System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving input from a user terminal for conducting a simulated interview; means for generating a next question based on the input; means for managing exchanges of a plurality of questions and answers; and means for providing feedback after the plurality of exchanges.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] This invention solves the problem of university students facing job hunting and internships lacking opportunities to efficiently identify their strengths and weaknesses and practice for interviews. Conventional interview practice relies on face-to-face mock interviews and evaluations by limited instructors, and is often inaccessible. Furthermore, feedback is often vague and lacking in specificity, making self-improvement difficult. [Means for solving the problem]

[0005] The present invention provides a system including a means for receiving input from a user terminal for conducting a mock interview, a means for a generation AI to generate the next question based on the input, a means for managing multiple exchanges of questions and answers, and a means for providing feedback after the multiple exchanges. This system allows users to easily conduct mock interviews and receive specific questions and feedback from the generation AI. The system also includes a means for a user to input what they focused on during their student days, a means for analyzing the input content based on a framework, and a means for the generation AI to generate feedback based on the analysis results, providing an environment in which users can deepen their self-analysis. Furthermore, by including a means for saving user information in a database and a means for managing the user's login status, users can continue to use the system and promote their own growth.

[0006] A mock interview is a simulated practice session that simulates a real interview.

[0007] A "user terminal" is a device such as a computer, smartphone, or tablet that is operated by a user.

[0008] "Generative AI" is a system that uses artificial intelligence technology to automatically generate and evaluate questions based on user input.

[0009] "Input" refers to the provision of information or operations performed by a user on a system.

[0010] "Questions" are questions that are posed to the user during the interview.

[0011] An "answer" is a response provided by a user to a question.

[0012] An "interaction" is a series of questions and answers.

[0013] "Feedback" refers to the evaluation and suggestions for improvement provided by the generating AI in response to the user's answers.

[0014] A "framework" is a standard framework or method for structuring the content of one's academic background (e.g., the STAR method).

[0015] "Analysis" is the process of analyzing the input in detail.

[0016] A "database" is a storage device or area within the system for storing user information and interview data.

[0017] The "logged-in state" refers to a state in which a user is authenticated to the system. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The following describes an embodiment of the present invention. This system is effective for allowing users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika).

[0040] System Overview

[0041] 1. User Registration and Login

[0042] When a user first accesses the system, they register or log in. They enter their name, email address, and password.

[0043] The terminal transmits the input data to the server.

[0044] The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen.

[0045] 2. Course Selection

[0046] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[0047] The terminal transmits the user's selection to the server.

[0048] The server generates an interface according to the selected course and transmits it to the terminal.

[0049] 3. Brush up on your academic background

[0050] If the user selects the "School Background Brush-up Course," a screen for inputting the details of what the user focused on during their school days is displayed.

[0051] The terminal transmits the inputted contents to the server.

[0052] The server uses a generation AI to analyze the content of the Gakuchika based on the framework. For example, if the user enters something like, "My Gakuchika is about my experience as a leader in a club activity at university. As I worked on a project, I came up with ways to deal with problems that arose," the generation AI will provide feedback by adding specific examples and organizing the content chronologically.

[0053] 4. Mock interviews

[0054] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[0055] The terminal sends a start request to the server.

[0056] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[0057] The user enters an answer to the question and clicks the "Submit" button.

[0058] The terminal sends the response to the server.

[0059] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[0060] 5. Providing Feedback

[0061] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[0062] The terminal sends a request to the server.

[0063] The server analyzes the entire response, and the generation AI generates comprehensive feedback (e.g., "Your response is specific and good, but it's important that you speak with more confidence") and sends it to the device.

[0064] The terminal displays the feedback content.

[0065] This system allows users to easily experience mock interviews and brush up on their academic background. Through specific feedback from the generative AI, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for the actual interview.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] A user accesses the system and registers or logs in. The user enters their name, email address, and password.

[0069] Step 2:

[0070] The terminal transmits the entered registration or login information to the server.

[0071] Step 3:

[0072] The server stores the received information in a database and manages the login status. If the login is successful, it sends an instruction to the terminal to redirect the user to the home screen.

[0073] Step 4:

[0074] The server confirms that the user has logged in, generates a screen for selecting either the "Interview Practice Course" or the "School Background Brush-up Course", and sends it to the terminal.

[0075] Step 5:

[0076] On the displayed screen, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course" and clicks the "Next" button.

[0077] Step 6:

[0078] The terminal transmits the user's selection to the server.

[0079] Step 7:

[0080] The server generates the next screen according to the selected course and transmits it to the terminal.

[0081] Step 8:

[0082] (If you select the Gakuchika Brush-up Course)

[0083] The server generates a screen containing input fields based on a framework for academic background (e.g., the STAR method) and sends it to the terminal.

[0084] Step 9:

[0085] The user inputs the details of what he / she focused on during his / her school days and clicks the "Submit" button.

[0086] Step 10:

[0087] The terminal transmits the entered contents of the academic background to the server.

[0088] Step 11:

[0089] The server passes the received academic background information to the generation AI for analysis.

[0090] Step 12:

[0091] The AI ​​analyzes the content of the student's academic background and generates feedback, which is then passed to the server.

[0092] Step 13:

[0093] The server transmits the generated feedback to the terminal and displays it to the user.

[0094] Step 14:

[0095] (If you select the Interview Practice Course)

[0096] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the terminal.

[0097] Step 15:

[0098] The user enters an answer to the initial question and clicks the "Submit" button.

[0099] Step 16:

[0100] The terminal transmits the user's answer to the server.

[0101] Step 17:

[0102] The server passes the received answers to the generation AI for evaluation, which then generates the next question and returns it to the server.

[0103] Step 18:

[0104] The server sends the next question received from the generation AI to the device. This process is repeated 10 times.

[0105] Step 19:

[0106] After 10 rounds of question and answer exchanges, the user clicks the "Get Feedback" button.

[0107] Step 20:

[0108] The terminal transmits the user's request to the server.

[0109] Step 21:

[0110] The server analyzes all the answers with the generation AI and generates comprehensive feedback, which is then passed back to the server.

[0111] Step 22:

[0112] The server transmits the generated feedback to the terminal and displays it to the user.

[0113] Example 1

[0114] 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."

[0115] In recent years, mock interviews and self-analysis have become increasingly required during job hunting, but there is a lack of effective tools for conducting these individually. It is also important to brush up on what you focused on during your student days (gakuchika), but there are limited efficient ways to do this. Furthermore, specific and accurate feedback is necessary for users to understand their strengths and weaknesses and improve their performance in actual interviews. A comprehensive system that can solve these issues is needed.

[0116] 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.

[0117] In this invention, the server includes means for receiving registration and login information from a user terminal, means for storing the information in a database and managing login status, means for the user to select a mock interview or brush-up course, means for receiving input from the user terminal for conducting the mock interview, means for the generative AI model to generate the next question based on the input, means for managing multiple question-and-answer exchanges, and means for providing feedback after the multiple exchanges. This allows users to easily experience mock interviews and brush up on their academic background. Furthermore, through specific feedback from the generative AI model, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for actual interviews.

[0118] A "user terminal" is a device used by a user to access the system, and includes a personal computer, smartphone, tablet, etc.

[0119] A "server" is a part of a computer system that receives and processes information sent from a user's device, storing data and analyzing it using generated AI.

[0120] A "database" is a system for systematically storing user information and other data, and for storing, retrieving, and managing information.

[0121] "Logged-in state" refers to a state in which a user has accessed the system, has been authenticated, and is able to perform operations within the system.

[0122] A "mock interview" is a simulation that mimics a real interview, and is a process in which a user practices an interview through question and answer exchanges.

[0123] The "Brush-up Course" is a program that helps users improve the things they focused on during their student days (gakuchika), and involves inputting and analyzing specific content.

[0124] A "generative AI model" is a system that uses artificial intelligence to generate questions and feedback based on user input.

[0125] "Feedback" refers to evaluations and advice provided based on the results of mock interviews and brush-ups conducted by the user.

[0126] A "framework" is a framework or standard for analyzing user input, and includes, for example, the STAR method (Situation, Task, Action, Result).

[0127] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and brush up on what they focused on during their student days (Gakuchika). This system utilizes a user terminal, a server, and a generative AI model.

[0128] First, a user terminal is a device that provides an interface with the system. Specifically, it includes personal computers, smartphones, tablets, etc. Users access the system through their terminal to register and log in.

[0129] The server receives information sent from the user's device, stores the data, and analyzes it using the generation AI. A database is connected to the server, and user information and mock interview data are systematically stored. A database management system such as MySQL (registered trademark) is used for the database.

[0130] The system works as follows: A user first accesses the system and enters their name, email address, and password on the new registration or login screen. The device sends the entered information to the server. The server stores the received information in a database and manages the login status. If authentication is successful, the user is redirected to the home screen.

[0131] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course." The course selection information is sent from the terminal to the server, and the server generates an interface corresponding to the selected course and sends it to the terminal.

[0132] If a user selects the "Gakuchika Brush-up Course," a screen will appear where they can enter details about what they focused on during their time as a student. The user enters the details, and the device sends the details to the server. The server uses a generative AI (e.g., OpenAI's GPT-4 (registered trademark)) to analyze the entered Gakuchika details and evaluate them based on a framework (such as the STAR method). The generative AI analyzes the details and generates specific feedback.

[0133] For example, if a user enters the following content, "My academic background is my experience as a leader in a club activity at university. When a problem arose during the project, I devised a way to deal with it," the server will use generative AI to provide feedback. For example, it will return advice such as, "Specifically, it would be good to explain in detail at what stage of the project the problem arose, what measures were taken, and what results were achieved as a result."

[0134] On the other hand, if the user selects the "Interview Practice Course," a screen to start the mock interview will be displayed. When the user clicks the start button, the device sends the request to the server. The server uses the generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device. The user enters an answer to the question, and the device sends the answer to the server. The server again uses the generation AI to generate the next question, and this process is repeated 10 times.

[0135] After completing the mock interview, the user clicks the "Receive Feedback" button. The device sends a request to the server, which analyzes all responses and uses a generative AI to generate comprehensive feedback, which is then sent to the device. The device then displays the feedback.

[0136] Examples of prompts include "Tell us about yourself" and "Tell us more about your Gakuchika." In this way, the system allows users to refine their Gakuchika through mock interviews and receive specific feedback.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1:

[0139] A user accesses the system and enters their name, email address, and password on the registration or login screen.

[0140] Input: Name, Email Address, Password

[0141] Specific actions: A user visits a web page, fills in a form, and clicks the "Submit" button.

[0142] Output: Input information is sent from the device to the server.

[0143] Step 2:

[0144] The device sends the entered information to the server, using the HTTPS protocol to send the data securely.

[0145] Input: Name, email address, and password entered by the user

[0146] Specific operation: The device packages the user's input information in JSON format, creates an HTTPS request, and sends it to the server.

[0147] Output: The input information reaches the server.

[0148] Step 3:

[0149] The server stores the received information in a database and manages the login status. MySQL is used for storage.

[0150] Input: Name, email address, and password sent from your device

[0151] Specific operation: The server connects to the database and saves the user information using an INSERT statement. Also, when the login is successful, it creates and manages session information.

[0152] Output: User information is saved in the database and a login session is created for the user.

[0153] Step 4:

[0154] The user is redirected to the home screen and the main menu is displayed. The user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[0155] Input: User login session, home screen request

[0156] Specific operation: After the server confirms the login status, it generates the HTML for the home screen and sends it to the device.

[0157] Output: The home screen is displayed on the user's device.

[0158] Step 5:

[0159] The course information selected by the user is sent from the terminal to the server.

[0160] Input: Course selection information (e.g., "Interview Practice Course" or "Gakuchika Brush-up Course")

[0161] Specific operation: The user clicks on the course icon, and the device sends the information to the server.

[0162] Output: Course selection information is sent to the server.

[0163] Step 6:

[0164] The server generates an interface according to the selected course and transmits it to the terminal.

[0165] Input: Course selection information

[0166] Specific operation: The server dynamically generates HTML according to the selected course and sends it to the terminal.

[0167] Output: A course-specific screen is displayed on the user's device.

[0168] Step 7:

[0169] If the user selects the "Gakuchika Brush-up Course," he or she inputs the contents of his or her Gakuchika.

[0170] Input: Content of your Gakuchika (e.g., "Experience as a leader in a club activity at university")

[0171] Specific behavior: The user enters the details of their academic background and clicks the "Submit" button.

[0172] Output: Input is sent from the terminal to the server.

[0173] Step 8:

[0174] The server sends the input content to the generation AI, which analyzes it based on a framework (e.g., the STAR method).

[0175] Input: Contents of your academic background

[0176] Specific operation: The server sends the user's input as text to the generative AI model and receives the analysis results.

[0177] Output: The analysis results from the generation AI are returned to the server.

[0178] Step 9:

[0179] The server sends the feedback received from the generated AI to the terminal and displays it to the user.

[0180] Input: Analysis results from the generative AI

[0181] Specific operation: The server sends the received feedback information to the terminal in HTML format.

[0182] Output: Specific feedback is displayed on the user's device.

[0183] Step 10:

[0184] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[0185] Input: Course selection information

[0186] Specific operation: When the user clicks "Start", the device sends the request to the server.

[0187] Output: The initial question is generated from the server and sent to the device.

[0188] Step 11:

[0189] The server uses a generation AI to generate mock interview questions and send them to the device.

[0190] Input: Request to start interview

[0191] Specific operation: The server has the generation AI generate the first question and send it to the device.

[0192] Output: The initial question is displayed on the user's terminal.

[0193] Step 12:

[0194] The user enters an answer to the question, and the terminal transmits the answer to the server.

[0195] Input: Answer to the question

[0196] Specific behavior: The user enters an answer and clicks the "Submit" button. The device sends the information to the server.

[0197] Output: The answer arrives at the server.

[0198] Step 13:

[0199] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[0200] Input: Previous answer

[0201] Specific operation: The server asks the generation AI to generate the next question and sends it to the device.

[0202] Output: The following question is displayed on the user's terminal:

[0203] Step 14:

[0204] After the user completes 10 mock interview questions, they click the "Receive Feedback" button.

[0205] Input: 10 questions and answers

[0206] Specific operation: The device sends a request to the server.

[0207] Output: The server sends the data to the generating AI.

[0208] Step 15:

[0209] The server uses generative AI to generate comprehensive feedback and send it to the device.

[0210] Input: All question and answer data

[0211] Specific operation: The server instructs the generation AI to generate feedback based on all data.

[0212] Output: Feedback information is sent to the terminal.

[0213] Step 16:

[0214] The device displays the feedback to the user.

[0215] Input: Feedback data from the generative AI

[0216] Specific behavior: The device receives the feedback information and displays it on the screen.

[0217] Output: Feedback is displayed on the user's screen.

[0218] This allows users to easily experience mock interviews and brush up on their academic background. In addition, through specific feedback from the generative AI model, users can gain a deeper understanding of their strengths and weaknesses, enabling them to effectively prepare for actual interviews.

[0219] (Application example 1)

[0220] 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."

[0221] Customer service in brick-and-mortar stores is directly linked to customer satisfaction, making training essential. However, traditional training methods make it difficult to obtain specific feedback in real time, limiting opportunities for self-improvement. Furthermore, mock interviews and other skill-improvement simulation tools are often provided individually, creating a need for a centralized training system. A system is needed that allows employees to effectively improve their skills without disrupting their daily work.

[0222] 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.

[0223] In this invention, the server includes means for receiving input from a user terminal for conducting a mock interview, means for a generation AI to generate the next question based on the input, means for managing multiple exchanges of questions and answers, means for providing feedback after the multiple exchanges, means for a salesperson to conduct a customer service simulation in a physical store, and means for the generation AI to generate feedback based on the results of the simulation, thereby enabling employees to evaluate and improve their customer service skills in real time through the simulation.

[0224] A "mock interview" is a training session conducted in a format that mimics a real interview.

[0225] A "user terminal" is an electronic device such as a smartphone or tablet that is operated by a user.

[0226] A "means for receiving input" is a mechanism for sending data or instructions from a user to a system.

[0227] "Generative AI" is a technology that uses artificial intelligence to dynamically generate content and responses.

[0228] The "means for generating the next question" is a mechanism by which the AI ​​automatically generates a new question based on the user's answer.

[0229] "Means for managing multiple question and answer exchanges" refers to a mechanism for providing consecutive questions and recording and analyzing the answers.

[0230] The "means for providing feedback" is a mechanism for conveying evaluations and areas for improvement based on the content of the user's responses.

[0231] The "means for sales staff to conduct customer service simulations in a real store" is a mechanism for sales staff working in a real store to practice customer service simulations.

[0232] "Means for the AI ​​to generate feedback based on the simulation results" refers to a mechanism in which the AI ​​analyzes the results of the customer service simulation and automatically generates appropriate feedback.

[0233] The system for implementing the present invention aims to enable users to improve their customer service skills through simulated customer service practice. Details of the system are described below.

[0234] 1. User Registration and Login

[0235] The user (store clerk) first accesses the system and registers or logs in. The user enters their name, email address, and store ID.

[0236] The smartphone sends the entered data to the server. The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen. This process uses MySQL as the database, a cloud server, and the smartphone.

[0237] 2. Select a training course

[0238] After logging in, the user selects a training course. They choose either "Initial Customer Service Training Course" or "Advanced Customer Service Training Course." The smartphone sends the user's selection to the server. The server generates an interface corresponding to the selected course and sends it to the smartphone.

[0239] 3. Customer Service Simulation

[0240] If the user selects the "Initial Customer Service Training Course," a basic customer service simulation is conducted. The user inputs the answers to the simulation and sends them to the server via their smartphone. The server uses a generative AI (e.g., OpenAI GPT-4) to generate the next question. The simulation is conducted over multiple rounds of interaction, with new questions automatically generated after each answer.

[0241] 4. Providing Feedback

[0242] At the end of the simulation, users can receive feedback. The server uses generative AI to generate feedback based on the simulation results and sends it to their smartphone. The feedback provides specific and practical advice, allowing users to improve their customer service skills.

[0243] For example, use the following prompt:

[0244] "A customer asks where an item is. How do you respond?"

[0245] The generative AI provides feedback such as:

[0246] "Your response is helpful, but it would be better if you provided more specific instructions and suggested next steps."

[0247] This system allows users to effectively improve their customer service skills without disrupting operations at physical stores, which is expected to improve the quality of service at stores.

[0248] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0249] Step 1:

[0250] A user (store clerk) accesses the system and performs new registration or login. The user enters their name, email address, and store ID. Once this data is entered, the smartphone sends it to the server. The server stores the received information in a database and manages the login status. Once login is complete, the user is redirected to the home screen. The input data is user information, and the output is the login status and home screen display.

[0251] Step 2:

[0252] After logging in, the user selects a training course. Specifically, they choose either the "Initial Customer Service Training Course" or the "Advanced Customer Service Training Course." The user's selection becomes input data, and the smartphone sends the selection data to the server. The server generates an interface according to the selected course and returns it to the smartphone as output data. This allows the user to access the appropriate interface.

[0253] Step 3:

[0254] If the user selects the "Initial Customer Service Training Course," a simulation begins. The server uses a generation AI to generate an initial customer service scenario (e.g., "A customer has entered the store. How would you respond?"). This scenario becomes the initial input data, and the server sends it to the smartphone. The user enters answers to the scenario and sends them to the server, where the answer data is stored.

[0255] Step 4:

[0256] The server analyzes the received user answers using a generative AI and automatically generates the next question. The analysis results become the input data for generating the next question. After generating the question, the server sends a new scenario to the smartphone. This process is repeated multiple times. The output data is the next scenario, which is presented to the user.

[0257] Step 5:

[0258] After the series of simulations is completed, the server generates feedback based on all response data. The input data for generating this feedback is a set of all responses. The generation AI analyzes this and generates feedback that includes areas for improvement. The server sends the generated feedback to a smartphone. The output data is the feedback content, which the user can check on their smartphone. The feedback includes specific examples and areas for improvement, helping to improve the user's skills.

[0259] 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.

[0260] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika). In addition, the present invention incorporates an emotion engine that recognizes the user's emotions, providing more detailed and appropriate feedback.

[0261] System Overview

[0262] 1. User Registration and Login

[0263] When a user first accesses the system, they register or log in. They enter their name, email address, and password.

[0264] The terminal transmits the input data to the server.

[0265] The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen.

[0266] 2. Course Selection

[0267] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[0268] The terminal transmits the user's selection to the server.

[0269] The server generates an interface according to the selected course and transmits it to the terminal.

[0270] 3. Brush up on your academic background

[0271] If the user selects the "School Background Brush-up Course," a screen for inputting the details of what the user focused on during their school days is displayed.

[0272] The terminal transmits the inputted contents to the server.

[0273] The server uses a generation AI to analyze the content of the Gakuchika based on the framework. For example, if the user enters something like, "My Gakuchika is about my experience as a leader in a club activity at university. As I worked on a project, I came up with ways to deal with problems that arose," the generation AI will provide feedback by adding specific examples and organizing the content chronologically.

[0274] 4. Mock interviews

[0275] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[0276] The terminal sends a start request to the server.

[0277] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[0278] The user enters an answer to the question and clicks the "Submit" button.

[0279] The terminal sends the response to the server.

[0280] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[0281] 5. Leveraging Emotional Engines

[0282] During the mock interview, the emotion engine collects facial expression data and voice data of the user. For example, the facial expression data indicates that the user looks anxious, and the voice data indicates that the user speaks in a tense voice.

[0283] The terminal transmits this data to the server in real time.

[0284] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[0285] The generative AI can adjust the next question based on the results of the emotion analysis, and can also provide specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[0286] 6. Providing Feedback

[0287] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[0288] The terminal sends a request to the server.

[0289] The server uses a generation AI to analyze the overall response and the sentiment analysis results, and generates comprehensive feedback (e.g., "Your response is specific and good, but it's important that you speak with more confidence.") The feedback also includes the results of the sentiment engine's analysis, resulting in more specific and useful advice for the user.

[0290] The terminal displays the feedback content to the user.

[0291] This system allows users to easily experience mock interviews and brush up on their academic background. Through specific feedback from the generative AI and emotion engine, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for the actual interview.

[0292] The processing flow will be explained below.

[0293] Step 1:

[0294] A user accesses the system and registers or logs in. The user enters their name, email address, and password.

[0295] Step 2:

[0296] The terminal transmits the entered registration or login information to the server.

[0297] Step 3:

[0298] The server stores the received information in a database and manages the login status. If the login is successful, it sends an instruction to the terminal to redirect the user to the home screen.

[0299] Step 4:

[0300] The server confirms that the user has logged in, generates a screen for selecting either the "Interview Practice Course" or the "School Background Brush-up Course", and sends it to the terminal.

[0301] Step 5:

[0302] On the displayed screen, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course" and clicks the "Next" button.

[0303] Step 6:

[0304] The terminal transmits the user's selection to the server.

[0305] Step 7:

[0306] The server generates the next screen according to the selected course and transmits it to the terminal.

[0307] Step 8:

[0308] (If you select the Gakuchika Brush-up Course)

[0309] The server generates a screen containing input fields based on a framework for academic background (e.g., the STAR method) and sends it to the terminal.

[0310] Step 9:

[0311] The user inputs the details of what he / she focused on during his / her school days and clicks the "Submit" button.

[0312] Step 10:

[0313] The terminal transmits the entered contents of the academic background to the server.

[0314] Step 11:

[0315] The server passes the received academic background information to the generation AI for analysis.

[0316] Step 12:

[0317] The AI ​​analyzes the content of the student's academic background and generates feedback, which is then passed to the server.

[0318] Step 13:

[0319] The server transmits the generated feedback to the terminal and displays it to the user.

[0320] Step 14:

[0321] (If you select the Interview Practice Course)

[0322] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the terminal.

[0323] Step 15:

[0324] The user enters an answer to the initial question and clicks the "Submit" button.

[0325] Step 16:

[0326] The terminal transmits the user's answer to the server.

[0327] Step 17:

[0328] The server passes the received answers to the generation AI for evaluation, which then generates the next question and returns it to the server.

[0329] Step 18:

[0330] The server sends the next question received from the generation AI to the device. This process is repeated 10 times.

[0331] Step 19:

[0332] During the mock interview, the emotion engine collects facial expression data and voice data of the user. For example, the facial expression data indicates that the user looks anxious, and the voice data indicates that the user speaks in a tense voice.

[0333] Step 20:

[0334] The terminal transmits this data to the server in real time.

[0335] Step 21:

[0336] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[0337] Step 22:

[0338] The generative AI adjusts the next question based on the results of the emotion analysis, and also provides specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[0339] Step 23:

[0340] After 10 rounds of question and answer exchanges, the user clicks the "Get Feedback" button.

[0341] Step 24:

[0342] The terminal transmits the user's request to the server.

[0343] Step 25:

[0344] The server then uses the AI ​​to analyze the overall responses and the emotion analysis results, generating comprehensive feedback. The feedback also includes the results of the emotion engine's analysis, allowing for more specific and useful advice for the user.

[0345] Step 26:

[0346] The server transmits the generated feedback to the terminal and displays it to the user.

[0347] Example 2

[0348] 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."

[0349] Current mock interview systems struggle to provide specific and appropriate feedback based on detailed analysis of users' emotions and responses. They also lack the functionality to systematically analyze the information users enter and provide advice and areas for improvement. This makes it difficult for users to gain a deep understanding of their strengths and weaknesses and effectively learn to improve their interview skills.

[0350] 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.

[0351] In this invention, the server includes means for receiving input from a user terminal, means for a generation AI to generate the next question, means for collecting and analyzing user emotion data using an emotion analysis engine, means for managing multiple question-and-answer exchanges, and means for providing feedback. This allows the user to receive detailed and appropriate feedback through the mock interview, thereby enabling them to gain a deeper understanding of their strengths and weaknesses and effectively improve their interview skills.

[0352] "User Terminal" means a computer or smart device that enables a User to access the System through an interface and input and receive data.

[0353] "Generative AI" refers to technology that uses artificial intelligence algorithms to generate the next question or feedback based on input data.

[0354] An "emotion engine" refers to a combination of hardware and software for analyzing a user's emotional state from facial expression data and voice data.

[0355] "Database" refers to a data storage system for systematically storing and managing user information, responses, analysis results, etc.

[0356] "Feedback" refers to specific advice and comments for improvement provided to users based on the analysis results of the generative AI and emotion engine.

[0357] "Means for managing question and answer interactions" refers to the system's ability to track and control the process of multiple questions and answers in a mock interview.

[0358] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika). Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions, providing more detailed and appropriate feedback.

[0359] Main components of the system

[0360] 1. User Registration and Login

[0361] A user accesses the system and registers or logs in. They must enter their name, email address, and password.

[0362] The terminal transmits the input data to the server.

[0363] The server saves the information in a database and manages the login state. If the login is successful, it redirects the user to the home screen.

[0364] 2. Course Selection

[0365] After logging in, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course."

[0366] The terminal transmits the user's selection to the server.

[0367] The server generates an interface according to the selected course and transmits it to the terminal.

[0368] 3. Brush up on your academic background

[0369] After the user selects the "Gakuchika Brush-up Course," a screen for inputting the contents of Gakuchika is displayed.

[0370] The terminal transmits the inputted contents to the server.

[0371] The server uses a generative AI model to analyze the content of the student's academic background and generate specific feedback. For example, in response to an input such as, "This is my experience as a leader in a club activity at university. As I was working on a project, I came up with a way to deal with problems that arose," the generative AI adds specific examples and organizes the timeline.

[0372] 4. Mock interviews

[0373] After the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[0374] The terminal sends a start request to the server.

[0375] The server uses a generative AI model to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[0376] The user enters an answer to the question and clicks the "Submit" button.

[0377] The terminal sends the response to the server.

[0378] The server uses the generative AI model to generate the next question and sends it to the device. This process is repeated 10 times.

[0379] 5. Leveraging Emotional Engines

[0380] During the user's mock interview, the emotion engine collects facial expression and voice data. For example, it detects when the user looks anxious in the facial expression data or when the user sounds nervous in the voice data.

[0381] The terminal transmits this data to the server in real time.

[0382] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[0383] The generative AI adjusts the next question based on the results of the emotion analysis, and also provides specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[0384] 6. Providing Feedback

[0385] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[0386] The terminal sends a request to the server.

[0387] The server uses a generation AI to analyze the overall response and sentiment analysis results and generate comprehensive feedback (e.g., "Your response is specific, but it's important that you speak with more confidence").

[0388] The terminal displays the feedback content to the user.

[0389] Specific examples

[0390] For example, if a user inputs something like, "This is my experience as a leader in a club activity at university. As I was working on a project, I came up with ways to deal with problems that arose," the generating AI will provide feedback by adding specific examples and organizing the content chronologically.

[0391] Examples of prompt statements

[0392] "Tell me about an experience you had as a leader in a university club. For example, tell me specifically how you brought members together, solved a problem, and achieved a final result."

[0393] Based on this prompt, users can specifically describe their experience and receive feedback from the generating AI.

[0394] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0395] Step 1:

[0396] User Registration and Login

[0397] Subject: User

[0398] Input: Name, Email Address, Password

[0399] How it works: A user accesses the system and enters their name, email address, and password to register or log in.

[0400] Output: Registration information or login credentials

[0401] Subject: Terminal

[0402] Input: Registration or login information entered by the user

[0403] Operation: The terminal sends the entered data to the server.

[0404] Output: Request to submit registration information or login credentials

[0405] Subject: Server

[0406] Input: User registration or login information

[0407] How it works: The server receives the submitted information, stores it in a database, or performs authentication. If authentication is successful, it generates a response that redirects the user to the home screen.

[0408] Output: Home screen display instructions

[0409] Step 2:

[0410] Course Selection

[0411] Subject: User

[0412] Input: Course selection ("Interview Practice Course" or "Gakuchika Brush-up Course")

[0413] How it works: The user selects the desired course on the displayed home screen and clicks the "Next" button.

[0414] Output: Course selection information

[0415] Subject: Terminal

[0416] Input: User's course selection information

[0417] Operation: The terminal transmits the selected course information to the server.

[0418] Output: Request to send selected course information

[0419] Subject: Server

[0420] Input: Course selection information

[0421] Operation: The server generates an interface according to the selected course and sends it to the terminal.

[0422] Output: The generated interface

[0423] Step 3:

[0424] Brushing up on your academic background

[0425] Subject: User

[0426] Input: What you focused on during your student days

[0427] How it works: After selecting the "Gakuchika Brush-up Course," the user enters details about what they focused on during their time as a student and clicks the "Submit" button.

[0428] Output: Input contents

[0429] Subject: Terminal

[0430] Input: The content of the academic background entered by the user

[0431] Operation: The terminal sends the input information to the server.

[0432] Output: Request to send input content

[0433] Subject: Server

[0434] Input: The content of the academic background entered by the user

[0435] How it works: The server passes the input data to the generative AI model, which analyzes it based on the framework. Once the analysis is complete, the generative AI adds specific examples and organizes the timeline.

[0436] Output: Feedback

[0437] Subject: Terminal

[0438] Input: Generated feedback

[0439] Action: The device displays the feedback to the user.

[0440] Output: Show feedback

[0441] Step 4:

[0442] Mock interviews

[0443] Subject: User

[0444] Input: Request to start mock interview

[0445] Action: The user clicks the "Start Mock Interview" button.

[0446] Output: Start request

[0447] Subject: Terminal

[0448] Input: User's start request

[0449] Operation: The terminal sends a start request to the server.

[0450] Output: Send start request

[0451] Subject: Server

[0452] Input: Request to start mock interview

[0453] How it works: The server uses a generative AI model to generate an initial question and sends it to the device (e.g., "Tell me about yourself").

[0454] Output: First question

[0455] Subject: Terminal

[0456] Input: First question

[0457] Action: The terminal displays the question to the user.

[0458] Output: Show question

[0459] Subject: User

[0460] Input: Answer to question

[0461] How it works: The user enters an answer to a question and clicks the "Submit" button.

[0462] Output:Answer

[0463] Subject: Terminal

[0464] Input: User's answer

[0465] Action: The device sends a response to the server.

[0466] Output: Request to send answer

[0467] Subject: Server

[0468] Input: User's answer

[0469] How it works: The server receives the answer, uses the generative AI model to generate the next question, and sends it to the device. This process is repeated 10 times.

[0470] Output: Next question

[0471] Subject: Terminal

[0472] Input: Next question

[0473] Action: The terminal displays the following question to the user:

[0474] Output: Show question

[0475] Step 5:

[0476] Utilizing the Emotion Engine

[0477] Subject: User

[0478] Input: facial expression data, voice data

[0479] How it works: The emotion engine collects facial and vocal data during a user's mock interview.

[0480] Output: Emotion data

[0481] Subject: Terminal

[0482] Input: Emotion data

[0483] Operation: The device transmits emotion data to the server in real time.

[0484] Output: Sending emotion data

[0485] Subject: Server

[0486] Input: Emotion data

[0487] How it works: The server analyzes the data collected by the emotion engine and passes the results to the generative AI.

[0488] Output: Analysis results

[0489] Subject: Generation AI

[0490] Input: Sentiment analysis results

[0491] How it works: The generative AI uses the results of the emotion analysis to adjust the next question and incorporate it into the feedback (e.g., "Try to be a bit more relaxed and softer when speaking").

[0492] Output: Tailored questions, feedback

[0493] Subject: Server

[0494] Input: Moderated questions, feedback

[0495] How it works: The server sends tailored questions and feedback to the device.

[0496] Output: Tailored questions and feedback submissions

[0497] Subject: Terminal

[0498] Input: Moderated questions and feedback

[0499] Action: The device displays tailored questions and feedback to the user.

[0500] Output: Display of tailored questions and feedback

[0501] Step 6:

[0502] Providing Feedback

[0503] Subject: User

[0504] Input: Feedback request

[0505] How it works: After completing 10 mock interview questions, the user clicks the "Receive Feedback" button.

[0506] Output: Feedback request

[0507] Subject: Terminal

[0508] Input: Feedback request

[0509] Operation: The device sends a request to the server.

[0510] Output: Sending a request

[0511] Subject: Server

[0512] Input: Feedback request

[0513] How it works: The server uses the generation AI to analyze the overall response and sentiment analysis results and generate comprehensive feedback (e.g., "Your response is specific, but it's important that you speak with more confidence").

[0514] Output: Generated feedback

[0515] Subject: Terminal

[0516] Input: Generated feedback

[0517] Action: The device displays the feedback to the user.

[0518] Output: Show feedback

[0519] (Application example 2)

[0520] 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."

[0521] The present invention aims to provide a system for conducting mock interviews that analyzes a user's emotions in real time and provides appropriate feedback based on the analysis results, thereby enabling the user to efficiently improve themselves. At the same time, it aims to solve the problem of providing real-time product recommendations and feedback using user emotion analysis in order to improve the shopping experience in physical stores.

[0522] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input from a user terminal for conducting a mock interview, means for the generation AI to generate the next question based on the input, means for managing multiple exchanges of questions and answers, means for providing feedback after the multiple exchanges, means for collecting facial expression data and voice data of the user in real time, an emotion engine for analyzing the facial expression data and voice data, and means for the generation AI to adjust the next question and feedback based on the emotion analysis results. This enables appropriate feedback based on the user's emotions.

[0523] A "user device" is an electronic device that allows a user to use the mock interview or shopping assistant app.

[0524] "Generative AI" is artificial intelligence that generates the next question or feedback based on user input and emotional analysis results.

[0525] The "emotion engine" is a system that analyzes a user's facial expression data and voice data in real time to evaluate the user's emotional state.

[0526] "Facial expression data" refers to data obtained by capturing the user's facial expression using a camera or the like, and used to analyze the user's emotions.

[0527] "Voice data" is data obtained by capturing the user's speaking style and tone of voice using a microphone or the like, and used to analyze the user's emotions.

[0528] "Means for providing feedback" refers to a function that presents the user with feedback generated by the generation AI based on the analysis results.

[0529] An "analysis engine" is a system that performs analysis based on data entered by a user or acquired data.

[0530] "User Information" means your personal identification information and login information, such as your name, email address, and password.

[0531] The "database" is a system for storing user information, interview records, emotion analysis data, etc.

[0532] The "means for collecting in real time" refers to a function or device for collecting facial expression data and voice data of a user in real time.

[0533] A "means for generating the next question" is an algorithm or system for generating the next question based on previous answers and emotional state.

[0534] A "shopping assistant app" is an application that provides product recommendations and feedback based on the results of user sentiment analysis in order to improve the shopping experience in physical stores.

[0535] A system for realizing this invention will be described below. This system analyzes a user's emotions in real time through a mock interview or shopping assistant application, and provides appropriate feedback.

[0536] System configuration

[0537] 1. User Device

[0538] A smartphone, tablet, or computer that connects to the server and runs the mock interview or shopping assistant application.

[0539] It is equipped with a camera and microphone to collect the user's facial expression and voice data.

[0540] Accepts user input and sends data to the server.

[0541] 2. Server

[0542] Receives input data and collected data and stores it in a database.

[0543] Use generative AI to generate the next question or feedback.

[0544] The emotion engine analyzes the user's facial expression and voice data.

[0545] Based on the analysis results, the generative AI adjusts the next questions and feedback.

[0546] Detailed System Description

[0547] 1. User Registration and Login

[0548] Users first access the app and either register or log in.

[0549] The user's name, email address, and password are entered and sent to the server.

[0550] The server stores the received information in a database and manages the login status.

[0551] 2. Mock interviews

[0552] When a user starts a mock interview, a start request is sent from the user terminal to the server.

[0553] The server uses a generation AI to generate an initial question and sends it to the terminal.

[0554] The user answers the questions and sends the answers to the server.

[0555] The server uses an emotion engine to analyze facial expression and voice data and passes the results to the generation AI.

[0556] The generative AI then adjusts the next question or feedback and repeats the process.

[0557] 3. Shopping Assistant App

[0558] Users use the app while walking around the store, and their smartphone's camera and microphone collect facial and voice data in real time.

[0559] The collected data is sent to a server and analyzed by the emotion engine.

[0560] The server passes the analysis results to the generation AI, which then provides product recommendations and feedback in real time.

[0561] For example, if the user is confused, "recommended items" will be presented, and if the user is excited, "additional suggestions for related products" will be made.

[0562] Specific examples

[0563] Example of a mock interview:

[0564] First question: "Please introduce yourself"

[0565] User Answer: "My name is △△ and I'm from XX University. I majored in □□ and during my student days I focused on XX activities."

[0566] Examples of shopping assistants:

[0567] User views product A:

[0568] Facial expression data: Confused

[0569] Voice Tone: Anxiety

[0570] Generated AI feedback: "What about product C? It's popular with many users."

[0571] Prompt Sentence Examples

[0572] Examples of input prompts for generative AI models include:

[0573] Use the following data to create feedback and product recommendations based on user sentiment.

[0574] User shopping history:

[0575] Product A: Viewing time 2 minutes, facial expression: Confused, voice tone: Anxious

[0576] Product B: Viewing time 5 minutes, facial expression: excitement, voice tone: joy

[0577] Emotion analysis results:

[0578] Facial expression data: confusion, anxiety, excitement, joy

[0579] Voice Tone: Anxiety, Joy

[0580] Such a system would allow users to receive appropriate advice and recommendations tailored to their emotional state, potentially leading to self-improvement and an improved shopping experience.

[0581] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0582] Step 1:

[0583] A user accesses the app and registers or logs in. The user enters their name, email address, and password, which the device sends to the server. The server saves the entered data in a database and manages the user's login status.

[0584] Input: Name, Email Address, Password

[0585] Output: Login session ID

[0586] Specific operation: The terminal receives user input and sends the data to the server, which saves it in the database, generates a session ID, and returns it to the user.

[0587] Step 2:

[0588] The user selects either the "Mock Interview" or "Shopping Assistant" course. The terminal sends the selection information to the server, which then generates an interface according to the selection and returns it to the terminal.

[0589] Input: Course selection information

[0590] Output: Course-specific interface

[0591] Specific operation: The device detects the user's selection and sends the data to the server. The server generates an interface according to the selection and sends it back to the device.

[0592] Step 3:

[0593] In the mock interview, the user enters answers to questions and the device sends them to the server, which uses a generative AI to generate the next question, repeating this process 10 times.

[0594] Input: User's answer

[0595] Output: The following questions are generated:

[0596] How it works: The device collects the user's answers and sends them to the server. The server then uses a generative AI to generate the next question and sends it back to the device. This process is repeated 10 times.

[0597] Step 4:

[0598] In the case of a shopping assistant, while the user is browsing products, the device collects facial expression and voice data in real time and sends it to a server, which then uses an emotion engine to analyze the data and pass the results to a generative AI.

[0599] Input: facial expression data, voice data

[0600] Output: Emotion analysis results

[0601] Specific operation: The device collects facial expression and voice data while browsing products and sends it to the server. The server analyzes it with an emotion engine and sends the results to the generation AI.

[0602] Step 5:

[0603] Based on the results of the emotion analysis, the generative AI generates appropriate feedback and the next question, which the server sends to the device and displays to the user.

[0604] Input: Sentiment analysis results

[0605] Output: Feedback and next questions

[0606] Specific operation: The server uses the generation AI to generate feedback and next questions based on the analysis results and sends them to the device, which then displays them to the user.

[0607] Step 6:

[0608] After the user completes the mock interview or shopping assistant session, they receive feedback. The device sends the user's request to the server, which then generates comprehensive feedback and sends it to the device.

[0609] Input: Session termination request

[0610] Output: Comprehensive feedback

[0611] How it works: After the user finishes their session, they submit a request. The server uses AI to generate comprehensive feedback based on the entire data, sends it to the device, and displays it to the user.

[0612] This allows users to receive appropriate advice and product recommendations based on their emotional state, which can lead to self-improvement and an improved shopping experience.

[0613] 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.

[0614] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0615] 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.

[0616] [Second embodiment]

[0617] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0618] 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.

[0619] 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).

[0620] 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.

[0621] 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.

[0622] 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).

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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."

[0629] The following describes an embodiment of the present invention. This system is effective for allowing users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika).

[0630] System Overview

[0631] 1. User Registration and Login

[0632] When a user first accesses the system, they register or log in. They enter their name, email address, and password.

[0633] The terminal transmits the input data to the server.

[0634] The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen.

[0635] 2. Course Selection

[0636] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[0637] The terminal transmits the user's selection to the server.

[0638] The server generates an interface according to the selected course and transmits it to the terminal.

[0639] 3. Brush up on your academic background

[0640] If the user selects the "School Background Brush-up Course," a screen for inputting the details of what the user focused on during their school days is displayed.

[0641] The terminal transmits the inputted contents to the server.

[0642] The server uses a generation AI to analyze the content of the Gakuchika based on the framework. For example, if the user enters something like, "My Gakuchika is about my experience as a leader in a club activity at university. As I worked on a project, I came up with ways to deal with problems that arose," the generation AI will provide feedback by adding specific examples and organizing the content chronologically.

[0643] 4. Mock interviews

[0644] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[0645] The terminal sends a start request to the server.

[0646] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[0647] The user enters an answer to the question and clicks the "Submit" button.

[0648] The terminal sends the response to the server.

[0649] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[0650] 5. Providing Feedback

[0651] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[0652] The terminal sends a request to the server.

[0653] The server analyzes the entire response, and the generation AI generates comprehensive feedback (e.g., "Your response is specific and good, but it's important that you speak with more confidence") and sends it to the device.

[0654] The terminal displays the feedback content.

[0655] This system allows users to easily experience mock interviews and brush up on their academic background. Through specific feedback from the generative AI, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for the actual interview.

[0656] The processing flow will be explained below.

[0657] Step 1:

[0658] A user accesses the system and registers or logs in. The user enters their name, email address, and password.

[0659] Step 2:

[0660] The terminal transmits the entered registration or login information to the server.

[0661] Step 3:

[0662] The server stores the received information in a database and manages the login status. If the login is successful, it sends an instruction to the terminal to redirect the user to the home screen.

[0663] Step 4:

[0664] The server confirms that the user has logged in, generates a screen for selecting either the "Interview Practice Course" or the "School Background Brush-up Course", and sends it to the terminal.

[0665] Step 5:

[0666] On the displayed screen, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course" and clicks the "Next" button.

[0667] Step 6:

[0668] The terminal transmits the user's selection to the server.

[0669] Step 7:

[0670] The server generates the next screen according to the selected course and transmits it to the terminal.

[0671] Step 8:

[0672] (If you select the Gakuchika Brush-up Course)

[0673] The server generates a screen containing input fields based on a framework for academic background (e.g., the STAR method) and sends it to the terminal.

[0674] Step 9:

[0675] The user inputs the details of what he / she focused on during his / her school days and clicks the "Submit" button.

[0676] Step 10:

[0677] The terminal transmits the entered contents of the academic background to the server.

[0678] Step 11:

[0679] The server passes the received academic background information to the generation AI for analysis.

[0680] Step 12:

[0681] The AI ​​analyzes the content of the student's academic background and generates feedback, which is then passed to the server.

[0682] Step 13:

[0683] The server transmits the generated feedback to the terminal and displays it to the user.

[0684] Step 14:

[0685] (If you select the Interview Practice Course)

[0686] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the terminal.

[0687] Step 15:

[0688] The user enters an answer to the initial question and clicks the "Submit" button.

[0689] Step 16:

[0690] The terminal transmits the user's answer to the server.

[0691] Step 17:

[0692] The server passes the received answers to the generation AI for evaluation, which then generates the next question and returns it to the server.

[0693] Step 18:

[0694] The server sends the next question received from the generation AI to the device. This process is repeated 10 times.

[0695] Step 19:

[0696] After 10 rounds of question and answer exchanges, the user clicks the "Get Feedback" button.

[0697] Step 20:

[0698] The terminal transmits the user's request to the server.

[0699] Step 21:

[0700] The server analyzes all the answers with the generation AI and generates comprehensive feedback, which is then passed back to the server.

[0701] Step 22:

[0702] The server transmits the generated feedback to the terminal and displays it to the user.

[0703] Example 1

[0704] 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."

[0705] In recent years, mock interviews and self-analysis have become increasingly required during job hunting, but there is a lack of effective tools for conducting these individually. It is also important to brush up on what you focused on during your student days (gakuchika), but there are limited efficient ways to do this. Furthermore, specific and accurate feedback is necessary for users to understand their strengths and weaknesses and improve their performance in actual interviews. A comprehensive system that can solve these issues is needed.

[0706] 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.

[0707] In this invention, the server includes means for receiving registration and login information from a user terminal, means for storing the information in a database and managing login status, means for the user to select a mock interview or brush-up course, means for receiving input from the user terminal for conducting the mock interview, means for the generative AI model to generate the next question based on the input, means for managing multiple question-and-answer exchanges, and means for providing feedback after the multiple exchanges. This allows users to easily experience mock interviews and brush up on their academic background. Furthermore, through specific feedback from the generative AI model, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for actual interviews.

[0708] A "user terminal" is a device used by a user to access the system, and includes a personal computer, smartphone, tablet, etc.

[0709] A "server" is a part of a computer system that receives and processes information sent from a user's device, storing data and analyzing it using generated AI.

[0710] A "database" is a system for systematically storing user information and other data, and for storing, retrieving, and managing information.

[0711] "Logged-in state" refers to a state in which a user has accessed the system, has been authenticated, and is able to perform operations within the system.

[0712] A "mock interview" is a simulation that mimics a real interview, and is a process in which a user practices an interview through question and answer exchanges.

[0713] The "Brush-up Course" is a program that helps users improve the things they focused on during their student days (gakuchika), and involves inputting and analyzing specific content.

[0714] A "generative AI model" is a system that uses artificial intelligence to generate questions and feedback based on user input.

[0715] "Feedback" refers to evaluations and advice provided based on the results of mock interviews and brush-ups conducted by the user.

[0716] A "framework" is a framework or standard for analyzing user input, and includes, for example, the STAR method (Situation, Task, Action, Result).

[0717] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and brush up on what they focused on during their student days (Gakuchika). This system utilizes a user terminal, a server, and a generative AI model.

[0718] First, a user terminal is a device that provides an interface with the system. Specifically, it includes personal computers, smartphones, tablets, etc. Users access the system through their terminal to register and log in.

[0719] The server receives information sent from the user's device, stores the data, and analyzes it using the generation AI. A database is connected to the server, and user information and mock interview data are systematically stored. A database management system such as MySQL is used for the database.

[0720] The system works as follows: A user first accesses the system and enters their name, email address, and password on the new registration or login screen. The device sends the entered information to the server. The server stores the received information in a database and manages the login status. If authentication is successful, the user is redirected to the home screen.

[0721] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course." The course selection information is sent from the terminal to the server, and the server generates an interface corresponding to the selected course and sends it to the terminal.

[0722] If a user selects the "Gakuchika Brush-up Course," a screen will appear where they can enter details about what they focused on during their time as a student. The user enters the details, and the device sends the details to the server. The server uses a generative AI (for example, OpenAI's GPT-4) to analyze the entered Gakuchika details and evaluate them based on a framework (such as the STAR method). The generative AI analyzes the details and generates specific feedback.

[0723] For example, if a user enters the following content, "My academic background is my experience as a leader in a club activity at university. When a problem arose during the project, I devised a way to deal with it," the server will use generative AI to provide feedback. For example, it will return advice such as, "Specifically, it would be good to explain in detail at what stage of the project the problem arose, what measures were taken, and what results were achieved as a result."

[0724] On the other hand, if the user selects the "Interview Practice Course," a screen to start the mock interview will be displayed. When the user clicks the start button, the device sends the request to the server. The server uses the generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device. The user enters an answer to the question, and the device sends the answer to the server. The server again uses the generation AI to generate the next question, and this process is repeated 10 times.

[0725] After completing the mock interview, the user clicks the "Receive Feedback" button. The device sends a request to the server, which analyzes all responses and uses a generative AI to generate comprehensive feedback, which is then sent to the device. The device then displays the feedback.

[0726] Examples of prompts include "Tell us about yourself" and "Tell us more about your Gakuchika." In this way, the system allows users to refine their Gakuchika through mock interviews and receive specific feedback.

[0727] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0728] Step 1:

[0729] A user accesses the system and enters their name, email address, and password on the registration or login screen.

[0730] Input: Name, Email Address, Password

[0731] Specific actions: A user visits a web page, fills in a form, and clicks the "Submit" button.

[0732] Output: Input information is sent from the device to the server.

[0733] Step 2:

[0734] The device sends the entered information to the server, using the HTTPS protocol to send the data securely.

[0735] Input: Name, email address, and password entered by the user

[0736] Specific operation: The device packages the user's input information in JSON format, creates an HTTPS request, and sends it to the server.

[0737] Output: The input information reaches the server.

[0738] Step 3:

[0739] The server stores the received information in a database and manages the login status. MySQL is used for storage.

[0740] Input: Name, email address, and password sent from your device

[0741] Specific operation: The server connects to the database and saves the user information using an INSERT statement. Also, when the login is successful, it creates and manages session information.

[0742] Output: User information is saved in the database and a login session is created for the user.

[0743] Step 4:

[0744] The user is redirected to the home screen and the main menu is displayed. The user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[0745] Input: User login session, home screen request

[0746] Specific operation: After the server confirms the login status, it generates the HTML for the home screen and sends it to the device.

[0747] Output: The home screen is displayed on the user's device.

[0748] Step 5:

[0749] The course information selected by the user is sent from the terminal to the server.

[0750] Input: Course selection information (e.g., "Interview Practice Course" or "Gakuchika Brush-up Course")

[0751] Specific operation: The user clicks on the course icon, and the device sends the information to the server.

[0752] Output: Course selection information is sent to the server.

[0753] Step 6:

[0754] The server generates an interface according to the selected course and transmits it to the terminal.

[0755] Input: Course selection information

[0756] Specific operation: The server dynamically generates HTML according to the selected course and sends it to the terminal.

[0757] Output: A course-specific screen is displayed on the user's device.

[0758] Step 7:

[0759] If the user selects the "Gakuchika Brush-up Course," he or she inputs the contents of his or her Gakuchika.

[0760] Input: Content of your Gakuchika (e.g., "Experience as a leader in a club activity at university")

[0761] Specific behavior: The user enters the details of their academic background and clicks the "Submit" button.

[0762] Output: Input is sent from the terminal to the server.

[0763] Step 8:

[0764] The server sends the input content to the generation AI, which analyzes it based on a framework (e.g., the STAR method).

[0765] Input: Contents of your academic background

[0766] Specific operation: The server sends the user's input as text to the generative AI model and receives the analysis results.

[0767] Output: The analysis results from the generation AI are returned to the server.

[0768] Step 9:

[0769] The server sends the feedback received from the generated AI to the terminal and displays it to the user.

[0770] Input: Analysis results from the generative AI

[0771] Specific operation: The server sends the received feedback information to the terminal in HTML format.

[0772] Output: Specific feedback is displayed on the user's device.

[0773] Step 10:

[0774] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[0775] Input: Course selection information

[0776] Specific operation: When the user clicks "Start", the device sends the request to the server.

[0777] Output: The initial question is generated from the server and sent to the device.

[0778] Step 11:

[0779] The server uses a generation AI to generate mock interview questions and send them to the device.

[0780] Input: Request to start interview

[0781] Specific operation: The server has the generation AI generate the first question and send it to the device.

[0782] Output: The initial question is displayed on the user's terminal.

[0783] Step 12:

[0784] The user enters an answer to the question, and the terminal transmits the answer to the server.

[0785] Input: Answer to the question

[0786] Specific behavior: The user enters an answer and clicks the "Submit" button. The device sends the information to the server.

[0787] Output: The answer arrives at the server.

[0788] Step 13:

[0789] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[0790] Input: Previous answer

[0791] Specific operation: The server asks the generation AI to generate the next question and sends it to the device.

[0792] Output: The following question is displayed on the user's terminal:

[0793] Step 14:

[0794] After the user completes 10 mock interview questions, they click the "Receive Feedback" button.

[0795] Input: 10 questions and answers

[0796] Specific operation: The device sends a request to the server.

[0797] Output: The server sends the data to the generating AI.

[0798] Step 15:

[0799] The server uses generative AI to generate comprehensive feedback and send it to the device.

[0800] Input: All question and answer data

[0801] Specific operation: The server instructs the generation AI to generate feedback based on all data.

[0802] Output: Feedback information is sent to the terminal.

[0803] Step 16:

[0804] The device displays the feedback to the user.

[0805] Input: Feedback data from the generative AI

[0806] Specific behavior: The device receives the feedback information and displays it on the screen.

[0807] Output: Feedback is displayed on the user's screen.

[0808] This allows users to easily experience mock interviews and brush up on their academic background. In addition, through specific feedback from the generative AI model, users can gain a deeper understanding of their strengths and weaknesses, enabling them to effectively prepare for actual interviews.

[0809] (Application example 1)

[0810] 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."

[0811] Customer service in brick-and-mortar stores is directly linked to customer satisfaction, making training essential. However, traditional training methods make it difficult to obtain specific feedback in real time, limiting opportunities for self-improvement. Furthermore, mock interviews and other skill-improvement simulation tools are often provided individually, creating a need for a centralized training system. A system is needed that allows employees to effectively improve their skills without disrupting their daily work.

[0812] 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.

[0813] In this invention, the server includes means for receiving input from a user terminal for conducting a mock interview, means for a generation AI to generate the next question based on the input, means for managing multiple exchanges of questions and answers, means for providing feedback after the multiple exchanges, means for a salesperson to conduct a customer service simulation in a physical store, and means for the generation AI to generate feedback based on the results of the simulation, thereby enabling employees to evaluate and improve their customer service skills in real time through the simulation.

[0814] A "mock interview" is a training session conducted in a format that mimics a real interview.

[0815] A "user terminal" is an electronic device such as a smartphone or tablet that is operated by a user.

[0816] A "means for receiving input" is a mechanism for sending data or instructions from a user to a system.

[0817] "Generative AI" is a technology that uses artificial intelligence to dynamically generate content and responses.

[0818] The "means for generating the next question" is a mechanism by which the AI ​​automatically generates a new question based on the user's answer.

[0819] "Means for managing multiple question and answer exchanges" refers to a mechanism for providing consecutive questions and recording and analyzing the answers.

[0820] The "means for providing feedback" is a mechanism for conveying evaluations and areas for improvement based on the content of the user's responses.

[0821] The "means for sales staff to conduct customer service simulations in a real store" is a mechanism for sales staff working in a real store to practice customer service simulations.

[0822] "Means for the AI ​​to generate feedback based on the simulation results" refers to a mechanism in which the AI ​​analyzes the results of the customer service simulation and automatically generates appropriate feedback.

[0823] The system for implementing the present invention aims to enable users to improve their customer service skills through simulated customer service practice. Details of the system are described below.

[0824] 1. User Registration and Login

[0825] The user (store clerk) first accesses the system and registers or logs in. The user enters their name, email address, and store ID.

[0826] The smartphone sends the entered data to the server. The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen. This process uses MySQL as the database, a cloud server, and the smartphone.

[0827] 2. Select a training course

[0828] After logging in, the user selects a training course. They choose either "Initial Customer Service Training Course" or "Advanced Customer Service Training Course." The smartphone sends the user's selection to the server. The server generates an interface corresponding to the selected course and sends it to the smartphone.

[0829] 3. Customer Service Simulation

[0830] If the user selects the "Initial Customer Service Training Course," a basic customer service simulation is conducted. The user inputs the answers to the simulation and sends them to the server via their smartphone. The server uses a generative AI (e.g., OpenAI GPT-4) to generate the next question. The simulation is conducted over multiple rounds of interaction, with new questions automatically generated after each answer.

[0831] 4. Providing Feedback

[0832] At the end of the simulation, users can receive feedback. The server uses generative AI to generate feedback based on the simulation results and sends it to their smartphone. The feedback provides specific and practical advice, allowing users to improve their customer service skills.

[0833] For example, use the following prompt:

[0834] "A customer asks where an item is. How do you respond?"

[0835] The generative AI provides feedback such as:

[0836] "Your response is helpful, but it would be better if you provided more specific instructions and suggested next steps."

[0837] This system allows users to effectively improve their customer service skills without disrupting operations at physical stores, which is expected to improve the quality of service at stores.

[0838] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0839] Step 1:

[0840] A user (store clerk) accesses the system and performs new registration or login. The user enters their name, email address, and store ID. Once this data is entered, the smartphone sends it to the server. The server stores the received information in a database and manages the login status. Once login is complete, the user is redirected to the home screen. The input data is user information, and the output is the login status and home screen display.

[0841] Step 2:

[0842] After logging in, the user selects a training course. Specifically, they choose either the "Initial Customer Service Training Course" or the "Advanced Customer Service Training Course." The user's selection becomes input data, and the smartphone sends the selection data to the server. The server generates an interface according to the selected course and returns it to the smartphone as output data. This allows the user to access the appropriate interface.

[0843] Step 3:

[0844] If the user selects the "Initial Customer Service Training Course," a simulation begins. The server uses a generation AI to generate an initial customer service scenario (e.g., "A customer has entered the store. How would you respond?"). This scenario becomes the initial input data, and the server sends it to the smartphone. The user enters answers to the scenario and sends them to the server, where the answer data is stored.

[0845] Step 4:

[0846] The server analyzes the received user answers using a generative AI and automatically generates the next question. The analysis results become the input data for generating the next question. After generating the question, the server sends a new scenario to the smartphone. This process is repeated multiple times. The output data is the next scenario, which is presented to the user.

[0847] Step 5:

[0848] After the series of simulations is completed, the server generates feedback based on all response data. The input data for generating this feedback is a set of all responses. The generation AI analyzes this and generates feedback that includes areas for improvement. The server sends the generated feedback to a smartphone. The output data is the feedback content, which the user can check on their smartphone. The feedback includes specific examples and areas for improvement, helping to improve the user's skills.

[0849] 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.

[0850] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika). In addition, the present invention incorporates an emotion engine that recognizes the user's emotions, providing more detailed and appropriate feedback.

[0851] System Overview

[0852] 1. User Registration and Login

[0853] When a user first accesses the system, they register or log in. They enter their name, email address, and password.

[0854] The terminal transmits the input data to the server.

[0855] The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen.

[0856] 2. Course Selection

[0857] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[0858] The terminal transmits the user's selection to the server.

[0859] The server generates an interface according to the selected course and transmits it to the terminal.

[0860] 3. Brush up on your academic background

[0861] If the user selects the "School Background Brush-up Course," a screen for inputting the details of what the user focused on during their school days is displayed.

[0862] The terminal transmits the inputted contents to the server.

[0863] The server uses a generation AI to analyze the content of the Gakuchika based on the framework. For example, if the user enters something like, "My Gakuchika is about my experience as a leader in a club activity at university. As I worked on a project, I came up with ways to deal with problems that arose," the generation AI will provide feedback by adding specific examples and organizing the content chronologically.

[0864] 4. Mock interviews

[0865] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[0866] The terminal sends a start request to the server.

[0867] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[0868] The user enters an answer to the question and clicks the "Submit" button.

[0869] The terminal sends the response to the server.

[0870] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[0871] 5. Leveraging Emotional Engines

[0872] During the mock interview, the emotion engine collects facial expression data and voice data of the user. For example, the facial expression data indicates that the user looks anxious, and the voice data indicates that the user speaks in a tense voice.

[0873] The terminal transmits this data to the server in real time.

[0874] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[0875] The generative AI can adjust the next question based on the results of the emotion analysis, and can also provide specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[0876] 6. Providing Feedback

[0877] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[0878] The terminal sends a request to the server.

[0879] The server uses a generation AI to analyze the overall response and the sentiment analysis results, and generates comprehensive feedback (e.g., "Your response is specific and good, but it's important that you speak with more confidence.") The feedback also includes the results of the sentiment engine's analysis, resulting in more specific and useful advice for the user.

[0880] The terminal displays the feedback content to the user.

[0881] This system allows users to easily experience mock interviews and brush up on their academic background. Through specific feedback from the generative AI and emotion engine, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for the actual interview.

[0882] The processing flow will be explained below.

[0883] Step 1:

[0884] A user accesses the system and registers or logs in. The user enters their name, email address, and password.

[0885] Step 2:

[0886] The terminal transmits the entered registration or login information to the server.

[0887] Step 3:

[0888] The server stores the received information in a database and manages the login status. If the login is successful, it sends an instruction to the terminal to redirect the user to the home screen.

[0889] Step 4:

[0890] The server confirms that the user has logged in, generates a screen for selecting either the "Interview Practice Course" or the "School Background Brush-up Course", and sends it to the terminal.

[0891] Step 5:

[0892] On the displayed screen, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course" and clicks the "Next" button.

[0893] Step 6:

[0894] The terminal transmits the user's selection to the server.

[0895] Step 7:

[0896] The server generates the next screen according to the selected course and transmits it to the terminal.

[0897] Step 8:

[0898] (If you select the Gakuchika Brush-up Course)

[0899] The server generates a screen containing input fields based on a framework for academic background (e.g., the STAR method) and sends it to the terminal.

[0900] Step 9:

[0901] The user inputs the details of what he / she focused on during his / her school days and clicks the "Submit" button.

[0902] Step 10:

[0903] The terminal transmits the entered contents of the academic background to the server.

[0904] Step 11:

[0905] The server passes the received academic background information to the generation AI for analysis.

[0906] Step 12:

[0907] The AI ​​analyzes the content of the student's academic background and generates feedback, which is then passed to the server.

[0908] Step 13:

[0909] The server transmits the generated feedback to the terminal and displays it to the user.

[0910] Step 14:

[0911] (If you select the Interview Practice Course)

[0912] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the terminal.

[0913] Step 15:

[0914] The user enters an answer to the initial question and clicks the "Submit" button.

[0915] Step 16:

[0916] The terminal transmits the user's answer to the server.

[0917] Step 17:

[0918] The server passes the received answers to the generation AI for evaluation, which then generates the next question and returns it to the server.

[0919] Step 18:

[0920] The server sends the next question received from the generation AI to the device. This process is repeated 10 times.

[0921] Step 19:

[0922] During the mock interview, the emotion engine collects facial expression data and voice data of the user. For example, the facial expression data indicates that the user looks anxious, and the voice data indicates that the user speaks in a tense voice.

[0923] Step 20:

[0924] The terminal transmits this data to the server in real time.

[0925] Step 21:

[0926] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[0927] Step 22:

[0928] The generative AI adjusts the next question based on the results of the emotion analysis, and also provides specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[0929] Step 23:

[0930] After 10 rounds of question and answer exchanges, the user clicks the "Get Feedback" button.

[0931] Step 24:

[0932] The terminal transmits the user's request to the server.

[0933] Step 25:

[0934] The server then uses the AI ​​to analyze the overall responses and the emotion analysis results, generating comprehensive feedback. The feedback also includes the results of the emotion engine's analysis, allowing for more specific and useful advice for the user.

[0935] Step 26:

[0936] The server transmits the generated feedback to the terminal and displays it to the user.

[0937] Example 2

[0938] 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."

[0939] Current mock interview systems struggle to provide specific and appropriate feedback based on detailed analysis of users' emotions and responses. They also lack the functionality to systematically analyze the information users enter and provide advice and areas for improvement. This makes it difficult for users to gain a deep understanding of their strengths and weaknesses and effectively learn to improve their interview skills.

[0940] 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.

[0941] In this invention, the server includes means for receiving input from a user terminal, means for a generation AI to generate the next question, means for collecting and analyzing user emotion data using an emotion analysis engine, means for managing multiple question-and-answer exchanges, and means for providing feedback. This allows the user to receive detailed and appropriate feedback through the mock interview, thereby enabling them to gain a deeper understanding of their strengths and weaknesses and effectively improve their interview skills.

[0942] "User Terminal" means a computer or smart device that enables a User to access the System through an interface and input and receive data.

[0943] "Generative AI" refers to technology that uses artificial intelligence algorithms to generate the next question or feedback based on input data.

[0944] An "emotion engine" refers to a combination of hardware and software for analyzing a user's emotional state from facial expression data and voice data.

[0945] "Database" refers to a data storage system for systematically storing and managing user information, responses, analysis results, etc.

[0946] "Feedback" refers to specific advice and comments for improvement provided to users based on the analysis results of the generative AI and emotion engine.

[0947] "Means for managing question and answer interactions" refers to the system's ability to track and control the process of multiple questions and answers in a mock interview.

[0948] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika). Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions, providing more detailed and appropriate feedback.

[0949] Main components of the system

[0950] 1. User Registration and Login

[0951] A user accesses the system and registers or logs in. They must enter their name, email address, and password.

[0952] The terminal transmits the input data to the server.

[0953] The server saves the information in a database and manages the login state. If the login is successful, it redirects the user to the home screen.

[0954] 2. Course Selection

[0955] After logging in, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course."

[0956] The terminal transmits the user's selection to the server.

[0957] The server generates an interface according to the selected course and transmits it to the terminal.

[0958] 3. Brush up on your academic background

[0959] After the user selects the "Gakuchika Brush-up Course," a screen for inputting the contents of Gakuchika is displayed.

[0960] The terminal transmits the inputted contents to the server.

[0961] The server uses a generative AI model to analyze the content of the student's academic background and generate specific feedback. For example, in response to an input such as, "This is my experience as a leader in a club activity at university. As I was working on a project, I came up with a way to deal with problems that arose," the generative AI adds specific examples and organizes the timeline.

[0962] 4. Mock interviews

[0963] After the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[0964] The terminal sends a start request to the server.

[0965] The server uses a generative AI model to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[0966] The user enters an answer to the question and clicks the "Submit" button.

[0967] The terminal sends the response to the server.

[0968] The server uses the generative AI model to generate the next question and sends it to the device. This process is repeated 10 times.

[0969] 5. Leveraging Emotional Engines

[0970] During the user's mock interview, the emotion engine collects facial expression and voice data. For example, it detects when the user looks anxious in the facial expression data or when the user sounds nervous in the voice data.

[0971] The terminal transmits this data to the server in real time.

[0972] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[0973] The generative AI adjusts the next question based on the results of the emotion analysis, and also provides specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[0974] 6. Providing Feedback

[0975] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[0976] The terminal sends a request to the server.

[0977] The server uses a generation AI to analyze the overall response and sentiment analysis results and generate comprehensive feedback (e.g., "Your response is specific, but it's important that you speak with more confidence").

[0978] The terminal displays the feedback content to the user.

[0979] Specific examples

[0980] For example, if a user inputs something like, "This is my experience as a leader in a club activity at university. As I was working on a project, I came up with ways to deal with problems that arose," the generating AI will provide feedback by adding specific examples and organizing the content chronologically.

[0981] Examples of prompt statements

[0982] "Tell me about an experience you had as a leader in a university club. For example, tell me specifically how you brought members together, solved a problem, and achieved a final result."

[0983] Based on this prompt, users can specifically describe their experience and receive feedback from the generating AI.

[0984] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0985] Step 1:

[0986] User Registration and Login

[0987] Subject: User

[0988] Input: Name, Email Address, Password

[0989] How it works: A user accesses the system and enters their name, email address, and password to register or log in.

[0990] Output: Registration information or login credentials

[0991] Subject: Terminal

[0992] Input: Registration or login information entered by the user

[0993] Operation: The terminal sends the entered data to the server.

[0994] Output: Request to submit registration information or login credentials

[0995] Subject: Server

[0996] Input: User registration or login information

[0997] How it works: The server receives the submitted information, stores it in a database, or performs authentication. If authentication is successful, it generates a response that redirects the user to the home screen.

[0998] Output: Home screen display instructions

[0999] Step 2:

[1000] Course Selection

[1001] Subject: User

[1002] Input: Course selection ("Interview Practice Course" or "Gakuchika Brush-up Course")

[1003] How it works: The user selects the desired course on the displayed home screen and clicks the "Next" button.

[1004] Output: Course selection information

[1005] Subject: Terminal

[1006] Input: User's course selection information

[1007] Operation: The terminal transmits the selected course information to the server.

[1008] Output: Request to send selected course information

[1009] Subject: Server

[1010] Input: Course selection information

[1011] Operation: The server generates an interface according to the selected course and sends it to the terminal.

[1012] Output: The generated interface

[1013] Step 3:

[1014] Brushing up on your academic background

[1015] Subject: User

[1016] Input: What you focused on during your student days

[1017] How it works: After selecting the "Gakuchika Brush-up Course," the user enters details about what they focused on during their time as a student and clicks the "Submit" button.

[1018] Output: Input contents

[1019] Subject: Terminal

[1020] Input: The content of the academic background entered by the user

[1021] Operation: The terminal sends the input information to the server.

[1022] Output: Request to send input content

[1023] Subject: Server

[1024] Input: The content of the academic background entered by the user

[1025] How it works: The server passes the input data to the generative AI model, which analyzes it based on the framework. Once the analysis is complete, the generative AI adds specific examples and organizes the timeline.

[1026] Output: Feedback

[1027] Subject: Terminal

[1028] Input: Generated feedback

[1029] Action: The device displays the feedback to the user.

[1030] Output: Show feedback

[1031] Step 4:

[1032] Mock interviews

[1033] Subject: User

[1034] Input: Request to start mock interview

[1035] Action: The user clicks the "Start Mock Interview" button.

[1036] Output: Start request

[1037] Subject: Terminal

[1038] Input: User's start request

[1039] Operation: The terminal sends a start request to the server.

[1040] Output: Send start request

[1041] Subject: Server

[1042] Input: Request to start mock interview

[1043] How it works: The server uses a generative AI model to generate an initial question and sends it to the device (e.g., "Tell me about yourself").

[1044] Output: First question

[1045] Subject: Terminal

[1046] Input: First question

[1047] Action: The terminal displays the question to the user.

[1048] Output: Show question

[1049] Subject: User

[1050] Input: Answer to question

[1051] How it works: The user enters an answer to a question and clicks the "Submit" button.

[1052] Output:Answer

[1053] Subject: Terminal

[1054] Input: User's answer

[1055] Action: The device sends a response to the server.

[1056] Output: Request to send answer

[1057] Subject: Server

[1058] Input: User's answer

[1059] How it works: The server receives the answer, uses the generative AI model to generate the next question, and sends it to the device. This process is repeated 10 times.

[1060] Output: Next question

[1061] Subject: Terminal

[1062] Input: Next question

[1063] Action: The terminal displays the following question to the user:

[1064] Output: Show question

[1065] Step 5:

[1066] Utilizing the Emotion Engine

[1067] Subject: User

[1068] Input: facial expression data, voice data

[1069] How it works: The emotion engine collects facial and vocal data during a user's mock interview.

[1070] Output: Emotion data

[1071] Subject: Terminal

[1072] Input: Emotion data

[1073] Operation: The device transmits emotion data to the server in real time.

[1074] Output: Sending emotion data

[1075] Subject: Server

[1076] Input: Emotion data

[1077] How it works: The server analyzes the data collected by the emotion engine and passes the results to the generative AI.

[1078] Output: Analysis results

[1079] Subject: Generation AI

[1080] Input: Sentiment analysis results

[1081] How it works: The generative AI uses the results of the emotion analysis to adjust the next question and incorporate it into the feedback (e.g., "Try to be a bit more relaxed and softer when speaking").

[1082] Output: Tailored questions, feedback

[1083] Subject: Server

[1084] Input: Moderated questions, feedback

[1085] How it works: The server sends tailored questions and feedback to the device.

[1086] Output: Tailored questions and feedback submissions

[1087] Subject: Terminal

[1088] Input: Moderated questions and feedback

[1089] Action: The device displays tailored questions and feedback to the user.

[1090] Output: Display of tailored questions and feedback

[1091] Step 6:

[1092] Providing Feedback

[1093] Subject: User

[1094] Input: Feedback request

[1095] How it works: After completing 10 mock interview questions, the user clicks the "Receive Feedback" button.

[1096] Output: Feedback request

[1097] Subject: Terminal

[1098] Input: Feedback request

[1099] Operation: The device sends a request to the server.

[1100] Output: Sending a request

[1101] Subject: Server

[1102] Input: Feedback request

[1103] How it works: The server uses the generation AI to analyze the overall response and sentiment analysis results and generate comprehensive feedback (e.g., "Your response is specific, but it's important that you speak with more confidence").

[1104] Output: Generated feedback

[1105] Subject: Terminal

[1106] Input: Generated feedback

[1107] Action: The device displays the feedback to the user.

[1108] Output: Show feedback

[1109] (Application example 2)

[1110] 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."

[1111] The present invention aims to provide a system for conducting mock interviews that analyzes a user's emotions in real time and provides appropriate feedback based on the analysis results, thereby enabling the user to efficiently improve themselves. At the same time, it aims to solve the problem of providing real-time product recommendations and feedback using user emotion analysis in order to improve the shopping experience in physical stores.

[1112] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input from a user terminal for conducting a mock interview, means for the generation AI to generate the next question based on the input, means for managing multiple exchanges of questions and answers, means for providing feedback after the multiple exchanges, means for collecting facial expression data and voice data of the user in real time, an emotion engine for analyzing the facial expression data and voice data, and means for the generation AI to adjust the next question and feedback based on the emotion analysis results. This enables appropriate feedback based on the user's emotions.

[1113] A "user device" is an electronic device that allows a user to use the mock interview or shopping assistant app.

[1114] "Generative AI" is artificial intelligence that generates the next question or feedback based on user input and emotional analysis results.

[1115] The "emotion engine" is a system that analyzes a user's facial expression data and voice data in real time to evaluate the user's emotional state.

[1116] "Facial expression data" refers to data obtained by capturing the user's facial expression using a camera or the like, and used to analyze the user's emotions.

[1117] "Voice data" is data obtained by capturing the user's speaking style and tone of voice using a microphone or the like, and used to analyze the user's emotions.

[1118] "Means for providing feedback" refers to a function that presents the user with feedback generated by the generation AI based on the analysis results.

[1119] An "analysis engine" is a system that performs analysis based on data entered by a user or acquired data.

[1120] "User Information" means your personal identification information and login information, such as your name, email address, and password.

[1121] The "database" is a system for storing user information, interview records, emotion analysis data, etc.

[1122] The "means for collecting in real time" refers to a function or device for collecting facial expression data and voice data of a user in real time.

[1123] A "means for generating the next question" is an algorithm or system for generating the next question based on previous answers and emotional state.

[1124] A "shopping assistant app" is an application that provides product recommendations and feedback based on the results of user sentiment analysis in order to improve the shopping experience in physical stores.

[1125] A system for realizing this invention will be described below. This system analyzes a user's emotions in real time through a mock interview or shopping assistant application, and provides appropriate feedback.

[1126] System configuration

[1127] 1. User Device

[1128] A smartphone, tablet, or computer that connects to the server and runs the mock interview or shopping assistant application.

[1129] It is equipped with a camera and microphone to collect the user's facial expression and voice data.

[1130] Accepts user input and sends data to the server.

[1131] 2. Server

[1132] Receives input data and collected data and stores it in a database.

[1133] Use generative AI to generate the next question or feedback.

[1134] The emotion engine analyzes the user's facial expression and voice data.

[1135] Based on the analysis results, the generative AI adjusts the next questions and feedback.

[1136] Detailed System Description

[1137] 1. User Registration and Login

[1138] Users first access the app and either register or log in.

[1139] The user's name, email address, and password are entered and sent to the server.

[1140] The server stores the received information in a database and manages the login status.

[1141] 2. Mock interviews

[1142] When a user starts a mock interview, a start request is sent from the user terminal to the server.

[1143] The server uses a generation AI to generate an initial question and sends it to the terminal.

[1144] The user answers the questions and sends the answers to the server.

[1145] The server uses an emotion engine to analyze facial expression and voice data and passes the results to the generation AI.

[1146] The generative AI then adjusts the next question or feedback and repeats the process.

[1147] 3. Shopping Assistant App

[1148] Users use the app while walking around the store, and their smartphone's camera and microphone collect facial and voice data in real time.

[1149] The collected data is sent to a server and analyzed by the emotion engine.

[1150] The server passes the analysis results to the generation AI, which then provides product recommendations and feedback in real time.

[1151] For example, if the user is confused, "recommended items" will be presented, and if the user is excited, "additional suggestions for related products" will be made.

[1152] Specific examples

[1153] Example of a mock interview:

[1154] First question: "Please introduce yourself"

[1155] User Answer: "My name is △△ and I'm from XX University. I majored in □□ and during my student days I focused on XX activities."

[1156] Examples of shopping assistants:

[1157] User views product A:

[1158] Facial expression data: Confused

[1159] Voice Tone: Anxiety

[1160] Generated AI feedback: "What about product C? It's popular with many users."

[1161] Prompt Sentence Examples

[1162] Examples of input prompts for generative AI models include:

[1163] Use the following data to create feedback and product recommendations based on user sentiment.

[1164] User shopping history:

[1165] Product A: Viewing time 2 minutes, facial expression: Confused, voice tone: Anxious

[1166] Product B: Viewing time 5 minutes, facial expression: excitement, voice tone: joy

[1167] Emotion analysis results:

[1168] Facial expression data: confusion, anxiety, excitement, joy

[1169] Voice Tone: Anxiety, Joy

[1170] Such a system would allow users to receive appropriate advice and recommendations tailored to their emotional state, potentially leading to self-improvement and an improved shopping experience.

[1171] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1172] Step 1:

[1173] A user accesses the app and registers or logs in. The user enters their name, email address, and password, which the device sends to the server. The server saves the entered data in a database and manages the user's login status.

[1174] Input: Name, Email Address, Password

[1175] Output: Login session ID

[1176] Specific operation: The terminal receives user input and sends the data to the server, which saves it in the database, generates a session ID, and returns it to the user.

[1177] Step 2:

[1178] The user selects either the "Mock Interview" or "Shopping Assistant" course. The terminal sends the selection information to the server, which then generates an interface according to the selection and returns it to the terminal.

[1179] Input: Course selection information

[1180] Output: Course-specific interface

[1181] Specific operation: The device detects the user's selection and sends the data to the server. The server generates an interface according to the selection and sends it back to the device.

[1182] Step 3:

[1183] In the mock interview, the user enters answers to questions and the device sends them to the server, which uses a generative AI to generate the next question, repeating this process 10 times.

[1184] Input: User's answer

[1185] Output: The following questions are generated:

[1186] How it works: The device collects the user's answers and sends them to the server. The server then uses a generative AI to generate the next question and sends it back to the device. This process is repeated 10 times.

[1187] Step 4:

[1188] In the case of a shopping assistant, while the user is browsing products, the device collects facial expression and voice data in real time and sends it to a server, which then uses an emotion engine to analyze the data and pass the results to a generative AI.

[1189] Input: facial expression data, voice data

[1190] Output: Emotion analysis results

[1191] Specific operation: The device collects facial expression and voice data while browsing products and sends it to the server. The server analyzes it with an emotion engine and sends the results to the generation AI.

[1192] Step 5:

[1193] Based on the results of the emotion analysis, the generative AI generates appropriate feedback and the next question, which the server sends to the device and displays to the user.

[1194] Input: Sentiment analysis results

[1195] Output: Feedback and next questions

[1196] Specific operation: The server uses the generation AI to generate feedback and next questions based on the analysis results and sends them to the device, which then displays them to the user.

[1197] Step 6:

[1198] After the user completes the mock interview or shopping assistant session, they receive feedback. The device sends the user's request to the server, which then generates comprehensive feedback and sends it to the device.

[1199] Input: Session termination request

[1200] Output: Comprehensive feedback

[1201] How it works: After the user finishes their session, they submit a request. The server uses AI to generate comprehensive feedback based on the entire data, sends it to the device, and displays it to the user.

[1202] This allows users to receive appropriate advice and product recommendations based on their emotional state, which can lead to self-improvement and an improved shopping experience.

[1203] 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.

[1204] 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.

[1205] 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.

[1206] [Third embodiment]

[1207] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1208] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1209] 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).

[1210] 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.

[1211] 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.

[1212] 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).

[1213] 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.

[1214] 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.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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."

[1219] The following describes an embodiment of the present invention. This system is effective for allowing users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika).

[1220] System Overview

[1221] 1. User Registration and Login

[1222] When a user first accesses the system, they register or log in. They enter their name, email address, and password.

[1223] The terminal transmits the input data to the server.

[1224] The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen.

[1225] 2. Course Selection

[1226] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[1227] The terminal transmits the user's selection to the server.

[1228] The server generates an interface according to the selected course and transmits it to the terminal.

[1229] 3. Brush up on your academic background

[1230] If the user selects the "School Background Brush-up Course," a screen for inputting the details of what the user focused on during their school days is displayed.

[1231] The terminal transmits the inputted contents to the server.

[1232] The server uses a generation AI to analyze the content of the Gakuchika based on the framework. For example, if the user enters something like, "My Gakuchika is about my experience as a leader in a club activity at university. As I worked on a project, I came up with ways to deal with problems that arose," the generation AI will provide feedback by adding specific examples and organizing the content chronologically.

[1233] 4. Mock interviews

[1234] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[1235] The terminal sends a start request to the server.

[1236] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[1237] The user enters an answer to the question and clicks the "Submit" button.

[1238] The terminal sends the response to the server.

[1239] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[1240] 5. Providing Feedback

[1241] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[1242] The terminal sends a request to the server.

[1243] The server analyzes the entire response, and the generation AI generates comprehensive feedback (e.g., "Your response is specific and good, but it's important that you speak with more confidence") and sends it to the device.

[1244] The terminal displays the feedback content.

[1245] This system allows users to easily experience mock interviews and brush up on their academic background. Through specific feedback from the generative AI, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for the actual interview.

[1246] The processing flow will be explained below.

[1247] Step 1:

[1248] A user accesses the system and registers or logs in. The user enters their name, email address, and password.

[1249] Step 2:

[1250] The terminal transmits the entered registration or login information to the server.

[1251] Step 3:

[1252] The server stores the received information in a database and manages the login status. If the login is successful, it sends an instruction to the terminal to redirect the user to the home screen.

[1253] Step 4:

[1254] The server confirms that the user has logged in, generates a screen for selecting either the "Interview Practice Course" or the "School Background Brush-up Course", and sends it to the terminal.

[1255] Step 5:

[1256] On the displayed screen, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course" and clicks the "Next" button.

[1257] Step 6:

[1258] The terminal transmits the user's selection to the server.

[1259] Step 7:

[1260] The server generates the next screen according to the selected course and transmits it to the terminal.

[1261] Step 8:

[1262] (If you select the Gakuchika Brush-up Course)

[1263] The server generates a screen containing input fields based on a framework for academic background (e.g., the STAR method) and sends it to the terminal.

[1264] Step 9:

[1265] The user inputs the details of what he / she focused on during his / her school days and clicks the "Submit" button.

[1266] Step 10:

[1267] The terminal transmits the entered contents of the academic background to the server.

[1268] Step 11:

[1269] The server passes the received academic background information to the generation AI for analysis.

[1270] Step 12:

[1271] The AI ​​analyzes the content of the student's academic background and generates feedback, which is then passed to the server.

[1272] Step 13:

[1273] The server transmits the generated feedback to the terminal and displays it to the user.

[1274] Step 14:

[1275] (If you select the Interview Practice Course)

[1276] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the terminal.

[1277] Step 15:

[1278] The user enters an answer to the initial question and clicks the "Submit" button.

[1279] Step 16:

[1280] The terminal transmits the user's answer to the server.

[1281] Step 17:

[1282] The server passes the received answers to the generation AI for evaluation, which then generates the next question and returns it to the server.

[1283] Step 18:

[1284] The server sends the next question received from the generation AI to the device. This process is repeated 10 times.

[1285] Step 19:

[1286] After 10 rounds of question and answer exchanges, the user clicks the "Get Feedback" button.

[1287] Step 20:

[1288] The terminal transmits the user's request to the server.

[1289] Step 21:

[1290] The server analyzes all the answers with the generation AI and generates comprehensive feedback, which is then passed back to the server.

[1291] Step 22:

[1292] The server transmits the generated feedback to the terminal and displays it to the user.

[1293] Example 1

[1294] 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."

[1295] In recent years, mock interviews and self-analysis have become increasingly required during job hunting, but there is a lack of effective tools for conducting these individually. It is also important to brush up on what you focused on during your student days (gakuchika), but there are limited efficient ways to do this. Furthermore, specific and accurate feedback is necessary for users to understand their strengths and weaknesses and improve their performance in actual interviews. A comprehensive system that can solve these issues is needed.

[1296] 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.

[1297] In this invention, the server includes means for receiving registration and login information from a user terminal, means for storing the information in a database and managing login status, means for the user to select a mock interview or brush-up course, means for receiving input from the user terminal for conducting the mock interview, means for the generative AI model to generate the next question based on the input, means for managing multiple question-and-answer exchanges, and means for providing feedback after the multiple exchanges. This allows users to easily experience mock interviews and brush up on their academic background. Furthermore, through specific feedback from the generative AI model, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for actual interviews.

[1298] A "user terminal" is a device used by a user to access the system, and includes a personal computer, smartphone, tablet, etc.

[1299] A "server" is a part of a computer system that receives and processes information sent from a user's device, storing data and analyzing it using generated AI.

[1300] A "database" is a system for systematically storing user information and other data, and for storing, retrieving, and managing information.

[1301] "Logged-in state" refers to a state in which a user has accessed the system, has been authenticated, and is able to perform operations within the system.

[1302] A "mock interview" is a simulation that mimics a real interview, and is a process in which a user practices an interview through question and answer exchanges.

[1303] The "Brush-up Course" is a program that helps users improve the things they focused on during their student days (gakuchika), and involves inputting and analyzing specific content.

[1304] A "generative AI model" is a system that uses artificial intelligence to generate questions and feedback based on user input.

[1305] "Feedback" refers to evaluations and advice provided based on the results of mock interviews and brush-ups conducted by the user.

[1306] A "framework" is a framework or standard for analyzing user input, and includes, for example, the STAR method (Situation, Task, Action, Result).

[1307] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and brush up on what they focused on during their student days (Gakuchika). This system utilizes a user terminal, a server, and a generative AI model.

[1308] First, a user terminal is a device that provides an interface with the system. Specifically, it includes personal computers, smartphones, tablets, etc. Users access the system through their terminal to register and log in.

[1309] The server receives information sent from the user's device, stores the data, and analyzes it using the generation AI. A database is connected to the server, and user information and mock interview data are systematically stored. A database management system such as MySQL is used for the database.

[1310] The system works as follows: A user first accesses the system and enters their name, email address, and password on the new registration or login screen. The device sends the entered information to the server. The server stores the received information in a database and manages the login status. If authentication is successful, the user is redirected to the home screen.

[1311] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course." The course selection information is sent from the terminal to the server, and the server generates an interface corresponding to the selected course and sends it to the terminal.

[1312] If a user selects the "Gakuchika Brush-up Course," a screen will appear where they can enter details about what they focused on during their time as a student. The user enters the details, and the device sends the details to the server. The server uses a generative AI (for example, OpenAI's GPT-4) to analyze the entered Gakuchika details and evaluate them based on a framework (such as the STAR method). The generative AI analyzes the details and generates specific feedback.

[1313] For example, if a user enters the following content, "My academic background is my experience as a leader in a club activity at university. When a problem arose during the project, I devised a way to deal with it," the server will use generative AI to provide feedback. For example, it will return advice such as, "Specifically, it would be good to explain in detail at what stage of the project the problem arose, what measures were taken, and what results were achieved as a result."

[1314] On the other hand, if the user selects the "Interview Practice Course," a screen to start the mock interview will be displayed. When the user clicks the start button, the device sends the request to the server. The server uses the generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device. The user enters an answer to the question, and the device sends the answer to the server. The server again uses the generation AI to generate the next question, and this process is repeated 10 times.

[1315] After completing the mock interview, the user clicks the "Receive Feedback" button. The device sends a request to the server, which analyzes all responses and uses a generative AI to generate comprehensive feedback, which is then sent to the device. The device then displays the feedback.

[1316] Examples of prompts include "Tell us about yourself" and "Tell us more about your Gakuchika." In this way, the system allows users to refine their Gakuchika through mock interviews and receive specific feedback.

[1317] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] A user accesses the system and enters their name, email address, and password on the registration or login screen.

[1320] Input: Name, Email Address, Password

[1321] Specific actions: A user visits a web page, fills in a form, and clicks the "Submit" button.

[1322] Output: Input information is sent from the device to the server.

[1323] Step 2:

[1324] The device sends the entered information to the server, using the HTTPS protocol to send the data securely.

[1325] Input: Name, email address, and password entered by the user

[1326] Specific operation: The device packages the user's input information in JSON format, creates an HTTPS request, and sends it to the server.

[1327] Output: The input information reaches the server.

[1328] Step 3:

[1329] The server stores the received information in a database and manages the login status. MySQL is used for storage.

[1330] Input: Name, email address, and password sent from your device

[1331] Specific operation: The server connects to the database and saves the user information using an INSERT statement. Also, when the login is successful, it creates and manages session information.

[1332] Output: User information is saved in the database and a login session is created for the user.

[1333] Step 4:

[1334] The user is redirected to the home screen and the main menu is displayed. The user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[1335] Input: User login session, home screen request

[1336] Specific operation: After the server confirms the login status, it generates the HTML for the home screen and sends it to the device.

[1337] Output: The home screen is displayed on the user's device.

[1338] Step 5:

[1339] The course information selected by the user is sent from the terminal to the server.

[1340] Input: Course selection information (e.g., "Interview Practice Course" or "Gakuchika Brush-up Course")

[1341] Specific operation: The user clicks on the course icon, and the device sends the information to the server.

[1342] Output: Course selection information is sent to the server.

[1343] Step 6:

[1344] The server generates an interface according to the selected course and transmits it to the terminal.

[1345] Input: Course selection information

[1346] Specific operation: The server dynamically generates HTML according to the selected course and sends it to the terminal.

[1347] Output: A course-specific screen is displayed on the user's device.

[1348] Step 7:

[1349] If the user selects the "Gakuchika Brush-up Course," he or she inputs the contents of his or her Gakuchika.

[1350] Input: Content of your Gakuchika (e.g., "Experience as a leader in a club activity at university")

[1351] Specific behavior: The user enters the details of their academic background and clicks the "Submit" button.

[1352] Output: Input is sent from the terminal to the server.

[1353] Step 8:

[1354] The server sends the input content to the generation AI, which analyzes it based on a framework (e.g., the STAR method).

[1355] Input: Contents of your academic background

[1356] Specific operation: The server sends the user's input as text to the generative AI model and receives the analysis results.

[1357] Output: The analysis results from the generation AI are returned to the server.

[1358] Step 9:

[1359] The server sends the feedback received from the generated AI to the terminal and displays it to the user.

[1360] Input: Analysis results from the generative AI

[1361] Specific operation: The server sends the received feedback information to the terminal in HTML format.

[1362] Output: Specific feedback is displayed on the user's device.

[1363] Step 10:

[1364] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[1365] Input: Course selection information

[1366] Specific operation: When the user clicks "Start", the device sends the request to the server.

[1367] Output: The initial question is generated from the server and sent to the device.

[1368] Step 11:

[1369] The server uses a generation AI to generate mock interview questions and send them to the device.

[1370] Input: Request to start interview

[1371] Specific operation: The server has the generation AI generate the first question and send it to the device.

[1372] Output: The initial question is displayed on the user's terminal.

[1373] Step 12:

[1374] The user enters an answer to the question, and the terminal transmits the answer to the server.

[1375] Input: Answer to the question

[1376] Specific behavior: The user enters an answer and clicks the "Submit" button. The device sends the information to the server.

[1377] Output: The answer arrives at the server.

[1378] Step 13:

[1379] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[1380] Input: Previous answer

[1381] Specific operation: The server asks the generation AI to generate the next question and sends it to the device.

[1382] Output: The following question is displayed on the user's terminal:

[1383] Step 14:

[1384] After the user completes 10 mock interview questions, they click the "Receive Feedback" button.

[1385] Input: 10 questions and answers

[1386] Specific operation: The device sends a request to the server.

[1387] Output: The server sends the data to the generating AI.

[1388] Step 15:

[1389] The server uses generative AI to generate comprehensive feedback and send it to the device.

[1390] Input: All question and answer data

[1391] Specific operation: The server instructs the generation AI to generate feedback based on all data.

[1392] Output: Feedback information is sent to the terminal.

[1393] Step 16:

[1394] The device displays the feedback to the user.

[1395] Input: Feedback data from the generative AI

[1396] Specific behavior: The device receives the feedback information and displays it on the screen.

[1397] Output: Feedback is displayed on the user's screen.

[1398] This allows users to easily experience mock interviews and brush up on their academic background. In addition, through specific feedback from the generative AI model, users can gain a deeper understanding of their strengths and weaknesses, enabling them to effectively prepare for actual interviews.

[1399] (Application example 1)

[1400] 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."

[1401] Customer service in brick-and-mortar stores is directly linked to customer satisfaction, making training essential. However, traditional training methods make it difficult to obtain specific feedback in real time, limiting opportunities for self-improvement. Furthermore, mock interviews and other skill-improvement simulation tools are often provided individually, creating a need for a centralized training system. A system is needed that allows employees to effectively improve their skills without disrupting their daily work.

[1402] 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.

[1403] In this invention, the server includes means for receiving input from a user terminal for conducting a mock interview, means for a generation AI to generate the next question based on the input, means for managing multiple exchanges of questions and answers, means for providing feedback after the multiple exchanges, means for a salesperson to conduct a customer service simulation in a physical store, and means for the generation AI to generate feedback based on the results of the simulation, thereby enabling employees to evaluate and improve their customer service skills in real time through the simulation.

[1404] A "mock interview" is a training session conducted in a format that mimics a real interview.

[1405] A "user terminal" is an electronic device such as a smartphone or tablet that is operated by a user.

[1406] A "means for receiving input" is a mechanism for sending data or instructions from a user to a system.

[1407] "Generative AI" is a technology that uses artificial intelligence to dynamically generate content and responses.

[1408] The "means for generating the next question" is a mechanism by which the AI ​​automatically generates a new question based on the user's answer.

[1409] "Means for managing multiple question and answer exchanges" refers to a mechanism for providing consecutive questions and recording and analyzing the answers.

[1410] The "means for providing feedback" is a mechanism for conveying evaluations and areas for improvement based on the content of the user's responses.

[1411] The "means for sales staff to conduct customer service simulations in a real store" is a mechanism for sales staff working in a real store to practice customer service simulations.

[1412] "Means for the AI ​​to generate feedback based on the simulation results" refers to a mechanism in which the AI ​​analyzes the results of the customer service simulation and automatically generates appropriate feedback.

[1413] The system for implementing the present invention aims to enable users to improve their customer service skills through simulated customer service practice. Details of the system are described below.

[1414] 1. User Registration and Login

[1415] The user (store clerk) first accesses the system and registers or logs in. The user enters their name, email address, and store ID.

[1416] The smartphone sends the entered data to the server. The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen. This process uses MySQL as the database, a cloud server, and the smartphone.

[1417] 2. Select a training course

[1418] After logging in, the user selects a training course. They choose either "Initial Customer Service Training Course" or "Advanced Customer Service Training Course." The smartphone sends the user's selection to the server. The server generates an interface corresponding to the selected course and sends it to the smartphone.

[1419] 3. Customer Service Simulation

[1420] If the user selects the "Initial Customer Service Training Course," a basic customer service simulation is conducted. The user inputs the answers to the simulation and sends them to the server via their smartphone. The server uses a generative AI (e.g., OpenAI GPT-4) to generate the next question. The simulation is conducted over multiple rounds of interaction, with new questions automatically generated after each answer.

[1421] 4. Providing Feedback

[1422] At the end of the simulation, users can receive feedback. The server uses generative AI to generate feedback based on the simulation results and sends it to their smartphone. The feedback provides specific and practical advice, allowing users to improve their customer service skills.

[1423] For example, use the following prompt:

[1424] "A customer asks where an item is. How do you respond?"

[1425] The generative AI provides feedback such as:

[1426] "Your response is helpful, but it would be better if you provided more specific instructions and suggested next steps."

[1427] This system allows users to effectively improve their customer service skills without disrupting operations at physical stores, which is expected to improve the quality of service at stores.

[1428] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1429] Step 1:

[1430] A user (store clerk) accesses the system and performs new registration or login. The user enters their name, email address, and store ID. Once this data is entered, the smartphone sends it to the server. The server stores the received information in a database and manages the login status. Once login is complete, the user is redirected to the home screen. The input data is user information, and the output is the login status and home screen display.

[1431] Step 2:

[1432] After logging in, the user selects a training course. Specifically, they choose either the "Initial Customer Service Training Course" or the "Advanced Customer Service Training Course." The user's selection becomes input data, and the smartphone sends the selection data to the server. The server generates an interface according to the selected course and returns it to the smartphone as output data. This allows the user to access the appropriate interface.

[1433] Step 3:

[1434] If the user selects the "Initial Customer Service Training Course," a simulation begins. The server uses a generation AI to generate an initial customer service scenario (e.g., "A customer has entered the store. How would you respond?"). This scenario becomes the initial input data, and the server sends it to the smartphone. The user enters answers to the scenario and sends them to the server, where the answer data is stored.

[1435] Step 4:

[1436] The server analyzes the received user answers using a generative AI and automatically generates the next question. The analysis results become the input data for generating the next question. After generating the question, the server sends a new scenario to the smartphone. This process is repeated multiple times. The output data is the next scenario, which is presented to the user.

[1437] Step 5:

[1438] After the series of simulations is completed, the server generates feedback based on all response data. The input data for generating this feedback is a set of all responses. The generation AI analyzes this and generates feedback that includes areas for improvement. The server sends the generated feedback to a smartphone. The output data is the feedback content, which the user can check on their smartphone. The feedback includes specific examples and areas for improvement, helping to improve the user's skills.

[1439] 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.

[1440] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika). In addition, the present invention incorporates an emotion engine that recognizes the user's emotions, providing more detailed and appropriate feedback.

[1441] System Overview

[1442] 1. User Registration and Login

[1443] When a user first accesses the system, they register or log in. They enter their name, email address, and password.

[1444] The terminal transmits the input data to the server.

[1445] The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen.

[1446] 2. Course Selection

[1447] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[1448] The terminal transmits the user's selection to the server.

[1449] The server generates an interface according to the selected course and transmits it to the terminal.

[1450] 3. Brush up on your academic background

[1451] If the user selects the "School Background Brush-up Course," a screen for inputting the details of what the user focused on during their school days is displayed.

[1452] The terminal transmits the inputted contents to the server.

[1453] The server uses a generation AI to analyze the content of the Gakuchika based on the framework. For example, if the user enters something like, "My Gakuchika is about my experience as a leader in a club activity at university. As I worked on a project, I came up with ways to deal with problems that arose," the generation AI will provide feedback by adding specific examples and organizing the content chronologically.

[1454] 4. Mock interviews

[1455] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[1456] The terminal sends a start request to the server.

[1457] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[1458] The user enters an answer to the question and clicks the "Submit" button.

[1459] The terminal sends the response to the server.

[1460] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[1461] 5. Leveraging Emotional Engines

[1462] During the mock interview, the emotion engine collects facial expression data and voice data of the user. For example, the facial expression data indicates that the user looks anxious, and the voice data indicates that the user speaks in a tense voice.

[1463] The terminal transmits this data to the server in real time.

[1464] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[1465] The generative AI can adjust the next question based on the results of the emotion analysis, and can also provide specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[1466] 6. Providing Feedback

[1467] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[1468] The terminal sends a request to the server.

[1469] The server uses a generation AI to analyze the overall response and the sentiment analysis results, and generates comprehensive feedback (e.g., "Your response is specific and good, but it's important that you speak with more confidence.") The feedback also includes the results of the sentiment engine's analysis, resulting in more specific and useful advice for the user.

[1470] The terminal displays the feedback content to the user.

[1471] This system allows users to easily experience mock interviews and brush up on their academic background. Through specific feedback from the generative AI and emotion engine, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for the actual interview.

[1472] The processing flow will be explained below.

[1473] Step 1:

[1474] A user accesses the system and registers or logs in. The user enters their name, email address, and password.

[1475] Step 2:

[1476] The terminal transmits the entered registration or login information to the server.

[1477] Step 3:

[1478] The server stores the received information in a database and manages the login status. If the login is successful, it sends an instruction to the terminal to redirect the user to the home screen.

[1479] Step 4:

[1480] The server confirms that the user has logged in, generates a screen for selecting either the "Interview Practice Course" or the "School Background Brush-up Course", and sends it to the terminal.

[1481] Step 5:

[1482] On the displayed screen, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course" and clicks the "Next" button.

[1483] Step 6:

[1484] The terminal transmits the user's selection to the server.

[1485] Step 7:

[1486] The server generates the next screen according to the selected course and transmits it to the terminal.

[1487] Step 8:

[1488] (If you select the Gakuchika Brush-up Course)

[1489] The server generates a screen containing input fields based on a framework for academic background (e.g., the STAR method) and sends it to the terminal.

[1490] Step 9:

[1491] The user inputs the details of what he / she focused on during his / her school days and clicks the "Submit" button.

[1492] Step 10:

[1493] The terminal transmits the entered contents of the academic background to the server.

[1494] Step 11:

[1495] The server passes the received academic background information to the generation AI for analysis.

[1496] Step 12:

[1497] The AI ​​analyzes the content of the student's academic background and generates feedback, which is then passed to the server.

[1498] Step 13:

[1499] The server transmits the generated feedback to the terminal and displays it to the user.

[1500] Step 14:

[1501] (If you select the Interview Practice Course)

[1502] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the terminal.

[1503] Step 15:

[1504] The user enters an answer to the initial question and clicks the "Submit" button.

[1505] Step 16:

[1506] The terminal transmits the user's answer to the server.

[1507] Step 17:

[1508] The server passes the received answers to the generation AI for evaluation, which then generates the next question and returns it to the server.

[1509] Step 18:

[1510] The server sends the next question received from the generation AI to the device. This process is repeated 10 times.

[1511] Step 19:

[1512] During the mock interview, the emotion engine collects facial expression data and voice data of the user. For example, the facial expression data indicates that the user looks anxious, and the voice data indicates that the user speaks in a tense voice.

[1513] Step 20:

[1514] The terminal transmits this data to the server in real time.

[1515] Step 21:

[1516] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[1517] Step 22:

[1518] The generative AI adjusts the next question based on the results of the emotion analysis, and also provides specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[1519] Step 23:

[1520] After 10 rounds of question and answer exchanges, the user clicks the "Get Feedback" button.

[1521] Step 24:

[1522] The terminal transmits the user's request to the server.

[1523] Step 25:

[1524] The server then uses the AI ​​to analyze the overall responses and the emotion analysis results, generating comprehensive feedback. The feedback also includes the results of the emotion engine's analysis, allowing for more specific and useful advice for the user.

[1525] Step 26:

[1526] The server transmits the generated feedback to the terminal and displays it to the user.

[1527] Example 2

[1528] 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."

[1529] Current mock interview systems struggle to provide specific and appropriate feedback based on detailed analysis of users' emotions and responses. They also lack the functionality to systematically analyze the information users enter and provide advice and areas for improvement. This makes it difficult for users to gain a deep understanding of their strengths and weaknesses and effectively learn to improve their interview skills.

[1530] 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.

[1531] In this invention, the server includes means for receiving input from a user terminal, means for a generation AI to generate the next question, means for collecting and analyzing user emotion data using an emotion analysis engine, means for managing multiple question-and-answer exchanges, and means for providing feedback. This allows the user to receive detailed and appropriate feedback through the mock interview, thereby enabling them to gain a deeper understanding of their strengths and weaknesses and effectively improve their interview skills.

[1532] "User Terminal" means a computer or smart device that enables a User to access the System through an interface and input and receive data.

[1533] "Generative AI" refers to technology that uses artificial intelligence algorithms to generate the next question or feedback based on input data.

[1534] An "emotion engine" refers to a combination of hardware and software for analyzing a user's emotional state from facial expression data and voice data.

[1535] "Database" refers to a data storage system for systematically storing and managing user information, responses, analysis results, etc.

[1536] "Feedback" refers to specific advice and comments for improvement provided to users based on the analysis results of the generative AI and emotion engine.

[1537] "Means for managing question and answer interactions" refers to the system's ability to track and control the process of multiple questions and answers in a mock interview.

[1538] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika). Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions, providing more detailed and appropriate feedback.

[1539] Main components of the system

[1540] 1. User Registration and Login

[1541] A user accesses the system and registers or logs in. They must enter their name, email address, and password.

[1542] The terminal transmits the input data to the server.

[1543] The server saves the information in a database and manages the login state. If the login is successful, it redirects the user to the home screen.

[1544] 2. Course Selection

[1545] After logging in, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course."

[1546] The terminal transmits the user's selection to the server.

[1547] The server generates an interface according to the selected course and transmits it to the terminal.

[1548] 3. Brush up on your academic background

[1549] After the user selects the "Gakuchika Brush-up Course," a screen for inputting the contents of Gakuchika is displayed.

[1550] The terminal transmits the inputted contents to the server.

[1551] The server uses a generative AI model to analyze the content of the student's academic background and generate specific feedback. For example, in response to an input such as, "This is my experience as a leader in a club activity at university. As I was working on a project, I came up with a way to deal with problems that arose," the generative AI adds specific examples and organizes the timeline.

[1552] 4. Mock interviews

[1553] After the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[1554] The terminal sends a start request to the server.

[1555] The server uses a generative AI model to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[1556] The user enters an answer to the question and clicks the "Submit" button.

[1557] The terminal sends the response to the server.

[1558] The server uses the generative AI model to generate the next question and sends it to the device. This process is repeated 10 times.

[1559] 5. Leveraging Emotional Engines

[1560] During the user's mock interview, the emotion engine collects facial expression and voice data. For example, it detects when the user looks anxious in the facial expression data or when the user sounds nervous in the voice data.

[1561] The terminal transmits this data to the server in real time.

[1562] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[1563] The generative AI adjusts the next question based on the results of the emotion analysis, and also provides specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[1564] 6. Providing Feedback

[1565] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[1566] The terminal sends a request to the server.

[1567] The server uses a generation AI to analyze the overall response and sentiment analysis results and generate comprehensive feedback (e.g., "Your response is specific, but it's important that you speak with more confidence").

[1568] The terminal displays the feedback content to the user.

[1569] Specific examples

[1570] For example, if a user inputs something like, "This is my experience as a leader in a club activity at university. As I was working on a project, I came up with ways to deal with problems that arose," the generating AI will provide feedback by adding specific examples and organizing the content chronologically.

[1571] Examples of prompt statements

[1572] "Tell me about an experience you had as a leader in a university club. For example, tell me specifically how you brought members together, solved a problem, and achieved a final result."

[1573] Based on this prompt, users can specifically describe their experience and receive feedback from the generating AI.

[1574] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1575] Step 1:

[1576] User Registration and Login

[1577] Subject: User

[1578] Input: Name, Email Address, Password

[1579] How it works: A user accesses the system and enters their name, email address, and password to register or log in.

[1580] Output: Registration information or login credentials

[1581] Subject: Terminal

[1582] Input: Registration or login information entered by the user

[1583] Operation: The terminal sends the entered data to the server.

[1584] Output: Request to submit registration information or login credentials

[1585] Subject: Server

[1586] Input: User registration or login information

[1587] How it works: The server receives the submitted information, stores it in a database, or performs authentication. If authentication is successful, it generates a response that redirects the user to the home screen.

[1588] Output: Home screen display instructions

[1589] Step 2:

[1590] Course Selection

[1591] Subject: User

[1592] Input: Course selection ("Interview Practice Course" or "Gakuchika Brush-up Course")

[1593] How it works: The user selects the desired course on the displayed home screen and clicks the "Next" button.

[1594] Output: Course selection information

[1595] Subject: Terminal

[1596] Input: User's course selection information

[1597] Operation: The terminal transmits the selected course information to the server.

[1598] Output: Request to send selected course information

[1599] Subject: Server

[1600] Input: Course selection information

[1601] Operation: The server generates an interface according to the selected course and sends it to the terminal.

[1602] Output: The generated interface

[1603] Step 3:

[1604] Brushing up on your academic background

[1605] Subject: User

[1606] Input: What you focused on during your student days

[1607] How it works: After selecting the "Gakuchika Brush-up Course," the user enters details about what they focused on during their time as a student and clicks the "Submit" button.

[1608] Output: Input contents

[1609] Subject: Terminal

[1610] Input: The content of the academic background entered by the user

[1611] Operation: The terminal sends the input information to the server.

[1612] Output: Request to send input content

[1613] Subject: Server

[1614] Input: The content of the academic background entered by the user

[1615] How it works: The server passes the input data to the generative AI model, which analyzes it based on the framework. Once the analysis is complete, the generative AI adds specific examples and organizes the timeline.

[1616] Output: Feedback

[1617] Subject: Terminal

[1618] Input: Generated feedback

[1619] Action: The device displays the feedback to the user.

[1620] Output: Show feedback

[1621] Step 4:

[1622] Mock interviews

[1623] Subject: User

[1624] Input: Request to start mock interview

[1625] Action: The user clicks the "Start Mock Interview" button.

[1626] Output: Start request

[1627] Subject: Terminal

[1628] Input: User's start request

[1629] Operation: The terminal sends a start request to the server.

[1630] Output: Send start request

[1631] Subject: Server

[1632] Input: Request to start mock interview

[1633] How it works: The server uses a generative AI model to generate an initial question and sends it to the device (e.g., "Tell me about yourself").

[1634] Output: First question

[1635] Subject: Terminal

[1636] Input: First question

[1637] Action: The terminal displays the question to the user.

[1638] Output: Show question

[1639] Subject: User

[1640] Input: Answer to question

[1641] How it works: The user enters an answer to a question and clicks the "Submit" button.

[1642] Output:Answer

[1643] Subject: Terminal

[1644] Input: User's answer

[1645] Action: The device sends a response to the server.

[1646] Output: Request to send answer

[1647] Subject: Server

[1648] Input: User's answer

[1649] How it works: The server receives the answer, uses the generative AI model to generate the next question, and sends it to the device. This process is repeated 10 times.

[1650] Output: Next question

[1651] Subject: Terminal

[1652] Input: Next question

[1653] Action: The terminal displays the following question to the user:

[1654] Output: Show question

[1655] Step 5:

[1656] Utilizing the Emotion Engine

[1657] Subject: User

[1658] Input: facial expression data, voice data

[1659] How it works: The emotion engine collects facial and vocal data during a user's mock interview.

[1660] Output: Emotion data

[1661] Subject: Terminal

[1662] Input: Emotion data

[1663] Operation: The device transmits emotion data to the server in real time.

[1664] Output: Sending emotion data

[1665] Subject: Server

[1666] Input: Emotion data

[1667] How it works: The server analyzes the data collected by the emotion engine and passes the results to the generative AI.

[1668] Output: Analysis results

[1669] Subject: Generation AI

[1670] Input: Sentiment analysis results

[1671] How it works: The generative AI uses the results of the emotion analysis to adjust the next question and incorporate it into the feedback (e.g., "Try to be a bit more relaxed and softer when speaking").

[1672] Output: Tailored questions, feedback

[1673] Subject: Server

[1674] Input: Moderated questions, feedback

[1675] How it works: The server sends tailored questions and feedback to the device.

[1676] Output: Tailored questions and feedback submissions

[1677] Subject: Terminal

[1678] Input: Moderated questions and feedback

[1679] Action: The device displays tailored questions and feedback to the user.

[1680] Output: Display of tailored questions and feedback

[1681] Step 6:

[1682] Providing Feedback

[1683] Subject: User

[1684] Input: Feedback request

[1685] How it works: After completing 10 mock interview questions, the user clicks the "Receive Feedback" button.

[1686] Output: Feedback request

[1687] Subject: Terminal

[1688] Input: Feedback request

[1689] Operation: The device sends a request to the server.

[1690] Output: Sending a request

[1691] Subject: Server

[1692] Input: Feedback request

[1693] How it works: The server uses the generation AI to analyze the overall response and sentiment analysis results and generate comprehensive feedback (e.g., "Your response is specific, but it's important that you speak with more confidence").

[1694] Output: Generated feedback

[1695] Subject: Terminal

[1696] Input: Generated feedback

[1697] Action: The device displays the feedback to the user.

[1698] Output: Show feedback

[1699] (Application example 2)

[1700] 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."

[1701] The present invention aims to provide a system for conducting mock interviews that analyzes a user's emotions in real time and provides appropriate feedback based on the analysis results, thereby enabling the user to efficiently improve themselves. At the same time, it aims to solve the problem of providing real-time product recommendations and feedback using user emotion analysis in order to improve the shopping experience in physical stores.

[1702] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input from a user terminal for conducting a mock interview, means for the generation AI to generate the next question based on the input, means for managing multiple exchanges of questions and answers, means for providing feedback after the multiple exchanges, means for collecting facial expression data and voice data of the user in real time, an emotion engine for analyzing the facial expression data and voice data, and means for the generation AI to adjust the next question and feedback based on the emotion analysis results. This enables appropriate feedback based on the user's emotions.

[1703] A "user device" is an electronic device that allows a user to use the mock interview or shopping assistant app.

[1704] "Generative AI" is artificial intelligence that generates the next question or feedback based on user input and emotional analysis results.

[1705] The "emotion engine" is a system that analyzes a user's facial expression data and voice data in real time to evaluate the user's emotional state.

[1706] "Facial expression data" refers to data obtained by capturing the user's facial expression using a camera or the like, and used to analyze the user's emotions.

[1707] "Voice data" is data obtained by capturing the user's speaking style and tone of voice using a microphone or the like, and used to analyze the user's emotions.

[1708] "Means for providing feedback" refers to a function that presents the user with feedback generated by the generation AI based on the analysis results.

[1709] An "analysis engine" is a system that performs analysis based on data entered by a user or acquired data.

[1710] "User Information" means your personal identification information and login information, such as your name, email address, and password.

[1711] The "database" is a system for storing user information, interview records, emotion analysis data, etc.

[1712] The "means for collecting in real time" refers to a function or device for collecting facial expression data and voice data of a user in real time.

[1713] A "means for generating the next question" is an algorithm or system for generating the next question based on previous answers and emotional state.

[1714] A "shopping assistant app" is an application that provides product recommendations and feedback based on the results of user sentiment analysis in order to improve the shopping experience in physical stores.

[1715] A system for realizing this invention will be described below. This system analyzes a user's emotions in real time through a mock interview or shopping assistant application, and provides appropriate feedback.

[1716] System configuration

[1717] 1. User Device

[1718] A smartphone, tablet, or computer that connects to the server and runs the mock interview or shopping assistant application.

[1719] It is equipped with a camera and microphone to collect the user's facial expression and voice data.

[1720] Accepts user input and sends data to the server.

[1721] 2. Server

[1722] Receives input data and collected data and stores it in a database.

[1723] Use generative AI to generate the next question or feedback.

[1724] The emotion engine analyzes the user's facial expression and voice data.

[1725] Based on the analysis results, the generative AI adjusts the next questions and feedback.

[1726] Detailed System Description

[1727] 1. User Registration and Login

[1728] Users first access the app and either register or log in.

[1729] The user's name, email address, and password are entered and sent to the server.

[1730] The server stores the received information in a database and manages the login status.

[1731] 2. Mock interviews

[1732] When a user starts a mock interview, a start request is sent from the user terminal to the server.

[1733] The server uses a generation AI to generate an initial question and sends it to the terminal.

[1734] The user answers the questions and sends the answers to the server.

[1735] The server uses an emotion engine to analyze facial expression and voice data and passes the results to the generation AI.

[1736] The generative AI then adjusts the next question or feedback and repeats the process.

[1737] 3. Shopping Assistant App

[1738] Users use the app while walking around the store, and their smartphone's camera and microphone collect facial and voice data in real time.

[1739] The collected data is sent to a server and analyzed by the emotion engine.

[1740] The server passes the analysis results to the generation AI, which then provides product recommendations and feedback in real time.

[1741] For example, if the user is confused, "recommended items" will be presented, and if the user is excited, "additional suggestions for related products" will be made.

[1742] Specific examples

[1743] Example of a mock interview:

[1744] First question: "Please introduce yourself"

[1745] User Answer: "My name is △△ and I'm from XX University. I majored in □□ and during my student days I focused on XX activities."

[1746] Examples of shopping assistants:

[1747] User views product A:

[1748] Facial expression data: Confused

[1749] Voice Tone: Anxiety

[1750] Generated AI feedback: "What about product C? It's popular with many users."

[1751] Prompt Sentence Examples

[1752] Examples of input prompts for generative AI models include:

[1753] Use the following data to create feedback and product recommendations based on user sentiment.

[1754] User shopping history:

[1755] Product A: Viewing time 2 minutes, facial expression: Confused, voice tone: Anxious

[1756] Product B: Viewing time 5 minutes, facial expression: excitement, voice tone: joy

[1757] Emotion analysis results:

[1758] Facial expression data: confusion, anxiety, excitement, joy

[1759] Voice Tone: Anxiety, Joy

[1760] Such a system would allow users to receive appropriate advice and recommendations tailored to their emotional state, potentially leading to self-improvement and an improved shopping experience.

[1761] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1762] Step 1:

[1763] A user accesses the app and registers or logs in. The user enters their name, email address, and password, which the device sends to the server. The server saves the entered data in a database and manages the user's login status.

[1764] Input: Name, Email Address, Password

[1765] Output: Login session ID

[1766] Specific operation: The terminal receives user input and sends the data to the server, which saves it in the database, generates a session ID, and returns it to the user.

[1767] Step 2:

[1768] The user selects either the "Mock Interview" or "Shopping Assistant" course. The terminal sends the selection information to the server, which then generates an interface according to the selection and returns it to the terminal.

[1769] Input: Course selection information

[1770] Output: Course-specific interface

[1771] Specific operation: The device detects the user's selection and sends the data to the server. The server generates an interface according to the selection and sends it back to the device.

[1772] Step 3:

[1773] In the mock interview, the user enters answers to questions and the device sends them to the server, which uses a generative AI to generate the next question, repeating this process 10 times.

[1774] Input: User's answer

[1775] Output: The following questions are generated:

[1776] How it works: The device collects the user's answers and sends them to the server. The server then uses a generative AI to generate the next question and sends it back to the device. This process is repeated 10 times.

[1777] Step 4:

[1778] In the case of a shopping assistant, while the user is browsing products, the device collects facial expression and voice data in real time and sends it to a server, which then uses an emotion engine to analyze the data and pass the results to a generative AI.

[1779] Input: facial expression data, voice data

[1780] Output: Emotion analysis results

[1781] Specific operation: The device collects facial expression and voice data while browsing products and sends it to the server. The server analyzes it with an emotion engine and sends the results to the generation AI.

[1782] Step 5:

[1783] Based on the results of the emotion analysis, the generative AI generates appropriate feedback and the next question, which the server sends to the device and displays to the user.

[1784] Input: Sentiment analysis results

[1785] Output: Feedback and next questions

[1786] Specific operation: The server uses the generation AI to generate feedback and next questions based on the analysis results and sends them to the device, which then displays them to the user.

[1787] Step 6:

[1788] After the user completes the mock interview or shopping assistant session, they receive feedback. The device sends the user's request to the server, which then generates comprehensive feedback and sends it to the device.

[1789] Input: Session termination request

[1790] Output: Comprehensive feedback

[1791] How it works: After the user finishes their session, they submit a request. The server uses AI to generate comprehensive feedback based on the entire data, sends it to the device, and displays it to the user.

[1792] This allows users to receive appropriate advice and product recommendations based on their emotional state, which can lead to self-improvement and an improved shopping experience.

[1793] 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.

[1794] 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.

[1795] 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.

[1796] [Fourth embodiment]

[1797] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1798] 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.

[1799] 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).

[1800] 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.

[1801] 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.

[1802] 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).

[1803] 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.

[1804] 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.

[1805] 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.

[1806] 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.

[1807] 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.

[1808] 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.

[1809] 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."

[1810] The following describes an embodiment of the present invention. This system is effective for allowing users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika).

[1811] System Overview

[1812] 1. User Registration and Login

[1813] When a user first accesses the system, they register or log in. They enter their name, email address, and password.

[1814] The terminal transmits the input data to the server.

[1815] The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen.

[1816] 2. Course Selection

[1817] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[1818] The terminal transmits the user's selection to the server.

[1819] The server generates an interface according to the selected course and transmits it to the terminal.

[1820] 3. Brush up on your academic background

[1821] If the user selects the "School Background Brush-up Course," a screen for inputting the details of what the user focused on during their school days is displayed.

[1822] The terminal transmits the inputted contents to the server.

[1823] The server uses a generation AI to analyze the content of the Gakuchika based on the framework. For example, if the user enters something like, "My Gakuchika is about my experience as a leader in a club activity at university. As I worked on a project, I came up with ways to deal with problems that arose," the generation AI will provide feedback by adding specific examples and organizing the content chronologically.

[1824] 4. Mock interviews

[1825] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[1826] The terminal sends a start request to the server.

[1827] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[1828] The user enters an answer to the question and clicks the "Submit" button.

[1829] The terminal sends the response to the server.

[1830] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[1831] 5. Providing Feedback

[1832] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[1833] The terminal sends a request to the server.

[1834] The server analyzes the entire response, and the generation AI generates comprehensive feedback (e.g., "Your response is specific and good, but it's important that you speak with more confidence") and sends it to the device.

[1835] The terminal displays the feedback content.

[1836] This system allows users to easily experience mock interviews and brush up on their academic background. Through specific feedback from the generative AI, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for the actual interview.

[1837] The processing flow will be explained below.

[1838] Step 1:

[1839] A user accesses the system and registers or logs in. The user enters their name, email address, and password.

[1840] Step 2:

[1841] The terminal transmits the entered registration or login information to the server.

[1842] Step 3:

[1843] The server stores the received information in a database and manages the login status. If the login is successful, it sends an instruction to the terminal to redirect the user to the home screen.

[1844] Step 4:

[1845] The server confirms that the user has logged in, generates a screen for selecting either the "Interview Practice Course" or the "School Background Brush-up Course", and sends it to the terminal.

[1846] Step 5:

[1847] On the displayed screen, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course" and clicks the "Next" button.

[1848] Step 6:

[1849] The terminal transmits the user's selection to the server.

[1850] Step 7:

[1851] The server generates the next screen according to the selected course and transmits it to the terminal.

[1852] Step 8:

[1853] (If you select the Gakuchika Brush-up Course)

[1854] The server generates a screen containing input fields based on a framework for academic background (e.g., the STAR method) and sends it to the terminal.

[1855] Step 9:

[1856] The user inputs the details of what he / she focused on during his / her school days and clicks the "Submit" button.

[1857] Step 10:

[1858] The terminal transmits the entered contents of the academic background to the server.

[1859] Step 11:

[1860] The server passes the received academic background information to the generation AI for analysis.

[1861] Step 12:

[1862] The AI ​​analyzes the content of the student's academic background and generates feedback, which is then passed to the server.

[1863] Step 13:

[1864] The server transmits the generated feedback to the terminal and displays it to the user.

[1865] Step 14:

[1866] (If you select the Interview Practice Course)

[1867] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the terminal.

[1868] Step 15:

[1869] The user enters an answer to the initial question and clicks the "Submit" button.

[1870] Step 16:

[1871] The terminal transmits the user's answer to the server.

[1872] Step 17:

[1873] The server passes the received answers to the generation AI for evaluation, which then generates the next question and returns it to the server.

[1874] Step 18:

[1875] The server sends the next question received from the generation AI to the device. This process is repeated 10 times.

[1876] Step 19:

[1877] After 10 rounds of question and answer exchanges, the user clicks the "Get Feedback" button.

[1878] Step 20:

[1879] The terminal transmits the user's request to the server.

[1880] Step 21:

[1881] The server analyzes all the answers with the generation AI and generates comprehensive feedback, which is then passed back to the server.

[1882] Step 22:

[1883] The server transmits the generated feedback to the terminal and displays it to the user.

[1884] Example 1

[1885] 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."

[1886] In recent years, mock interviews and self-analysis have become increasingly required during job hunting, but there is a lack of effective tools for conducting these individually. It is also important to brush up on what you focused on during your student days (gakuchika), but there are limited efficient ways to do this. Furthermore, specific and accurate feedback is necessary for users to understand their strengths and weaknesses and improve their performance in actual interviews. A comprehensive system that can solve these issues is needed.

[1887] 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.

[1888] In this invention, the server includes means for receiving registration and login information from a user terminal, means for storing the information in a database and managing login status, means for the user to select a mock interview or brush-up course, means for receiving input from the user terminal for conducting the mock interview, means for the generative AI model to generate the next question based on the input, means for managing multiple question-and-answer exchanges, and means for providing feedback after the multiple exchanges. This allows users to easily experience mock interviews and brush up on their academic background. Furthermore, through specific feedback from the generative AI model, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for actual interviews.

[1889] A "user terminal" is a device used by a user to access the system, and includes a personal computer, smartphone, tablet, etc.

[1890] A "server" is a part of a computer system that receives and processes information sent from a user's device, storing data and analyzing it using generated AI.

[1891] A "database" is a system for systematically storing user information and other data, and for storing, retrieving, and managing information.

[1892] "Logged-in state" refers to a state in which a user has accessed the system, has been authenticated, and is able to perform operations within the system.

[1893] A "mock interview" is a simulation that mimics a real interview, and is a process in which a user practices an interview through question and answer exchanges.

[1894] The "Brush-up Course" is a program that helps users improve the things they focused on during their student days (gakuchika), and involves inputting and analyzing specific content.

[1895] A "generative AI model" is a system that uses artificial intelligence to generate questions and feedback based on user input.

[1896] "Feedback" refers to evaluations and advice provided based on the results of mock interviews and brush-ups conducted by the user.

[1897] A "framework" is a framework or standard for analyzing user input, and includes, for example, the STAR method (Situation, Task, Action, Result).

[1898] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and brush up on what they focused on during their student days (Gakuchika). This system utilizes a user terminal, a server, and a generative AI model.

[1899] First, a user terminal is a device that provides an interface with the system. Specifically, it includes personal computers, smartphones, tablets, etc. Users access the system through their terminal to register and log in.

[1900] The server receives information sent from the user's device, stores the data, and analyzes it using the generation AI. A database is connected to the server, and user information and mock interview data are systematically stored. A database management system such as MySQL is used for the database.

[1901] The system works as follows: A user first accesses the system and enters their name, email address, and password on the new registration or login screen. The device sends the entered information to the server. The server stores the received information in a database and manages the login status. If authentication is successful, the user is redirected to the home screen.

[1902] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course." The course selection information is sent from the terminal to the server, and the server generates an interface corresponding to the selected course and sends it to the terminal.

[1903] If a user selects the "Gakuchika Brush-up Course," a screen will appear where they can enter details about what they focused on during their time as a student. The user enters the details, and the device sends the details to the server. The server uses a generative AI (for example, OpenAI's GPT-4) to analyze the entered Gakuchika details and evaluate them based on a framework (such as the STAR method). The generative AI analyzes the details and generates specific feedback.

[1904] For example, if a user enters the following content, "My academic background is my experience as a leader in a club activity at university. When a problem arose during the project, I devised a way to deal with it," the server will use generative AI to provide feedback. For example, it will return advice such as, "Specifically, it would be good to explain in detail at what stage of the project the problem arose, what measures were taken, and what results were achieved as a result."

[1905] On the other hand, if the user selects the "Interview Practice Course," a screen to start the mock interview will be displayed. When the user clicks the start button, the device sends the request to the server. The server uses the generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device. The user enters an answer to the question, and the device sends the answer to the server. The server again uses the generation AI to generate the next question, and this process is repeated 10 times.

[1906] After completing the mock interview, the user clicks the "Receive Feedback" button. The device sends a request to the server, which analyzes all responses and uses a generative AI to generate comprehensive feedback, which is then sent to the device. The device then displays the feedback.

[1907] Examples of prompts include "Tell us about yourself" and "Tell us more about your Gakuchika." In this way, the system allows users to refine their Gakuchika through mock interviews and receive specific feedback.

[1908] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1909] Step 1:

[1910] A user accesses the system and enters their name, email address, and password on the registration or login screen.

[1911] Input: Name, Email Address, Password

[1912] Specific actions: A user visits a web page, fills in a form, and clicks the "Submit" button.

[1913] Output: Input information is sent from the device to the server.

[1914] Step 2:

[1915] The device sends the entered information to the server, using the HTTPS protocol to send the data securely.

[1916] Input: Name, email address, and password entered by the user

[1917] Specific operation: The device packages the user's input information in JSON format, creates an HTTPS request, and sends it to the server.

[1918] Output: The input information reaches the server.

[1919] Step 3:

[1920] The server stores the received information in a database and manages the login status. MySQL is used for storage.

[1921] Input: Name, email address, and password sent from your device

[1922] Specific operation: The server connects to the database and saves the user information using an INSERT statement. Also, when the login is successful, it creates and manages session information.

[1923] Output: User information is saved in the database and a login session is created for the user.

[1924] Step 4:

[1925] The user is redirected to the home screen and the main menu is displayed. The user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[1926] Input: User login session, home screen request

[1927] Specific operation: After the server confirms the login status, it generates the HTML for the home screen and sends it to the device.

[1928] Output: The home screen is displayed on the user's device.

[1929] Step 5:

[1930] The course information selected by the user is sent from the terminal to the server.

[1931] Input: Course selection information (e.g., "Interview Practice Course" or "Gakuchika Brush-up Course")

[1932] Specific operation: The user clicks on the course icon, and the device sends the information to the server.

[1933] Output: Course selection information is sent to the server.

[1934] Step 6:

[1935] The server generates an interface according to the selected course and transmits it to the terminal.

[1936] Input: Course selection information

[1937] Specific operation: The server dynamically generates HTML according to the selected course and sends it to the terminal.

[1938] Output: A course-specific screen is displayed on the user's device.

[1939] Step 7:

[1940] If the user selects the "Gakuchika Brush-up Course," he or she inputs the contents of his or her Gakuchika.

[1941] Input: Content of your Gakuchika (e.g., "Experience as a leader in a club activity at university")

[1942] Specific behavior: The user enters the details of their academic background and clicks the "Submit" button.

[1943] Output: Input is sent from the terminal to the server.

[1944] Step 8:

[1945] The server sends the input content to the generation AI, which analyzes it based on a framework (e.g., the STAR method).

[1946] Input: Contents of your academic background

[1947] Specific operation: The server sends the user's input as text to the generative AI model and receives the analysis results.

[1948] Output: The analysis results from the generation AI are returned to the server.

[1949] Step 9:

[1950] The server sends the feedback received from the generated AI to the terminal and displays it to the user.

[1951] Input: Analysis results from the generative AI

[1952] Specific operation: The server sends the received feedback information to the terminal in HTML format.

[1953] Output: Specific feedback is displayed on the user's device.

[1954] Step 10:

[1955] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[1956] Input: Course selection information

[1957] Specific operation: When the user clicks "Start", the device sends the request to the server.

[1958] Output: The initial question is generated from the server and sent to the device.

[1959] Step 11:

[1960] The server uses a generation AI to generate mock interview questions and send them to the device.

[1961] Input: Request to start interview

[1962] Specific operation: The server has the generation AI generate the first question and send it to the device.

[1963] Output: The initial question is displayed on the user's terminal.

[1964] Step 12:

[1965] The user enters an answer to the question, and the terminal transmits the answer to the server.

[1966] Input: Answer to the question

[1967] Specific behavior: The user enters an answer and clicks the "Submit" button. The device sends the information to the server.

[1968] Output: The answer arrives at the server.

[1969] Step 13:

[1970] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[1971] Input: Previous answer

[1972] Specific operation: The server asks the generation AI to generate the next question and sends it to the device.

[1973] Output: The following question is displayed on the user's terminal:

[1974] Step 14:

[1975] After the user completes 10 mock interview questions, they click the "Receive Feedback" button.

[1976] Input: 10 questions and answers

[1977] Specific operation: The device sends a request to the server.

[1978] Output: The server sends the data to the generating AI.

[1979] Step 15:

[1980] The server uses generative AI to generate comprehensive feedback and send it to the device.

[1981] Input: All question and answer data

[1982] Specific operation: The server instructs the generation AI to generate feedback based on all data.

[1983] Output: Feedback information is sent to the terminal.

[1984] Step 16:

[1985] The device displays the feedback to the user.

[1986] Input: Feedback data from the generative AI

[1987] Specific behavior: The device receives the feedback information and displays it on the screen.

[1988] Output: Feedback is displayed on the user's screen.

[1989] This allows users to easily experience mock interviews and brush up on their academic background. In addition, through specific feedback from the generative AI model, users can gain a deeper understanding of their strengths and weaknesses, enabling them to effectively prepare for actual interviews.

[1990] (Application example 1)

[1991] 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."

[1992] Customer service in brick-and-mortar stores is directly linked to customer satisfaction, making training essential. However, traditional training methods make it difficult to obtain specific feedback in real time, limiting opportunities for self-improvement. Furthermore, mock interviews and other skill-improvement simulation tools are often provided individually, creating a need for a centralized training system. A system is needed that allows employees to effectively improve their skills without disrupting their daily work.

[1993] 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.

[1994] In this invention, the server includes means for receiving input from a user terminal for conducting a mock interview, means for a generation AI to generate the next question based on the input, means for managing multiple exchanges of questions and answers, means for providing feedback after the multiple exchanges, means for a salesperson to conduct a customer service simulation in a physical store, and means for the generation AI to generate feedback based on the results of the simulation, thereby enabling employees to evaluate and improve their customer service skills in real time through the simulation.

[1995] A "mock interview" is a training session conducted in a format that mimics a real interview.

[1996] A "user terminal" is an electronic device such as a smartphone or tablet that is operated by a user.

[1997] A "means for receiving input" is a mechanism for sending data or instructions from a user to a system.

[1998] "Generative AI" is a technology that uses artificial intelligence to dynamically generate content and responses.

[1999] The "means for generating the next question" is a mechanism by which the AI ​​automatically generates a new question based on the user's answer.

[2000] "Means for managing multiple question and answer exchanges" refers to a mechanism for providing consecutive questions and recording and analyzing the answers.

[2001] The "means for providing feedback" is a mechanism for conveying evaluations and areas for improvement based on the content of the user's responses.

[2002] The "means for sales staff to conduct customer service simulations in a real store" is a mechanism for sales staff working in a real store to practice customer service simulations.

[2003] "Means for the AI ​​to generate feedback based on the simulation results" refers to a mechanism in which the AI ​​analyzes the results of the customer service simulation and automatically generates appropriate feedback.

[2004] The system for implementing the present invention aims to enable users to improve their customer service skills through simulated customer service practice. Details of the system are described below.

[2005] 1. User Registration and Login

[2006] The user (store clerk) first accesses the system and registers or logs in. The user enters their name, email address, and store ID.

[2007] The smartphone sends the entered data to the server. The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen. This process uses MySQL as the database, a cloud server, and the smartphone.

[2008] 2. Select a training course

[2009] After logging in, the user selects a training course. They choose either "Initial Customer Service Training Course" or "Advanced Customer Service Training Course." The smartphone sends the user's selection to the server. The server generates an interface corresponding to the selected course and sends it to the smartphone.

[2010] 3. Customer Service Simulation

[2011] If the user selects the "Initial Customer Service Training Course," a basic customer service simulation is conducted. The user inputs the answers to the simulation and sends them to the server via their smartphone. The server uses a generative AI (e.g., OpenAI GPT-4) to generate the next question. The simulation is conducted over multiple rounds of interaction, with new questions automatically generated after each answer.

[2012] 4. Providing Feedback

[2013] At the end of the simulation, users can receive feedback. The server uses generative AI to generate feedback based on the simulation results and sends it to their smartphone. The feedback provides specific and practical advice, allowing users to improve their customer service skills.

[2014] For example, use the following prompt:

[2015] "A customer asks where an item is. How do you respond?"

[2016] The generative AI provides feedback such as:

[2017] "Your response is helpful, but it would be better if you provided more specific instructions and suggested next steps."

[2018] This system allows users to effectively improve their customer service skills without disrupting operations at physical stores, which is expected to improve the quality of service at stores.

[2019] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2020] Step 1:

[2021] A user (store clerk) accesses the system and performs new registration or login. The user enters their name, email address, and store ID. Once this data is entered, the smartphone sends it to the server. The server stores the received information in a database and manages the login status. Once login is complete, the user is redirected to the home screen. The input data is user information, and the output is the login status and home screen display.

[2022] Step 2:

[2023] After logging in, the user selects a training course. Specifically, they choose either the "Initial Customer Service Training Course" or the "Advanced Customer Service Training Course." The user's selection becomes input data, and the smartphone sends the selection data to the server. The server generates an interface according to the selected course and returns it to the smartphone as output data. This allows the user to access the appropriate interface.

[2024] Step 3:

[2025] If the user selects the "Initial Customer Service Training Course," a simulation begins. The server uses a generation AI to generate an initial customer service scenario (e.g., "A customer has entered the store. How would you respond?"). This scenario becomes the initial input data, and the server sends it to the smartphone. The user enters answers to the scenario and sends them to the server, where the answer data is stored.

[2026] Step 4:

[2027] The server analyzes the received user answers using a generative AI and automatically generates the next question. The analysis results become the input data for generating the next question. After generating the question, the server sends a new scenario to the smartphone. This process is repeated multiple times. The output data is the next scenario, which is presented to the user.

[2028] Step 5:

[2029] After the series of simulations is completed, the server generates feedback based on all response data. The input data for generating this feedback is a set of all responses. The generation AI analyzes this and generates feedback that includes areas for improvement. The server sends the generated feedback to a smartphone. The output data is the feedback content, which the user can check on their smartphone. The feedback includes specific examples and areas for improvement, helping to improve the user's skills.

[2030] 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.

[2031] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika). In addition, the present invention incorporates an emotion engine that recognizes the user's emotions, providing more detailed and appropriate feedback.

[2032] System Overview

[2033] 1. User Registration and Login

[2034] When a user first accesses the system, they register or log in. They enter their name, email address, and password.

[2035] The terminal transmits the input data to the server.

[2036] The server stores the received information in a database and manages the login status. Once the login is complete, the user is redirected to the home screen.

[2037] 2. Course Selection

[2038] After logging in, the user selects either the "Interview Practice Course" or the "Gakuchika Brush-up Course."

[2039] The terminal transmits the user's selection to the server.

[2040] The server generates an interface according to the selected course and transmits it to the terminal.

[2041] 3. Brush up on your academic background

[2042] If the user selects the "School Background Brush-up Course," a screen for inputting the details of what the user focused on during their school days is displayed.

[2043] The terminal transmits the inputted contents to the server.

[2044] The server uses a generation AI to analyze the content of the Gakuchika based on the framework. For example, if the user enters something like, "My Gakuchika is about my experience as a leader in a club activity at university. As I worked on a project, I came up with ways to deal with problems that arose," the generation AI will provide feedback by adding specific examples and organizing the content chronologically.

[2045] 4. Mock interviews

[2046] If the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[2047] The terminal sends a start request to the server.

[2048] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[2049] The user enters an answer to the question and clicks the "Submit" button.

[2050] The terminal sends the response to the server.

[2051] The server uses the generation AI to generate the next question and sends it to the device. This process is repeated 10 times.

[2052] 5. Leveraging Emotional Engines

[2053] During the mock interview, the emotion engine collects facial expression data and voice data of the user. For example, the facial expression data indicates that the user looks anxious, and the voice data indicates that the user speaks in a tense voice.

[2054] The terminal transmits this data to the server in real time.

[2055] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[2056] The generative AI can adjust the next question based on the results of the emotion analysis, and can also provide specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[2057] 6. Providing Feedback

[2058] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[2059] The terminal sends a request to the server.

[2060] The server uses a generation AI to analyze the overall response and the sentiment analysis results, and generates comprehensive feedback (e.g., "Your response is specific and good, but it's important that you speak with more confidence.") The feedback also includes the results of the sentiment engine's analysis, resulting in more specific and useful advice for the user.

[2061] The terminal displays the feedback content to the user.

[2062] This system allows users to easily experience mock interviews and brush up on their academic background. Through specific feedback from the generative AI and emotion engine, users can gain a deeper understanding of their strengths and weaknesses and effectively prepare for the actual interview.

[2063] The processing flow will be explained below.

[2064] Step 1:

[2065] A user accesses the system and registers or logs in. The user enters their name, email address, and password.

[2066] Step 2:

[2067] The terminal transmits the entered registration or login information to the server.

[2068] Step 3:

[2069] The server stores the received information in a database and manages the login status. If the login is successful, it sends an instruction to the terminal to redirect the user to the home screen.

[2070] Step 4:

[2071] The server confirms that the user has logged in, generates a screen for selecting either the "Interview Practice Course" or the "School Background Brush-up Course", and sends it to the terminal.

[2072] Step 5:

[2073] On the displayed screen, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course" and clicks the "Next" button.

[2074] Step 6:

[2075] The terminal transmits the user's selection to the server.

[2076] Step 7:

[2077] The server generates the next screen according to the selected course and transmits it to the terminal.

[2078] Step 8:

[2079] (If you select the Gakuchika Brush-up Course)

[2080] The server generates a screen containing input fields based on a framework for academic background (e.g., the STAR method) and sends it to the terminal.

[2081] Step 9:

[2082] The user inputs the details of what he / she focused on during his / her school days and clicks the "Submit" button.

[2083] Step 10:

[2084] The terminal transmits the entered contents of the academic background to the server.

[2085] Step 11:

[2086] The server passes the received academic background information to the generation AI for analysis.

[2087] Step 12:

[2088] The AI ​​analyzes the content of the student's academic background and generates feedback, which is then passed to the server.

[2089] Step 13:

[2090] The server transmits the generated feedback to the terminal and displays it to the user.

[2091] Step 14:

[2092] (If you select the Interview Practice Course)

[2093] The server uses a generation AI to generate an initial question (e.g., "Please introduce yourself") and sends it to the terminal.

[2094] Step 15:

[2095] The user enters an answer to the initial question and clicks the "Submit" button.

[2096] Step 16:

[2097] The terminal transmits the user's answer to the server.

[2098] Step 17:

[2099] The server passes the received answers to the generation AI for evaluation, which then generates the next question and returns it to the server.

[2100] Step 18:

[2101] The server sends the next question received from the generation AI to the device. This process is repeated 10 times.

[2102] Step 19:

[2103] During the mock interview, the emotion engine collects facial expression data and voice data of the user. For example, the facial expression data indicates that the user looks anxious, and the voice data indicates that the user speaks in a tense voice.

[2104] Step 20:

[2105] The terminal transmits this data to the server in real time.

[2106] Step 21:

[2107] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[2108] Step 22:

[2109] The generative AI adjusts the next question based on the results of the emotion analysis, and also provides specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[2110] Step 23:

[2111] After 10 rounds of question and answer exchanges, the user clicks the "Get Feedback" button.

[2112] Step 24:

[2113] The terminal transmits the user's request to the server.

[2114] Step 25:

[2115] The server then uses the AI ​​to analyze the overall responses and the emotion analysis results, generating comprehensive feedback. The feedback also includes the results of the emotion engine's analysis, allowing for more specific and useful advice for the user.

[2116] Step 26:

[2117] The server transmits the generated feedback to the terminal and displays it to the user.

[2118] Example 2

[2119] 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."

[2120] Current mock interview systems struggle to provide specific and appropriate feedback based on detailed analysis of users' emotions and responses. They also lack the functionality to systematically analyze the information users enter and provide advice and areas for improvement. This makes it difficult for users to gain a deep understanding of their strengths and weaknesses and effectively learn to improve their interview skills.

[2121] 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.

[2122] In this invention, the server includes means for receiving input from a user terminal, means for a generation AI to generate the next question, means for collecting and analyzing user emotion data using an emotion analysis engine, means for managing multiple question-and-answer exchanges, and means for providing feedback. This allows the user to receive detailed and appropriate feedback through the mock interview, thereby enabling them to gain a deeper understanding of their strengths and weaknesses and effectively improve their interview skills.

[2123] "User Terminal" means a computer or smart device that enables a User to access the System through an interface and input and receive data.

[2124] "Generative AI" refers to technology that uses artificial intelligence algorithms to generate the next question or feedback based on input data.

[2125] An "emotion engine" refers to a combination of hardware and software for analyzing a user's emotional state from facial expression data and voice data.

[2126] "Database" refers to a data storage system for systematically storing and managing user information, responses, analysis results, etc.

[2127] "Feedback" refers to specific advice and comments for improvement provided to users based on the analysis results of the generative AI and emotion engine.

[2128] "Means for managing question and answer interactions" refers to the system's ability to track and control the process of multiple questions and answers in a mock interview.

[2129] The following describes an embodiment of the present invention. This system is effective for users to understand their own strengths and weaknesses through mock interviews and to brush up on the things they focused on during their student days (gakuchika). Furthermore, the present invention incorporates an emotion engine that recognizes the user's emotions, providing more detailed and appropriate feedback.

[2130] Main components of the system

[2131] 1. User Registration and Login

[2132] A user accesses the system and registers or logs in. They must enter their name, email address, and password.

[2133] The terminal transmits the input data to the server.

[2134] The server saves the information in a database and manages the login state. If the login is successful, it redirects the user to the home screen.

[2135] 2. Course Selection

[2136] After logging in, the user selects either the "Interview Practice Course" or the "School Background Brush-up Course."

[2137] The terminal transmits the user's selection to the server.

[2138] The server generates an interface according to the selected course and transmits it to the terminal.

[2139] 3. Brush up on your academic background

[2140] After the user selects the "Gakuchika Brush-up Course," a screen for inputting the contents of Gakuchika is displayed.

[2141] The terminal transmits the inputted contents to the server.

[2142] The server uses a generative AI model to analyze the content of the student's academic background and generate specific feedback. For example, in response to an input such as, "This is my experience as a leader in a club activity at university. As I was working on a project, I came up with a way to deal with problems that arose," the generative AI adds specific examples and organizes the timeline.

[2143] 4. Mock interviews

[2144] After the user selects the "interview practice course," a screen for starting the mock interview is displayed.

[2145] The terminal sends a start request to the server.

[2146] The server uses a generative AI model to generate an initial question (e.g., "Please introduce yourself") and sends it to the device.

[2147] The user enters an answer to the question and clicks the "Submit" button.

[2148] The terminal sends the response to the server.

[2149] The server uses the generative AI model to generate the next question and sends it to the device. This process is repeated 10 times.

[2150] 5. Leveraging Emotional Engines

[2151] During the user's mock interview, the emotion engine collects facial expression and voice data. For example, it detects when the user looks anxious in the facial expression data or when the user sounds nervous in the voice data.

[2152] The terminal transmits this data to the server in real time.

[2153] The server uses an emotion engine to analyze the collected data and pass the results to the generative AI.

[2154] The generative AI adjusts the next question based on the results of the emotion analysis, and also provides specific feedback that reflects the results of the emotion analysis (e.g., "Try to be more relaxed and soften your facial expression when speaking").

[2155] 6. Providing Feedback

[2156] After completing the 10 mock interview questions and answers, the user clicks the "Receive Feedback" button.

[2157] The terminal sends a request to the server.

[2158] The server uses a generation AI to analyze the overall response and sentiment analysis results and generate comprehensive feedback (e.g., "Your response is specific, but it's important that you speak with more confidence").

[2159] The terminal displays the feedback content to the user.

[2160] Specific examples

[2161] For example, if a user inputs something like, "This is my experience as a leader in a club activity at university. As I was working on a project, I came up with ways to deal with problems that arose," the generating AI will provide feedback by adding specific examples and organizing the content chronologically.

[2162] Examples of prompt statements

[2163] "Tell me about an experience you had as a leader in a university club. For example, tell me specifically how you brought members together, solved a problem, and achieved a final result."

[2164] Based on this prompt, users can specifically describe their experience and receive feedback from the generating AI.

[2165] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2166] Step 1:

[2167] User Registration and Login

[2168] Subject: User

[2169] Input: Name, Email Address, Password

[2170] How it works: A user accesses the system and enters their name, email address, and password to register or log in.

[2171] Output: Registration information or login credentials

[2172] Subject: Terminal

[2173] Input: Registration or login information entered by the user

[2174] Operation: The terminal sends the entered data to the server.

[2175] Output: Request to submit registration information or login credentials

[2176] Subject: Server

[2177] Input: User registration or login information

[2178] How it works: The server receives the submitted information, stores it in a database, or performs authentication. If authentication is successful, it generates a response that redirects the user to the home screen.

[2179] Output: Home screen display instructions

[2180] Step 2:

[2181] Course Selection

[2182] Subject: User

[2183] Input: Course selection ("Interview Practice Course" or "Gakuchika Brush-up Course")

[2184] How it works: The user selects the desired course on the displayed home screen and clicks the "Next" button.

[2185] Output: Course selection information

[2186] Subject: Terminal

[2187] Input: User's course selection information

[2188] Operation: The terminal transmits the selected course information to the server.

[2189] Output: Request to send selected course information

[2190] Subject: Server

[2191] Input: Course selection information

[2192] Operation: The server generates an interface according to the selected course and sends it to the terminal.

[2193] Output: The generated interface

[2194] Step 3:

[2195] Brushing up on your academic background

[2196] Subject: User

[2197] Input: What you focused on during your student days

[2198] How it works: After selecting the "Gakuchika Brush-up Course," the user enters details about what they focused on during their time as a student and clicks the "Submit" button.

[2199] Output: Input contents

[2200] Subject: Terminal

[2201] Input: The content of the academic background entered by the user

[2202] Operation: The terminal sends the input information to the server.

[2203] Output: Request to send input content

[2204] Subject: Server

[2205] Input: The content of the academic background entered by the user

[2206] How it works: The server passes the input data to the generative AI model, which analyzes it based on the framework. Once the analysis is complete, the generative AI adds specific examples and organizes the timeline.

[2207] Output: Feedback

[2208] Subject: Terminal

[2209] Input: Generated feedback

[2210] Action: The device displays the feedback to the user.

[2211] Output: Show feedback

[2212] Step 4:

[2213] Mock interviews

[2214] Subject: User

[2215] Input: Request to start mock interview

[2216] Action: The user clicks the "Start Mock Interview" button.

[2217] Output: Start request

[2218] Subject: Terminal

[2219] Input: User's start request

[2220] Operation: The terminal sends a start request to the server.

[2221] Output: Send start request

[2222] Subject: Server

[2223] Input: Request to start mock interview

[2224] How it works: The server uses a generative AI model to generate an initial question and sends it to the device (e.g., "Tell me about yourself").

[2225] Output: First question

[2226] Subject: Terminal

[2227] Input: First question

[2228] Action: The terminal displays the question to the user.

[2229] Output: Show question

[2230] Subject: User

[2231] Input: Answer to question

[2232] How it works: The user enters an answer to a question and clicks the "Submit" button.

[2233] Output:Answer

[2234] Subject: Terminal

[2235] Input: User's answer

[2236] Action: The device sends a response to the server.

[2237] Output: Request to send answer

[2238] Subject: Server

[2239] Input: User's answer

[2240] How it works: The server receives the answer, uses the generative AI model to generate the next question, and sends it to the device. This process is repeated 10 times.

[2241] Output: Next question

[2242] Subject: Terminal

[2243] Input: Next question

[2244] Action: The terminal displays the following question to the user:

[2245] Output: Show question

[2246] Step 5:

[2247] Utilizing the Emotion Engine

[2248] Subject: User

[2249] Input: facial expression data, voice data

[2250] How it works: The emotion engine collects facial and vocal data during a user's mock interview.

[2251] Output: Emotion data

[2252] Subject: Terminal

[2253] Input: Emotion data

[2254] Operation: The device transmits emotion data to the server in real time.

[2255] Output: Sending emotion data

[2256] Subject: Server

[2257] Input: Emotion data

[2258] How it works: The server analyzes the data collected by the emotion engine and passes the results to the generative AI.

[2259] Output: Analysis results

[2260] Subject: Generation AI

[2261] Input: Sentiment analysis results

[2262] How it works: The generative AI uses the results of the emotion analysis to adjust the next question and incorporate it into the feedback (e.g., "Try to be a bit more relaxed and softer when speaking").

[2263] Output: Tailored questions, feedback

[2264] Subject: Server

[2265] Input: Moderated questions, feedback

[2266] How it works: The server sends tailored questions and feedback to the device.

[2267] Output: Tailored questions and feedback submissions

[2268] Subject: Terminal

[2269] Input: Moderated questions and feedback

[2270] Action: The device displays tailored questions and feedback to the user.

[2271] Output: Display of tailored questions and feedback

[2272] Step 6:

[2273] Providing Feedback

[2274] Subject: User

[2275] Input: Feedback request

[2276] How it works: After completing 10 mock interview questions, the user clicks the "Receive Feedback" button.

[2277] Output: Feedback request

[2278] Subject: Terminal

[2279] Input: Feedback request

[2280] Operation: The device sends a request to the server.

[2281] Output: Sending a request

[2282] Subject: Server

[2283] Input: Feedback request

[2284] How it works: The server uses the generation AI to analyze the overall response and sentiment analysis results and generate comprehensive feedback (e.g., "Your response is specific, but it's important that you speak with more confidence").

[2285] Output: Generated feedback

[2286] Subject: Terminal

[2287] Input: Generated feedback

[2288] Action: The device displays the feedback to the user.

[2289] Output: Show feedback

[2290] (Application example 2)

[2291] 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."

[2292] The present invention aims to provide a system for conducting mock interviews that analyzes a user's emotions in real time and provides appropriate feedback based on the analysis results, thereby enabling the user to efficiently improve themselves. At the same time, it aims to solve the problem of providing real-time product recommendations and feedback using user emotion analysis in order to improve the shopping experience in physical stores.

[2293] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input from a user terminal for conducting a mock interview, means for the generation AI to generate the next question based on the input, means for managing multiple exchanges of questions and answers, means for providing feedback after the multiple exchanges, means for collecting facial expression data and voice data of the user in real time, an emotion engine for analyzing the facial expression data and voice data, and means for the generation AI to adjust the next question and feedback based on the emotion analysis results. This enables appropriate feedback based on the user's emotions.

[2294] A "user device" is an electronic device that allows a user to use the mock interview or shopping assistant app.

[2295] "Generative AI" is artificial intelligence that generates the next question or feedback based on user input and emotional analysis results.

[2296] The "emotion engine" is a system that analyzes a user's facial expression data and voice data in real time to evaluate the user's emotional state.

[2297] "Facial expression data" refers to data obtained by capturing the user's facial expression using a camera or the like, and used to analyze the user's emotions.

[2298] "Voice data" is data obtained by capturing the user's speaking style and tone of voice using a microphone or the like, and used to analyze the user's emotions.

[2299] "Means for providing feedback" refers to a function that presents the user with feedback generated by the generation AI based on the analysis results.

[2300] An "analysis engine" is a system that performs analysis based on data entered by a user or acquired data.

[2301] "User Information" means your personal identification information and login information, such as your name, email address, and password.

[2302] The "database" is a system for storing user information, interview records, emotion analysis data, etc.

[2303] The "means for collecting in real time" refers to a function or device for collecting facial expression data and voice data of a user in real time.

[2304] A "means for generating the next question" is an algorithm or system for generating the next question based on previous answers and emotional state.

[2305] A "shopping assistant app" is an application that provides product recommendations and feedback based on the results of user sentiment analysis in order to improve the shopping experience in physical stores.

[2306] A system for realizing this invention will be described below. This system analyzes a user's emotions in real time through a mock interview or shopping assistant application, and provides appropriate feedback.

[2307] System configuration

[2308] 1. User Device

[2309] A smartphone, tablet, or computer that connects to the server and runs the mock interview or shopping assistant application.

[2310] It is equipped with a camera and microphone to collect the user's facial expression and voice data.

[2311] Accepts user input and sends data to the server.

[2312] 2. Server

[2313] Receives input data and collected data and stores it in a database.

[2314] Use generative AI to generate the next question or feedback.

[2315] The emotion engine analyzes the user's facial expression and voice data.

[2316] Based on the analysis results, the generative AI adjusts the next questions and feedback.

[2317] Detailed System Description

[2318] 1. User Registration and Login

[2319] Users first access the app and either register or log in.

[2320] The user's name, email address, and password are entered and sent to the server.

[2321] The server stores the received information in a database and manages the login status.

[2322] 2. Mock interviews

[2323] When a user starts a mock interview, a start request is sent from the user terminal to the server.

[2324] The server uses a generation AI to generate an initial question and sends it to the terminal.

[2325] The user answers the questions and sends the answers to the server.

[2326] The server uses an emotion engine to analyze facial expression and voice data and passes the results to the generation AI.

[2327] The generative AI then adjusts the next question or feedback and repeats the process.

[2328] 3. Shopping Assistant App

[2329] Users use the app while walking around the store, and their smartphone's camera and microphone collect facial and voice data in real time.

[2330] The collected data is sent to a server and analyzed by the emotion engine.

[2331] The server passes the analysis results to the generation AI, which then provides product recommendations and feedback in real time.

[2332] For example, if the user is confused, "recommended items" will be presented, and if the user is excited, "additional suggestions for related products" will be made.

[2333] Specific examples

[2334] Example of a mock interview:

[2335] First question: "Please introduce yourself"

[2336] User Answer: "My name is △△ and I'm from XX University. I majored in □□ and during my student days I focused on XX activities."

[2337] Examples of shopping assistants:

[2338] User views product A:

[2339] Facial expression data: Confused

[2340] Voice Tone: Anxiety

[2341] Generated AI feedback: "What about product C? It's popular with many users."

[2342] Prompt Sentence Examples

[2343] Examples of input prompts for generative AI models include:

[2344] Use the following data to create feedback and product recommendations based on user sentiment.

[2345] User shopping history:

[2346] Product A: Viewing time 2 minutes, facial expression: Confused, voice tone: Anxious

[2347] Product B: Viewing time 5 minutes, facial expression: excitement, voice tone: joy

[2348] Emotion analysis results:

[2349] Facial expression data: confusion, anxiety, excitement, joy

[2350] Voice Tone: Anxiety, Joy

[2351] Such a system would allow users to receive appropriate advice and recommendations tailored to their emotional state, potentially leading to self-improvement and an improved shopping experience.

[2352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2353] Step 1:

[2354] A user accesses the app and registers or logs in. The user enters their name, email address, and password, which the device sends to the server. The server saves the entered data in a database and manages the user's login status.

[2355] Input: Name, Email Address, Password

[2356] Output: Login session ID

[2357] Specific operation: The terminal receives user input and sends the data to the server, which saves it in the database, generates a session ID, and returns it to the user.

[2358] Step 2:

[2359] The user selects either the "Mock Interview" or "Shopping Assistant" course. The terminal sends the selection information to the server, which then generates an interface according to the selection and returns it to the terminal.

[2360] Input: Course selection information

[2361] Output: Course-specific interface

[2362] Specific operation: The device detects the user's selection and sends the data to the server. The server generates an interface according to the selection and sends it back to the device.

[2363] Step 3:

[2364] In the mock interview, the user enters answers to questions and the device sends them to the server, which uses a generative AI to generate the next question, repeating this process 10 times.

[2365] Input: User's answer

[2366] Output: The following questions are generated:

[2367] How it works: The device collects the user's answers and sends them to the server. The server then uses a generative AI to generate the next question and sends it back to the device. This process is repeated 10 times.

[2368] Step 4:

[2369] In the case of a shopping assistant, while the user is browsing products, the device collects facial expression and voice data in real time and sends it to a server, which then uses an emotion engine to analyze the data and pass the results to a generative AI.

[2370] Input: facial expression data, voice data

[2371] Output: Emotion analysis results

[2372] Specific operation: The device collects facial expression and voice data while browsing products and sends it to the server. The server analyzes it with an emotion engine and sends the results to the generation AI.

[2373] Step 5:

[2374] Based on the results of the emotion analysis, the generative AI generates appropriate feedback and the next question, which the server sends to the device and displays to the user.

[2375] Input: Sentiment analysis results

[2376] Output: Feedback and next questions

[2377] Specific operation: The server uses the generation AI to generate feedback and next questions based on the analysis results and sends them to the device, which then displays them to the user.

[2378] Step 6:

[2379] After the user completes the mock interview or shopping assistant session, they receive feedback. The device sends the user's request to the server, which then generates comprehensive feedback and sends it to the device.

[2380] Input: Session termination request

[2381] Output: Comprehensive feedback

[2382] How it works: After the user finishes their session, they submit a request. The server uses AI to generate comprehensive feedback based on the entire data, sends it to the device, and displays it to the user.

[2383] This allows users to receive appropriate advice and product recommendations based on their emotional state, which can lead to self-improvement and an improved shopping experience.

[2384] 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.

[2385] 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.

[2386] 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.

[2387] 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.

[2388] 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.

[2389] 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.

[2390] 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).

[2391] 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.

[2392] 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."

[2393] 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.

[2394] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2395] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2396] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2397] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2398] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2399] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2400] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2401] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2402] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2403] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2404] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2405] The following is further disclosed regarding the above embodiment.

[2406] (Claim 1)

[2407] means for receiving input from a user terminal for conducting a mock interview;

[2408] A means for generating a next question by a generation AI based on the input;

[2409] A means of managing multiple question and answer exchanges;

[2410] means for providing feedback after said plurality of interactions;

[2411] A system including:

[2412] (Claim 2)

[2413] A means for users to input what they focused on during their school days;

[2414] means for analyzing the input content based on a framework;

[2415] A means for generating feedback by a generation AI based on the analysis result;

[2416] The system of claim 1 further comprising:

[2417] (Claim 3)

[2418] a means for storing user information in a database;

[2419] a means for managing the login status of users;

[2420] The system of claim 1 further comprising:

[2421] "Example 1"

[2422] (Claim 1)

[2423] means for receiving registration and login information from a user terminal;

[2424] a means for storing the information in a database and managing the login status;

[2425] A means for a user to select a mock interview or brush-up course;

[2426] means for receiving input from a user terminal for conducting a mock interview;

[2427] means for a generative AI model to generate a next question based on the input;

[2428] A means of managing multiple question and answer exchanges;

[2429] means for providing feedback after said plurality of interactions;

[2430] A system including:

[2431] (Claim 2)

[2432] A means for users to input what they focused on during their school days;

[2433] means for analyzing the input content based on a framework;

[2434] A means for generating feedback by a generative AI model based on the analysis results;

[2435] The system of claim 1 further comprising:

[2436] (Claim 3)

[2437] a means for storing user information in a database;

[2438] a means for managing the login status of users;

[2439] The system of claim 1 further comprising:

[2440] "Application Example 1"

[2441] (Claim 1)

[2442] means for receiving input from a user terminal for conducting a mock interview;

[2443] A means for generating a next question by a generation AI based on the input;

[2444] A means of managing multiple question and answer exchanges;

[2445] means for providing feedback after said plurality of interactions;

[2446] A means for store staff to conduct customer service simulations in a real store;

[2447] A means for generating feedback by a generation AI based on the simulation results;

[2448] A system including:

[2449] (Claim 2)

[2450] A means for users to input what they focused on during their school days;

[2451] means for analyzing the input content based on a framework;

[2452] A means for generating feedback by a generation AI based on the analysis result;

[2453] The system of claim 1 further comprising:

[2454] (Claim 3)

[2455] a means for storing user information in a database;

[2456] a means for managing the login status of users;

[2457] The system of claim 1 further comprising:

[2458] "Example 2: Combining Emotion Engines"

[2459] (Claim 1)

[2460] means for receiving input from a user terminal;

[2461] A means for generating a next question by a generation AI based on the input;

[2462] a means for collecting and analyzing user emotion data using an emotion analysis engine;

[2463] A means of managing multiple question and answer exchanges;

[2464] means for providing feedback after said plurality of int...

Claims

1. means for receiving input from a user terminal for conducting a mock interview; A means for generating a next question by a generation AI based on the input; A means of managing multiple question and answer exchanges; means for providing feedback after said plurality of interactions; A system including:

2. A means for users to input what they focused on during their school days; means for analyzing the input content based on a framework; A means for generating feedback by a generation AI based on the analysis result; The system of claim 1 further comprising:

3. a means for storing user information in a database; a means for managing the login status of users; The system of claim 1 further comprising:

Images