers to a technology or system that analyzes and generates emotional data from user text input.

[0341] "Emotion data" refers to data indicating an emotional state (e.g., joy, sadness, anger, etc.) extracted from a user's text input.

[0342] "Response" refers to the message that the generative AI model generates based on user input and emotional data.

[0343] "Usage history" refers to past consultation details and feedback generated while a user is using the system.

[0344] "Training Data" refers to the datasets used by generative AI models and emotion engines to improve their performance.

[0345] "Progress" refers to information about how a user is progressing toward achieving a goal.

[0346] "Updates" refers to new information entered by a user to report progress or make changes.

[0347] This invention provides a system called "Buddy AI" that supports in-company mentoring programs by combining a generative AI model and an emotion engine. The system allows users to initiate consultations through their devices, and the server provides appropriate responses and feedback. It also uses the emotion engine to recognize the user's emotions and delivers personalized responses based on those emotions.

[0348] Hardware and software used

[0349] Terminal: A device such as a PC or smartphone through which a user accesses the system.

[0350] Server: The central computer system of the system that stores and processes data and manages communication with other components.

[0351] Generative AI model: An artificial intelligence model that uses natural language processing techniques to generate appropriate responses and feedback in response to user input, such as OpenAI's GPT-3.

[0352] Emotion engine: Technology that analyzes and generates emotional data from user input text, such as Microsoft's Text Analytics.

[0353] Database: A data storage device such as MySQL for managing user information, progress, consultation details, etc.

[0354] System processing overview

[0355] 1. User Registration

[0356] The user opens a web browser on their device (PC or smartphone) and accesses the specified URL. They enter the required information (name, email address, password, etc.) into the new registration form and submit their registration request. The server receives this information and stores it in a database. The server then sends an email notifying the user that registration is complete.

[0357] 2. Starting a consultation

[0358] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request containing the user's ID and session information to the generative AI model. The generative AI model generates an initial greeting message (e.g., "Hello! What would you like to consult about today?") and displays it on the user's device via the server.

[0359] 3. Dialogue Progress

[0360] The user inputs and submits the content of their consultation. The server sends this input text to the emotion engine, which generates emotion data. The emotion engine analyzes the user's emotional state and returns the generated emotion data to the server. The server then sends the emotion data and the content of their consultation to the generative AI model, which then generates a response that takes the emotion data into account. The response is returned to the server in JSON format, and the server displays it on the device.

[0361] Specific examples

[0362] For example, when a user consults about schedule management for a new project, the following dialogue takes place:

[0363] User: "I'm having trouble managing the schedule for my new project."

[0364] The emotion engine generates "stress" emotion data.

[0365] Generative AI model: "Project management is hard, but it's achievable if you take it one step at a time. Let's figure out the next steps together."

[0366] Next, if the user requests a goal setting consultation, the server sends the request to the generative AI model.

[0367] Generative AI model: "To set your goal, what do you want to achieve first?"

[0368] Once the user enters their answer, the generative AI model creates an outline, which the server displays on the device.

[0369] Through these steps, the system of the present invention provides personalized assistance to users and solves the challenges of mentoring within a company.

[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0371] Step 1:

[0372] The user accesses the "Buddy AI" system via a terminal and applies for registration by entering the necessary information into the new registration form.

[0373] Input: User information (name, email address, password, etc.)

[0374] and output: Registration completion notification email

[0375] Specific operation: The user opens a web browser, accesses the specified URL, enters the required information in the registration form, and clicks the "Register" button.

[0376] The server receives this information and stores it in a database.

[0377] Input: User registration information

[0378] Output: User information stored in the database, email notifying registration completion

[0379] Specific operation: The server receives the form data, stores it in a database such as MySQL, and then sends an email to notify the user that registration has been completed using the SMTP protocol.

[0380] Step 2:

[0381] The user logs in from the terminal and clicks the "Start Consultation" button.

[0382] Input: Login information (email address, password)

[0383] Output: Show initial greeting message

[0384] Specific operation: The user accesses the login page, enters their email address and password, and clicks the "Login" button. After logging in, they click the "Start Consultation" button from the menu.

[0385] The server sends a request to the generative AI model, including the user's ID and session information.

[0386] Input: User ID, session information

[0387] Output: An initial greeting message from the generative AI model

[0388] Specific operation: The server constructs session information and sends a request to the generative AI model using an API. The generative AI model generates an initial greeting message (e.g., "Hello! What would you like to discuss today?") and displays it on the device via the server.

[0389] Step 3:

[0390] The user inputs the consultation content and sends it.

[0391] Input: Text of consultation content

[0392] Output: Emotion data, response from generative AI model

[0393] Specific operation: The user enters the content of the consultation into the chat window and clicks the "Send" button.

[0394] The server sends the input content to the emotion engine, which generates emotion data.

[0395] Input: User's inquiry

[0396] Output: Emotion data

[0397] Specific operation: The server sends the user's consultation content to the emotion engine API, and the emotion engine analyzes the text and generates emotion data (e.g., "joy," "sadness," "anger," etc.).

[0398] The server sends the emotion data and the consultation details to the generative AI model, which generates a response.

[0399] Input: User's consultation details, emotional data

[0400] Output: The response from the generative AI model

[0401] Specific operation: The server sends a request containing emotion data and the consultation content to the generative AI model, which then generates a response that takes the emotion data into account. The server receives the generative AI model's response and displays it on the device.

[0402] Step 4:

[0403] The server receives the generated response and displays it on the user's terminal.

[0404] Input: Response from a generative AI model

[0405] Output: The response displayed on the user's terminal

[0406] Specific operation: The server receives the response from the generative AI model, converts it into HTML format, and displays it in the chat window.

[0407] The user continues the dialogue or inputs their goal setting preference.

[0408] Input: New consultation or goal setting request

[0409] Output: The next response from the generative AI model

[0410] Specific action: The user enters and submits a new consultation, or clicks the "Set Goal" button to submit a request.

[0411] Step 5:

[0412] The server sends the goal setting consultation to the generative AI model.

[0413] Input: Goal setting request

[0414] Output: Goal setting questions

[0415] Specific operation: The server sends a request regarding goal setting to the generative AI model, and the generative AI model generates a question regarding goal setting.

[0416] A generative AI model generates goal-setting questions that are displayed on the device.

[0417] Input: Goal setting request

[0418] Output: Goal setting questions

[0419] Specific behavior: The generative AI model generates questions related to goal setting, and the server displays them on the device (e.g., "What is the first step to achieving your goal?").

[0420] Users enter answers to questions, and the server stores them and sends them to the generative AI model.

[0421] Input: User's answer

[0422] Output: The answer sent to the generative AI model

[0423] What happens: The user answers the goal-setting questions and clicks the "Submit" button. The server stores the answers in a database and sends them to the generative AI model.

[0424] A generative AI model creates an outline of the goal setting, which the server displays on the device.

[0425] Input: User's answer

[0426] Output: Goal setting outline

[0427] How it works: The generative AI model creates an outline of goal setting based on the user's answers (e.g., "A plan for efficiently managing the schedule of a new project"), and the server displays it on the device.

[0428] Step 6:

[0429] The user enters updates to report progress, which the server stores and sends to the emotion engine.

[0430] Input: Progress update

[0431] Output: Emotion data, feedback from generative AI models

[0432] Specific operation: The user enters the progress status in the chat window and clicks the "Send" button. The server saves the progress status in the database and sends it to the emotion engine.

[0433] The emotion engine analyzes the updated information and generates emotion data.

[0434] Input: Progress update

[0435] Output: Emotion data

[0436] Specific behavior: The emotion engine analyzes the progress text and generates emotion data.

[0437] The server sends the emotion data and updates to the generative AI model to generate feedback.

[0438] Input: Emotion data, progress updates

[0439] Output: Feedback

[0440] Specific operation: The generative AI model generates feedback based on emotional data and progress information, and the server displays it on the device (e.g., "Thank you for your progress report last week. To keep up the good work, let's focus on the following tasks as the next step").

[0441] Step 7:

[0442] The server periodically generates usage history and sends it to the AI ​​model and emotion engine as learning data, which is then used for personalization.

[0443] Input: Usage history data

[0444] Output: Personalized responses and feedback

[0445] Specific operation: The server periodically extracts usage history data and sends it to the generative AI model and emotion engine. This enables the generative AI model and emotion engine to provide optimized feedback for each user (e.g., "Based on your past consultation history, we will narrow down and suggest important points for schedule management for a new project").

[0446] (Application example 2)

[0447] 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."

[0448] Conventional in-house mentoring systems lack an environment where employees can easily seek advice, and do not provide sufficient support to individual employees. Furthermore, appropriate responses and feedback to consultations are often delayed, often hindering the improvement of individual employees' performance. The present invention aims to solve these problems and provide an environment where employees can easily seek advice and support at any time.

[0449] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0450] In this invention, the server includes means for a user to send a request to start a consultation via a terminal, means for starting a training program selected by the user and recording progress, means for an emotion engine to recognize the user's emotional state and generate a feedback message based on a generative AI model, and means for analyzing the user's historical data and creating new learning suggestions using the generative AI model and displaying them on the user's terminal. This allows employees to receive continuous personalized feedback, enabling efficient learning and improved performance.

[0451] "User" means an individual who utilizes the System to conduct training programs or consultations.

[0452] A "terminal" is a device, such as a smartphone or head-mounted display, that connects to the system and operates it.

[0453] A "request" is a request or inquiry sent by a user to a system.

[0454] A "server" is a computer system that receives requests and interacts with generative AI models and emotion engines.

[0455] A "generative AI model" is an artificial intelligence model that generates responses or feedback messages based on requests.

[0456] An "initial greeting message" is the first message generated by the generative AI model when a user begins a consultation.

[0457] A "Training Program" is a set of educational content or activities that a user selects for learning or training.

[0458] "Progress" is information that indicates the degree of progress and achievement of the user as he or she progresses through the training program.

[0459] An "emotion engine" is a system that has the ability to analyze user input data and recognize the user's emotional state.

[0460] A "feedback message" is a response message to the user that the generative AI model generates based on the analysis results of the emotion engine.

[0461] "History data" refers to data from when a user has used the system in the past, including learning and consultation history.

[0462] "Learning suggestions" are suggestions for new learning and improvement that the generative AI model creates based on the user's historical data.

[0463] An "outline" is a summary or plan created by a generative AI model related to goal setting.

[0464] This invention provides a system called "Buddy AI" that combines generative AI and an emotion engine to solve the challenges of in-company mentoring programs. With this system, users start consultations via their devices, and the server uses a generative AI model to provide appropriate responses and feedback. Furthermore, the emotion engine recognizes the user's emotions and provides personalized responses based on these, creating an environment where users can easily receive consultations and support at any time.

[0465] Hardware and software used

[0466] Hardware

[0467] Terminal: A device that connects to the system and operates it, such as a smartphone or head-mounted display.

[0468] Server: A computer system that receives requests and interacts with the generative AI model and emotion engine.

[0469] software

[0470] Programming languages: Python, JavaScript

[0471] Frameworks: TensorFlow (generative AI), NLP (natural language processing), Emotion API

[0472] Database: MySQL

[0473] Frontend: React Native

[0474] Natural language processing explanation

[0475] 1. User Registration and Login

[0476] A user accesses the system using a terminal and creates an account by entering the required information in a new registration form.

[0477] This information is sent to the server and stored in a MySQL database, and an authentication token is generated and sent to the user.

[0478] 2. Select and begin a training program

[0479] After logging in, the user can see a list of training programs offered, which are retrieved from a database via a query and displayed on the terminal.

[0480] When the user selects a training program, the server records the selection and triggers the initiation process.

[0481] 3. Progress management and feedback

[0482] During the course of the program, user input data is collected and sent to the server.

[0483] The server sends this data to the emotion engine for sentiment analysis, which generates the analysis results and sends them to the generative AI model.

[0484] Based on the analysis results, the generative AI model generates a feedback message that takes into account the user's emotions and displays it on the device.

[0485] 4. Personalized study suggestions

[0486] The server periodically collects user history data and sends it to the generative AI model.

[0487] The generative AI model analyzes historical data and generates new learning suggestions based on learning progress and emotional state.

[0488] The content of the proposal is sent from the server to the user's terminal and displayed.

[0489] Specific examples

[0490] Suppose the user enters the following prompt text:

[0491] "I'm working on a new program, but progress is slow and it's frustrating."

[0492] "Based on past history, what areas should we pay particular attention to?"

[0493] In response, the generative AI and emotion engine generate a response like this:

[0494] "It's natural to feel like you're making slow progress. Try setting incremental goals like this..."

[0495] "Based on your history, X is an area that requires special attention. The key takeaway here is..."

[0496] In this way, the system allows users to receive continuous personalized feedback, promoting effective learning and growth.

[0497] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0498] Step 1:

[0499] A user accesses the system via a terminal and applies for registration by entering the required information into a new registration form. The input data, including the user name, email address, and password, is sent to the server. The server receives this and stores it in a MySQL database. After registration is complete, the server generates an authentication token and sends it to the user by email.

[0500] Input: User information entered into the registration form

[0501] Output: Save data to database and generate token

[0502] Step 2:

[0503] The user logs in and checks the list of training programs. The login data (email address and password) is entered into the terminal and sent to the server. The server performs authentication, retrieves the user's training program history from the database, and sends it to the terminal. The user checks the list of programs offered and selects one.

[0504] Input: Login information

[0505] Output: Display a list of programs

[0506] Step 3:

[0507] The user selects and starts a training program, the selected program is sent to the server, which records the selection, and the initial content of the training program is then delivered from the server to the terminal.

[0508] Input: Selected training program

[0509] Output: Initial content delivery

[0510] Step 4:

[0511] As the user progresses through the training program, the device collects and transmits data about the user's progress to a server, which stores the data in a database.

[0512] Input: User progress data

[0513] Output: Save to database

[0514] Step 5:

[0515] The server sends the collected progress data to the emotion engine, which analyzes the data, recognizes the user's emotional state, and generates emotion data, which is then sent back to the server.

[0516] Input: Progress data

[0517] Output: Emotion data

[0518] Step 6:

[0519] The server sends emotion data and progress data to the generative AI model and sends a request to generate a feedback message. The generative AI model generates appropriate feedback based on the emotion data and progress data and sends it back to the server.

[0520] Input: Emotion data and progress data

[0521] Output: Feedback message

[0522] Step 7:

[0523] The server sends the generated feedback message to the terminal and displays it to the user, who receives the feedback and continues training.

[0524] Input: Feedback message

[0525] Output: Message displayed on the terminal

[0526] Step 8:

[0527] Periodically, the server collects the user's historical data and sends it to the generative AI model. The generative AI model analyzes the historical data and generates personalized learning suggestions, which are then sent back to the server. The server then sends these suggestions to the user's device for display.

[0528] Input: User history data

[0529] Output: Generate and display learning suggestions

[0530] 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.

[0531] 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.

[0532] 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.

[0533] [Second embodiment]

[0534] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0535] 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.

[0536] 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).

[0537] 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.

[0538] 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.

[0539] 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).

[0540] 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.

[0541] 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.

[0542] 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.

[0543] 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.

[0544] 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.

[0545] 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."

[0546] This invention provides a system called "Buddy AI" that uses generative AI to solve the problems of in-house mentoring programs. This system allows users to start a consultation via their device, and the server uses a generative AI model to provide appropriate responses and feedback, creating an environment where users can easily receive consultation and support at any time.

[0547] The system configuration of the present invention is as follows.

[0548] 1. User Registration

[0549] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration.

[0550] 2. Starting a consultation

[0551] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device. For example, a message such as "Hello! What would you like to consult about today?" is displayed.

[0552] 3. Dialogue Progress

[0553] The user inputs and sends the inquiry. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the device. For example, in response to a question such as, "I'm having trouble managing the schedule for a new project. Do you have any advice?" the generative AI model provides specific advice.

[0554] 4. Goal setting and progress management

[0555] When a user requests a consultation on goal setting, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. The generative AI model creates an outline for goal setting, and the server displays it on the device. For example, the model might provide content such as, "To efficiently manage the schedule of a new project, we propose the following plan..."

[0556] 5. Providing Feedback

[0557] The user enters progress updates on the device. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, which the server displays on the device. For example, feedback might be provided such as, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[0558] 6. Usage history learning and personalization

[0559] The server periodically sends the user's usage history to the generative AI model as learning data. The generative AI model learns from that data and provides the user with more personalized feedback. For example, personalized feedback such as "Based on your past consultation history, we will narrow down and suggest important points for schedule management for your new project..." is provided.

[0560] In this way, this invention is a system that uses generative AI to provide an environment where employees can easily consult and receive feedback at any time, solving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] The user accesses the Buddy AI system website via their device and opens the registration page.

[0564] Step 2:

[0565] The user enters the required information (name, email address, job title, department, etc.) into the registration form.

[0566] Step 3:

[0567] The user clicks the "Register" button and submits the registration information.

[0568] Step 4:

[0569] The server receives the user's input and stores it in a database.

[0570] Step 5:

[0571] The server will send the user an email notifying them of the completion of registration.

[0572] Step 6:

[0573] The user logs into the Buddy AI system from their device and goes to the dashboard screen.

[0574] Step 7:

[0575] The user clicks the "Start Consultation" button.

[0576] Step 8:

[0577] The server receives the user's consultation request and sends a request to the generative AI model to start a session.

[0578] Step 9:

[0579] The generative AI model creates an initial greeting message and returns it to the server.

[0580] Step 10:

[0581] The server displays an initial greeting message on the user's terminal.

[0582] For example: "Hello! What would you like to discuss today?"

[0583] Step 11:

[0584] The user enters the consultation content in the chat box and clicks the "Send" button.

[0585] Step 12:

[0586] The server receives user input and sends it to the generative AI model.

[0587] Step 13:

[0588] The generative AI model generates a response based on the user's inquiry.

[0589] Step 14:

[0590] The server receives the generated response and displays it on the user's terminal.

[0591] Step 15:

[0592] If the user wishes to continue the dialogue or set a goal, they input a request for goal setting.

[0593] Step 16:

[0594] The server sends a goal setting request to the generative AI model.

[0595] Step 17:

[0596] The generative AI model generates questions to assist with goal setting and returns them to the server.

[0597] Step 18:

[0598] The server displays the generated question on the user's terminal.

[0599] Step 19:

[0600] The user answers the question and submits the answer in the chat box.

[0601] Step 20:

[0602] The server receives the user's answers and sends them to the generative AI model.

[0603] Step 21:

[0604] A generative AI model generates a goal setting outline based on the user's answers.

[0605] Step 22:

[0606] The server displays the generated outline on the user's terminal.

[0607] Step 23:

[0608] After setting a goal, if the user wishes to report progress, they can enter and submit updated information from their device.

[0609] Step 24:

[0610] The server receives the user's updated information and stores it in a database.

[0611] Step 25:

[0612] The server sends updates to the generative AI model.

[0613] Step 26:

[0614] The generative AI model generates feedback based on the updated information and returns it to the server.

[0615] Step 27:

[0616] The server displays the generated feedback on the user's terminal.

[0617] Step 28:

[0618] The server periodically generates the user's usage history and sends it to the AI ​​model as learning data.

[0619] Step 29:

[0620] A generative AI model learns from users' usage history and generates increasingly personalized feedback.

[0621] Step 30:

[0622] The server displays the personalized feedback on the user's terminal.

[0623] In this way, users can use "Buddy AI" to receive individual consultations, set goals, monitor progress, and receive feedback.

[0624] Example 1

[0625] 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."

[0626] Traditional in-company mentoring systems have many restrictions on the timing and content of consultations, making it difficult to receive appropriate feedback quickly. Furthermore, some employees may become overly reliant on specific mentors, making it difficult to receive personalized advice. This can lead to ineffective goal setting and progress management for employees, hindering work efficiency and growth.

[0627] 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.

[0628] In this invention, the server includes a means for a user to send a request to start a consultation via a terminal, a means for sending a request to the generative AI model to generate an initial greeting message, and a means for the generative AI model to receive a request to start a session including the user's basic information. This enables the generative AI model to provide specific advice based on the user's input. The generative AI model also generates a response based on user information stored in a database, allowing for more personalized feedback to the user. This provides an environment where employees can easily receive consultation and support at any time, enabling effective goal setting and progress management.

[0629] "User" refers to an individual who uses the system to receive consultation and feedback.

[0630] "Terminal" refers to a device, such as a PC or smartphone, that a user uses to access the system.

[0631] A "request" refers to an action or request made by a user to a server.

[0632] "Server" refers to a computer that receives a user's request, communicates with a generative AI model to generate an appropriate response, and returns it to the user.

[0633] A "generative AI model" refers to software that uses artificial intelligence to generate appropriate responses to user input.

[0634] "Initial greeting message" refers to a message containing a welcome message or question that a generative AI model generates during its first interaction with a user.

[0635] A "session" refers to a series of interactions between a user and a generative AI model.

[0636] "Personalized feedback" refers to tailored feedback provided based on a user's past usage history and specific needs.

[0637] "Response" refers to the reply or advice that a generative AI model generates based on a user's request.

[0638] "Goal setting" refers to the process of defining the objectives or goals that users want to achieve.

[0639] "Progress management" refers to the process of monitoring a user's progress toward achieving their goals and providing appropriate advice or corrections.

[0640] This invention provides a system called "Buddy AI" that uses a generative AI model to solve the problems of in-house mentoring programs. This system allows users to start a consultation via their device, and the server uses a generative AI model to provide appropriate responses and feedback, creating an environment where users can easily receive consultation and support at any time.

[0641] System Configuration

[0642] 1. User Registration

[0643] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration. Specifically, the user enters information such as name, email address, and department into the registration form, and the server stores that information in a database.

[0644] 2. Starting a consultation

[0645] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device. For example, a message such as "Hello! What would you like to consult about today?" is displayed.

[0646] 3. Dialogue Progress

[0647] The user inputs and submits the content of their inquiry. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the device. For example, if a user asks, "I'm having trouble managing the schedule for a new project. Do you have any advice?" the generative AI model will provide specific advice.

[0648] 4. Goal setting and progress management

[0649] When a user requests a consultation on goal setting, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. For example, the service might provide content such as, "To efficiently manage the schedule of a new project, we propose the following plan..."

[0650] 5. Providing Feedback

[0651] The user enters progress updates on the device. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, which the server displays on the device. For example, the feedback might be, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[0652] 6. Usage history learning and personalization

[0653] The server periodically sends the user's usage history to the generative AI model as learning data. The generative AI model learns from that data and provides the user with more personalized feedback. For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest important points for schedule management for your new project..." is provided.

[0654] In this way, the present invention is a system that uses a generative AI model to provide an environment where employees can easily consult with or receive feedback at any time, thereby resolving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

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

[0656] Step 1:

[0657] A user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information in the new registration form. The input data includes name, email address, department, etc. This data is sent to the server. Specifically, the user opens a browser, enters the system's URL, enters the required information in the form, and clicks the submit button.

[0658] Step 2:

[0659] The server receives the user's input information and saves the data in a database. The received data includes the user name, email address, department, etc., and performs data validation to ensure that it is saved accurately in the database. As a concrete example, the server issues an insert query to the database and saves the data. If the save is successful, the result is confirmed.

[0660] Step 3:

[0661] The server sends the user an email to notify them that registration is complete. The email contains a message informing them that registration is complete and instructions for the next step. The server uses the user's email address as input data and uses the email sending API to send a confirmation email for registration completion.

[0662] Step 4:

[0663] A user logs in to the system from a terminal. An email address and password are required as input data. The server uses this input data to authenticate the user, and if authentication is successful, the dashboard screen is displayed on the terminal. Specifically, the user opens the login page in a browser, enters their email address and password, and clicks the login button.

[0664] Step 5:

[0665] The user clicks the "Start Consultation" button. The server sends a session start request to the generative AI model, including the user's basic information. The user's basic information is used as input data, and an initial greeting message is generated as output. The generative AI model receives this request and generates a prompt message such as "Hello! What would you like to consult about today?", which is then displayed on the device.

[0666] Step 6:

[0667] The user inputs and sends the consultation content. The input data is the consulting content, such as "I'm having trouble managing the schedule of a new project. Do you have any advice?" The server receives this input data, sends it to the generative AI model, and generates an appropriate response. The generative AI model creates an answer based on the user's input and generates advice as output data. The generated response is displayed on the device.

[0668] Step 7:

[0669] A user requests advice on goal setting. The server sends the request to the generative AI model. The input data is the user's request regarding their goal. The generative AI model generates a question to clarify the user's goal, and the server displays the question on the device. Specifically, the generative AI model generates the question, "What kind of goal do you want to set?"

[0670] Step 8:

[0671] The user answers questions, and the server saves the answers and sends them to the generative AI model. The input data are the answers about the user's goals. The server saves the data in a database, and the generative AI model receives the data and creates an outline for goal setting. Once the outline is generated, the server displays it on the user's device. For example, an outline such as "We propose the following plan to efficiently manage the schedule of a new project..." may be displayed.

[0672] Step 9:

[0673] The user inputs progress updates on their device. The input data includes their current progress and achievements. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, and the server displays the feedback on the device. For example, the feedback might read, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[0674] Step 10:

[0675] The server periodically sends the user's usage history to the generative AI model as learning data. The input data includes past consultation details and progress data. The generative AI model learns from this data and provides personalized feedback to the user. The output data is feedback tailored to the user's specific needs. For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest key points for schedule management for your new project..." is generated.

[0676] (Application example 1)

[0677] 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."

[0678] Currently, factories lack an environment where workers can receive real-time advice on robot and machine operation. As a result, there are problems with efficient work flows and machine maintenance. There is also a lack of systems that effectively support goal setting and progress management, which is a factor that reduces production efficiency. Therefore, it is necessary to provide an environment where real-time support and consultation can be provided between robots and machines and workers on factory floors.

[0679] 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.

[0680] In this invention, the server includes a means for a user to send a request to start a consultation via a terminal, a means for the server to receive the request and send a request to the generative AI model to generate an initial greeting message, a means for the generative AI model to generate the initial greeting message based on the request, a means for displaying the initial greeting message on the user's terminal, a means for sending a request for assistance with physical work, a means for generating a work procedure based on the request, and a means for displaying the work procedure on the user's terminal. This enables workers to receive real-time assistance and consultation regarding the operation and maintenance of robots and machines. It also enhances support for goal setting and progress management.

[0681] A "user" is a person who starts a consultation via a terminal and uses the functions provided by the system.

[0682] A "terminal" is an electronic device used by a user to access the system, including a PC or smartphone.

[0683] A "server" is a central computer that manages the entire system and receives and processes various requests.

[0684] A "generative AI model" is an artificial intelligence technology that generates initial greeting messages, responses, goal setting outlines, and more based on user requests.

[0685] A "request" is an operation request or consultation content that a user sends to a server via a terminal.

[0686] The "initial greeting message" is the greeting that the generative AI model first generates upon receiving a user request.

[0687] "Consulting content" refers to the specific consultation matters and questions that users ask about through the system.

[0688] A "response" is a reply or advice generated by the generative AI model based on the consulting content.

[0689] "Goal setting" is the process of clarifying the specific goals that users want to achieve.

[0690] "Progress" refers to the status or report of how far you have progressed toward your goal.

[0691] "Feedback" is advice and suggestions for improvement generated by the generative AI model based on its progress.

[0692] A "work procedure" is a specific work procedure or manual that a generative AI model generates to assist with physical work.

[0693] In a system embodying this invention, a "Robo Buddy AI" is installed in a robot working in a factory, and real-time support and consultation is provided between the factory worker and the robot. Specific embodiments are described below.

[0694] Hardware and Software

[0695] 1. Hardware:

[0696] Factory robot control terminals (PCs, smartphones, etc.)

[0697] Server equipment (a central computer for database and AI model processing)

[0698] 2. Software:

[0699] Python

[0700] Flask

[0701] OpenAI API (generative AI model)

[0702] System Operation

[0703] 1. User Registration

[0704] The user accesses the system via a terminal and applies for registration by entering the required information in the new registration form. The server receives this information and stores it in a database. The server then sends the user a notification that registration is complete. With this operation, the user is ready to begin consultations and support.

[0705] 2. Starting a consultation

[0706] The user logs in to the system from their device and clicks the "Start Consultation" button. The server sends the consultation request to the AI ​​model and generates an initial greeting message. The initial greeting message might be something like "Hello! What would you like to consult about today?"

[0707] 3. Dialogue Progress

[0708] The user inputs the content of their inquiry and sends it to the server. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the user's device. For example, if a user inputs, "Please tell me how to maintain this machine," the generative AI model generates detailed instructions such as, "To maintain this machine, follow these steps..."

[0709] 4. Goal setting and progress management

[0710] When a user requests a consultation on goal setting, the server sends the request to the generative AI model, which then generates a question about goal setting. The server displays the question on the user's device, and the user answers by entering information. The server then sends the input to the generative AI model, which generates an outline of goal setting. This operation allows the user to clarify their goals and effectively manage their progress.

[0711] 5. Providing Feedback

[0712] When a user inputs progress updates on their device, the server stores the updates in a database and sends them to the generative AI model, which generates feedback based on the updates and displays it on the user's device, allowing them to receive specific advice on next steps.

[0713] Specific prompt examples

[0714] Example 1:

[0715] User: How do I maintain this machine?

[0716] Buddy AI:

[0717] Example 2:

[0718] User: I'm having trouble managing the schedule for a new project. Any advice?

[0719] Buddy AI:

[0720] In this way, RoboBuddy AI can be applied to factory robots, enabling real-time support and consultation between workers and robots, improving work efficiency and maintenance quality.

[0721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0722] Step 1:

[0723] The user accesses the system via a terminal and applies for registration by entering the required information in the new registration form. The input data includes the user's personal information and authentication information. The server receives this information and stores it in a database. The server then sends a notification to the user that registration is complete. Based on the input, the user information is stored in the database and a registration completion notification is generated.

[0724] Step 2:

[0725] The user logs in to the system from their device and clicks the "Start Consultation" button. The server sends the consultation request to the generation AI model and requests it to generate an initial greeting message. The generation AI model receives the request and generates the initial greeting message. The initial greeting message is chosen to be something like "Hello! What would you like to consult about today?" The server displays the generated greeting message on the user's device. The initial greeting message is generated based on the request and displayed on the user's device.

[0726] Step 3:

[0727] The user inputs the consultation content and sends it to the server. For example, "Please tell me how to maintain this machine." The server sends the input content to the generative AI model and sends a request to generate an appropriate response. The generative AI model receives the consulting request and generates a response based on the content. A response such as "The maintenance of this machine will be carried out using the following steps..." is generated. The server displays the generated response on the user's device. Based on the input of the consultation content, specific operating procedures are generated and displayed on the user's device.

[0728] Step 4:

[0729] When a user wishes to consult about goal setting, they send a dedicated request. The server sends the goal setting request to the generative AI model, which then sends a request to generate a question related to goal setting. The generative AI model receives the request and generates a question related to goal setting. The question might be something like, "What should you aim for in order to efficiently manage the schedule of a new project?" This is then displayed on the user's device. The user enters information to answer the question and sends it to the server. The input is sent to the generative AI model, which generates a goal setting outline. The outline is generated and displayed on the user's device. Specific goal setting questions and their outlines are generated based on the input and displayed on the user's device.

[0730] Step 5:

[0731] The user inputs update information from their device to report their progress and sends it to the server. The server stores this update information in a database and sends it to the generative AI model. The generative AI model generates feedback based on the update information. Feedback such as "Thank you for reporting on your progress last week. To keep up the good work, let's focus on the following task as your next step..." is generated. The server displays the generated feedback on the user's device. Specific feedback is generated based on the progress input and displayed on the user's device.

[0732] 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.

[0733] This invention provides a system called "Buddy AI" that combines generative AI and an emotion engine to solve the challenges of in-company mentoring programs. With this system, users start consultations via their devices, and the server uses a generative AI model to provide appropriate responses and feedback. Furthermore, the emotion engine recognizes the user's emotions and provides personalized responses based on these, creating an environment where users can easily receive consultations and support at any time.

[0734] The system configuration of the present invention is as follows.

[0735] 1. User Registration

[0736] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration.

[0737] 2. Starting a consultation

[0738] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device.

[0739] For example, a message might say, "Hello! What would you like to talk about today?"

[0740] 3. Dialogue Progress

[0741] The user inputs and submits the consultation content. The server sends the input content to the emotion engine, which analyzes the text entered by the user and generates emotion data. The emotion data includes information about the user's emotional state (joy, sadness, anger, etc.).

[0742] 4. Use of Emotional Data

[0743] The server sends the emotional data and the content of the consultation to the generative AI model, which then generates a response based on this information. The response is tailored to take into account the user's emotional state.

[0744] For example, if a user inputs, "I'm having trouble managing the schedule for a new project," and the emotional data indicates "stress," the generative AI model will generate a response such as, "Project management is certainly difficult, but if you take it one step at a time, you can definitely achieve it. Let's think together about the next step."

[0745] 5. Providing a Response

[0746] The server receives the generated response and displays it on the user's terminal. The user can continue the dialogue or, if they wish to set a goal, enter a request for goal setting.

[0747] 6. Goal setting and progress management

[0748] When a user requests a goal setting consultation, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. The generative AI model creates a goal setting outline, which the server displays on the device.

[0749] For example, you might receive something like, "We propose the following plan to efficiently manage the schedule of your new project..."

[0750] 7. Providing Feedback

[0751] The user inputs update information from the device to report progress. The server stores the update information in a database and sends it to the emotion engine. The emotion engine analyzes the update information and generates emotion data. The server sends the emotion data and update information to the generative AI model, which then generates feedback based on it and the server displays it on the device.

[0752] For example, feedback might be provided such as, "Thank you for your progress report last week. To keep up, let's focus on the following tasks as next steps..."

[0753] 8. Usage learning and personalization

[0754] The server periodically sends the user's usage history to the generative AI model and emotion engine as learning data, which the generative AI model and emotion engine then use to learn from the data and provide the user with more personalized feedback.

[0755] For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest key points for schedule management for your new project..." is provided.

[0756] In this way, this invention is a system that uses generative AI and an emotion engine to provide an environment where employees can easily consult with or receive feedback at any time, solving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[0757] The processing flow will be explained below.

[0758] Step 1:

[0759] The user accesses the Buddy AI system website via their device and opens the new registration page.

[0760] Step 2:

[0761] The user enters the required information (name, email address, job title, department, etc.) into the registration form.

[0762] Step 3:

[0763] The user clicks the "Register" button and submits the registration information.

[0764] Step 4:

[0765] The server receives the user's registration information and stores it in a database.

[0766] Step 5:

[0767] The server will send the user an email notifying them of the completion of registration.

[0768] Step 6:

[0769] The user logs into the Buddy AI system from their device and goes to the dashboard screen.

[0770] Step 7:

[0771] The user clicks the "Start Consultation" button.

[0772] Step 8:

[0773] The server receives the user's consultation request and sends a request to the generative AI model to start a session.

[0774] Step 9:

[0775] The generative AI model creates an initial greeting message and returns it to the server.

[0776] For example, "Hello! What would you like to discuss today?"

[0777] Step 10:

[0778] The server displays an initial greeting message on the user's terminal.

[0779] Step 11:

[0780] The user enters the consultation content in the chat box and clicks the "Send" button.

[0781] Step 12:

[0782] The server receives the user's input and sends it to the emotion engine.

[0783] Step 13:

[0784] The emotion engine analyzes the user's input text and generates emotion data.

[0785] Example: Detecting emotions such as "stress" or "anxiety" from text.

[0786] Step 14:

[0787] The server sends the user's consultation details, including emotional data, to the generative AI model.

[0788] Step 15:

[0789] A generative AI model generates a response based on emotional data and the content of the consultation.

[0790] For example: "Project management can be challenging, but it can be achieved if you take it one step at a time. Let's figure out next steps together."

[0791] Step 16:

[0792] The server receives the generated response and displays it on the user's terminal.

[0793] Step 17:

[0794] If the user wishes to continue the dialogue or set a goal, they input a request for goal setting.

[0795] Step 18:

[0796] The server sends a goal setting request to the generative AI model.

[0797] Step 19:

[0798] The generative AI model generates questions to clarify the user's goals and returns them to the server.

[0799] Step 20:

[0800] The server displays the generated question on the user's terminal.

[0801] Step 21:

[0802] The user answers the question and submits the answer in the chat box.

[0803] Step 22:

[0804] The server receives the user's answers and sends them to the generative AI model.

[0805] Step 23:

[0806] A generative AI model generates a goal setting outline based on the user's answers.

[0807] Step 24:

[0808] The server displays the generated outline on the user's terminal.

[0809] For example: "To efficiently manage the schedule for the new project, we propose the following plan..."

[0810] Step 25:

[0811] After setting a goal, if the user wishes to report progress, they can enter and submit updated information from their device.

[0812] Step 26:

[0813] The server receives the user's updated information and stores it in a database.

[0814] Step 27:

[0815] The server sends updates to the emotion engine.

[0816] Step 28:

[0817] The emotion engine analyzes the updated information and generates emotion data.

[0818] Step 29:

[0819] The server sends the emotion data and updates to the generative AI model.

[0820] Step 30:

[0821] A generative AI model generates feedback based on emotional data and updates.

[0822] Step 31:

[0823] The server displays the generated feedback on the user's terminal.

[0824] For example: "Thank you for your progress report last week. To keep up, let's focus on these next tasks..."

[0825] Step 32:

[0826] The server periodically generates user usage history and sends it to the AI ​​model and emotion engine as learning data.

[0827] Step 33:

[0828] Generative AI models and emotion engines learn from usage history and generate personalized feedback.

[0829] Step 34:

[0830] The server displays the personalized feedback on the user's terminal.

[0831] Example: "Based on past consultation history, we will narrow down and propose key points for schedule management for the new project..."

[0832] In this way, users can use "Buddy AI" to receive individual consultations, goal setting, progress management, and feedback. Furthermore, by combining it with an emotion engine, the system can provide personalized responses that take into account the user's emotional state, resolving various issues in mentoring programs.

[0833] Example 2

[0834] 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."

[0835] Traditional mentoring systems have struggled to provide personalized feedback and consultation to individual employees, particularly in providing emotional support and appropriate responses in a timely manner. This can lead to a risk of lowering employee motivation and efficiency, potentially negatively impacting corporate performance. Furthermore, it has been difficult to balance consistency and individual attention when it comes to employee progress management and goal setting.

[0836] 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.

[0837] In this invention, the server includes: means for the user to send a request to start a consultation via a terminal; means for the server to receive the request and send a request to the generative AI model to generate an initial greeting message; means for the generative AI model to generate the initial greeting message based on the request; means for the server to display the initial greeting message on the user's terminal; means for the server to send the user's input to the emotion engine and send a request to generate emotion data; means for the emotion engine to generate emotion data based on the request; means for the server to send the emotion data and the user's input to the generative AI model and send a request to generate a response; means for the generative AI model to generate a response based on the request and taking the emotion data into consideration; means for displaying the response on the user's terminal; means for periodically sending the user's usage history to the generative AI model and the emotion engine as learning data and using it for personalization; means for the server to store the user's progress in a database, send update information to the emotion engine to generate emotion data, and means for generating a response based on the emotion data and displaying it on the user's terminal. This enables personalized responses and feedback to be provided to individual employees, improving employee motivation and efficiency and contributing to improved corporate performance.

[0838] "User" refers to an individual who uses the system to provide consultation and feedback.

[0839] A "terminal" is a device used by a user to access the system, including a PC, smartphone, etc.

[0840] "Request" refers to a command or request for information sent by a user or system to a generative AI model or emotion engine.

[0841] A "server" is a computer system that is the central part of the system and manages data storage, processing, and communication with other components.

[0842] A "generative AI model" refers to an artificial intelligence model that uses natural language processing techniques to generate appropriate responses or feedback in response to user input.

[0843] An "initial greeting message" refers to the first message sent by the generative AI model when a user begins a consultation.

[0844] "Emotion engine" refers to a technology or system that analyzes and generates emotional data from user text input.

[0845] "Emotion data" refers to data indicating an emotional state (e.g., joy, sadness, anger, etc.) extracted from a user's text input.

[0846] "Response" refers to the message that the generative AI model generates based on user input and emotional data.

[0847] "Usage history" refers to past consultation details and feedback generated while a user is using the system.

[0848] "Training Data" refers to the datasets used by generative AI models and emotion engines to improve their performance.

[0849] "Progress" refers to information about how a user is progressing toward achieving a goal.

[0850] "Updates" refers to new information entered by a user to report progress or make changes.

[0851] This invention provides a system called "Buddy AI" that supports in-company mentoring programs by combining a generative AI model and an emotion engine. The system allows users to initiate consultations through their devices, and the server provides appropriate responses and feedback. It also uses the emotion engine to recognize the user's emotions and delivers personalized responses based on those emotions.

[0852] Hardware and software used

[0853] Terminal: A device such as a PC or smartphone through which a user accesses the system.

[0854] Server: The central computer system of the system that stores and processes data and manages communication with other components.

[0855] Generative AI model: An artificial intelligence model that uses natural language processing techniques to generate appropriate responses and feedback in response to user input, such as OpenAI's GPT-3.

[0856] Emotion engine: Technology that analyzes and generates emotional data from user input text, such as Microsoft's Text Analytics.

[0857] Database: A data storage device such as MySQL for managing user information, progress, consultation details, etc.

[0858] System processing overview

[0859] 1. User Registration

[0860] The user opens a web browser on their device (PC or smartphone) and accesses the specified URL. They enter the required information (name, email address, password, etc.) into the new registration form and submit their registration request. The server receives this information and stores it in a database. The server then sends an email notifying the user that registration is complete.

[0861] 2. Starting a consultation

[0862] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request containing the user's ID and session information to the generative AI model. The generative AI model generates an initial greeting message (e.g., "Hello! What would you like to consult about today?") and displays it on the user's device via the server.

[0863] 3. Dialogue Progress

[0864] The user inputs and submits the content of their consultation. The server sends this input text to the emotion engine, which generates emotion data. The emotion engine analyzes the user's emotional state and returns the generated emotion data to the server. The server then sends the emotion data and the content of their consultation to the generative AI model, which then generates a response that takes the emotion data into account. The response is returned to the server in JSON format, and the server displays it on the device.

[0865] Specific examples

[0866] For example, when a user consults about schedule management for a new project, the following dialogue takes place:

[0867] User: "I'm having trouble managing the schedule for my new project."

[0868] The emotion engine generates "stress" emotion data.

[0869] Generative AI model: "Project management is hard, but it's achievable if you take it one step at a time. Let's figure out the next steps together."

[0870] Next, if the user requests a goal setting consultation, the server sends the request to the generative AI model.

[0871] Generative AI model: "To set your goal, what do you want to achieve first?"

[0872] Once the user enters their answer, the generative AI model creates an outline, which the server displays on the device.

[0873] Through these steps, the system of the present invention provides personalized assistance to users and solves the challenges of mentoring within a company.

[0874] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0875] Step 1:

[0876] The user accesses the "Buddy AI" system via a terminal and applies for registration by entering the necessary information into the new registration form.

[0877] Input: User information (name, email address, password, etc.)

[0878] and output: Registration completion notification email

[0879] Specific operation: The user opens a web browser, accesses the specified URL, enters the required information in the registration form, and clicks the "Register" button.

[0880] The server receives this information and stores it in a database.

[0881] Input: User registration information

[0882] Output: User information stored in the database, email notifying registration completion

[0883] Specific operation: The server receives the form data, stores it in a database such as MySQL, and then sends an email to notify the user that registration has been completed using the SMTP protocol.

[0884] Step 2:

[0885] The user logs in from the terminal and clicks the "Start Consultation" button.

[0886] Input: Login information (email address, password)

[0887] Output: Show initial greeting message

[0888] Specific operation: The user accesses the login page, enters their email address and password, and clicks the "Login" button. After logging in, they click the "Start Consultation" button from the menu.

[0889] The server sends a request to the generative AI model, including the user's ID and session information.

[0890] Input: User ID, session information

[0891] Output: An initial greeting message from the generative AI model

[0892] Specific operation: The server constructs session information and sends a request to the generative AI model using an API. The generative AI model generates an initial greeting message (e.g., "Hello! What would you like to discuss today?") and displays it on the device via the server.

[0893] Step 3:

[0894] The user inputs the consultation content and sends it.

[0895] Input: Text of consultation content

[0896] Output: Emotion data, response from generative AI model

[0897] Specific operation: The user enters the content of the consultation into the chat window and clicks the "Send" button.

[0898] The server sends the input content to the emotion engine, which generates emotion data.

[0899] Input: User's inquiry

[0900] Output: Emotion data

[0901] Specific operation: The server sends the user's consultation content to the emotion engine API, and the emotion engine analyzes the text and generates emotion data (e.g., "joy," "sadness," "anger," etc.).

[0902] The server sends the emotion data and the consultation details to the generative AI model, which generates a response.

[0903] Input: User's consultation details, emotional data

[0904] Output: The response from the generative AI model

[0905] Specific operation: The server sends a request containing emotion data and the consultation content to the generative AI model, which then generates a response that takes the emotion data into account. The server receives the generative AI model's response and displays it on the device.

[0906] Step 4:

[0907] The server receives the generated response and displays it on the user's terminal.

[0908] Input: Response from a generative AI model

[0909] Output: The response displayed on the user's terminal

[0910] Specific operation: The server receives the response from the generative AI model, converts it into HTML format, and displays it in the chat window.

[0911] The user continues the dialogue or inputs their goal setting preference.

[0912] Input: New consultation or goal setting request

[0913] Output: The next response from the generative AI model

[0914] Specific action: The user enters and submits a new consultation, or clicks the "Set Goal" button to submit a request.

[0915] Step 5:

[0916] The server sends the goal setting consultation to the generative AI model.

[0917] Input: Goal setting request

[0918] Output: Goal setting questions

[0919] Specific operation: The server sends a request regarding goal setting to the generative AI model, and the generative AI model generates a question regarding goal setting.

[0920] A generative AI model generates goal-setting questions that are displayed on the device.

[0921] Input: Goal setting request

[0922] Output: Goal setting questions

[0923] Specific behavior: The generative AI model generates questions related to goal setting, and the server displays them on the device (e.g., "What is the first step to achieving your goal?").

[0924] Users enter answers to questions, and the server stores them and sends them to the generative AI model.

[0925] Input: User's answer

[0926] Output: The answer sent to the generative AI model

[0927] What happens: The user answers the goal-setting questions and clicks the "Submit" button. The server stores the answers in a database and sends them to the generative AI model.

[0928] A generative AI model creates an outline of the goal setting, which the server displays on the device.

[0929] Input: User's answer

[0930] Output: Goal setting outline

[0931] How it works: The generative AI model creates an outline of goal setting based on the user's answers (e.g., "A plan for efficiently managing the schedule of a new project"), and the server displays it on the device.

[0932] Step 6:

[0933] The user enters updates to report progress, which the server stores and sends to the emotion engine.

[0934] Input: Progress update

[0935] Output: Emotion data, feedback from generative AI models

[0936] Specific operation: The user enters the progress status in the chat window and clicks the "Send" button. The server saves the progress status in the database and sends it to the emotion engine.

[0937] The emotion engine analyzes the updated information and generates emotion data.

[0938] Input: Progress update

[0939] Output: Emotion data

[0940] Specific behavior: The emotion engine analyzes the progress text and generates emotion data.

[0941] The server sends the emotion data and updates to the generative AI model to generate feedback.

[0942] Input: Emotion data, progress updates

[0943] Output: Feedback

[0944] Specific operation: The generative AI model generates feedback based on emotional data and progress information, and the server displays it on the device (e.g., "Thank you for your progress report last week. To keep up the good work, let's focus on the following tasks as the next step").

[0945] Step 7:

[0946] The server periodically generates usage history and sends it to the AI ​​model and emotion engine as learning data, which is then used for personalization.

[0947] Input: Usage history data

[0948] Output: Personalized responses and feedback

[0949] Specific operation: The server periodically extracts usage history data and sends it to the generative AI model and emotion engine. This enables the generative AI model and emotion engine to provide optimized feedback for each user (e.g., "Based on your past consultation history, we will narrow down and suggest important points for schedule management for a new project").

[0950] (Application example 2)

[0951] 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."

[0952] Conventional in-house mentoring systems lack an environment where employees can easily seek advice, and do not provide sufficient support to individual employees. Furthermore, appropriate responses and feedback to consultations are often delayed, often hindering the improvement of individual employees' performance. The present invention aims to solve these problems and provide an environment where employees can easily seek advice and support at any time.

[0953] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0954] In this invention, the server includes means for a user to send a request to start a consultation via a terminal, means for starting a training program selected by the user and recording progress, means for an emotion engine to recognize the user's emotional state and generate a feedback message based on a generative AI model, and means for analyzing the user's historical data and creating new learning suggestions using the generative AI model and displaying them on the user's terminal. This allows employees to receive continuous personalized feedback, enabling efficient learning and improved performance.

[0955] "User" means an individual who utilizes the System to conduct training programs or consultations.

[0956] A "terminal" is a device, such as a smartphone or head-mounted display, that connects to the system and operates it.

[0957] A "request" is a request or inquiry sent by a user to a system.

[0958] A "server" is a computer system that receives requests and interacts with generative AI models and emotion engines.

[0959] A "generative AI model" is an artificial intelligence model that generates responses or feedback messages based on requests.

[0960] An "initial greeting message" is the first message generated by the generative AI model when a user begins a consultation.

[0961] A "Training Program" is a set of educational content or activities that a user selects for learning or training.

[0962] "Progress" is information that indicates the degree of progress and achievement of the user as he or she progresses through the training program.

[0963] An "emotion engine" is a system that has the ability to analyze user input data and recognize the user's emotional state.

[0964] A "feedback message" is a response message to the user that the generative AI model generates based on the analysis results of the emotion engine.

[0965] "History data" refers to data from when a user has used the system in the past, including learning and consultation history.

[0966] "Learning suggestions" are suggestions for new learning and improvement that the generative AI model creates based on the user's historical data.

[0967] An "outline" is a summary or plan created by a generative AI model related to goal setting.

[0968] This invention provides a system called "Buddy AI" that combines generative AI and an emotion engine to solve the challenges of in-company mentoring programs. With this system, users start consultations via their devices, and the server uses a generative AI model to provide appropriate responses and feedback. Furthermore, the emotion engine recognizes the user's emotions and provides personalized responses based on these, creating an environment where users can easily receive consultations and support at any time.

[0969] Hardware and software used

[0970] Hardware

[0971] Terminal: A device that connects to the system and operates it, such as a smartphone or head-mounted display.

[0972] Server: A computer system that receives requests and interacts with the generative AI model and emotion engine.

[0973] software

[0974] Programming languages: Python, JavaScript

[0975] Frameworks: TensorFlow (generative AI), NLP (natural language processing), Emotion API

[0976] Database: MySQL

[0977] Frontend: React Native

[0978] Natural language processing explanation

[0979] 1. User Registration and Login

[0980] A user accesses the system using a terminal and creates an account by entering the required information in a new registration form.

[0981] This information is sent to the server and stored in a MySQL database, and an authentication token is generated and sent to the user.

[0982] 2. Select and begin a training program

[0983] After logging in, the user can see a list of training programs offered, which are retrieved from a database via a query and displayed on the terminal.

[0984] When the user selects a training program, the server records the selection and triggers the initiation process.

[0985] 3. Progress management and feedback

[0986] During the course of the program, user input data is collected and sent to the server.

[0987] The server sends this data to the emotion engine for sentiment analysis, which generates the analysis results and sends them to the generative AI model.

[0988] Based on the analysis results, the generative AI model generates a feedback message that takes into account the user's emotions and displays it on the device.

[0989] 4. Personalized study suggestions

[0990] The server periodically collects user history data and sends it to the generative AI model.

[0991] The generative AI model analyzes historical data and generates new learning suggestions based on learning progress and emotional state.

[0992] The content of the proposal is sent from the server to the user's terminal and displayed.

[0993] Specific examples

[0994] Suppose the user enters the following prompt text:

[0995] "I'm working on a new program, but progress is slow and it's frustrating."

[0996] "Based on past history, what areas should we pay particular attention to?"

[0997] In response, the generative AI and emotion engine generate a response like this:

[0998] "It's natural to feel like you're making slow progress. Try setting incremental goals like this..."

[0999] "Based on your history, X is an area that requires special attention. The key takeaway here is..."

[1000] In this way, the system allows users to receive continuous personalized feedback, promoting effective learning and growth.

[1001] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1002] Step 1:

[1003] A user accesses the system via a terminal and applies for registration by entering the required information into a new registration form. The input data, including the user name, email address, and password, is sent to the server. The server receives this and stores it in a MySQL database. After registration is complete, the server generates an authentication token and sends it to the user by email.

[1004] Input: User information entered into the registration form

[1005] Output: Save data to database and generate token

[1006] Step 2:

[1007] The user logs in and checks the list of training programs. The login data (email address and password) is entered into the terminal and sent to the server. The server performs authentication, retrieves the user's training program history from the database, and sends it to the terminal. The user checks the list of programs offered and selects one.

[1008] Input: Login information

[1009] Output: Display a list of programs

[1010] Step 3:

[1011] The user selects and starts a training program, the selected program is sent to the server, which records the selection, and the initial content of the training program is then delivered from the server to the terminal.

[1012] Input: Selected training program

[1013] Output: Initial content delivery

[1014] Step 4:

[1015] As the user progresses through the training program, the device collects and transmits data about the user's progress to a server, which stores the data in a database.

[1016] Input: User progress data

[1017] Output: Save to database

[1018] Step 5:

[1019] The server sends the collected progress data to the emotion engine, which analyzes the data, recognizes the user's emotional state, and generates emotion data, which is then sent back to the server.

[1020] Input: Progress data

[1021] Output: Emotion data

[1022] Step 6:

[1023] The server sends emotion data and progress data to the generative AI model and sends a request to generate a feedback message. The generative AI model generates appropriate feedback based on the emotion data and progress data and sends it back to the server.

[1024] Input: Emotion data and progress data

[1025] Output: Feedback message

[1026] Step 7:

[1027] The server sends the generated feedback message to the terminal and displays it to the user, who receives the feedback and continues training.

[1028] Input: Feedback message

[1029] Output: Message displayed on the terminal

[1030] Step 8:

[1031] Periodically, the server collects the user's historical data and sends it to the generative AI model. The generative AI model analyzes the historical data and generates personalized learning suggestions, which are then sent back to the server. The server then sends these suggestions to the user's device for display.

[1032] Input: User history data

[1033] Output: Generate and display learning suggestions

[1034] 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.

[1035] 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.

[1036] 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.

[1037] [Third embodiment]

[1038] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1039] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1040] 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).

[1041] 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.

[1042] 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.

[1043] 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).

[1044] 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.

[1045] 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.

[1046] 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.

[1047] 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.

[1048] 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.

[1049] 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."

[1050] This invention provides a system called "Buddy AI" that uses generative AI to solve the problems of in-house mentoring programs. This system allows users to start a consultation via their device, and the server uses a generative AI model to provide appropriate responses and feedback, creating an environment where users can easily receive consultation and support at any time.

[1051] The system configuration of the present invention is as follows.

[1052] 1. User Registration

[1053] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration.

[1054] 2. Starting a consultation

[1055] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device. For example, a message such as "Hello! What would you like to consult about today?" is displayed.

[1056] 3. Dialogue Progress

[1057] The user inputs and sends the inquiry. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the device. For example, in response to a question such as, "I'm having trouble managing the schedule for a new project. Do you have any advice?" the generative AI model provides specific advice.

[1058] 4. Goal setting and progress management

[1059] When a user requests a consultation on goal setting, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. The generative AI model creates an outline for goal setting, and the server displays it on the device. For example, the model might provide content such as, "To efficiently manage the schedule of a new project, we propose the following plan..."

[1060] 5. Providing Feedback

[1061] The user enters progress updates on the device. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, which the server displays on the device. For example, feedback might be provided such as, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[1062] 6. Usage history learning and personalization

[1063] The server periodically sends the user's usage history to the generative AI model as learning data. The generative AI model learns from that data and provides the user with more personalized feedback. For example, personalized feedback such as "Based on your past consultation history, we will narrow down and suggest important points for schedule management for your new project..." is provided.

[1064] In this way, this invention is a system that uses generative AI to provide an environment where employees can easily consult and receive feedback at any time, solving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[1065] The processing flow will be explained below.

[1066] Step 1:

[1067] The user accesses the Buddy AI system website via their device and opens the registration page.

[1068] Step 2:

[1069] The user enters the required information (name, email address, job title, department, etc.) into the registration form.

[1070] Step 3:

[1071] The user clicks the "Register" button and submits the registration information.

[1072] Step 4:

[1073] The server receives the user's input and stores it in a database.

[1074] Step 5:

[1075] The server will send the user an email notifying them of the completion of registration.

[1076] Step 6:

[1077] The user logs into the Buddy AI system from their device and goes to the dashboard screen.

[1078] Step 7:

[1079] The user clicks the "Start Consultation" button.

[1080] Step 8:

[1081] The server receives the user's consultation request and sends a request to the generative AI model to start a session.

[1082] Step 9:

[1083] The generative AI model creates an initial greeting message and returns it to the server.

[1084] Step 10:

[1085] The server displays an initial greeting message on the user's terminal.

[1086] For example: "Hello! What would you like to discuss today?"

[1087] Step 11:

[1088] The user enters the consultation content in the chat box and clicks the "Send" button.

[1089] Step 12:

[1090] The server receives user input and sends it to the generative AI model.

[1091] Step 13:

[1092] The generative AI model generates a response based on the user's inquiry.

[1093] Step 14:

[1094] The server receives the generated response and displays it on the user's terminal.

[1095] Step 15:

[1096] If the user wishes to continue the dialogue or set a goal, they input a request for goal setting.

[1097] Step 16:

[1098] The server sends a goal setting request to the generative AI model.

[1099] Step 17:

[1100] The generative AI model generates questions to assist with goal setting and returns them to the server.

[1101] Step 18:

[1102] The server displays the generated question on the user's terminal.

[1103] Step 19:

[1104] The user answers the question and submits the answer in the chat box.

[1105] Step 20:

[1106] The server receives the user's answers and sends them to the generative AI model.

[1107] Step 21:

[1108] A generative AI model generates a goal setting outline based on the user's answers.

[1109] Step 22:

[1110] The server displays the generated outline on the user's terminal.

[1111] Step 23:

[1112] After setting a goal, if the user wishes to report progress, they can enter and submit updated information from their device.

[1113] Step 24:

[1114] The server receives the user's updated information and stores it in a database.

[1115] Step 25:

[1116] The server sends updates to the generative AI model.

[1117] Step 26:

[1118] The generative AI model generates feedback based on the updated information and returns it to the server.

[1119] Step 27:

[1120] The server displays the generated feedback on the user's terminal.

[1121] Step 28:

[1122] The server periodically generates the user's usage history and sends it to the AI ​​model as learning data.

[1123] Step 29:

[1124] A generative AI model learns from users' usage history and generates increasingly personalized feedback.

[1125] Step 30:

[1126] The server displays the personalized feedback on the user's terminal.

[1127] In this way, users can use "Buddy AI" to receive individual consultations, set goals, monitor progress, and receive feedback.

[1128] Example 1

[1129] 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."

[1130] Traditional in-company mentoring systems have many restrictions on the timing and content of consultations, making it difficult to receive appropriate feedback quickly. Furthermore, some employees may become overly reliant on specific mentors, making it difficult to receive personalized advice. This can lead to ineffective goal setting and progress management for employees, hindering work efficiency and growth.

[1131] 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.

[1132] In this invention, the server includes a means for a user to send a request to start a consultation via a terminal, a means for sending a request to the generative AI model to generate an initial greeting message, and a means for the generative AI model to receive a request to start a session including the user's basic information. This enables the generative AI model to provide specific advice based on the user's input. The generative AI model also generates a response based on user information stored in a database, allowing for more personalized feedback to the user. This provides an environment where employees can easily receive consultation and support at any time, enabling effective goal setting and progress management.

[1133] "User" refers to an individual who uses the system to receive consultation and feedback.

[1134] "Terminal" refers to a device, such as a PC or smartphone, that a user uses to access the system.

[1135] A "request" refers to an action or request made by a user to a server.

[1136] "Server" refers to a computer that receives a user's request, communicates with a generative AI model to generate an appropriate response, and returns it to the user.

[1137] A "generative AI model" refers to software that uses artificial intelligence to generate appropriate responses to user input.

[1138] "Initial greeting message" refers to a message containing a welcome message or question that a generative AI model generates during its first interaction with a user.

[1139] A "session" refers to a series of interactions between a user and a generative AI model.

[1140] "Personalized feedback" refers to tailored feedback provided based on a user's past usage history and specific needs.

[1141] "Response" refers to the reply or advice that a generative AI model generates based on a user's request.

[1142] "Goal setting" refers to the process of defining the objectives or goals that users want to achieve.

[1143] "Progress management" refers to the process of monitoring a user's progress toward achieving their goals and providing appropriate advice or corrections.

[1144] This invention provides a system called "Buddy AI" that uses a generative AI model to solve the problems of in-house mentoring programs. This system allows users to start a consultation via their device, and the server uses a generative AI model to provide appropriate responses and feedback, creating an environment where users can easily receive consultation and support at any time.

[1145] System Configuration

[1146] 1. User Registration

[1147] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration. Specifically, the user enters information such as name, email address, and department into the registration form, and the server stores that information in a database.

[1148] 2. Starting a consultation

[1149] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device. For example, a message such as "Hello! What would you like to consult about today?" is displayed.

[1150] 3. Dialogue Progress

[1151] The user inputs and submits the content of their inquiry. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the device. For example, if a user asks, "I'm having trouble managing the schedule for a new project. Do you have any advice?" the generative AI model will provide specific advice.

[1152] 4. Goal setting and progress management

[1153] When a user requests a consultation on goal setting, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. For example, the service might provide content such as, "To efficiently manage the schedule of a new project, we propose the following plan..."

[1154] 5. Providing Feedback

[1155] The user enters progress updates on the device. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, which the server displays on the device. For example, the feedback might be, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[1156] 6. Usage history learning and personalization

[1157] The server periodically sends the user's usage history to the generative AI model as learning data. The generative AI model learns from that data and provides the user with more personalized feedback. For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest important points for schedule management for your new project..." is provided.

[1158] In this way, the present invention is a system that uses a generative AI model to provide an environment where employees can easily consult with or receive feedback at any time, thereby resolving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[1159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1160] Step 1:

[1161] A user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information in the new registration form. The input data includes name, email address, department, etc. This data is sent to the server. Specifically, the user opens a browser, enters the system's URL, enters the required information in the form, and clicks the submit button.

[1162] Step 2:

[1163] The server receives the user's input information and saves the data in a database. The received data includes the user name, email address, department, etc., and performs data validation to ensure that it is saved accurately in the database. As a concrete example, the server issues an insert query to the database and saves the data. If the save is successful, the result is confirmed.

[1164] Step 3:

[1165] The server sends the user an email to notify them that registration is complete. The email contains a message informing them that registration is complete and instructions for the next step. The server uses the user's email address as input data and uses the email sending API to send a confirmation email for registration completion.

[1166] Step 4:

[1167] A user logs in to the system from a terminal. An email address and password are required as input data. The server uses this input data to authenticate the user, and if authentication is successful, the dashboard screen is displayed on the terminal. Specifically, the user opens the login page in a browser, enters their email address and password, and clicks the login button.

[1168] Step 5:

[1169] The user clicks the "Start Consultation" button. The server sends a session start request to the generative AI model, including the user's basic information. The user's basic information is used as input data, and an initial greeting message is generated as output. The generative AI model receives this request and generates a prompt message such as "Hello! What would you like to consult about today?", which is then displayed on the device.

[1170] Step 6:

[1171] The user inputs and sends the consultation content. The input data is the consulting content, such as "I'm having trouble managing the schedule of a new project. Do you have any advice?" The server receives this input data, sends it to the generative AI model, and generates an appropriate response. The generative AI model creates an answer based on the user's input and generates advice as output data. The generated response is displayed on the device.

[1172] Step 7:

[1173] A user requests advice on goal setting. The server sends the request to the generative AI model. The input data is the user's request regarding their goal. The generative AI model generates a question to clarify the user's goal, and the server displays the question on the device. Specifically, the generative AI model generates the question, "What kind of goal do you want to set?"

[1174] Step 8:

[1175] The user answers questions, and the server saves the answers and sends them to the generative AI model. The input data are the answers about the user's goals. The server saves the data in a database, and the generative AI model receives the data and creates an outline for goal setting. Once the outline is generated, the server displays it on the user's device. For example, an outline such as "We propose the following plan to efficiently manage the schedule of a new project..." may be displayed.

[1176] Step 9:

[1177] The user inputs progress updates on their device. The input data includes their current progress and achievements. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, and the server displays the feedback on the device. For example, the feedback might read, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[1178] Step 10:

[1179] The server periodically sends the user's usage history to the generative AI model as learning data. The input data includes past consultation details and progress data. The generative AI model learns from this data and provides personalized feedback to the user. The output data is feedback tailored to the user's specific needs. For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest key points for schedule management for your new project..." is generated.

[1180] (Application example 1)

[1181] 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."

[1182] Currently, factories lack an environment where workers can receive real-time advice on robot and machine operation. As a result, there are problems with efficient work flows and machine maintenance. There is also a lack of systems that effectively support goal setting and progress management, which is a factor that reduces production efficiency. Therefore, it is necessary to provide an environment where real-time support and consultation can be provided between robots and machines and workers on factory floors.

[1183] 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.

[1184] In this invention, the server includes a means for a user to send a request to start a consultation via a terminal, a means for the server to receive the request and send a request to the generative AI model to generate an initial greeting message, a means for the generative AI model to generate the initial greeting message based on the request, a means for displaying the initial greeting message on the user's terminal, a means for sending a request for assistance with physical work, a means for generating a work procedure based on the request, and a means for displaying the work procedure on the user's terminal. This enables workers to receive real-time assistance and consultation regarding the operation and maintenance of robots and machines. It also enhances support for goal setting and progress management.

[1185] A "user" is a person who starts a consultation via a terminal and uses the functions provided by the system.

[1186] A "terminal" is an electronic device used by a user to access the system, including a PC or smartphone.

[1187] A "server" is a central computer that manages the entire system and receives and processes various requests.

[1188] A "generative AI model" is an artificial intelligence technology that generates initial greeting messages, responses, goal setting outlines, and more based on user requests.

[1189] A "request" is an operation request or consultation content that a user sends to a server via a terminal.

[1190] The "initial greeting message" is the greeting that the generative AI model first generates upon receiving a user request.

[1191] "Consulting content" refers to the specific consultation matters and questions that users ask about through the system.

[1192] A "response" is a reply or advice generated by the generative AI model based on the consulting content.

[1193] "Goal setting" is the process of clarifying the specific goals that users want to achieve.

[1194] "Progress" refers to the status or report of how far you have progressed toward your goal.

[1195] "Feedback" is advice and suggestions for improvement generated by the generative AI model based on its progress.

[1196] A "work procedure" is a specific work procedure or manual that a generative AI model generates to assist with physical work.

[1197] In a system embodying this invention, a "Robo Buddy AI" is installed in a robot working in a factory, and real-time support and consultation is provided between the factory worker and the robot. Specific embodiments are described below.

[1198] Hardware and Software

[1199] 1. Hardware:

[1200] Factory robot control terminals (PCs, smartphones, etc.)

[1201] Server equipment (a central computer for database and AI model processing)

[1202] 2. Software:

[1203] Python

[1204] Flask

[1205] OpenAI API (generative AI model)

[1206] System Operation

[1207] 1. User Registration

[1208] The user accesses the system via a terminal and applies for registration by entering the required information in the new registration form. The server receives this information and stores it in a database. The server then sends the user a notification that registration is complete. With this operation, the user is ready to begin consultations and support.

[1209] 2. Starting a consultation

[1210] The user logs in to the system from their device and clicks the "Start Consultation" button. The server sends the consultation request to the AI ​​model and generates an initial greeting message. The initial greeting message might be something like "Hello! What would you like to consult about today?"

[1211] 3. Dialogue Progress

[1212] The user inputs the content of their inquiry and sends it to the server. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the user's device. For example, if a user inputs, "Please tell me how to maintain this machine," the generative AI model generates detailed instructions such as, "To maintain this machine, follow these steps..."

[1213] 4. Goal setting and progress management

[1214] When a user requests a consultation on goal setting, the server sends the request to the generative AI model, which then generates a question about goal setting. The server displays the question on the user's device, and the user answers by entering information. The server then sends the input to the generative AI model, which generates an outline of goal setting. This operation allows the user to clarify their goals and effectively manage their progress.

[1215] 5. Providing Feedback

[1216] When a user inputs progress updates on their device, the server stores the updates in a database and sends them to the generative AI model, which generates feedback based on the updates and displays it on the user's device, allowing them to receive specific advice on next steps.

[1217] Specific prompt examples

[1218] Example 1:

[1219] User: How do I maintain this machine?

[1220] Buddy AI:

[1221] Example 2:

[1222] User: I'm having trouble managing the schedule for a new project. Any advice?

[1223] Buddy AI:

[1224] In this way, RoboBuddy AI can be applied to factory robots, enabling real-time support and consultation between workers and robots, improving work efficiency and maintenance quality.

[1225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1226] Step 1:

[1227] The user accesses the system via a terminal and applies for registration by entering the required information in the new registration form. The input data includes the user's personal information and authentication information. The server receives this information and stores it in a database. The server then sends a notification to the user that registration is complete. Based on the input, the user information is stored in the database and a registration completion notification is generated.

[1228] Step 2:

[1229] The user logs in to the system from their device and clicks the "Start Consultation" button. The server sends the consultation request to the generation AI model and requests it to generate an initial greeting message. The generation AI model receives the request and generates the initial greeting message. The initial greeting message is chosen to be something like "Hello! What would you like to consult about today?" The server displays the generated greeting message on the user's device. The initial greeting message is generated based on the request and displayed on the user's device.

[1230] Step 3:

[1231] The user inputs the consultation content and sends it to the server. For example, "Please tell me how to maintain this machine." The server sends the input content to the generative AI model and sends a request to generate an appropriate response. The generative AI model receives the consulting request and generates a response based on the content. A response such as "The maintenance of this machine will be carried out using the following steps..." is generated. The server displays the generated response on the user's device. Based on the input of the consultation content, specific operating procedures are generated and displayed on the user's device.

[1232] Step 4:

[1233] When a user wishes to consult about goal setting, they send a dedicated request. The server sends the goal setting request to the generative AI model, which then sends a request to generate a question related to goal setting. The generative AI model receives the request and generates a question related to goal setting. The question might be something like, "What should you aim for in order to efficiently manage the schedule of a new project?" This is then displayed on the user's device. The user enters information to answer the question and sends it to the server. The input is sent to the generative AI model, which generates a goal setting outline. The outline is generated and displayed on the user's device. Specific goal setting questions and their outlines are generated based on the input and displayed on the user's device.

[1234] Step 5:

[1235] The user inputs update information from their device to report their progress and sends it to the server. The server stores this update information in a database and sends it to the generative AI model. The generative AI model generates feedback based on the update information. Feedback such as "Thank you for reporting on your progress last week. To keep up the good work, let's focus on the following task as your next step..." is generated. The server displays the generated feedback on the user's device. Specific feedback is generated based on the progress input and displayed on the user's device.

[1236] 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.

[1237] This invention provides a system called "Buddy AI" that combines generative AI and an emotion engine to solve the challenges of in-company mentoring programs. With this system, users start consultations via their devices, and the server uses a generative AI model to provide appropriate responses and feedback. Furthermore, the emotion engine recognizes the user's emotions and provides personalized responses based on these, creating an environment where users can easily receive consultations and support at any time.

[1238] The system configuration of the present invention is as follows.

[1239] 1. User Registration

[1240] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration.

[1241] 2. Starting a consultation

[1242] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device.

[1243] For example, a message might say, "Hello! What would you like to talk about today?"

[1244] 3. Dialogue Progress

[1245] The user inputs and submits the consultation content. The server sends the input content to the emotion engine, which analyzes the text entered by the user and generates emotion data. The emotion data includes information about the user's emotional state (joy, sadness, anger, etc.).

[1246] 4. Use of Emotional Data

[1247] The server sends the emotional data and the content of the consultation to the generative AI model, which then generates a response based on this information. The response is tailored to take into account the user's emotional state.

[1248] For example, if a user inputs, "I'm having trouble managing the schedule for a new project," and the emotional data indicates "stress," the generative AI model will generate a response such as, "Project management is certainly difficult, but if you take it one step at a time, you can definitely achieve it. Let's think together about the next step."

[1249] 5. Providing a Response

[1250] The server receives the generated response and displays it on the user's terminal. The user can continue the dialogue or, if they wish to set a goal, enter a request for goal setting.

[1251] 6. Goal setting and progress management

[1252] When a user requests a goal setting consultation, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. The generative AI model creates a goal setting outline, which the server displays on the device.

[1253] For example, you might receive something like, "We propose the following plan to efficiently manage the schedule of your new project..."

[1254] 7. Providing Feedback

[1255] The user inputs update information from the device to report progress. The server stores the update information in a database and sends it to the emotion engine. The emotion engine analyzes the update information and generates emotion data. The server sends the emotion data and update information to the generative AI model, which then generates feedback based on it and the server displays it on the device.

[1256] For example, feedback might be provided such as, "Thank you for your progress report last week. To keep up, let's focus on the following tasks as next steps..."

[1257] 8. Usage learning and personalization

[1258] The server periodically sends the user's usage history to the generative AI model and emotion engine as learning data, which the generative AI model and emotion engine then use to learn from the data and provide the user with more personalized feedback.

[1259] For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest key points for schedule management for your new project..." is provided.

[1260] In this way, this invention is a system that uses generative AI and an emotion engine to provide an environment where employees can easily consult with or receive feedback at any time, solving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[1261] The processing flow will be explained below.

[1262] Step 1:

[1263] The user accesses the Buddy AI system website via their device and opens the new registration page.

[1264] Step 2:

[1265] The user enters the required information (name, email address, job title, department, etc.) into the registration form.

[1266] Step 3:

[1267] The user clicks the "Register" button and submits the registration information.

[1268] Step 4:

[1269] The server receives the user's registration information and stores it in a database.

[1270] Step 5:

[1271] The server will send the user an email notifying them of the completion of registration.

[1272] Step 6:

[1273] The user logs into the Buddy AI system from their device and goes to the dashboard screen.

[1274] Step 7:

[1275] The user clicks the "Start Consultation" button.

[1276] Step 8:

[1277] The server receives the user's consultation request and sends a request to the generative AI model to start a session.

[1278] Step 9:

[1279] The generative AI model creates an initial greeting message and returns it to the server.

[1280] For example, "Hello! What would you like to discuss today?"

[1281] Step 10:

[1282] The server displays an initial greeting message on the user's terminal.

[1283] Step 11:

[1284] The user enters the consultation content in the chat box and clicks the "Send" button.

[1285] Step 12:

[1286] The server receives the user's input and sends it to the emotion engine.

[1287] Step 13:

[1288] The emotion engine analyzes the user's input text and generates emotion data.

[1289] Example: Detecting emotions such as "stress" or "anxiety" from text.

[1290] Step 14:

[1291] The server sends the user's consultation details, including emotional data, to the generative AI model.

[1292] Step 15:

[1293] A generative AI model generates a response based on emotional data and the content of the consultation.

[1294] For example: "Project management can be challenging, but it can be achieved if you take it one step at a time. Let's figure out next steps together."

[1295] Step 16:

[1296] The server receives the generated response and displays it on the user's terminal.

[1297] Step 17:

[1298] If the user wishes to continue the dialogue or set a goal, they input a request for goal setting.

[1299] Step 18:

[1300] The server sends a goal setting request to the generative AI model.

[1301] Step 19:

[1302] The generative AI model generates questions to clarify the user's goals and returns them to the server.

[1303] Step 20:

[1304] The server displays the generated question on the user's terminal.

[1305] Step 21:

[1306] The user answers the question and submits the answer in the chat box.

[1307] Step 22:

[1308] The server receives the user's answers and sends them to the generative AI model.

[1309] Step 23:

[1310] A generative AI model generates a goal setting outline based on the user's answers.

[1311] Step 24:

[1312] The server displays the generated outline on the user's terminal.

[1313] For example: "To efficiently manage the schedule for the new project, we propose the following plan..."

[1314] Step 25:

[1315] After setting a goal, if the user wishes to report progress, they can enter and submit updated information from their device.

[1316] Step 26:

[1317] The server receives the user's updated information and stores it in a database.

[1318] Step 27:

[1319] The server sends updates to the emotion engine.

[1320] Step 28:

[1321] The emotion engine analyzes the updated information and generates emotion data.

[1322] Step 29:

[1323] The server sends the emotion data and updates to the generative AI model.

[1324] Step 30:

[1325] A generative AI model generates feedback based on emotional data and updates.

[1326] Step 31:

[1327] The server displays the generated feedback on the user's terminal.

[1328] For example: "Thank you for your progress report last week. To keep up, let's focus on these next tasks..."

[1329] Step 32:

[1330] The server periodically generates user usage history and sends it to the AI ​​model and emotion engine as learning data.

[1331] Step 33:

[1332] Generative AI models and emotion engines learn from usage history and generate personalized feedback.

[1333] Step 34:

[1334] The server displays the personalized feedback on the user's terminal.

[1335] Example: "Based on past consultation history, we will narrow down and propose key points for schedule management for the new project..."

[1336] In this way, users can use "Buddy AI" to receive individual consultations, goal setting, progress management, and feedback. Furthermore, by combining it with an emotion engine, the system can provide personalized responses that take into account the user's emotional state, resolving various issues in mentoring programs.

[1337] Example 2

[1338] 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."

[1339] Traditional mentoring systems have struggled to provide personalized feedback and consultation to individual employees, particularly in providing emotional support and appropriate responses in a timely manner. This can lead to a risk of lowering employee motivation and efficiency, potentially negatively impacting corporate performance. Furthermore, it has been difficult to balance consistency and individual attention when it comes to employee progress management and goal setting.

[1340] 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.

[1341] In this invention, the server includes: means for the user to send a request to start a consultation via a terminal; means for the server to receive the request and send a request to the generative AI model to generate an initial greeting message; means for the generative AI model to generate the initial greeting message based on the request; means for the server to display the initial greeting message on the user's terminal; means for the server to send the user's input to the emotion engine and send a request to generate emotion data; means for the emotion engine to generate emotion data based on the request; means for the server to send the emotion data and the user's input to the generative AI model and send a request to generate a response; means for the generative AI model to generate a response based on the request and taking the emotion data into consideration; means for displaying the response on the user's terminal; means for periodically sending the user's usage history to the generative AI model and the emotion engine as learning data and using it for personalization; means for the server to store the user's progress in a database, send update information to the emotion engine to generate emotion data, and means for generating a response based on the emotion data and displaying it on the user's terminal. This enables personalized responses and feedback to be provided to individual employees, improving employee motivation and efficiency and contributing to improved corporate performance.

[1342] "User" refers to an individual who uses the system to provide consultation and feedback.

[1343] A "terminal" is a device used by a user to access the system, including a PC, smartphone, etc.

[1344] "Request" refers to a command or request for information sent by a user or system to a generative AI model or emotion engine.

[1345] A "server" is a computer system that is the central part of the system and manages data storage, processing, and communication with other components.

[1346] A "generative AI model" refers to an artificial intelligence model that uses natural language processing techniques to generate appropriate responses or feedback in response to user input.

[1347] An "initial greeting message" refers to the first message sent by the generative AI model when a user begins a consultation.

[1348] "Emotion engine" refers to a technology or system that analyzes and generates emotional data from user text input.

[1349] "Emotion data" refers to data indicating an emotional state (e.g., joy, sadness, anger, etc.) extracted from a user's text input.

[1350] "Response" refers to the message that the generative AI model generates based on user input and emotional data.

[1351] "Usage history" refers to past consultation details and feedback generated while a user is using the system.

[1352] "Training Data" refers to the datasets used by generative AI models and emotion engines to improve their performance.

[1353] "Progress" refers to information about how a user is progressing toward achieving a goal.

[1354] "Updates" refers to new information entered by a user to report progress or make changes.

[1355] This invention provides a system called "Buddy AI" that supports in-company mentoring programs by combining a generative AI model and an emotion engine. The system allows users to initiate consultations through their devices, and the server provides appropriate responses and feedback. It also uses the emotion engine to recognize the user's emotions and delivers personalized responses based on those emotions.

[1356] Hardware and software used

[1357] Terminal: A device such as a PC or smartphone through which a user accesses the system.

[1358] Server: The central computer system of the system that stores and processes data and manages communication with other components.

[1359] Generative AI model: An artificial intelligence model that uses natural language processing techniques to generate appropriate responses and feedback in response to user input, such as OpenAI's GPT-3.

[1360] Emotion engine: Technology that analyzes and generates emotional data from user input text, such as Microsoft's Text Analytics.

[1361] Database: A data storage device such as MySQL for managing user information, progress, consultation details, etc.

[1362] System processing overview

[1363] 1. User Registration

[1364] The user opens a web browser on their device (PC or smartphone) and accesses the specified URL. They enter the required information (name, email address, password, etc.) into the new registration form and submit their registration request. The server receives this information and stores it in a database. The server then sends an email notifying the user that registration is complete.

[1365] 2. Starting a consultation

[1366] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request containing the user's ID and session information to the generative AI model. The generative AI model generates an initial greeting message (e.g., "Hello! What would you like to consult about today?") and displays it on the user's device via the server.

[1367] 3. Dialogue Progress

[1368] The user inputs and submits the content of their consultation. The server sends this input text to the emotion engine, which generates emotion data. The emotion engine analyzes the user's emotional state and returns the generated emotion data to the server. The server then sends the emotion data and the content of their consultation to the generative AI model, which then generates a response that takes the emotion data into account. The response is returned to the server in JSON format, and the server displays it on the device.

[1369] Specific examples

[1370] For example, when a user consults about schedule management for a new project, the following dialogue takes place:

[1371] User: "I'm having trouble managing the schedule for my new project."

[1372] The emotion engine generates "stress" emotion data.

[1373] Generative AI model: "Project management is hard, but it's achievable if you take it one step at a time. Let's figure out the next steps together."

[1374] Next, if the user requests a goal setting consultation, the server sends the request to the generative AI model.

[1375] Generative AI model: "To set your goal, what do you want to achieve first?"

[1376] Once the user enters their answer, the generative AI model creates an outline, which the server displays on the device.

[1377] Through these steps, the system of the present invention provides personalized assistance to users and solves the challenges of mentoring within a company.

[1378] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1379] Step 1:

[1380] The user accesses the "Buddy AI" system via a terminal and applies for registration by entering the necessary information into the new registration form.

[1381] Input: User information (name, email address, password, etc.)

[1382] and output: Registration completion notification email

[1383] Specific operation: The user opens a web browser, accesses the specified URL, enters the required information in the registration form, and clicks the "Register" button.

[1384] The server receives this information and stores it in a database.

[1385] Input: User registration information

[1386] Output: User information stored in the database, email notifying registration completion

[1387] Specific operation: The server receives the form data, stores it in a database such as MySQL, and then sends an email to notify the user that registration has been completed using the SMTP protocol.

[1388] Step 2:

[1389] The user logs in from the terminal and clicks the "Start Consultation" button.

[1390] Input: Login information (email address, password)

[1391] Output: Show initial greeting message

[1392] Specific operation: The user accesses the login page, enters their email address and password, and clicks the "Login" button. After logging in, they click the "Start Consultation" button from the menu.

[1393] The server sends a request to the generative AI model, including the user's ID and session information.

[1394] Input: User ID, session information

[1395] Output: An initial greeting message from the generative AI model

[1396] Specific operation: The server constructs session information and sends a request to the generative AI model using an API. The generative AI model generates an initial greeting message (e.g., "Hello! What would you like to discuss today?") and displays it on the device via the server.

[1397] Step 3:

[1398] The user inputs the consultation content and sends it.

[1399] Input: Text of consultation content

[1400] Output: Emotion data, response from generative AI model

[1401] Specific operation: The user enters the content of the consultation into the chat window and clicks the "Send" button.

[1402] The server sends the input content to the emotion engine, which generates emotion data.

[1403] Input: User's inquiry

[1404] Output: Emotion data

[1405] Specific operation: The server sends the user's consultation content to the emotion engine API, and the emotion engine analyzes the text and generates emotion data (e.g., "joy," "sadness," "anger," etc.).

[1406] The server sends the emotion data and the consultation details to the generative AI model, which generates a response.

[1407] Input: User's consultation details, emotional data

[1408] Output: The response from the generative AI model

[1409] Specific operation: The server sends a request containing emotion data and the consultation content to the generative AI model, which then generates a response that takes the emotion data into account. The server receives the generative AI model's response and displays it on the device.

[1410] Step 4:

[1411] The server receives the generated response and displays it on the user's terminal.

[1412] Input: Response from a generative AI model

[1413] Output: The response displayed on the user's terminal

[1414] Specific operation: The server receives the response from the generative AI model, converts it into HTML format, and displays it in the chat window.

[1415] The user continues the dialogue or inputs their goal setting preference.

[1416] Input: New consultation or goal setting request

[1417] Output: The next response from the generative AI model

[1418] Specific action: The user enters and submits a new consultation, or clicks the "Set Goal" button to submit a request.

[1419] Step 5:

[1420] The server sends the goal setting consultation to the generative AI model.

[1421] Input: Goal setting request

[1422] Output: Goal setting questions

[1423] Specific operation: The server sends a request regarding goal setting to the generative AI model, and the generative AI model generates a question regarding goal setting.

[1424] A generative AI model generates goal-setting questions that are displayed on the device.

[1425] Input: Goal setting request

[1426] Output: Goal setting questions

[1427] Specific behavior: The generative AI model generates questions related to goal setting, and the server displays them on the device (e.g., "What is the first step to achieving your goal?").

[1428] Users enter answers to questions, and the server stores them and sends them to the generative AI model.

[1429] Input: User's answer

[1430] Output: The answer sent to the generative AI model

[1431] What happens: The user answers the goal-setting questions and clicks the "Submit" button. The server stores the answers in a database and sends them to the generative AI model.

[1432] A generative AI model creates an outline of the goal setting, which the server displays on the device.

[1433] Input: User's answer

[1434] Output: Goal setting outline

[1435] How it works: The generative AI model creates an outline of goal setting based on the user's answers (e.g., "A plan for efficiently managing the schedule of a new project"), and the server displays it on the device.

[1436] Step 6:

[1437] The user enters updates to report progress, which the server stores and sends to the emotion engine.

[1438] Input: Progress update

[1439] Output: Emotion data, feedback from generative AI models

[1440] Specific operation: The user enters the progress status in the chat window and clicks the "Send" button. The server saves the progress status in the database and sends it to the emotion engine.

[1441] The emotion engine analyzes the updated information and generates emotion data.

[1442] Input: Progress update

[1443] Output: Emotion data

[1444] Specific behavior: The emotion engine analyzes the progress text and generates emotion data.

[1445] The server sends the emotion data and updates to the generative AI model to generate feedback.

[1446] Input: Emotion data, progress updates

[1447] Output: Feedback

[1448] Specific operation: The generative AI model generates feedback based on emotional data and progress information, and the server displays it on the device (e.g., "Thank you for your progress report last week. To keep up the good work, let's focus on the following tasks as the next step").

[1449] Step 7:

[1450] The server periodically generates usage history and sends it to the AI ​​model and emotion engine as learning data, which is then used for personalization.

[1451] Input: Usage history data

[1452] Output: Personalized responses and feedback

[1453] Specific operation: The server periodically extracts usage history data and sends it to the generative AI model and emotion engine. This enables the generative AI model and emotion engine to provide optimized feedback for each user (e.g., "Based on your past consultation history, we will narrow down and suggest important points for schedule management for a new project").

[1454] (Application example 2)

[1455] 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."

[1456] Conventional in-house mentoring systems lack an environment where employees can easily seek advice, and do not provide sufficient support to individual employees. Furthermore, appropriate responses and feedback to consultations are often delayed, often hindering the improvement of individual employees' performance. The present invention aims to solve these problems and provide an environment where employees can easily seek advice and support at any time.

[1457] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1458] In this invention, the server includes means for a user to send a request to start a consultation via a terminal, means for starting a training program selected by the user and recording progress, means for an emotion engine to recognize the user's emotional state and generate a feedback message based on a generative AI model, and means for analyzing the user's historical data and creating new learning suggestions using the generative AI model and displaying them on the user's terminal. This allows employees to receive continuous personalized feedback, enabling efficient learning and improved performance.

[1459] "User" means an individual who utilizes the System to conduct training programs or consultations.

[1460] A "terminal" is a device, such as a smartphone or head-mounted display, that connects to the system and operates it.

[1461] A "request" is a request or inquiry sent by a user to a system.

[1462] A "server" is a computer system that receives requests and interacts with generative AI models and emotion engines.

[1463] A "generative AI model" is an artificial intelligence model that generates responses or feedback messages based on requests.

[1464] An "initial greeting message" is the first message generated by the generative AI model when a user begins a consultation.

[1465] A "Training Program" is a set of educational content or activities that a user selects for learning or training.

[1466] "Progress" is information that indicates the degree of progress and achievement of the user as he or she progresses through the training program.

[1467] An "emotion engine" is a system that has the ability to analyze user input data and recognize the user's emotional state.

[1468] A "feedback message" is a response message to the user that the generative AI model generates based on the analysis results of the emotion engine.

[1469] "History data" refers to data from when a user has used the system in the past, including learning and consultation history.

[1470] "Learning suggestions" are suggestions for new learning and improvement that the generative AI model creates based on the user's historical data.

[1471] An "outline" is a summary or plan created by a generative AI model related to goal setting.

[1472] This invention provides a system called "Buddy AI" that combines generative AI and an emotion engine to solve the challenges of in-company mentoring programs. With this system, users start consultations via their devices, and the server uses a generative AI model to provide appropriate responses and feedback. Furthermore, the emotion engine recognizes the user's emotions and provides personalized responses based on these, creating an environment where users can easily receive consultations and support at any time.

[1473] Hardware and software used

[1474] Hardware

[1475] Terminal: A device that connects to the system and operates it, such as a smartphone or head-mounted display.

[1476] Server: A computer system that receives requests and interacts with the generative AI model and emotion engine.

[1477] software

[1478] Programming languages: Python, JavaScript

[1479] Frameworks: TensorFlow (generative AI), NLP (natural language processing), Emotion API

[1480] Database: MySQL

[1481] Frontend: React Native

[1482] Natural language processing explanation

[1483] 1. User Registration and Login

[1484] A user accesses the system using a terminal and creates an account by entering the required information in a new registration form.

[1485] This information is sent to the server and stored in a MySQL database, and an authentication token is generated and sent to the user.

[1486] 2. Select and begin a training program

[1487] After logging in, the user can see a list of training programs offered, which are retrieved from a database via a query and displayed on the terminal.

[1488] When the user selects a training program, the server records the selection and triggers the initiation process.

[1489] 3. Progress management and feedback

[1490] During the course of the program, user input data is collected and sent to the server.

[1491] The server sends this data to the emotion engine for sentiment analysis, which generates the analysis results and sends them to the generative AI model.

[1492] Based on the analysis results, the generative AI model generates a feedback message that takes into account the user's emotions and displays it on the device.

[1493] 4. Personalized study suggestions

[1494] The server periodically collects user history data and sends it to the generative AI model.

[1495] The generative AI model analyzes historical data and generates new learning suggestions based on learning progress and emotional state.

[1496] The content of the proposal is sent from the server to the user's terminal and displayed.

[1497] Specific examples

[1498] Suppose the user enters the following prompt text:

[1499] "I'm working on a new program, but progress is slow and it's frustrating."

[1500] "Based on past history, what areas should we pay particular attention to?"

[1501] In response, the generative AI and emotion engine generate a response like this:

[1502] "It's natural to feel like you're making slow progress. Try setting incremental goals like this..."

[1503] "Based on your history, X is an area that requires special attention. The key takeaway here is..."

[1504] In this way, the system allows users to receive continuous personalized feedback, promoting effective learning and growth.

[1505] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1506] Step 1:

[1507] A user accesses the system via a terminal and applies for registration by entering the required information into a new registration form. The input data, including the user name, email address, and password, is sent to the server. The server receives this and stores it in a MySQL database. After registration is complete, the server generates an authentication token and sends it to the user by email.

[1508] Input: User information entered into the registration form

[1509] Output: Save data to database and generate token

[1510] Step 2:

[1511] The user logs in and checks the list of training programs. The login data (email address and password) is entered into the terminal and sent to the server. The server performs authentication, retrieves the user's training program history from the database, and sends it to the terminal. The user checks the list of programs offered and selects one.

[1512] Input: Login information

[1513] Output: Display a list of programs

[1514] Step 3:

[1515] The user selects and starts a training program, the selected program is sent to the server, which records the selection, and the initial content of the training program is then delivered from the server to the terminal.

[1516] Input: Selected training program

[1517] Output: Initial content delivery

[1518] Step 4:

[1519] As the user progresses through the training program, the device collects and transmits data about the user's progress to a server, which stores the data in a database.

[1520] Input: User progress data

[1521] Output: Save to database

[1522] Step 5:

[1523] The server sends the collected progress data to the emotion engine, which analyzes the data, recognizes the user's emotional state, and generates emotion data, which is then sent back to the server.

[1524] Input: Progress data

[1525] Output: Emotion data

[1526] Step 6:

[1527] The server sends emotion data and progress data to the generative AI model and sends a request to generate a feedback message. The generative AI model generates appropriate feedback based on the emotion data and progress data and sends it back to the server.

[1528] Input: Emotion data and progress data

[1529] Output: Feedback message

[1530] Step 7:

[1531] The server sends the generated feedback message to the terminal and displays it to the user, who receives the feedback and continues training.

[1532] Input: Feedback message

[1533] Output: Message displayed on the terminal

[1534] Step 8:

[1535] Periodically, the server collects the user's historical data and sends it to the generative AI model. The generative AI model analyzes the historical data and generates personalized learning suggestions, which are then sent back to the server. The server then sends these suggestions to the user's device for display.

[1536] Input: User history data

[1537] Output: Generate and display learning suggestions

[1538] 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.

[1539] 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.

[1540] 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.

[1541] [Fourth embodiment]

[1542] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1543] 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.

[1544] 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).

[1545] 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.

[1546] 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.

[1547] 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).

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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."

[1555] This invention provides a system called "Buddy AI" that uses generative AI to solve the problems of in-house mentoring programs. This system allows users to start a consultation via their device, and the server uses a generative AI model to provide appropriate responses and feedback, creating an environment where users can easily receive consultation and support at any time.

[1556] The system configuration of the present invention is as follows.

[1557] 1. User Registration

[1558] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration.

[1559] 2. Starting a consultation

[1560] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device. For example, a message such as "Hello! What would you like to consult about today?" is displayed.

[1561] 3. Dialogue Progress

[1562] The user inputs and sends the inquiry. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the device. For example, in response to a question such as, "I'm having trouble managing the schedule for a new project. Do you have any advice?" the generative AI model provides specific advice.

[1563] 4. Goal setting and progress management

[1564] When a user requests a consultation on goal setting, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. The generative AI model creates an outline for goal setting, and the server displays it on the device. For example, the model might provide content such as, "To efficiently manage the schedule of a new project, we propose the following plan..."

[1565] 5. Providing Feedback

[1566] The user enters progress updates on the device. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, which the server displays on the device. For example, feedback might be provided such as, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[1567] 6. Usage history learning and personalization

[1568] The server periodically sends the user's usage history to the generative AI model as learning data. The generative AI model learns from that data and provides the user with more personalized feedback. For example, personalized feedback such as "Based on your past consultation history, we will narrow down and suggest important points for schedule management for your new project..." is provided.

[1569] In this way, this invention is a system that uses generative AI to provide an environment where employees can easily consult and receive feedback at any time, solving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[1570] The processing flow will be explained below.

[1571] Step 1:

[1572] The user accesses the Buddy AI system website via their device and opens the registration page.

[1573] Step 2:

[1574] The user enters the required information (name, email address, job title, department, etc.) into the registration form.

[1575] Step 3:

[1576] The user clicks the "Register" button and submits the registration information.

[1577] Step 4:

[1578] The server receives the user's input and stores it in a database.

[1579] Step 5:

[1580] The server will send the user an email notifying them of the completion of registration.

[1581] Step 6:

[1582] The user logs into the Buddy AI system from their device and goes to the dashboard screen.

[1583] Step 7:

[1584] The user clicks the "Start Consultation" button.

[1585] Step 8:

[1586] The server receives the user's consultation request and sends a request to the generative AI model to start a session.

[1587] Step 9:

[1588] The generative AI model creates an initial greeting message and returns it to the server.

[1589] Step 10:

[1590] The server displays an initial greeting message on the user's terminal.

[1591] For example: "Hello! What would you like to discuss today?"

[1592] Step 11:

[1593] The user enters the consultation content in the chat box and clicks the "Send" button.

[1594] Step 12:

[1595] The server receives user input and sends it to the generative AI model.

[1596] Step 13:

[1597] The generative AI model generates a response based on the user's inquiry.

[1598] Step 14:

[1599] The server receives the generated response and displays it on the user's terminal.

[1600] Step 15:

[1601] If the user wishes to continue the dialogue or set a goal, they input a request for goal setting.

[1602] Step 16:

[1603] The server sends a goal setting request to the generative AI model.

[1604] Step 17:

[1605] The generative AI model generates questions to assist with goal setting and returns them to the server.

[1606] Step 18:

[1607] The server displays the generated question on the user's terminal.

[1608] Step 19:

[1609] The user answers the question and submits the answer in the chat box.

[1610] Step 20:

[1611] The server receives the user's answers and sends them to the generative AI model.

[1612] Step 21:

[1613] A generative AI model generates a goal setting outline based on the user's answers.

[1614] Step 22:

[1615] The server displays the generated outline on the user's terminal.

[1616] Step 23:

[1617] After setting a goal, if the user wishes to report progress, they can enter and submit updated information from their device.

[1618] Step 24:

[1619] The server receives the user's updated information and stores it in a database.

[1620] Step 25:

[1621] The server sends updates to the generative AI model.

[1622] Step 26:

[1623] The generative AI model generates feedback based on the updated information and returns it to the server.

[1624] Step 27:

[1625] The server displays the generated feedback on the user's terminal.

[1626] Step 28:

[1627] The server periodically generates the user's usage history and sends it to the AI ​​model as learning data.

[1628] Step 29:

[1629] A generative AI model learns from users' usage history and generates increasingly personalized feedback.

[1630] Step 30:

[1631] The server displays the personalized feedback on the user's terminal.

[1632] In this way, users can use "Buddy AI" to receive individual consultations, set goals, monitor progress, and receive feedback.

[1633] Example 1

[1634] 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."

[1635] Traditional in-company mentoring systems have many restrictions on the timing and content of consultations, making it difficult to receive appropriate feedback quickly. Furthermore, some employees may become overly reliant on specific mentors, making it difficult to receive personalized advice. This can lead to ineffective goal setting and progress management for employees, hindering work efficiency and growth.

[1636] 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.

[1637] In this invention, the server includes a means for a user to send a request to start a consultation via a terminal, a means for sending a request to the generative AI model to generate an initial greeting message, and a means for the generative AI model to receive a request to start a session including the user's basic information. This enables the generative AI model to provide specific advice based on the user's input. The generative AI model also generates a response based on user information stored in a database, allowing for more personalized feedback to the user. This provides an environment where employees can easily receive consultation and support at any time, enabling effective goal setting and progress management.

[1638] "User" refers to an individual who uses the system to receive consultation and feedback.

[1639] "Terminal" refers to a device, such as a PC or smartphone, that a user uses to access the system.

[1640] A "request" refers to an action or request made by a user to a server.

[1641] "Server" refers to a computer that receives a user's request, communicates with a generative AI model to generate an appropriate response, and returns it to the user.

[1642] A "generative AI model" refers to software that uses artificial intelligence to generate appropriate responses to user input.

[1643] "Initial greeting message" refers to a message containing a welcome message or question that a generative AI model generates during its first interaction with a user.

[1644] A "session" refers to a series of interactions between a user and a generative AI model.

[1645] "Personalized feedback" refers to tailored feedback provided based on a user's past usage history and specific needs.

[1646] "Response" refers to the reply or advice that a generative AI model generates based on a user's request.

[1647] "Goal setting" refers to the process of defining the objectives or goals that users want to achieve.

[1648] "Progress management" refers to the process of monitoring a user's progress toward achieving their goals and providing appropriate advice or corrections.

[1649] This invention provides a system called "Buddy AI" that uses a generative AI model to solve the problems of in-house mentoring programs. This system allows users to start a consultation via their device, and the server uses a generative AI model to provide appropriate responses and feedback, creating an environment where users can easily receive consultation and support at any time.

[1650] System Configuration

[1651] 1. User Registration

[1652] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration. Specifically, the user enters information such as name, email address, and department into the registration form, and the server stores that information in a database.

[1653] 2. Starting a consultation

[1654] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device. For example, a message such as "Hello! What would you like to consult about today?" is displayed.

[1655] 3. Dialogue Progress

[1656] The user inputs and submits the content of their inquiry. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the device. For example, if a user asks, "I'm having trouble managing the schedule for a new project. Do you have any advice?" the generative AI model will provide specific advice.

[1657] 4. Goal setting and progress management

[1658] When a user requests a consultation on goal setting, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. For example, the service might provide content such as, "To efficiently manage the schedule of a new project, we propose the following plan..."

[1659] 5. Providing Feedback

[1660] The user enters progress updates on the device. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, which the server displays on the device. For example, the feedback might be, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[1661] 6. Usage history learning and personalization

[1662] The server periodically sends the user's usage history to the generative AI model as learning data. The generative AI model learns from that data and provides the user with more personalized feedback. For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest important points for schedule management for your new project..." is provided.

[1663] In this way, the present invention is a system that uses a generative AI model to provide an environment where employees can easily consult with or receive feedback at any time, thereby resolving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[1664] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1665] Step 1:

[1666] A user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information in the new registration form. The input data includes name, email address, department, etc. This data is sent to the server. Specifically, the user opens a browser, enters the system's URL, enters the required information in the form, and clicks the submit button.

[1667] Step 2:

[1668] The server receives the user's input information and saves the data in a database. The received data includes the user name, email address, department, etc., and performs data validation to ensure that it is saved accurately in the database. As a concrete example, the server issues an insert query to the database and saves the data. If the save is successful, the result is confirmed.

[1669] Step 3:

[1670] The server sends the user an email to notify them that registration is complete. The email contains a message informing them that registration is complete and instructions for the next step. The server uses the user's email address as input data and uses the email sending API to send a confirmation email for registration completion.

[1671] Step 4:

[1672] A user logs in to the system from a terminal. An email address and password are required as input data. The server uses this input data to authenticate the user, and if authentication is successful, the dashboard screen is displayed on the terminal. Specifically, the user opens the login page in a browser, enters their email address and password, and clicks the login button.

[1673] Step 5:

[1674] The user clicks the "Start Consultation" button. The server sends a session start request to the generative AI model, including the user's basic information. The user's basic information is used as input data, and an initial greeting message is generated as output. The generative AI model receives this request and generates a prompt message such as "Hello! What would you like to consult about today?", which is then displayed on the device.

[1675] Step 6:

[1676] The user inputs and sends the consultation content. The input data is the consulting content, such as "I'm having trouble managing the schedule of a new project. Do you have any advice?" The server receives this input data, sends it to the generative AI model, and generates an appropriate response. The generative AI model creates an answer based on the user's input and generates advice as output data. The generated response is displayed on the device.

[1677] Step 7:

[1678] A user requests advice on goal setting. The server sends the request to the generative AI model. The input data is the user's request regarding their goal. The generative AI model generates a question to clarify the user's goal, and the server displays the question on the device. Specifically, the generative AI model generates the question, "What kind of goal do you want to set?"

[1679] Step 8:

[1680] The user answers questions, and the server saves the answers and sends them to the generative AI model. The input data are the answers about the user's goals. The server saves the data in a database, and the generative AI model receives the data and creates an outline for goal setting. Once the outline is generated, the server displays it on the user's device. For example, an outline such as "We propose the following plan to efficiently manage the schedule of a new project..." may be displayed.

[1681] Step 9:

[1682] The user inputs progress updates on their device. The input data includes their current progress and achievements. The server stores the updates in a database and sends them to the generative AI model. The generative AI model generates feedback based on the updates, and the server displays the feedback on the device. For example, the feedback might read, "Thank you for reporting on your progress last week. To keep up, let's focus on the following tasks as your next steps..."

[1683] Step 10:

[1684] The server periodically sends the user's usage history to the generative AI model as learning data. The input data includes past consultation details and progress data. The generative AI model learns from this data and provides personalized feedback to the user. The output data is feedback tailored to the user's specific needs. For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest key points for schedule management for your new project..." is generated.

[1685] (Application example 1)

[1686] 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."

[1687] Currently, factories lack an environment where workers can receive real-time advice on robot and machine operation. As a result, there are problems with efficient work flows and machine maintenance. There is also a lack of systems that effectively support goal setting and progress management, which is a factor that reduces production efficiency. Therefore, it is necessary to provide an environment where real-time support and consultation can be provided between robots and machines and workers on factory floors.

[1688] 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.

[1689] In this invention, the server includes a means for a user to send a request to start a consultation via a terminal, a means for the server to receive the request and send a request to the generative AI model to generate an initial greeting message, a means for the generative AI model to generate the initial greeting message based on the request, a means for displaying the initial greeting message on the user's terminal, a means for sending a request for assistance with physical work, a means for generating a work procedure based on the request, and a means for displaying the work procedure on the user's terminal. This enables workers to receive real-time assistance and consultation regarding the operation and maintenance of robots and machines. It also enhances support for goal setting and progress management.

[1690] A "user" is a person who starts a consultation via a terminal and uses the functions provided by the system.

[1691] A "terminal" is an electronic device used by a user to access the system, including a PC or smartphone.

[1692] A "server" is a central computer that manages the entire system and receives and processes various requests.

[1693] A "generative AI model" is an artificial intelligence technology that generates initial greeting messages, responses, goal setting outlines, and more based on user requests.

[1694] A "request" is an operation request or consultation content that a user sends to a server via a terminal.

[1695] The "initial greeting message" is the greeting that the generative AI model first generates upon receiving a user request.

[1696] "Consulting content" refers to the specific consultation matters and questions that users ask about through the system.

[1697] A "response" is a reply or advice generated by the generative AI model based on the consulting content.

[1698] "Goal setting" is the process of clarifying the specific goals that users want to achieve.

[1699] "Progress" refers to the status or report of how far you have progressed toward your goal.

[1700] "Feedback" is advice and suggestions for improvement generated by the generative AI model based on its progress.

[1701] A "work procedure" is a specific work procedure or manual that a generative AI model generates to assist with physical work.

[1702] In a system embodying this invention, a "Robo Buddy AI" is installed in a robot working in a factory, and real-time support and consultation is provided between the factory worker and the robot. Specific embodiments are described below.

[1703] Hardware and Software

[1704] 1. Hardware:

[1705] Factory robot control terminals (PCs, smartphones, etc.)

[1706] Server equipment (a central computer for database and AI model processing)

[1707] 2. Software:

[1708] Python

[1709] Flask

[1710] OpenAI API (generative AI model)

[1711] System Operation

[1712] 1. User Registration

[1713] The user accesses the system via a terminal and applies for registration by entering the required information in the new registration form. The server receives this information and stores it in a database. The server then sends the user a notification that registration is complete. With this operation, the user is ready to begin consultations and support.

[1714] 2. Starting a consultation

[1715] The user logs in to the system from their device and clicks the "Start Consultation" button. The server sends the consultation request to the AI ​​model and generates an initial greeting message. The initial greeting message might be something like "Hello! What would you like to consult about today?"

[1716] 3. Dialogue Progress

[1717] The user inputs the content of their inquiry and sends it to the server. The server sends the input to the generative AI model, which generates an appropriate response. The generative AI model creates an answer based on the user's input, and the server displays the response on the user's device. For example, if a user inputs, "Please tell me how to maintain this machine," the generative AI model generates detailed instructions such as, "To maintain this machine, follow these steps..."

[1718] 4. Goal setting and progress management

[1719] When a user requests a consultation on goal setting, the server sends the request to the generative AI model, which then generates a question about goal setting. The server displays the question on the user's device, and the user answers by entering information. The server then sends the input to the generative AI model, which generates an outline of goal setting. This operation allows the user to clarify their goals and effectively manage their progress.

[1720] 5. Providing Feedback

[1721] When a user inputs progress updates on their device, the server stores the updates in a database and sends them to the generative AI model, which generates feedback based on the updates and displays it on the user's device, allowing them to receive specific advice on next steps.

[1722] Specific prompt examples

[1723] Example 1:

[1724] User: How do I maintain this machine?

[1725] Buddy AI:

[1726] Example 2:

[1727] User: I'm having trouble managing the schedule for a new project. Any advice?

[1728] Buddy AI:

[1729] In this way, RoboBuddy AI can be applied to factory robots, enabling real-time support and consultation between workers and robots, improving work efficiency and maintenance quality.

[1730] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1731] Step 1:

[1732] The user accesses the system via a terminal and applies for registration by entering the required information in the new registration form. The input data includes the user's personal information and authentication information. The server receives this information and stores it in a database. The server then sends a notification to the user that registration is complete. Based on the input, the user information is stored in the database and a registration completion notification is generated.

[1733] Step 2:

[1734] The user logs in to the system from their device and clicks the "Start Consultation" button. The server sends the consultation request to the generation AI model and requests it to generate an initial greeting message. The generation AI model receives the request and generates the initial greeting message. The initial greeting message is chosen to be something like "Hello! What would you like to consult about today?" The server displays the generated greeting message on the user's device. The initial greeting message is generated based on the request and displayed on the user's device.

[1735] Step 3:

[1736] The user inputs the consultation content and sends it to the server. For example, "Please tell me how to maintain this machine." The server sends the input content to the generative AI model and sends a request to generate an appropriate response. The generative AI model receives the consulting request and generates a response based on the content. A response such as "The maintenance of this machine will be carried out using the following steps..." is generated. The server displays the generated response on the user's device. Based on the input of the consultation content, specific operating procedures are generated and displayed on the user's device.

[1737] Step 4:

[1738] When a user wishes to consult about goal setting, they send a dedicated request. The server sends the goal setting request to the generative AI model, which then sends a request to generate a question related to goal setting. The generative AI model receives the request and generates a question related to goal setting. The question might be something like, "What should you aim for in order to efficiently manage the schedule of a new project?" This is then displayed on the user's device. The user enters information to answer the question and sends it to the server. The input is sent to the generative AI model, which generates a goal setting outline. The outline is generated and displayed on the user's device. Specific goal setting questions and their outlines are generated based on the input and displayed on the user's device.

[1739] Step 5:

[1740] The user inputs update information from their device to report their progress and sends it to the server. The server stores this update information in a database and sends it to the generative AI model. The generative AI model generates feedback based on the update information. Feedback such as "Thank you for reporting on your progress last week. To keep up the good work, let's focus on the following task as your next step..." is generated. The server displays the generated feedback on the user's device. Specific feedback is generated based on the progress input and displayed on the user's device.

[1741] 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.

[1742] This invention provides a system called "Buddy AI" that combines generative AI and an emotion engine to solve the challenges of in-company mentoring programs. With this system, users start consultations via their devices, and the server uses a generative AI model to provide appropriate responses and feedback. Furthermore, the emotion engine recognizes the user's emotions and provides personalized responses based on these, creating an environment where users can easily receive consultations and support at any time.

[1743] The system configuration of the present invention is as follows.

[1744] 1. User Registration

[1745] The user accesses the "Buddy AI" system from a device (such as a PC or smartphone) and applies for registration by entering the required information into the new registration form. The server receives this information and stores it in a database. The server then sends the user an email notifying them of the completion of registration.

[1746] 2. Starting a consultation

[1747] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request to the generative AI model to start a session, including the user's basic information. The generative AI model generates an initial greeting message and displays it on the device.

[1748] For example, a message might say, "Hello! What would you like to talk about today?"

[1749] 3. Dialogue Progress

[1750] The user inputs and submits the consultation content. The server sends the input content to the emotion engine, which analyzes the text entered by the user and generates emotion data. The emotion data includes information about the user's emotional state (joy, sadness, anger, etc.).

[1751] 4. Use of Emotional Data

[1752] The server sends the emotional data and the content of the consultation to the generative AI model, which then generates a response based on this information. The response is tailored to take into account the user's emotional state.

[1753] For example, if a user inputs, "I'm having trouble managing the schedule for a new project," and the emotional data indicates "stress," the generative AI model will generate a response such as, "Project management is certainly difficult, but if you take it one step at a time, you can definitely achieve it. Let's think together about the next step."

[1754] 5. Providing a Response

[1755] The server receives the generated response and displays it on the user's terminal. The user can continue the dialogue or, if they wish to set a goal, enter a request for goal setting.

[1756] 6. Goal setting and progress management

[1757] When a user requests a goal setting consultation, the server sends the request to the generative AI model. The generative AI model generates questions to clarify the user's goals, and the server displays the questions on the device. The user enters answers, which the server saves and sends to the generative AI model. The generative AI model creates a goal setting outline, which the server displays on the device.

[1758] For example, you might receive something like, "We propose the following plan to efficiently manage the schedule of your new project..."

[1759] 7. Providing Feedback

[1760] The user inputs update information from the device to report progress. The server stores the update information in a database and sends it to the emotion engine. The emotion engine analyzes the update information and generates emotion data. The server sends the emotion data and update information to the generative AI model, which then generates feedback based on it and the server displays it on the device.

[1761] For example, feedback might be provided such as, "Thank you for your progress report last week. To keep up, let's focus on the following tasks as next steps..."

[1762] 8. Usage learning and personalization

[1763] The server periodically sends the user's usage history to the generative AI model and emotion engine as learning data, which the generative AI model and emotion engine then use to learn from the data and provide the user with more personalized feedback.

[1764] For example, personalized feedback such as, "Based on your past consultation history, we will narrow down and suggest key points for schedule management for your new project..." is provided.

[1765] In this way, this invention is a system that uses generative AI and an emotion engine to provide an environment where employees can easily consult with or receive feedback at any time, solving various issues in mentoring programs. By supporting employee goal setting and progress management, it can promote efficient work execution and growth.

[1766] The processing flow will be explained below.

[1767] Step 1:

[1768] The user accesses the Buddy AI system website via their device and opens the new registration page.

[1769] Step 2:

[1770] The user enters the required information (name, email address, job title, department, etc.) into the registration form.

[1771] Step 3:

[1772] The user clicks the "Register" button and submits the registration information.

[1773] Step 4:

[1774] The server receives the user's registration information and stores it in a database.

[1775] Step 5:

[1776] The server will send the user an email notifying them of the completion of registration.

[1777] Step 6:

[1778] The user logs into the Buddy AI system from their device and goes to the dashboard screen.

[1779] Step 7:

[1780] The user clicks the "Start Consultation" button.

[1781] Step 8:

[1782] The server receives the user's consultation request and sends a request to the generative AI model to start a session.

[1783] Step 9:

[1784] The generative AI model creates an initial greeting message and returns it to the server.

[1785] For example, "Hello! What would you like to discuss today?"

[1786] Step 10:

[1787] The server displays an initial greeting message on the user's terminal.

[1788] Step 11:

[1789] The user enters the consultation content in the chat box and clicks the "Send" button.

[1790] Step 12:

[1791] The server receives the user's input and sends it to the emotion engine.

[1792] Step 13:

[1793] The emotion engine analyzes the user's input text and generates emotion data.

[1794] Example: Detecting emotions such as "stress" or "anxiety" from text.

[1795] Step 14:

[1796] The server sends the user's consultation details, including emotional data, to the generative AI model.

[1797] Step 15:

[1798] A generative AI model generates a response based on emotional data and the content of the consultation.

[1799] For example: "Project management can be challenging, but it can be achieved if you take it one step at a time. Let's figure out next steps together."

[1800] Step 16:

[1801] The server receives the generated response and displays it on the user's terminal.

[1802] Step 17:

[1803] If the user wishes to continue the dialogue or set a goal, they input a request for goal setting.

[1804] Step 18:

[1805] The server sends a goal setting request to the generative AI model.

[1806] Step 19:

[1807] The generative AI model generates questions to clarify the user's goals and returns them to the server.

[1808] Step 20:

[1809] The server displays the generated question on the user's terminal.

[1810] Step 21:

[1811] The user answers the question and submits the answer in the chat box.

[1812] Step 22:

[1813] The server receives the user's answers and sends them to the generative AI model.

[1814] Step 23:

[1815] A generative AI model generates a goal setting outline based on the user's answers.

[1816] Step 24:

[1817] The server displays the generated outline on the user's terminal.

[1818] For example: "To efficiently manage the schedule for the new project, we propose the following plan..."

[1819] Step 25:

[1820] After setting a goal, if the user wishes to report progress, they can enter and submit updated information from their device.

[1821] Step 26:

[1822] The server receives the user's updated information and stores it in a database.

[1823] Step 27:

[1824] The server sends updates to the emotion engine.

[1825] Step 28:

[1826] The emotion engine analyzes the updated information and generates emotion data.

[1827] Step 29:

[1828] The server sends the emotion data and updates to the generative AI model.

[1829] Step 30:

[1830] A generative AI model generates feedback based on emotional data and updates.

[1831] Step 31:

[1832] The server displays the generated feedback on the user's terminal.

[1833] For example: "Thank you for your progress report last week. To keep up, let's focus on these next tasks..."

[1834] Step 32:

[1835] The server periodically generates user usage history and sends it to the AI ​​model and emotion engine as learning data.

[1836] Step 33:

[1837] Generative AI models and emotion engines learn from usage history and generate personalized feedback.

[1838] Step 34:

[1839] The server displays the personalized feedback on the user's terminal.

[1840] Example: "Based on past consultation history, we will narrow down and propose key points for schedule management for the new project..."

[1841] In this way, users can use "Buddy AI" to receive individual consultations, goal setting, progress management, and feedback. Furthermore, by combining it with an emotion engine, the system can provide personalized responses that take into account the user's emotional state, resolving various issues in mentoring programs.

[1842] Example 2

[1843] 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."

[1844] Traditional mentoring systems have struggled to provide personalized feedback and consultation to individual employees, particularly in providing emotional support and appropriate responses in a timely manner. This can lead to a risk of lowering employee motivation and efficiency, potentially negatively impacting corporate performance. Furthermore, it has been difficult to balance consistency and individual attention when it comes to employee progress management and goal setting.

[1845] 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.

[1846] In this invention, the server includes: means for the user to send a request to start a consultation via a terminal; means for the server to receive the request and send a request to the generative AI model to generate an initial greeting message; means for the generative AI model to generate the initial greeting message based on the request; means for the server to display the initial greeting message on the user's terminal; means for the server to send the user's input to the emotion engine and send a request to generate emotion data; means for the emotion engine to generate emotion data based on the request; means for the server to send the emotion data and the user's input to the generative AI model and send a request to generate a response; means for the generative AI model to generate a response based on the request and taking the emotion data into consideration; means for displaying the response on the user's terminal; means for periodically sending the user's usage history to the generative AI model and the emotion engine as learning data and using it for personalization; means for the server to store the user's progress in a database, send update information to the emotion engine to generate emotion data, and means for generating a response based on the emotion data and displaying it on the user's terminal. This enables personalized responses and feedback to be provided to individual employees, improving employee motivation and efficiency and contributing to improved corporate performance.

[1847] "User" refers to an individual who uses the system to provide consultation and feedback.

[1848] A "terminal" is a device used by a user to access the system, including a PC, smartphone, etc.

[1849] "Request" refers to a command or request for information sent by a user or system to a generative AI model or emotion engine.

[1850] A "server" is a computer system that is the central part of the system and manages data storage, processing, and communication with other components.

[1851] A "generative AI model" refers to an artificial intelligence model that uses natural language processing techniques to generate appropriate responses or feedback in response to user input.

[1852] An "initial greeting message" refers to the first message sent by the generative AI model when a user begins a consultation.

[1853] "Emotion engine" refers to a technology or system that analyzes and generates emotional data from user text input.

[1854] "Emotion data" refers to data indicating an emotional state (e.g., joy, sadness, anger, etc.) extracted from a user's text input.

[1855] "Response" refers to the message that the generative AI model generates based on user input and emotional data.

[1856] "Usage history" refers to past consultation details and feedback generated while a user is using the system.

[1857] "Training Data" refers to the datasets used by generative AI models and emotion engines to improve their performance.

[1858] "Progress" refers to information about how a user is progressing toward achieving a goal.

[1859] "Updates" refers to new information entered by a user to report progress or make changes.

[1860] This invention provides a system called "Buddy AI" that supports in-company mentoring programs by combining a generative AI model and an emotion engine. The system allows users to initiate consultations through their devices, and the server provides appropriate responses and feedback. It also uses the emotion engine to recognize the user's emotions and delivers personalized responses based on those emotions.

[1861] Hardware and software used

[1862] Terminal: A device such as a PC or smartphone through which a user accesses the system.

[1863] Server: The central computer system of the system that stores and processes data and manages communication with other components.

[1864] Generative AI model: An artificial intelligence model that uses natural language processing techniques to generate appropriate responses and feedback in response to user input, such as OpenAI's GPT-3.

[1865] Emotion engine: Technology that analyzes and generates emotional data from user input text, such as Microsoft's Text Analytics.

[1866] Database: A data storage device such as MySQL for managing user information, progress, consultation details, etc.

[1867] System processing overview

[1868] 1. User Registration

[1869] The user opens a web browser on their device (PC or smartphone) and accesses the specified URL. They enter the required information (name, email address, password, etc.) into the new registration form and submit their registration request. The server receives this information and stores it in a database. The server then sends an email notifying the user that registration is complete.

[1870] 2. Starting a consultation

[1871] The user logs in from their device and clicks the "Start Consultation" button. The server sends a request containing the user's ID and session information to the generative AI model. The generative AI model generates an initial greeting message (e.g., "Hello! What would you like to consult about today?") and displays it on the user's device via the server.

[1872] 3. Dialogue Progress

[1873] The user inputs and submits the content of their consultation. The server sends this input text to the emotion engine, which generates emotion data. The emotion engine analyzes the user's emotional state and returns the generated emotion data to the server. The server then sends the emotion data and the content of their consultation to the generative AI model, which then generates a response that takes the emotion data into account. The response is returned to the server in JSON format, and the server displays it on the device.

[1874] Specific examples

[1875] For example, when a user consults about schedule management for a new project, the following dialogue takes place:

[1876] User: "I'm having trouble managing the schedule for my new project."

[1877] The emotion engine generates "stress" emotion data.

[1878] Generative AI model: "Project management is hard, but it's achievable if you take it one step at a time. Let's figure out the next steps together."

[1879] Next, if the user requests a goal setting consultation, the server sends the request to the generative AI model.

[1880] Generative AI model: "To set your goal, what do you want to achieve first?"

[1881] Once the user enters their answer, the generative AI model creates an outline, which the server displays on the device.

[1882] Through these steps, the system of the present invention provides personalized assistance to users and solves the challenges of mentoring within a company.

[1883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1884] Step 1:

[1885] The user accesses the "Buddy AI" system via a terminal and applies for registration by entering the necessary information into the new registration form.

[1886] Input: User information (name, email address, password, etc.)

[1887] and output: Registration completion notification email

[1888] Specific operation: The user opens a web browser, accesses the specified URL, enters the required information in the registration form, and clicks the "Register" button.

[1889] The server receives this information and stores it in a database.

[1890] Input: User registration information

[1891] Output: User information stored in the database, email notifying registration completion

[1892] Specific operation: The server receives the form data, stores it in a database such as MySQL, and then sends an email to notify the user that registration has been completed using the SMTP protocol.

[1893] Step 2:

[1894] The user logs in from the terminal and clicks the "Start Consultation" button.

[1895] Input: Login information (email address, password)

[1896] Output: Show initial greeting message

[1897] Specific operation: The user accesses the login page, enters their email address and password, and clicks the "Login" button. After logging in, they click the "Start Consultation" button from the menu.

[1898] The server sends a request to the generative AI model, including the user's ID and session information.

[1899] Input: User ID, session information

[1900] Output: An initial greeting message from the generative AI model

[1901] Specific operation: The server constructs session information and sends a request to the generative AI model using an API. The generative AI model generates an initial greeting message (e.g., "Hello! What would you like to discuss today?") and displays it on the device via the server.

[1902] Step 3:

[1903] The user inputs the consultation content and sends it.

[1904] Input: Text of consultation content

[1905] Output: Emotion data, response from generative AI model

[1906] Specific operation: The user enters the content of the consultation into the chat window and clicks the "Send" button.

[1907] The server sends the input content to the emotion engine, which generates emotion data.

[1908] Input: User's inquiry

[1909] Output: Emotion data

[1910] Specific operation: The server sends the user's consultation content to the emotion engine API, and the emotion engine analyzes the text and generates emotion data (e.g., "joy," "sadness," "anger," etc.).

[1911] The server sends the emotion data and the consultation details to the generative AI model, which generates a response.

[1912] Input: User's consultation details, emotional data

[1913] Output: The response from the generative AI model

[1914] Specific operation: The server sends a request containing emotion data and the consultation content to the generative AI model, which then generates a response that takes the emotion data into account. The server receives the generative AI model's response and displays it on the device.

[1915] Step 4:

[1916] The server receives the generated response and displays it on the user's terminal.

[1917] Input: Response from a generative AI model

[1918] Output: The response displayed on the user's terminal

[1919] Specific operation: The server receives the response from the generative AI model, converts it into HTML format, and displays it in the chat window.

[1920] The user continues the dialogue or inputs their goal setting preference.

[1921] Input: New consultation or goal setting request

[1922] Output: The next response from the generative AI model

[1923] Specific action: The user enters and submits a new consultation, or clicks the "Set Goal" button to submit a request.

[1924] Step 5:

[1925] The server sends the goal setting consultation to the generative AI model.

[1926] Input: Goal setting request

[1927] Output: Goal setting questions

[1928] Specific operation: The server sends a request regarding goal setting to the generative AI model, and the generative AI model generates a question regarding goal setting.

[1929] A generative AI model generates goal-setting questions that are displayed on the device.

[1930] Input: Goal setting request

[1931] Output: Goal setting questions

[1932] Specific behavior: The generative AI model generates questions related to goal setting, and the server displays them on the device (e.g., "What is the first step to achieving your goal?").

[1933] Users enter answers to questions, and the server stores them and sends them to the generative AI model.

[1934] Input: User's answer

[1935] Output: The answer sent to the generative AI model

[1936] What happens: The user answers the goal-setting questions and clicks the "Submit" button. The server stores the answers in a database and sends them to the generative AI model.

[1937] A generative AI model creates an outline of the goal setting, which the server displays on the device.

[1938] Input: User's answer

[1939] Output: Goal setting outline

[1940] How it works: The generative AI model creates an outline of goal setting based on the user's answers (e.g., "A plan for efficiently managing the schedule of a new project"), and the server displays it on the device.

[1941] Step 6:

[1942] The user enters updates to report progress, which the server stores and sends to the emotion engine.

[1943] Input: Progress update

[1944] Output: Emotion data, feedback from generative AI models

[1945] Specific operation: The user enters the progress status in the chat window and clicks the "Send" button. The server saves the progress status in the database and sends it to the emotion engine.

[1946] The emotion engine analyzes the updated information and generates emotion data.

[1947] Input: Progress update

[1948] Output: Emotion data

[1949] Specific behavior: The emotion engine analyzes the progress text and generates emotion data.

[1950] The server sends the emotion data and updates to the generative AI model to generate feedback.

[1951] Input: Emotion data, progress updates

[1952] Output: Feedback

[1953] Specific operation: The generative AI model generates feedback based on emotional data and progress information, and the server displays it on the device (e.g., "Thank you for your progress report last week. To keep up the good work, let's focus on the following tasks as the next step").

[1954] Step 7:

[1955] The server periodically generates usage history and sends it to the AI ​​model and emotion engine as learning data, which is then used for personalization.

[1956] Input: Usage history data

[1957] Output: Personalized responses and feedback

[1958] Specific operation: The server periodically extracts usage history data and sends it to the generative AI model and emotion engine. This enables the generative AI model and emotion engine to provide optimized feedback for each user (e.g., "Based on your past consultation history, we will narrow down and suggest important points for schedule management for a new project").

[1959] (Application example 2)

[1960] 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."

[1961] Conventional in-house mentoring systems lack an environment where employees can easily seek advice, and do not provide sufficient support to individual employees. Furthermore, appropriate responses and feedback to consultations are often delayed, often hindering the improvement of individual employees' performance. The present invention aims to solve these problems and provide an environment where employees can easily seek advice and support at any time.

[1962] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1963] In this invention, the server includes means for a user to send a request to start a consultation via a terminal, means for starting a training program selected by the user and recording progress, means for an emotion engine to recognize the user's emotional state and generate a feedback message based on a generative AI model, and means for analyzing the user's historical data and creating new learning suggestions using the generative AI model and displaying them on the user's terminal. This allows employees to receive continuous personalized feedback, enabling efficient learning and improved performance.

[1964] "User" means an individual who utilizes the System to conduct training programs or consultations.

[1965] A "terminal" is a device, such as a smartphone or head-mounted display, that connects to the system and operates it.

[1966] A "request" is a request or inquiry sent by a user to a system.

[1967] A "server" is a computer system that receives requests and interacts with generative AI models and emotion engines.

[1968] A "generative AI model" is an artificial intelligence model that generates responses or feedback messages based on requests.

[1969] An "initial greeting message" is the first message generated by the generative AI model when a user begins a consultation.

[1970] A "Training Program" is a set of educational content or activities that a user selects for learning or training.

[1971] "Progress" is information that indicates the degree of progress and achievement of the user as he or she progresses through the training program.

[1972] An "emotion engine" is a system that has the ability to analyze user input data and recognize the user's emotional state.

[1973] A "feedback message" is a response message to the user that the generative AI model generates based on the analysis results of the emotion engine.

[1974] "History data" refers to data from when a user has used the system in the past, including learning and consultation history.

[1975] "Learning suggestions" are suggestions for new learning and improvement that the generative AI model creates based on the user's historical data.

[1976] An "outline" is a summary or plan created by a generative AI model related to goal setting.

[1977] This invention provides a system called "Buddy AI" that combines generative AI and an emotion engine to solve the challenges of in-company mentoring programs. With this system, users start consultations via their devices, and the server uses a generative AI model to provide appropriate responses and feedback. Furthermore, the emotion engine recognizes the user's emotions and provides personalized responses based on these, creating an environment where users can easily receive consultations and support at any time.

[1978] Hardware and software used

[1979] Hardware

[1980] Terminal: A device that connects to the system and operates it, such as a smartphone or head-mounted display.

[1981] Server: A computer system that receives requests and interacts with the generative AI model and emotion engine.

[1982] software

[1983] Programming languages: Python, JavaScript

[1984] Frameworks: TensorFlow (generative AI), NLP (natural language processing), Emotion API

[1985] Database: MySQL

[1986] Frontend: React Native

[1987] Natural language processing explanation

[1988] 1. User Registration and Login

[1989] A user accesses the system using a terminal and creates an account by entering the required information in a new registration form.

[1990] This information is sent to the server and stored in a MySQL database, and an authentication token is generated and sent to the user.

[1991] 2. Select and begin a training program

[1992] After logging in, the user can see a list of training programs offered, which are retrieved from a database via a query and displayed on the terminal.

[1993] When the user selects a training program, the server records the selection and triggers the initiation process.

[1994] 3. Progress management and feedback

[1995] During the course of the program, user input data is collected and sent to the server.

[1996] The server sends this data to the emotion engine for sentiment analysis, which generates the analysis results and sends them to the generative AI model.

[1997] Based on the analysis results, the generative AI model generates a feedback message that takes into account the user's emotions and displays it on the device.

[1998] 4. Personalized study suggestions

[1999] The server periodically collects user history data and sends it to the generative AI model.

[2000] The generative AI model analyzes historical data and generates new learning suggestions based on learning progress and emotional state.

[2001] The content of the proposal is sent from the server to the user's terminal and displayed.

[2002] Specific examples

[2003] Suppose the user enters the following prompt text:

[2004] "I'm working on a new program, but progress is slow and it's frustrating."

[2005] "Based on past history, what areas should we pay particular attention to?"

[2006] In response, the generative AI and emotion engine generate a response like this:

[2007] "It's natural to feel like you're making slow progress. Try setting incremental goals like this..."

[2008] "Based on your history, X is an area that requires special attention. The key takeaway here is..."

[2009] In this way, the system allows users to receive continuous personalized feedback, promoting effective learning and growth.

[2010] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2011] Step 1:

[2012] A user accesses the system via a terminal and applies for registration by entering the required information into a new registration form. The input data, including the user name, email address, and password, is sent to the server. The server receives this and stores it in a MySQL database. After registration is complete, the server generates an authentication token and sends it to the user by email.

[2013] Input: User information entered into the registration form

[2014] Output: Save data to database and generate token

[2015] Step 2:

[2016] The user logs in and checks the list of training programs. The login data (email address and password) is entered into the terminal and sent to the server. The server performs authentication, retrieves the user's training program history from the database, and sends it to the terminal. The user checks the list of programs offered and selects one.

[2017] Input: Login information

[2018] Output: Display a list of programs

[2019] Step 3:

[2020] The user selects and starts a training program, the selected program is sent to the server, which records the selection, and the initial content of the training program is then delivered from the server to the terminal.

[2021] Input: Selected training program

[2022] Output: Initial content delivery

[2023] Step 4:

[2024] As the user progresses through the training program, the device collects and transmits data about the user's progress to a server, which stores the data in a database.

[2025] Input: User progress data

[2026] Output: Save to database

[2027] Step 5:

[2028] The server sends the collected progress data to the emotion engine, which analyzes the data, recognizes the user's emotional state, and generates emotion data, which is then sent back to the server.

[2029] Input: Progress data

[2030] Output: Emotion data

[2031] Step 6:

[2032] The server sends emotion data and progress data to the generative AI model and sends a request to generate a feedback message. The generative AI model generates appropriate feedback based on the emotion data and progress data and sends it back to the server.

[2033] Input: Emotion data and progress data

[2034] Output: Feedback message

[2035] Step 7:

[2036] The server sends the generated feedback message to the terminal and displays it to the user, who receives the feedback and continues training.

[2037] Input: Feedback message

[2038] Output: Message displayed on the terminal

[2039] Step 8:

[2040] Periodically, the server collects the user's historical data and sends it to the generative AI model. The generative AI model analyzes the historical data and generates personalized learning suggestions, which are then sent back to the server. The server then sends these suggestions to the user's device for display.

[2041] Input: User history data

[2042] Output: Generate and display learning suggestions

[2043] 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.

[2044] 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.

[2045] 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.

[2046] 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.

[2047] 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.

[2048] 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.

[2049] 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).

[2050] 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.

[2051] 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."

[2052] 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.

[2053] 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 presen...

Claims

1. A means for a user to send a request to start a consultation via a terminal; A server receives the request and sends a request to generate an initial greeting message to the generative AI model; means for a generative AI model to generate an initial greeting message based on the request; The system includes means for displaying the initial greeting message on a user terminal.

2. A means for users to input consulting details; means for the server to send the input to a generative AI model and send a request to generate an appropriate response; means for a generative AI model to generate a response based on the request; 2. The system of claim 1, further comprising means for displaying said response on a user terminal.

3. a means for a user to submit a request for a goal setting consultation; a server sending the request to a generative AI model to generate a goal setting question; means for a generative AI model to generate goal-setting questions based on the request; means for displaying the question on a user's terminal; A means for the user to input information to answer questions; a server means for receiving the input and transmitting it to a generative AI model; means for a generative AI model to generate a goal setting outline based on said input; 2. The system of claim 1, further comprising means for displaying said outline on a user terminal.

Images