system

Abstract

Provide a system. The method includes: a means for verifying authentication information input by a user via a terminal in a server; means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful; means for transmitting answer prompts to be input by the user from the terminal to the server; A means for the AI ​​on the server to generate an answer based on the prompt and return the generated answer to the terminal; means for displaying the generated answers to the user and submitting the answer determined as the final answer from the terminal to the server; A means for evaluating the submitted answers using AI on the server and sending the evaluation results to the terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional employment testing systems lack a way for candidates to generate answers using AI, or a way to properly and fairly evaluate those generated answers. This can prevent candidates from making the most of their skills and knowledge, potentially reducing the reliability of test results. Furthermore, when test evaluation is done manually, the subjectivity of the evaluator can creep in, making it difficult to achieve a fair evaluation. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: a means for verifying authentication information entered by a user via a terminal on a server; a means for transmitting test questions from the server to the terminal to be displayed to the user if authentication is successful; a means for transmitting answer prompts entered by the user from the terminal to the server; a means for an AI on the server to generate answers based on the prompts and return the generated answers to the terminal; a means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server; and a means for evaluating the submitted answers with the AI ​​on the server and transmitting the evaluation results to the terminal. Furthermore, the reliability and usability of the system are improved by adding a means for recording the evaluation results on the server and a means for transmitting an error message to the terminal if authentication fails.

[0006] "User" refers to a person who accesses the system via a terminal and answers test questions.

[0007] "Terminal" refers to the electronic device on which the user enters authentication information and displays test questions and AI-generated answers.

[0008] "Authentication Information" means information used to identify a user and authorize access to a system, such as a user ID and password.

[0009] A "server" refers to a computer system that verifies authentication information from users and performs processes such as distributing test questions, generating answers using AI, and final evaluation.

[0010] "Exam Questions" refers to a collection of questions or tasks that a user must answer.

[0011] An "answer prompt" refers to a question or instruction that a user enters into an AI.

[0012] "AI" refers to a software program that uses artificial intelligence to generate appropriate answers based on input prompts.

[0013] "Generated answers" refers to answers that AI creates based on user prompts.

[0014] "Final answer" refers to the definitive answer that the user submits after reviewing the answer provided by the AI ​​and correcting it if necessary.

[0015] "Evaluation results" refers to the scores and feedback given by the AI ​​on the server after evaluating the final answer.

[0016] An "error message" refers to information that notifies the user of the details of the error when authentication fails, etc. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] overview

[0039] This invention relates to a system in which candidates use AI to answer questions during employment examinations and the answers are evaluated by AI. This system is composed of terminals, a server, and AI, and provides users with a fair and prompt evaluation.

[0040] System configuration

[0041] The system is implemented with the following main components:

[0042] 1. Terminal

[0043] This is a device that users access, such as a PC, tablet, or smartphone. The device displays the login screen, the test question screen, and an interface for entering answer prompts.

[0044] 2. Server

[0045] The server plays a key role in verifying user authentication information, sending test questions to the device, and generating and evaluating answers using AI. The server is equipped with an AI module that generates and evaluates answers based on prompts.

[0046] 3. AI Module

[0047] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users and is also responsible for evaluating the final answers submitted and generating scores and feedback.

[0048] Program processing

[0049] User operations

[0050] The user enters authentication information (user ID and password) on the login screen. This information is sent from the terminal to the server. The server verifies the authentication information, and if the user is legitimate, a list of test questions is sent to the user terminal.

[0051] Server authentication and test question transmission

[0052] The server checks the authentication information against a database, and only if successful does it send the test questions to the terminal. The test questions are preset, and the user selects the questions to answer from this list.

[0053] Generate answer prompts

[0054] The user checks the test questions displayed on the terminal and inputs the answer prompts. For example, if the user inputs a prompt such as "Explain the basic principles of programming," the terminal sends the prompt to the server.

[0055] AI-powered answer generation

[0056] The AI ​​module on the server receives prompts from the user and generates an answer based on the prompts. The answer (e.g., "The fundamental principles of programming include algorithms, data structures, modularization, and error handling") is then sent back to the device.

[0057] User decides the final answer

[0058] The user checks the answers generated by the AI ​​and decides on the final answer based on the content. If necessary, the user can modify the answer and submit it to the server as the final answer.

[0059] Evaluating answers

[0060] The final answer submitted is then evaluated by the AI ​​module on the server. The AI ​​module evaluates the appropriateness and comprehensiveness of the answer and generates a score and feedback. For example, if a score of 90 is given, this is sent to the terminal along with the evaluation result.

[0061] Specific examples

[0062] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user then enters the answer prompt "Explain the basic principles of programming," and the server passes this prompt to the AI ​​module. The AI ​​generates an answer and sends it back to the terminal. When the user decides on the final answer and submits it to the server, the server's AI evaluates it and provides the user with a score and feedback.

[0063] In this way, the system according to the present invention allows users to answer test questions with the help of AI and have their answers evaluated quickly and fairly.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The user enters the user ID "user123" and password "password" on the login screen of the device and presses the login button.

[0067] Step 2:

[0068] The terminal sends the authentication information entered by the user to the server.

[0069] Step 3:

[0070] The server checks the user ID and password against an authentication database.

[0071] Step 4:

[0072] If the server is successful in the authentication, it prepares a test question list and sends it to the terminal, otherwise it sends an error message to the terminal.

[0073] Step 5:

[0074] The terminal receives the test question list and displays it to the user.

[0075] Step 6:

[0076] The user selects any test question and presses the start button.

[0077] Step 7:

[0078] The terminal requests the selected test question from the server and receives details of the question.

[0079] Step 8:

[0080] The terminal displays test questions to the user and provides an interface for entering answer prompts.

[0081] Step 9:

[0082] The user inputs the answer prompt "Explain the basic principles of programming."

[0083] Step 10:

[0084] The terminal sends the entered prompt to the server.

[0085] Step 11:

[0086] The server receives the prompt and passes it to the AI ​​module.

[0087] Step 12:

[0088] Based on the prompt, the AI ​​(server) generates an answer: "The fundamental principles of programming include algorithms, data structures, modularization, and error handling" and sends it back to the terminal via the server.

[0089] Step 13:

[0090] The device receives the AI-generated answer and displays it to the user.

[0091] Step 14:

[0092] The user checks the AI's answer, corrects it as necessary, and decides on the final answer.

[0093] Step 15:

[0094] The user presses a button to submit the final answer.

[0095] Step 16:

[0096] The terminal sends the user's final answer to the server.

[0097] Step 17:

[0098] The server passes the final answer back to the AI ​​module for evaluation.

[0099] Step 18:

[0100] The AI ​​(server) evaluates the answer, determines that the answer is appropriate and comprehensive, and assigns a score (e.g., 90 points).

[0101] Step 19:

[0102] The server records the evaluation results and feedback and sends them to the device.

[0103] Step 20:

[0104] The terminal displays the evaluation results to the user.

[0105] Example 1

[0106] 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."

[0107] In traditional recruitment tests, the challenges of evaluating candidates fairly and providing results quickly have been posed. Manual evaluation consumes a large amount of time and human resources, and it is difficult to ensure fairness. Furthermore, if candidates do not have time to thoroughly consider their answers, they may not receive an appropriate evaluation.

[0108] 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.

[0109] In this invention, the server includes means for verifying authentication information entered by a user via a terminal on the server, means for transmitting test questions from the server to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an artificial intelligence on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, and means for evaluating the submitted answers with the artificial intelligence on the server, generating feedback together with the evaluation results and transmitting it to the terminal. This allows candidates to be evaluated efficiently and fairly, and test results to be obtained quickly.

[0110] "Authentication Information" means information provided by a user to prove his or her identity, and typically includes a user ID and password.

[0111] A "server" is a computer system that processes data and provides services over a network.

[0112] A "terminal" is a device operated by a user, and includes a personal computer, a tablet, a smartphone, and the like.

[0113] "Exam Questions" means questions or tasks designed to assess a candidate's abilities or knowledge.

[0114] An "answer prompt" is text or instructions that assist the user in entering an answer to a test question.

[0115] "Artificial intelligence" refers to computer programs that mimic human intelligence to learn and solve problems.

[0116] "Evaluation" is the process of judging the appropriateness and comprehensiveness of submitted answers and generating scores and feedback.

[0117] "Feedback" refers to advice or comments provided to the user based on the evaluation results.

[0118] overview

[0119] This invention relates to a system in which candidates use artificial intelligence (AI) to answer questions during employment examinations, and the answers are evaluated by AI. The system consists of a terminal, a server, and an AI module, and provides users with a fair and prompt evaluation.

[0120] System configuration

[0121] The system is implemented with the following main components:

[0122] 1. Terminal

[0123] The terminal is a device for user access, and includes a personal computer, tablet, smartphone, etc. The terminal displays a login screen, a screen displaying test questions, and an interface for inputting answer prompts.

[0124] 2. Server

[0125] The server plays a key role in verifying user credentials, sending test questions to the device, and generating and evaluating answers using artificial intelligence. An AI module is installed on the server, which generates and evaluates answers based on prompt input.

[0126] 3. AI Module

[0127] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by the user and evaluates the final answers submitted and generates scores and feedback. A pre-trained generative AI model (e.g., GPT-3®) is used.

[0128] Program processing

[0129] 1. User authentication

[0130] The user enters authentication information (user ID and password) on the login screen displayed on the terminal. This information is sent from the terminal to the server. The server compares it with the database, and if authentication is successful, it sends a list of test questions to the terminal.

[0131] 2. Display of exam questions

[0132] The test question list sent from the server is displayed on the terminal, and the user selects the questions to answer from the displayed test questions.

[0133] 3. Enter the answer prompt

[0134] The user checks the test questions displayed on the terminal and inputs the answer prompt, for example, "Explain the basic principles of programming." This prompt is sent from the terminal to the server.

[0135] 4. AI-generated answers

[0136] The AI ​​module on the server uses a generative AI model to generate an answer based on the prompt received from the user, for example, "The fundamental principles of programming include algorithms, data structures, modularization, and error handling." This answer is then sent back from the server to the device.

[0137] 5. User decides on the final answer

[0138] The user checks the answers generated by the AI ​​on their device, and if necessary, makes corrections to determine the final answer, which is then sent from the device to the server.

[0139] 6. Rating and Feedback on Answers

[0140] The AI ​​module on the server evaluates the final answer and generates a score and feedback (for example, a score of 90) that is sent to the device. The feedback also includes specific advice and comments.

[0141] Specific examples

[0142] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user enters the answer prompt "Explain the basic principles of programming," and the server passes this to the AI ​​module. The AI ​​generates an answer: "The basic principles of programming include algorithms, data structures, modularization, and error handling," and sends it back to the terminal. When the user decides on a final answer and submits it to the server, the AI ​​evaluates it and sends 90 points and feedback to the terminal. This process allows the user to generate answers efficiently and have them evaluated fairly.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Program processing flow

[0145] Step 1: Perform user authentication

[0146] The user enters their user ID and password into the login screen on the terminal. This input information is sent to the server as an HTTP request. The server compares the received authentication information with the database, and if authentication is successful, sends a successful authentication response to the terminal. The input is "user123" and "password", and the output is a message indicating successful authentication. Specifically, the server searches the database using the user ID as a key and compares it with the corresponding password.

[0147] Step 2: View the exam questions

[0148] The server sends a pre-set list of test questions to the terminal along with a response of successful authentication. The terminal displays the received test questions on the screen, and the user selects questions to answer from the list. The input is an authentication success message, and the output is a list of test questions. Specifically, the server retrieves the list from a database or configuration file that stores test question data, and sends it to the terminal.

[0149] Step 3: Enter the answer prompts

[0150] The user checks the test questions displayed on the terminal and enters the answer prompt. For example, they enter "Explain the basic principles of programming" and press the send button. The terminal sends this input as an HTTP request to the server. The input is the answer prompt, "Explain the basic principles of programming," and the output is a confirmation of sending the prompt to the server. Specifically, the terminal constructs form data and sends it to the server.

[0151] Step 4: AI-generated answers

[0152] The server passes the prompt received from the device to the AI ​​module. The AI ​​module uses the generative AI model to generate an answer based on the prompt. For example, if the prompt is "Explain the basic principles of programming," the AI ​​generates the answer "The basic principles of programming include algorithms, data structures, modularization, and error handling." The generated answer is sent back from the server to the device. The input is the prompt, and the output is the generated answer. Specifically, the AI ​​module performs natural language processing to generate an answer.

[0153] Step 5: User decides on final answer

[0154] The user checks the AI-generated answer received on their device and makes corrections as necessary. The final answer is sent to the server by pressing the send button. The input is the AI-generated answer and the user's corrections, and the output is the final answer. Specifically, the user edits the answer using a text editor and resubmits it to the server.

[0155] Step 6: Rate and give feedback on your answers

[0156] The server passes the received final answer back to the AI ​​module. The AI ​​module evaluates the answer and generates feedback along with the evaluation result. For example, if the answer is appropriate and comprehensive, feedback of 90 points will be generated. This is sent from the server to the terminal and displayed to the user. The input is the final answer, and the output is the evaluation result and feedback. Specifically, the AI ​​module evaluates based on the set evaluation criteria and generates feedback.

[0157] (Application example 1)

[0158] 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."

[0159] In conventional factory robot operation training, operator candidates are evaluated by human evaluators, which can lead to problems of lack of fairness and speed. Furthermore, there is a lack of systems for efficiently training in operation procedures. This can lead to extended training periods and inefficient operation, negatively impacting corporate productivity.

[0160] 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.

[0161] In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting a training task from the server to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for a generating AI on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, and means for evaluating the submitted answers with the generating AI on the server and transmitting the evaluation results to the terminal, thereby enabling fair and prompt training evaluation and efficient acquisition of operating procedures.

[0162] A "terminal" is a device used by a user for access, such as a smartphone, tablet, or personal computer.

[0163] "Authentication information" refers to the information a user uses to log in to a system, and typically consists of a user ID and password.

[0164] A "server" is a computer system that is connected to a network and performs functions such as user authentication, data processing, and AI evaluation.

[0165] "Training tasks" refer to instructions and problems sent from the server to train potential operators in robot operation.

[0166] An "answer prompt" is a specific question or instruction that a user enters to answer a training task.

[0167] "Generative AI" is an AI model that has the ability to generate answers based on answer prompts from a user and to evaluate those answers.

[0168] The "evaluation result" is the evaluation made by the generating AI on the user's final answer, and is provided to the user as a score or feedback.

[0169] This invention relates to a factory robot operation training evaluation system in which operator candidates answer training questions with the help of AI, and the AI ​​evaluates their answers. This system is composed of a terminal, a server, and a generative AI. Each component and its operation are described in detail below.

[0170] 1. System Configuration

[0171] 1.1 Terminal

[0172] A terminal is a device that users access, such as a smartphone, tablet, or personal computer. The terminal provides a user authentication screen, a display screen for training tasks, and an input interface for answer prompts.

[0173] 1.2 Server

[0174] The server is a computer system connected to the network that authenticates users, provides training assignments, generates answers, and evaluates them. The server has a database that stores user authentication information, training assignments, and evaluation results.

[0175] 1.3 Generative Artificial Intelligence

[0176] The generative AI is an AI model implemented on a server that generates answers based on prompts sent by the user and evaluates the final answers submitted. Specifically, a generative AI model (e.g., OpenAI's GPT model) is used.

[0177] 2. Operational Details

[0178] 2.1 User Authentication

[0179] The user enters authentication information (user ID and password) via the terminal. This information is sent from the terminal to the server, which then verifies it against a database. If authentication is successful, the server sends the user a training assignment.

[0180] 2.2 Displaying training tasks and generating response prompts

[0181] The training tasks sent from the server are displayed on the terminal and the user confirms them. The user inputs answer prompts for the training tasks and sends them from the terminal to the server.

[0182] Prompt Sentence Examples

[0183] "Please explain the basic operating procedure for a factory robot. Specifically, how to accurately place part A at position X."

[0184] 2.3 Answer generation and display using AI

[0185] The server-based AI generates an answer based on the user's prompts. The generated answer is then sent back to the terminal and displayed to the user. The user can then review the displayed answer, modify it as necessary, and determine the final answer.

[0186] 2.4 Submission and evaluation of final answers

[0187] When the user submits the final answer to the server, the server-based AI evaluates the answer, and the evaluation results (e.g., score and feedback) are sent to the terminal and provided to the user.

[0188] Specific examples

[0189] When an operator candidate logs into the system using a smartphone, the server performs authentication, and if successful, a training task is sent to the terminal: "Please explain the basic operating procedures for a factory robot. Specifically, please state the steps for placing part A at position X." The candidate enters the answer prompt, "Steps for placing part A at position X," and the server passes this prompt to the generating artificial intelligence. The procedure generated by the AI ​​is checked, and the candidate makes corrections and submits it to the server as the final answer, which the AI ​​evaluates and provides a score and feedback.

[0190] In this way, the system according to the present invention enables operator candidates to be effectively trained with the assistance of AI, and enables fair and rapid evaluation.

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] The user enters authentication information (user ID and password) via the terminal. The terminal sends this authentication information to the server. The server receives the authentication information and authenticates the user by checking it against a database. If authentication is successful, the server sends a training task to the terminal.

[0194] Input: User ID, Password

[0195] Output: Authentication results, training tasks

[0196] Step 2:

[0197] The training task sent by the server is displayed on the terminal. The user checks the training task through the terminal and inputs an answer prompt. The terminal sends this answer prompt to the server.

[0198] Input: Training task, response prompt

[0199] Output: Answer prompt

[0200] Step 3:

[0201] The server passes the answer prompt received from the terminal to the generative AI model and requests it to generate an answer. The generative AI model generates an answer based on the prompt and returns the result to the server. The server then sends the generated answer to the terminal.

[0202] Input:Answer prompt

[0203] Output: The generated answer

[0204] Step 4:

[0205] The user checks the answer generated by the generative AI model displayed on the terminal, corrects the answer as necessary, and submits it to the server from the terminal as the final answer.

[0206] Input: Generated answers, user corrections

[0207] Output: Final answer

[0208] Step 5:

[0209] The server passes the final answer to the generative AI model and requests an evaluation. The generative AI model evaluates the final answer and returns the evaluation result to the server. The server then sends the evaluation result to the terminal.

[0210] Input: Final answer

[0211] Output: Evaluation results

[0212] Step 6:

[0213] The evaluation results are displayed on the terminal. The user checks the evaluation results and understands the results of the training. The server records the evaluation results in a database for future reference.

[0214] Input: Evaluation result

[0215] Output: Record of evaluation results

[0216] In this way, a system is realized that allows users to train efficiently with the support of AI and have their results evaluated fairly and quickly.

[0217] 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.

[0218] overview

[0219] This invention relates to a system in which candidates use AI and an emotion engine to answer questions during employment tests, and the answers are evaluated by AI. This system is composed of a terminal, a server, an AI module, and an emotion engine, and provides users with fair and prompt evaluations and feedback based on their emotions.

[0220] System configuration

[0221] The system is implemented with the following main components:

[0222] 1. Terminal

[0223] This is a device that users access, such as a PC, tablet, or smartphone. The device displays the login screen, the test question screen, and an interface for entering answer prompts.

[0224] 2. Server

[0225] It verifies the user's authentication information, sends the test questions to the device, and uses AI and emotion engines to generate and evaluate answers.

[0226] 3. AI Module

[0227] It is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users, and is responsible for evaluating the final answers submitted and generating scores and feedback.

[0228] 4. Emotion Engine

[0229] This is a program that analyzes the user's emotions and adjusts the AI's response generation and error messages according to those emotions.

[0230] Program processing

[0231] User operations

[0232] The user enters authentication information (user ID and password) on the login screen. This information is sent from the terminal to the server. The server verifies the authentication information, and if the user is legitimate, a list of test questions is sent to the user terminal. If authentication fails, the emotion engine analyzes the user's emotions and generates an appropriate error message.

[0233] Server authentication and test question transmission

[0234] The server checks the authentication information against a database, and only if successful does it send the test questions to the terminal. The test questions are preset, and the user selects the questions to answer from this list.

[0235] Generate answer prompts

[0236] The user checks the test questions displayed on the terminal and inputs the answer prompts. For example, if the user inputs a prompt such as "Explain the basic principles of programming," the terminal sends this prompt to the server.

[0237] AI-based answer generation and emotion engine usage

[0238] The AI ​​module on the server receives prompts from the user and generates an answer based on the prompts. The generated answer (e.g., "The basic principles of programming include algorithms, data structures, modularization, and error handling") is then sent back to the device. At the same time, the emotion engine analyzes the user's emotions and adjusts the answer accordingly.

[0239] User decides the final answer

[0240] The user checks the answers generated by the AI ​​and decides on the final answer based on the content. If necessary, the user can modify the answer and submit it to the server as the final answer.

[0241] Evaluating answers

[0242] The final answer submitted is then evaluated by the AI ​​module on the server. The AI ​​module evaluates the appropriateness and comprehensiveness of the answer and generates a score and feedback. For example, if a score of 90 is given, the evaluation result and the analysis results from the emotion engine are also recorded.

[0243] Generate an error message when authentication fails

[0244] If the authentication information is incorrect, the emotion engine analyzes the user's emotion, generates an appropriate error message according to that emotion, and sends it to the terminal.

[0245] Specific examples

[0246] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user enters the answer prompt "Explain the basic principles of programming," and the server passes this prompt to the AI ​​module. The AI ​​generates an answer and sends it back to the terminal. At the same time, the emotion engine analyzes the user's emotions and adjusts the expression of the answer based on the user's emotions. When the user decides on a final answer and submits it to the server, the server's AI evaluates it and provides the user with a score (e.g., 90 points) and feedback. The emotion engine's analysis results are also added to the evaluation result and recorded. If authentication fails, the emotion engine adjusts the error message and displays it to the user.

[0247] In this way, the system of the present invention allows users to answer test questions with the help of AI and an emotion engine, quickly and fairly evaluate the answers, and provide feedback based on the user's emotions.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] The user enters the user ID "user123" and password "password" on the login screen of the device and presses the login button.

[0251] Step 2:

[0252] The terminal sends the authentication information entered by the user to the server.

[0253] Step 3:

[0254] The server checks the user ID and password against a database.

[0255] Step 4:

[0256] If the server is successful in the authentication, it prepares a list of test questions and sends it to the terminal.

[0257] Step 5:

[0258] If the server fails the authentication, it uses an emotion engine to analyze the user's emotion, generates an appropriate error message, and sends it to the terminal.

[0259] Step 6:

[0260] The terminal receives the test question list and displays it to the user.

[0261] Step 7:

[0262] The user selects any test question and presses the start button.

[0263] Step 8:

[0264] The terminal requests the selected test question from the server and receives details of the question.

[0265] Step 9:

[0266] The terminal displays test questions to the user and provides an interface for entering answer prompts.

[0267] Step 10:

[0268] The user inputs the answer prompt "Explain the basic principles of programming."

[0269] Step 11:

[0270] The terminal sends the entered prompt to the server.

[0271] Step 12:

[0272] The server receives the prompt and passes it to the AI ​​module.

[0273] Step 13:

[0274] The AI ​​(server) generates an answer based on the prompt: "Fundamental principles of programming include algorithms, data structures, modularity, and error handling."

[0275] Step 14:

[0276] The emotion engine (server) analyzes the user's emotions and determines whether the generated answers need to be adjusted.

[0277] Step 15:

[0278] The server sends back to the device an answer generated and adjusted by the AI ​​module and emotion engine.

[0279] Step 16:

[0280] The device receives the answers generated by the AI ​​and emotion engine and displays them to the user.

[0281] Step 17:

[0282] The user checks the AI's answer, corrects it as necessary, and decides on the final answer.

[0283] Step 18:

[0284] The user presses a button to submit the final answer.

[0285] Step 19:

[0286] The terminal sends the user's final answer to the server.

[0287] Step 20:

[0288] The server passes the final answer back to the AI ​​module for evaluation.

[0289] Step 21:

[0290] The AI ​​(server) evaluates the answer, determines that the answer is appropriate and comprehensive, and assigns a score (e.g., 90 points).

[0291] Step 22:

[0292] The emotion engine (server) analyzes the user's emotions regarding the evaluation results and adjusts the feedback.

[0293] Step 23:

[0294] The server records the evaluation results and feedback and sends them to the terminal.

[0295] Step 24:

[0296] The terminal displays the evaluation results to the user.

[0297] Example 2

[0298] 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."

[0299] In conventional recruitment testing systems, it was difficult to quickly and fairly evaluate the answers entered by candidates, and it was also difficult to provide feedback that took into account the candidates' emotions.It was also a challenge to provide an appropriate error message when authentication failed.

[0300] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting test questions to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an AI module on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, means for the AI ​​module on the server to evaluate the submitted answers and transmit the evaluation results to the terminal, and an emotion engine means for analyzing the user's emotions and adjusting the expression of the answers based on the emotions. This makes it possible to quickly and fairly evaluate the answers entered by the user and provide feedback that takes the candidate's emotions into consideration. It is also possible to provide an appropriate error message if authentication fails.

[0301] A "user" is an individual or entity that accesses the system through a terminal, enters authentication information, and answers exam questions.

[0302] A "terminal" is a device through which a user accesses the system, and includes a PC, tablet, smartphone, etc.

[0303] "Server" is a central computer system that verifies user credentials, transmits test questions, and uses AI modules and emotion engines to generate and evaluate answers.

[0304] "Authentication information" means information such as a user ID and password that enables a user to legitimately access a system.

[0305] A "quiz question" is a question or challenge sent by a server for a user to answer, for assessment purposes.

[0306] An "answer prompt" is a command or question that a user enters in response to a test question.

[0307] "AI Module" means an artificial intelligence program implemented on a server that generates answers based on user response prompts and evaluates the final answers submitted.

[0308] The "emotion engine" is a program that analyzes the user's emotions and adjusts the AI ​​module's response and error messages based on those emotions.

[0309] "Evaluation Results" refers to the score and feedback provided by the AI ​​module to evaluate the user's final answer based on its appropriateness and comprehensiveness.

[0310] An "error message" is a notification message that is generated by the server using the emotion engine when user authentication fails, and that is based on the user's emotion.

[0311] This invention relates to a system in which candidates use AI and an emotion engine to answer questions during employment examinations, and the answers are evaluated by AI. This system is composed of a terminal, a server, an AI module, and an emotion engine, and provides users with fair and prompt evaluations and feedback according to their emotions.

[0312] System configuration

[0313] 1. Terminal

[0314] The terminal is the device through which the user accesses the test, such as a PC, tablet, or smartphone. The terminal displays a login screen, a screen displaying test questions, and an interface for entering answer prompts.

[0315] 2. Server

[0316] The server is a central computer system that verifies user credentials, sends test questions to the terminal, and uses AI modules and emotion engines to generate and evaluate answers.

[0317] 3. AI Module

[0318] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by the user and is also responsible for evaluating the final answers submitted and generating scores and feedback.

[0319] 4. Emotion Engine

[0320] The emotion engine is a program that analyzes the user's emotions and adjusts the AI ​​module's response generation and error message display based on those emotions.

[0321] Hardware and software used

[0322] Hardware: PCs, tablets, smartphones

[0323] Software: Server, AI module, emotion engine

[0324] Examples: AI platforms and sentiment analysis APIs implemented on virtual machines

[0325] Specific examples

[0326] The user enters the login information "user123" and "password" and attempts to log in. The server receives this information and checks it against the database. If authentication is successful, the test question "Explain the basic principles of programming" is sent to the terminal.

[0327] The user checks the test questions displayed on the terminal and enters the answer prompt, "Explain the basic principles of programming." The terminal sends this prompt to the server, which passes it to the server's AI module.

[0328] The AI ​​module generates answers based on the prompts, explaining that "fundamental principles of programming include algorithms, data structures, modularization, and error handling." The generated answers are then sent back to the device from the server.

[0329] At the same time, the emotion engine analyzes the user's emotions, and if the user is feeling anxious, for example, it will add a phrase such as "Don't worry, you can solve this problem if you understand it well" and display it.

[0330] The user checks the generated answers, makes corrections as necessary, and decides on the final answer, which is then submitted to the server from the terminal.

[0331] The server then passes the submitted final answer back to the AI ​​module, generates an evaluation score (e.g., 90 points) and feedback, and sends it to the device. The evaluation result also records the analysis results of the emotion engine.

[0332] If authentication fails, the emotion engine analyzes the user's emotions and generates an error message such as "The password you entered is incorrect. Please try again." and sends it to the terminal, providing the user with appropriate feedback.

[0333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0334] Step 1:

[0335] The user enters authentication information (user ID and password) on the login screen of the terminal. The terminal sends this input information to the server. The input is the user ID and password, and the output is the authentication information sent to the server.

[0336] Step 2:

[0337] The server compares the received authentication information with the database to confirm whether the user is a legitimate user. For example, it retrieves the corresponding user ID and password record from the database and matches it with the entered information. If authentication is successful, the server sends a list of test questions to the terminal. The input is authentication information, and the output is the authentication results and a list of test questions. If there is a mismatch, the emotion engine generates an error message based on the user's emotion and sends it to the terminal.

[0338] Step 3:

[0339] The terminal displays the test questions sent from the server and the user selects the questions to answer. The terminal takes the user's selection as input and sends the selection information to the server. The input is the selection of the test question, and the output is the transmission of the selection information.

[0340] Step 4:

[0341] The user inputs an answer prompt to the multiple-choice question displayed on the terminal. For example, they input "Explain the basic principles of programming." The terminal sends this prompt to the server. The input is the answer prompt, and the output is the sending of the prompt.

[0342] Step 5:

[0343] The server passes the received prompt to the AI ​​module, which then generates an answer based on the prompt. For example, it might generate, "The fundamental principles of programming include algorithms, data structures, modularization, and error handling." The generated answer is then sent back to the terminal. The input is the prompt, and the output is the generated answer.

[0344] Step 6:

[0345] At the same time, the emotion engine analyzes the user's emotions. For example, if the user is anxious, the emotion engine adds a phrase such as "Don't worry, you can solve this problem if you understand it well" to the answer. The input is the user's emotional data, and the output is the adjusted answer. The adjusted answer is then sent back to the device from the server.

[0346] Step 7:

[0347] The user checks the generated answer on the terminal, corrects it if necessary, and decides on the final answer. The corrected final answer is then submitted to the server. The input is the corrected answer, and the output is the transmission of the final answer.

[0348] Step 8:

[0349] The server then passes the submitted final answer back to the AI ​​module, which then evaluates it based on its appropriateness and comprehensiveness. For example, it generates a score of 90. The generated evaluation result and feedback are sent from the server to the device. The input is the final answer, and the output is the evaluation result and feedback.

[0350] Step 9:

[0351] The server records the analysis results of the emotion engine along with the evaluation results to check whether the user's emotions match the server's feedback. The input is the evaluation results and emotion data, and the output is the recorded data.

[0352] Step 10:

[0353] If authentication fails, the server's emotion engine analyzes the user's emotion and generates an appropriate error message based on that emotion. The server then sends this error message to the terminal and displays it to the user. The input is authentication information and emotion data, and the output is an error message.

[0354] In this way, the system allows users to answer test questions with the help of AI and an emotion engine, quickly and fairly evaluates the answers, and provides feedback based on the user's emotions.

[0355] (Application example 2)

[0356] 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."

[0357] In recent years, advances in autonomous driving technology have led to increased demand for passenger safety and comfort. However, conventional autonomous vehicles lack effective means for responding appropriately to passenger questions and resolving their concerns and doubts. This can result in lower passenger satisfaction and a loss of trust in the safety of the vehicle. Therefore, there is a need for a system that can quickly and appropriately respond to passenger questions and adjust feedback by analyzing passenger emotions.

[0358] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting test questions to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an AI on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, means for an AI on the server to evaluate the submitted answers and send the evaluation results to the terminal, and means for analyzing the user's emotions using an emotion analysis engine and adjusting feedback based on the generated answers. This makes it possible to quickly and accurately generate answers to passenger questions and further analyze the passenger's emotions based on the answers to provide appropriate feedback.

[0359] "Means for the server to verify the authentication information entered by the user via the terminal" refers to a function that allows the server to obtain the authentication information entered by the user (e.g., user ID and password) and verify it against pre-set authentication data to perform authentication.

[0360] "Means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful" is a function that allows the server to send test questions to the terminal for a user who has been successfully authenticated and display them.

[0361] The "means for transmitting an answer prompt input by a user from a terminal to a server" is a function for transmitting an answer prompt input by a user to a terminal to a server.

[0362] "Means for AI on the server to generate an answer based on the prompt and return the generated answer to the terminal" refers to a function that allows artificial intelligence (AI) on the server to analyze the prompt, create an answer based on that, and return that answer to the user's terminal.

[0363] "Means for displaying the generated answer to the user and submitting the answer determined as the final answer from the terminal to the server" is a function for displaying the generated answer on the user's terminal, allowing the user to check the answer, determine it as the final answer, and submit it from the terminal to the server.

[0364] "Means for evaluating submitted answers using AI on the server and sending the evaluation results to the terminal" refers to a function for evaluating the final answer submitted by the user using AI on the server and sending the evaluation results to the user's terminal.

[0365] "Means for analyzing a user's emotions using an emotion analysis engine and adjusting feedback based on the generated answer" refers to a function that uses an emotion analysis engine to analyze emotions from the user's facial expressions, voice data, etc., and adjusts the expression and content of the generated answer according to those emotions to provide feedback.

[0366] The system for implementing this invention incorporates AI and an emotion engine into the user interface of an autonomous vehicle. The system components include a terminal, a server, an AI module, and an emotion engine. This section provides a detailed description of each component and how they work together.

[0367] 1. Terminal

[0368] The device could be an infotainment system installed in the autonomous vehicle or a passenger's smartphone or tablet. Users use this device to access the system, enter login information, ask questions, and confirm answers.

[0369] 2. Server

[0370] The server, which can be located in the cloud or in the vehicle, has the following main functions:

[0371] Credentials validation

[0372] Submitting exam questions

[0373] Receiving answer prompts

[0374] AI-powered answer generation

[0375] Sentiment analysis and feedback adjustment

[0376] User response rating

[0377] 3. AI Module

[0378] The AI ​​module uses a generative AI model, such as OpenAI's GPT-4 (registered trademark), to generate answers based on prompts entered by the user and send the answers back to the device via a server.

[0379] 4. Emotion Engine

[0380] The emotion engine uses Microsoft® Azure® Emotion API and other tools to analyze the user's voice tone and facial expression data to understand the user's emotions in real time. The analyzed emotion data is used to adjust the expression and content of the generated answers.

[0381] Specific examples

[0382] 1. The user enters their login information into the terminal, which is verified by the server. If authentication is successful, the next step is performed.

[0383] 2. The user types a question into the terminal, such as "How long will it take to get to my destination?" The prompt is sent to the server.

[0384] 3. The server's AI module analyzes the prompt and generates an answer such as, "Based on current traffic conditions, about 30 minutes."

[0385] 4. The emotion engine analyzes the user's emotions (e.g., anxiety) and adds feedback to the response as needed, such as "Don't worry, we'll get you to your destination safely."

[0386] 5. The final answer is displayed on the terminal and the user confirms it.

[0387] Prompt Sentence Examples

[0388] "Please tell me how long it will take to get to your destination."

[0389] "Tell me about this car's safety features."

[0390] This system will allow passengers to have any questions or concerns about self-driving vehicles resolved, allowing them to ride with peace of mind.

[0391] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0392] Step 1:

[0393] The user enters authentication information (user ID and password) via the terminal. The terminal sends this to the server. The server receives the authentication information entered by the user and verifies it against the information in the database. If authentication is successful, it sends the test questions to the terminal.

[0394] Input: User ID, Password

[0395] Data processing: The server checks the authentication information against a database

[0396] Output: Authentication success or failure message

[0397] Step 2:

[0398] When the server detects successful authentication, it sends the test questions to the user's terminal, where they are displayed and the user confirms them.

[0399] Input: Authentication success message

[0400] Data processing: Sending exam questions

[0401] Output: Display of exam questions

[0402] Step 3:

[0403] The user inputs answer prompts for the test questions into the terminal, which then sends the prompts to the server.

[0404] Input:Answer prompt

[0405] Data Processing: Send Prompt

[0406] Output: Send prompt to server

[0407] Step 4:

[0408] An AI module on the server analyzes the prompts sent by the user and generates appropriate answers, which are then sent back to the device.

[0409] Input:Answer prompt

[0410] Data processing: prompt analysis and answer generation

[0411] Output: The generated answer

[0412] Step 5:

[0413] The generated answer is displayed on the device. At the same time, the emotion engine analyzes the user's facial expressions and voice data to generate emotional data. This emotional data is sent to the AI ​​module and used to adjust the expression of the answer.

[0414] Input: User's facial expression data, voice data

[0415] Data processing: sentiment analysis, feedback adjustment

[0416] Output: Adjusted answer

[0417] Step 6:

[0418] The adjusted answer is displayed on the terminal. The user checks the displayed answer and, if necessary, modifies and decides on the final answer. The final answer is then submitted to the server.

[0419] Input: Adjusted answer, user confirmation

[0420] Data processing: determining and sending the final answer

[0421] Output: Final response sent

[0422] Step 7:

[0423] The server evaluates the submitted final answer again using the AI ​​module and generates an evaluation result, which is sent to the terminal and displayed to the user.

[0424] Input: Final answer

[0425] Data processing: Evaluation analysis

[0426] Output: Generating and sending evaluation results

[0427] 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.

[0428] 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.

[0429] 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.

[0430] [Second embodiment]

[0431] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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."

[0443] overview

[0444] This invention relates to a system in which candidates use AI to answer questions during employment examinations and the answers are evaluated by AI. This system is composed of terminals, a server, and AI, and provides users with a fair and prompt evaluation.

[0445] System configuration

[0446] The system is implemented with the following main components:

[0447] 1. Terminal

[0448] This is a device that users access, such as a PC, tablet, or smartphone. The device displays the login screen, the test question screen, and an interface for entering answer prompts.

[0449] 2. Server

[0450] The server plays a key role in verifying user authentication information, sending test questions to the device, and generating and evaluating answers using AI. The server is equipped with an AI module that generates and evaluates answers based on prompts.

[0451] 3. AI Module

[0452] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users and is also responsible for evaluating the final answers submitted and generating scores and feedback.

[0453] Program processing

[0454] User operations

[0455] The user enters authentication information (user ID and password) on the login screen. This information is sent from the terminal to the server. The server verifies the authentication information, and if the user is legitimate, a list of test questions is sent to the user terminal.

[0456] Server authentication and test question transmission

[0457] The server checks the authentication information against a database, and only if successful does it send the test questions to the terminal. The test questions are preset, and the user selects the questions to answer from this list.

[0458] Generate answer prompts

[0459] The user checks the test questions displayed on the terminal and inputs the answer prompts. For example, if the user inputs a prompt such as "Explain the basic principles of programming," the terminal sends the prompt to the server.

[0460] AI-powered answer generation

[0461] The AI ​​module on the server receives prompts from the user and generates an answer based on the prompts. The answer (e.g., "The fundamental principles of programming include algorithms, data structures, modularization, and error handling") is then sent back to the device.

[0462] User decides the final answer

[0463] The user checks the answers generated by the AI ​​and decides on the final answer based on the content. If necessary, the user can modify the answer and submit it to the server as the final answer.

[0464] Evaluating answers

[0465] The final answer submitted is then evaluated by the AI ​​module on the server. The AI ​​module evaluates the appropriateness and comprehensiveness of the answer and generates a score and feedback. For example, if a score of 90 is given, this is sent to the terminal along with the evaluation result.

[0466] Specific examples

[0467] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user then enters the answer prompt "Explain the basic principles of programming," and the server passes this prompt to the AI ​​module. The AI ​​generates an answer and sends it back to the terminal. When the user decides on the final answer and submits it to the server, the server's AI evaluates it and provides the user with a score and feedback.

[0468] In this way, the system according to the present invention allows users to answer test questions with the help of AI and have their answers evaluated quickly and fairly.

[0469] The processing flow will be explained below.

[0470] Step 1:

[0471] The user enters the user ID "user123" and password "password" on the login screen of the device and presses the login button.

[0472] Step 2:

[0473] The terminal sends the authentication information entered by the user to the server.

[0474] Step 3:

[0475] The server checks the user ID and password against an authentication database.

[0476] Step 4:

[0477] If the server is successful in the authentication, it prepares a test question list and sends it to the terminal, otherwise it sends an error message to the terminal.

[0478] Step 5:

[0479] The terminal receives the test question list and displays it to the user.

[0480] Step 6:

[0481] The user selects any test question and presses the start button.

[0482] Step 7:

[0483] The terminal requests the selected test question from the server and receives details of the question.

[0484] Step 8:

[0485] The terminal displays test questions to the user and provides an interface for entering answer prompts.

[0486] Step 9:

[0487] The user inputs the answer prompt "Explain the basic principles of programming."

[0488] Step 10:

[0489] The terminal sends the entered prompt to the server.

[0490] Step 11:

[0491] The server receives the prompt and passes it to the AI ​​module.

[0492] Step 12:

[0493] Based on the prompt, the AI ​​(server) generates an answer: "The fundamental principles of programming include algorithms, data structures, modularization, and error handling" and sends it back to the terminal via the server.

[0494] Step 13:

[0495] The device receives the AI-generated answer and displays it to the user.

[0496] Step 14:

[0497] The user checks the AI's answer, corrects it as necessary, and decides on the final answer.

[0498] Step 15:

[0499] The user presses a button to submit the final answer.

[0500] Step 16:

[0501] The terminal sends the user's final answer to the server.

[0502] Step 17:

[0503] The server passes the final answer back to the AI ​​module for evaluation.

[0504] Step 18:

[0505] The AI ​​(server) evaluates the answer, determines that the answer is appropriate and comprehensive, and assigns a score (e.g., 90 points).

[0506] Step 19:

[0507] The server records the evaluation results and feedback and sends them to the device.

[0508] Step 20:

[0509] The terminal displays the evaluation results to the user.

[0510] Example 1

[0511] 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."

[0512] In traditional recruitment tests, the challenges of evaluating candidates fairly and providing results quickly have been posed. Manual evaluation consumes a large amount of time and human resources, and it is difficult to ensure fairness. Furthermore, if candidates do not have time to thoroughly consider their answers, they may not receive an appropriate evaluation.

[0513] 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.

[0514] In this invention, the server includes means for verifying authentication information entered by a user via a terminal on the server, means for transmitting test questions from the server to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an artificial intelligence on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, and means for evaluating the submitted answers with the artificial intelligence on the server, generating feedback together with the evaluation results and transmitting it to the terminal. This allows candidates to be evaluated efficiently and fairly, and test results to be obtained quickly.

[0515] "Authentication Information" means information provided by a user to prove his or her identity, and typically includes a user ID and password.

[0516] A "server" is a computer system that processes data and provides services over a network.

[0517] A "terminal" is a device operated by a user, and includes a personal computer, a tablet, a smartphone, and the like.

[0518] "Exam Questions" means questions or tasks designed to assess a candidate's abilities or knowledge.

[0519] An "answer prompt" is text or instructions that assist the user in entering an answer to a test question.

[0520] "Artificial intelligence" refers to computer programs that mimic human intelligence to learn and solve problems.

[0521] "Evaluation" is the process of judging the appropriateness and comprehensiveness of submitted answers and generating scores and feedback.

[0522] "Feedback" refers to advice or comments provided to the user based on the evaluation results.

[0523] overview

[0524] This invention relates to a system in which candidates use artificial intelligence (AI) to answer questions during employment examinations, and the answers are evaluated by AI. The system consists of a terminal, a server, and an AI module, and provides users with a fair and prompt evaluation.

[0525] System configuration

[0526] The system is implemented with the following main components:

[0527] 1. Terminal

[0528] The terminal is a device for user access, and includes a personal computer, tablet, smartphone, etc. The terminal displays a login screen, a screen displaying test questions, and an interface for inputting answer prompts.

[0529] 2. Server

[0530] The server plays a key role in verifying user credentials, sending test questions to the device, and generating and evaluating answers using artificial intelligence. An AI module is installed on the server, which generates and evaluates answers based on prompt input.

[0531] 3. AI Module

[0532] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users, and is responsible for evaluating the final answers submitted and generating scores and feedback. A pre-trained generative AI model (e.g., GPT-3) is used.

[0533] Program processing

[0534] 1. User authentication

[0535] The user enters authentication information (user ID and password) on the login screen displayed on the terminal. This information is sent from the terminal to the server. The server compares it with the database, and if authentication is successful, it sends a list of test questions to the terminal.

[0536] 2. Display of exam questions

[0537] The test question list sent from the server is displayed on the terminal, and the user selects the questions to answer from the displayed test questions.

[0538] 3. Enter the answer prompt

[0539] The user checks the test questions displayed on the terminal and inputs the answer prompt, for example, "Explain the basic principles of programming." This prompt is sent from the terminal to the server.

[0540] 4. AI-generated answers

[0541] The AI ​​module on the server uses a generative AI model to generate an answer based on the prompt received from the user, for example, "The fundamental principles of programming include algorithms, data structures, modularization, and error handling." This answer is then sent back from the server to the device.

[0542] 5. User decides on the final answer

[0543] The user checks the answers generated by the AI ​​on their device, and if necessary, makes corrections to determine the final answer, which is then sent from the device to the server.

[0544] 6. Rating and Feedback on Answers

[0545] The AI ​​module on the server evaluates the final answer and generates a score and feedback (for example, a score of 90) that is sent to the device. The feedback also includes specific advice and comments.

[0546] Specific examples

[0547] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user enters the answer prompt "Explain the basic principles of programming," and the server passes this to the AI ​​module. The AI ​​generates an answer: "The basic principles of programming include algorithms, data structures, modularization, and error handling," and sends it back to the terminal. When the user decides on a final answer and submits it to the server, the AI ​​evaluates it and sends 90 points and feedback to the terminal. This process allows the user to generate answers efficiently and have them evaluated fairly.

[0548] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0549] Program processing flow

[0550] Step 1: Perform user authentication

[0551] The user enters their user ID and password into the login screen on the terminal. This input information is sent to the server as an HTTP request. The server compares the received authentication information with the database, and if authentication is successful, sends a successful authentication response to the terminal. The input is "user123" and "password", and the output is a message indicating successful authentication. Specifically, the server searches the database using the user ID as a key and compares it with the corresponding password.

[0552] Step 2: View the exam questions

[0553] The server sends a pre-set list of test questions to the terminal along with a response of successful authentication. The terminal displays the received test questions on the screen, and the user selects questions to answer from the list. The input is an authentication success message, and the output is a list of test questions. Specifically, the server retrieves the list from a database or configuration file that stores test question data, and sends it to the terminal.

[0554] Step 3: Enter the answer prompts

[0555] The user checks the test questions displayed on the terminal and enters the answer prompt. For example, they enter "Explain the basic principles of programming" and press the send button. The terminal sends this input as an HTTP request to the server. The input is the answer prompt, "Explain the basic principles of programming," and the output is a confirmation of sending the prompt to the server. Specifically, the terminal constructs form data and sends it to the server.

[0556] Step 4: AI-generated answers

[0557] The server passes the prompt received from the device to the AI ​​module. The AI ​​module uses the generative AI model to generate an answer based on the prompt. For example, if the prompt is "Explain the basic principles of programming," the AI ​​generates the answer "The basic principles of programming include algorithms, data structures, modularization, and error handling." The generated answer is sent back from the server to the device. The input is the prompt, and the output is the generated answer. Specifically, the AI ​​module performs natural language processing to generate an answer.

[0558] Step 5: User decides on final answer

[0559] The user checks the AI-generated answer received on their device and makes corrections as necessary. The final answer is sent to the server by pressing the send button. The input is the AI-generated answer and the user's corrections, and the output is the final answer. Specifically, the user edits the answer using a text editor and resubmits it to the server.

[0560] Step 6: Rate and give feedback on your answers

[0561] The server passes the received final answer back to the AI ​​module. The AI ​​module evaluates the answer and generates feedback along with the evaluation result. For example, if the answer is appropriate and comprehensive, feedback of 90 points will be generated. This is sent from the server to the terminal and displayed to the user. The input is the final answer, and the output is the evaluation result and feedback. Specifically, the AI ​​module evaluates based on the set evaluation criteria and generates feedback.

[0562] (Application example 1)

[0563] 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."

[0564] In conventional factory robot operation training, operator candidates are evaluated by human evaluators, which can lead to problems of lack of fairness and speed. Furthermore, there is a lack of systems for efficiently training in operation procedures. This can lead to extended training periods and inefficient operation, negatively impacting corporate productivity.

[0565] 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.

[0566] In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting a training task from the server to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for a generating AI on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, and means for evaluating the submitted answers with the generating AI on the server and transmitting the evaluation results to the terminal, thereby enabling fair and prompt training evaluation and efficient acquisition of operating procedures.

[0567] A "terminal" is a device used by a user for access, such as a smartphone, tablet, or personal computer.

[0568] "Authentication information" refers to the information a user uses to log in to a system, and typically consists of a user ID and password.

[0569] A "server" is a computer system that is connected to a network and performs functions such as user authentication, data processing, and AI evaluation.

[0570] "Training tasks" refer to instructions and problems sent from the server to train potential operators in robot operation.

[0571] An "answer prompt" is a specific question or instruction that a user enters to answer a training task.

[0572] "Generative AI" is an AI model that has the ability to generate answers based on answer prompts from a user and to evaluate those answers.

[0573] The "evaluation result" is the evaluation made by the generating AI on the user's final answer, and is provided to the user as a score or feedback.

[0574] This invention relates to a factory robot operation training evaluation system in which operator candidates answer training questions with the help of AI, and the AI ​​evaluates their answers. This system is composed of a terminal, a server, and a generative AI. Each component and its operation are described in detail below.

[0575] 1. System Configuration

[0576] 1.1 Terminal

[0577] A terminal is a device that users access, such as a smartphone, tablet, or personal computer. The terminal provides a user authentication screen, a display screen for training tasks, and an input interface for answer prompts.

[0578] 1.2 Server

[0579] The server is a computer system connected to the network that authenticates users, provides training assignments, generates answers, and evaluates them. The server has a database that stores user authentication information, training assignments, and evaluation results.

[0580] 1.3 Generative Artificial Intelligence

[0581] Generative AI is an AI model implemented on a server that generates answers based on prompts sent by users and evaluates the final answers submitted. Specifically, a generative AI model (e.g., OpenAI's GPT model) is used.

[0582] 2. Operational Details

[0583] 2.1 User Authentication

[0584] The user enters authentication information (user ID and password) via the terminal. This information is sent from the terminal to the server, which then verifies it against a database. If authentication is successful, the server sends the user a training assignment.

[0585] 2.2 Displaying training tasks and generating response prompts

[0586] The training tasks sent from the server are displayed on the terminal and the user confirms them. The user inputs answer prompts for the training tasks and sends them from the terminal to the server.

[0587] Prompt Sentence Examples

[0588] "Please explain the basic operating procedure for a factory robot. Specifically, how to accurately place part A at position X."

[0589] 2.3 Answer generation and display using AI

[0590] The server-based AI generates an answer based on the user's prompts. The generated answer is then sent back to the terminal and displayed to the user. The user can then review the displayed answer, modify it as necessary, and determine the final answer.

[0591] 2.4 Submission and evaluation of final answers

[0592] When the user submits the final answer to the server, the server-based AI evaluates the answer, and the evaluation results (e.g., score and feedback) are sent to the terminal and provided to the user.

[0593] Specific examples

[0594] When an operator candidate logs into the system using a smartphone, the server performs authentication, and if successful, a training task is sent to the terminal: "Please explain the basic operating procedures for a factory robot. Specifically, please state the steps for placing part A at position X." The candidate enters the answer prompt, "Steps for placing part A at position X," and the server passes this prompt to the generating artificial intelligence. The procedure generated by the AI ​​is checked, and the candidate makes corrections and submits it to the server as the final answer, which the AI ​​evaluates and provides a score and feedback.

[0595] In this way, the system according to the present invention enables operator candidates to be effectively trained with the assistance of AI, and enables fair and rapid evaluation.

[0596] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0597] Step 1:

[0598] The user enters authentication information (user ID and password) via the terminal. The terminal sends this authentication information to the server. The server receives the authentication information and authenticates the user by checking it against a database. If authentication is successful, the server sends a training task to the terminal.

[0599] Input: User ID, Password

[0600] Output: Authentication results, training tasks

[0601] Step 2:

[0602] The training task sent by the server is displayed on the terminal. The user checks the training task through the terminal and inputs an answer prompt. The terminal sends this answer prompt to the server.

[0603] Input: Training task, response prompt

[0604] Output: Answer prompt

[0605] Step 3:

[0606] The server passes the answer prompt received from the terminal to the generative AI model and requests it to generate an answer. The generative AI model generates an answer based on the prompt and returns the result to the server. The server then sends the generated answer to the terminal.

[0607] Input:Answer prompt

[0608] Output: The generated answer

[0609] Step 4:

[0610] The user checks the answer generated by the generative AI model displayed on the terminal, corrects the answer as necessary, and submits it to the server from the terminal as the final answer.

[0611] Input: Generated answers, user corrections

[0612] Output: Final answer

[0613] Step 5:

[0614] The server passes the final answer to the generative AI model and requests an evaluation. The generative AI model evaluates the final answer and returns the evaluation result to the server. The server then sends the evaluation result to the terminal.

[0615] Input: Final answer

[0616] Output: Evaluation results

[0617] Step 6:

[0618] The evaluation results are displayed on the terminal. The user checks the evaluation results and understands the results of the training. The server records the evaluation results in a database for future reference.

[0619] Input: Evaluation result

[0620] Output: Record of evaluation results

[0621] In this way, a system is realized that allows users to train efficiently with the support of AI and have their results evaluated fairly and quickly.

[0622] 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.

[0623] overview

[0624] This invention relates to a system in which candidates use AI and an emotion engine to answer questions during employment tests, and the answers are evaluated by AI. This system is composed of a terminal, a server, an AI module, and an emotion engine, and provides users with fair and prompt evaluations and feedback based on their emotions.

[0625] System configuration

[0626] The system is implemented with the following main components:

[0627] 1. Terminal

[0628] This is a device that users access, such as a PC, tablet, or smartphone. The device displays the login screen, the test question screen, and an interface for entering answer prompts.

[0629] 2. Server

[0630] It verifies the user's authentication information, sends the test questions to the device, and uses AI and emotion engines to generate and evaluate answers.

[0631] 3. AI Module

[0632] It is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users, and is responsible for evaluating the final answers submitted and generating scores and feedback.

[0633] 4. Emotion Engine

[0634] This is a program that analyzes the user's emotions and adjusts the AI's response generation and error messages according to those emotions.

[0635] Program processing

[0636] User operations

[0637] The user enters authentication information (user ID and password) on the login screen. This information is sent from the terminal to the server. The server verifies the authentication information, and if the user is legitimate, a list of test questions is sent to the user terminal. If authentication fails, the emotion engine analyzes the user's emotions and generates an appropriate error message.

[0638] Server authentication and test question transmission

[0639] The server checks the authentication information against a database, and only if successful does it send the test questions to the terminal. The test questions are preset, and the user selects the questions to answer from this list.

[0640] Generate answer prompts

[0641] The user checks the test questions displayed on the terminal and inputs the answer prompts. For example, if the user inputs a prompt such as "Explain the basic principles of programming," the terminal sends this prompt to the server.

[0642] AI-based answer generation and emotion engine usage

[0643] The AI ​​module on the server receives prompts from the user and generates an answer based on the prompts. The generated answer (e.g., "The basic principles of programming include algorithms, data structures, modularization, and error handling") is then sent back to the device. At the same time, the emotion engine analyzes the user's emotions and adjusts the answer accordingly.

[0644] User decides the final answer

[0645] The user checks the answers generated by the AI ​​and decides on the final answer based on the content. If necessary, the user can modify the answer and submit it to the server as the final answer.

[0646] Evaluating answers

[0647] The final answer submitted is then evaluated by the AI ​​module on the server. The AI ​​module evaluates the appropriateness and comprehensiveness of the answer and generates a score and feedback. For example, if a score of 90 is given, the evaluation result and the analysis results from the emotion engine are also recorded.

[0648] Generate an error message when authentication fails

[0649] If the authentication information is incorrect, the emotion engine analyzes the user's emotion, generates an appropriate error message according to that emotion, and sends it to the terminal.

[0650] Specific examples

[0651] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user enters the answer prompt "Explain the basic principles of programming," and the server passes this prompt to the AI ​​module. The AI ​​generates an answer and sends it back to the terminal. At the same time, the emotion engine analyzes the user's emotions and adjusts the expression of the answer based on the user's emotions. When the user decides on a final answer and submits it to the server, the server's AI evaluates it and provides the user with a score (e.g., 90 points) and feedback. The emotion engine's analysis results are also added to the evaluation result and recorded. If authentication fails, the emotion engine adjusts the error message and displays it to the user.

[0652] In this way, the system of the present invention allows users to answer test questions with the help of AI and an emotion engine, quickly and fairly evaluate the answers, and provide feedback based on the user's emotions.

[0653] The processing flow will be explained below.

[0654] Step 1:

[0655] The user enters the user ID "user123" and password "password" on the login screen of the device and presses the login button.

[0656] Step 2:

[0657] The terminal sends the authentication information entered by the user to the server.

[0658] Step 3:

[0659] The server checks the user ID and password against a database.

[0660] Step 4:

[0661] If the server is successful in the authentication, it prepares a list of test questions and sends it to the terminal.

[0662] Step 5:

[0663] If the server fails the authentication, it uses an emotion engine to analyze the user's emotion, generates an appropriate error message, and sends it to the terminal.

[0664] Step 6:

[0665] The terminal receives the test question list and displays it to the user.

[0666] Step 7:

[0667] The user selects any test question and presses the start button.

[0668] Step 8:

[0669] The terminal requests the selected test question from the server and receives details of the question.

[0670] Step 9:

[0671] The terminal displays test questions to the user and provides an interface for entering answer prompts.

[0672] Step 10:

[0673] The user inputs the answer prompt "Explain the basic principles of programming."

[0674] Step 11:

[0675] The terminal sends the entered prompt to the server.

[0676] Step 12:

[0677] The server receives the prompt and passes it to the AI ​​module.

[0678] Step 13:

[0679] The AI ​​(server) generates an answer based on the prompt: "Fundamental principles of programming include algorithms, data structures, modularity, and error handling."

[0680] Step 14:

[0681] The emotion engine (server) analyzes the user's emotions and determines whether the generated answers need to be adjusted.

[0682] Step 15:

[0683] The server sends back to the device an answer generated and adjusted by the AI ​​module and emotion engine.

[0684] Step 16:

[0685] The device receives the answers generated by the AI ​​and emotion engine and displays them to the user.

[0686] Step 17:

[0687] The user checks the AI's answer, corrects it as necessary, and decides on the final answer.

[0688] Step 18:

[0689] The user presses a button to submit the final answer.

[0690] Step 19:

[0691] The terminal sends the user's final answer to the server.

[0692] Step 20:

[0693] The server passes the final answer back to the AI ​​module for evaluation.

[0694] Step 21:

[0695] The AI ​​(server) evaluates the answer, determines that the answer is appropriate and comprehensive, and assigns a score (e.g., 90 points).

[0696] Step 22:

[0697] The emotion engine (server) analyzes the user's emotions regarding the evaluation results and adjusts the feedback.

[0698] Step 23:

[0699] The server records the evaluation results and feedback and sends them to the terminal.

[0700] Step 24:

[0701] The terminal displays the evaluation results to the user.

[0702] Example 2

[0703] 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."

[0704] In conventional recruitment testing systems, it was difficult to quickly and fairly evaluate the answers entered by candidates, and it was also difficult to provide feedback that took into account the candidates' emotions.It was also a challenge to provide an appropriate error message when authentication failed.

[0705] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting test questions to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an AI module on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, means for the AI ​​module on the server to evaluate the submitted answers and transmit the evaluation results to the terminal, and an emotion engine means for analyzing the user's emotions and adjusting the expression of the answers based on the emotions. This makes it possible to quickly and fairly evaluate the answers entered by the user and provide feedback that takes the candidate's emotions into consideration. It is also possible to provide an appropriate error message if authentication fails.

[0706] A "user" is an individual or entity that accesses the system through a terminal, enters authentication information, and answers exam questions.

[0707] A "terminal" is a device through which a user accesses the system, and includes a PC, tablet, smartphone, etc.

[0708] "Server" is a central computer system that verifies user credentials, transmits test questions, and uses AI modules and emotion engines to generate and evaluate answers.

[0709] "Authentication information" means information such as a user ID and password that enables a user to legitimately access a system.

[0710] A "quiz question" is a question or challenge sent by a server for a user to answer, for assessment purposes.

[0711] An "answer prompt" is a command or question that a user enters in response to a test question.

[0712] "AI Module" means an artificial intelligence program implemented on a server that generates answers based on user response prompts and evaluates the final answers submitted.

[0713] The "emotion engine" is a program that analyzes the user's emotions and adjusts the AI ​​module's response and error messages based on those emotions.

[0714] "Evaluation Results" refers to the score and feedback provided by the AI ​​module to evaluate the user's final answer based on its appropriateness and comprehensiveness.

[0715] An "error message" is a notification message that is generated by the server using the emotion engine when user authentication fails, and that is based on the user's emotion.

[0716] This invention relates to a system in which candidates use AI and an emotion engine to answer questions during employment examinations, and the answers are evaluated by AI. This system is composed of a terminal, a server, an AI module, and an emotion engine, and provides users with fair and prompt evaluations and feedback according to their emotions.

[0717] System configuration

[0718] 1. Terminal

[0719] The terminal is the device through which the user accesses the test, such as a PC, tablet, or smartphone. The terminal displays a login screen, a screen displaying test questions, and an interface for entering answer prompts.

[0720] 2. Server

[0721] The server is a central computer system that verifies user credentials, sends test questions to the terminal, and uses AI modules and emotion engines to generate and evaluate answers.

[0722] 3. AI Module

[0723] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by the user and is also responsible for evaluating the final answers submitted and generating scores and feedback.

[0724] 4. Emotion Engine

[0725] The emotion engine is a program that analyzes the user's emotions and adjusts the AI ​​module's response generation and error message display based on those emotions.

[0726] Hardware and software used

[0727] Hardware: PCs, tablets, smartphones

[0728] Software: Server, AI module, emotion engine

[0729] Examples: AI platforms and sentiment analysis APIs implemented on virtual machines

[0730] Specific examples

[0731] The user enters the login information "user123" and "password" and attempts to log in. The server receives this information and checks it against the database. If authentication is successful, the test question "Explain the basic principles of programming" is sent to the terminal.

[0732] The user checks the test questions displayed on the terminal and enters the answer prompt, "Explain the basic principles of programming." The terminal sends this prompt to the server, which passes it to the server's AI module.

[0733] The AI ​​module generates answers based on the prompts, explaining that "fundamental principles of programming include algorithms, data structures, modularization, and error handling." The generated answers are then sent back to the device from the server.

[0734] At the same time, the emotion engine analyzes the user's emotions, and if the user is feeling anxious, for example, it will add a phrase such as "Don't worry, you can solve this problem if you understand it well" and display it.

[0735] The user checks the generated answers, makes corrections as necessary, and decides on the final answer, which is then submitted to the server from the terminal.

[0736] The server then passes the submitted final answer back to the AI ​​module, generates an evaluation score (e.g., 90 points) and feedback, and sends it to the device. The evaluation result also records the analysis results of the emotion engine.

[0737] If authentication fails, the emotion engine analyzes the user's emotions and generates an error message such as "The password you entered is incorrect. Please try again." and sends it to the terminal, providing the user with appropriate feedback.

[0738] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0739] Step 1:

[0740] The user enters authentication information (user ID and password) on the login screen of the terminal. The terminal sends this input information to the server. The input is the user ID and password, and the output is the authentication information sent to the server.

[0741] Step 2:

[0742] The server compares the received authentication information with the database to confirm whether the user is a legitimate user. For example, it retrieves the corresponding user ID and password record from the database and matches it with the entered information. If authentication is successful, the server sends a list of test questions to the terminal. The input is authentication information, and the output is the authentication results and a list of test questions. If there is a mismatch, the emotion engine generates an error message based on the user's emotion and sends it to the terminal.

[0743] Step 3:

[0744] The terminal displays the test questions sent from the server and the user selects the questions to answer. The terminal takes the user's selection as input and sends the selection information to the server. The input is the selection of the test question, and the output is the transmission of the selection information.

[0745] Step 4:

[0746] The user inputs an answer prompt to the multiple-choice question displayed on the terminal. For example, they input "Explain the basic principles of programming." The terminal sends this prompt to the server. The input is the answer prompt, and the output is the sending of the prompt.

[0747] Step 5:

[0748] The server passes the received prompt to the AI ​​module, which then generates an answer based on the prompt. For example, it might generate, "The fundamental principles of programming include algorithms, data structures, modularization, and error handling." The generated answer is then sent back to the terminal. The input is the prompt, and the output is the generated answer.

[0749] Step 6:

[0750] At the same time, the emotion engine analyzes the user's emotions. For example, if the user is anxious, the emotion engine adds a phrase such as "Don't worry, you can solve this problem if you understand it well" to the answer. The input is the user's emotional data, and the output is the adjusted answer. The adjusted answer is then sent back to the device from the server.

[0751] Step 7:

[0752] The user checks the generated answer on the terminal, corrects it if necessary, and decides on the final answer. The corrected final answer is then submitted to the server. The input is the corrected answer, and the output is the transmission of the final answer.

[0753] Step 8:

[0754] The server then passes the submitted final answer back to the AI ​​module, which then evaluates it based on its appropriateness and comprehensiveness. For example, it generates a score of 90. The generated evaluation result and feedback are sent from the server to the device. The input is the final answer, and the output is the evaluation result and feedback.

[0755] Step 9:

[0756] The server records the analysis results of the emotion engine along with the evaluation results to check whether the user's emotions match the server's feedback. The input is the evaluation results and emotion data, and the output is the recorded data.

[0757] Step 10:

[0758] If authentication fails, the server's emotion engine analyzes the user's emotion and generates an appropriate error message based on that emotion. The server then sends this error message to the terminal and displays it to the user. The input is authentication information and emotion data, and the output is an error message.

[0759] In this way, the system allows users to answer test questions with the help of AI and an emotion engine, quickly and fairly evaluates the answers, and provides feedback based on the user's emotions.

[0760] (Application example 2)

[0761] 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."

[0762] In recent years, advances in autonomous driving technology have led to increased demand for passenger safety and comfort. However, conventional autonomous vehicles lack effective means for responding appropriately to passenger questions and resolving their concerns and doubts. This can result in lower passenger satisfaction and a loss of trust in the safety of the vehicle. Therefore, there is a need for a system that can quickly and appropriately respond to passenger questions and adjust feedback by analyzing passenger emotions.

[0763] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting test questions to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an AI on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, means for an AI on the server to evaluate the submitted answers and send the evaluation results to the terminal, and means for analyzing the user's emotions using an emotion analysis engine and adjusting feedback based on the generated answers. This makes it possible to quickly and accurately generate answers to passenger questions and further analyze the passenger's emotions based on the answers to provide appropriate feedback.

[0764] "Means for the server to verify the authentication information entered by the user via the terminal" refers to a function that allows the server to obtain the authentication information entered by the user (e.g., user ID and password) and verify it against pre-set authentication data to perform authentication.

[0765] "Means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful" is a function that allows the server to send test questions to the terminal for a user who has been successfully authenticated and display them.

[0766] The "means for transmitting an answer prompt input by a user from a terminal to a server" is a function for transmitting an answer prompt input by a user to a terminal to a server.

[0767] "Means for AI on the server to generate an answer based on the prompt and return the generated answer to the terminal" refers to a function that allows artificial intelligence (AI) on the server to analyze the prompt, create an answer based on that, and return that answer to the user's terminal.

[0768] "Means for displaying the generated answer to the user and submitting the answer determined as the final answer from the terminal to the server" is a function for displaying the generated answer on the user's terminal, allowing the user to check the answer, determine it as the final answer, and submit it from the terminal to the server.

[0769] "Means for evaluating submitted answers using AI on the server and sending the evaluation results to the terminal" refers to a function for evaluating the final answer submitted by the user using AI on the server and sending the evaluation results to the user's terminal.

[0770] "Means for analyzing a user's emotions using an emotion analysis engine and adjusting feedback based on the generated answer" refers to a function that uses an emotion analysis engine to analyze emotions from the user's facial expressions, voice data, etc., and adjusts the expression and content of the generated answer according to those emotions to provide feedback.

[0771] The system for implementing this invention incorporates AI and an emotion engine into the user interface of an autonomous vehicle. The system components include a terminal, a server, an AI module, and an emotion engine. This section provides a detailed description of each component and how they work together.

[0772] 1. Terminal

[0773] The device could be an infotainment system installed in the autonomous vehicle or a passenger's smartphone or tablet. Users use this device to access the system, enter login information, ask questions, and confirm answers.

[0774] 2. Server

[0775] The server, which can be located in the cloud or in the vehicle, has the following main functions:

[0776] Credentials validation

[0777] Submitting exam questions

[0778] Receiving answer prompts

[0779] AI-powered answer generation

[0780] Sentiment analysis and feedback adjustment

[0781] User response rating

[0782] 3. AI Module

[0783] The AI ​​module uses a generative AI model, such as OpenAI's GPT-4, to generate answers based on prompts entered by the user and send the answers back to the device via a server.

[0784] 4. Emotion Engine

[0785] The emotion engine uses Microsoft Azure's Emotion API and other tools to analyze the user's voice tone and facial expression data to understand the user's emotions in real time. The analyzed emotion data is used to adjust the expression and content of the generated answers.

[0786] Specific examples

[0787] 1. The user enters their login information into the terminal, which is verified by the server. If authentication is successful, the next step is performed.

[0788] 2. The user types a question into the terminal, such as "How long will it take to get to my destination?" The prompt is sent to the server.

[0789] 3. The server's AI module analyzes the prompt and generates an answer such as, "Based on current traffic conditions, about 30 minutes."

[0790] 4. The emotion engine analyzes the user's emotions (e.g., anxiety) and adds feedback to the response as needed, such as "Don't worry, we'll get you to your destination safely."

[0791] 5. The final answer is displayed on the terminal and the user confirms it.

[0792] Prompt Sentence Examples

[0793] "Please tell me how long it will take to get to your destination."

[0794] "Tell me about this car's safety features."

[0795] This system will allow passengers to have any questions or concerns about self-driving vehicles resolved, allowing them to ride with peace of mind.

[0796] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0797] Step 1:

[0798] The user enters authentication information (user ID and password) via the terminal. The terminal sends this to the server. The server receives the authentication information entered by the user and verifies it against the information in the database. If authentication is successful, it sends the test questions to the terminal.

[0799] Input: User ID, Password

[0800] Data processing: The server checks the authentication information against a database

[0801] Output: Authentication success or failure message

[0802] Step 2:

[0803] When the server detects successful authentication, it sends the test questions to the user's terminal, where they are displayed and the user confirms them.

[0804] Input: Authentication success message

[0805] Data processing: Sending exam questions

[0806] Output: Display of exam questions

[0807] Step 3:

[0808] The user inputs answer prompts for the test questions into the terminal, which then sends the prompts to the server.

[0809] Input:Answer prompt

[0810] Data Processing: Send Prompt

[0811] Output: Send prompt to server

[0812] Step 4:

[0813] An AI module on the server analyzes the prompts sent by the user and generates appropriate answers, which are then sent back to the device.

[0814] Input:Answer prompt

[0815] Data processing: prompt analysis and answer generation

[0816] Output: The generated answer

[0817] Step 5:

[0818] The generated answer is displayed on the device. At the same time, the emotion engine analyzes the user's facial expressions and voice data to generate emotional data. This emotional data is sent to the AI ​​module and used to adjust the expression of the answer.

[0819] Input: User's facial expression data, voice data

[0820] Data processing: sentiment analysis, feedback adjustment

[0821] Output: Adjusted answer

[0822] Step 6:

[0823] The adjusted answer is displayed on the terminal. The user checks the displayed answer and, if necessary, modifies and decides on the final answer. The final answer is then submitted to the server.

[0824] Input: Adjusted answer, user confirmation

[0825] Data processing: determining and sending the final answer

[0826] Output: Final response sent

[0827] Step 7:

[0828] The server evaluates the submitted final answer again using the AI ​​module and generates an evaluation result, which is sent to the terminal and displayed to the user.

[0829] Input: Final answer

[0830] Data processing: Evaluation analysis

[0831] Output: Generating and sending evaluation results

[0832] 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.

[0833] 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.

[0834] 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.

[0835] [Third embodiment]

[0836] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0837] 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.

[0838] 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).

[0839] 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.

[0840] 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.

[0841] 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).

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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."

[0848] overview

[0849] This invention relates to a system in which candidates use AI to answer questions during employment examinations and the answers are evaluated by AI. This system is composed of terminals, a server, and AI, and provides users with a fair and prompt evaluation.

[0850] System configuration

[0851] The system is implemented with the following main components:

[0852] 1. Terminal

[0853] This is a device that users access, such as a PC, tablet, or smartphone. The device displays the login screen, the test question screen, and an interface for entering answer prompts.

[0854] 2. Server

[0855] The server plays a key role in verifying user authentication information, sending test questions to the device, and generating and evaluating answers using AI. The server is equipped with an AI module that generates and evaluates answers based on prompts.

[0856] 3. AI Module

[0857] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users and is also responsible for evaluating the final answers submitted and generating scores and feedback.

[0858] Program processing

[0859] User operations

[0860] The user enters authentication information (user ID and password) on the login screen. This information is sent from the terminal to the server. The server verifies the authentication information, and if the user is legitimate, a list of test questions is sent to the user terminal.

[0861] Server authentication and test question transmission

[0862] The server checks the authentication information against a database, and only if successful does it send the test questions to the terminal. The test questions are preset, and the user selects the questions to answer from this list.

[0863] Generate answer prompts

[0864] The user checks the test questions displayed on the terminal and inputs the answer prompts. For example, if the user inputs a prompt such as "Explain the basic principles of programming," the terminal sends the prompt to the server.

[0865] AI-powered answer generation

[0866] The AI ​​module on the server receives prompts from the user and generates an answer based on the prompts. The answer (e.g., "The fundamental principles of programming include algorithms, data structures, modularization, and error handling") is then sent back to the device.

[0867] User decides the final answer

[0868] The user checks the answers generated by the AI ​​and decides on the final answer based on the content. If necessary, the user can modify the answer and submit it to the server as the final answer.

[0869] Evaluating answers

[0870] The final answer submitted is then evaluated by the AI ​​module on the server. The AI ​​module evaluates the appropriateness and comprehensiveness of the answer and generates a score and feedback. For example, if a score of 90 is given, this is sent to the terminal along with the evaluation result.

[0871] Specific examples

[0872] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user then enters the answer prompt "Explain the basic principles of programming," and the server passes this prompt to the AI ​​module. The AI ​​generates an answer and sends it back to the terminal. When the user decides on the final answer and submits it to the server, the server's AI evaluates it and provides the user with a score and feedback.

[0873] In this way, the system according to the present invention allows users to answer test questions with the help of AI and have their answers evaluated quickly and fairly.

[0874] The processing flow will be explained below.

[0875] Step 1:

[0876] The user enters the user ID "user123" and password "password" on the login screen of the device and presses the login button.

[0877] Step 2:

[0878] The terminal sends the authentication information entered by the user to the server.

[0879] Step 3:

[0880] The server checks the user ID and password against an authentication database.

[0881] Step 4:

[0882] If the server is successful in the authentication, it prepares a test question list and sends it to the terminal, otherwise it sends an error message to the terminal.

[0883] Step 5:

[0884] The terminal receives the test question list and displays it to the user.

[0885] Step 6:

[0886] The user selects any test question and presses the start button.

[0887] Step 7:

[0888] The terminal requests the selected test question from the server and receives details of the question.

[0889] Step 8:

[0890] The terminal displays test questions to the user and provides an interface for entering answer prompts.

[0891] Step 9:

[0892] The user inputs the answer prompt "Explain the basic principles of programming."

[0893] Step 10:

[0894] The terminal sends the entered prompt to the server.

[0895] Step 11:

[0896] The server receives the prompt and passes it to the AI ​​module.

[0897] Step 12:

[0898] Based on the prompt, the AI ​​(server) generates an answer: "The fundamental principles of programming include algorithms, data structures, modularization, and error handling" and sends it back to the terminal via the server.

[0899] Step 13:

[0900] The device receives the AI-generated answer and displays it to the user.

[0901] Step 14:

[0902] The user checks the AI's answer, corrects it as necessary, and decides on the final answer.

[0903] Step 15:

[0904] The user presses a button to submit the final answer.

[0905] Step 16:

[0906] The terminal sends the user's final answer to the server.

[0907] Step 17:

[0908] The server passes the final answer back to the AI ​​module for evaluation.

[0909] Step 18:

[0910] The AI ​​(server) evaluates the answer, determines that the answer is appropriate and comprehensive, and assigns a score (e.g., 90 points).

[0911] Step 19:

[0912] The server records the evaluation results and feedback and sends them to the device.

[0913] Step 20:

[0914] The terminal displays the evaluation results to the user.

[0915] Example 1

[0916] 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."

[0917] In traditional recruitment tests, the challenges of evaluating candidates fairly and providing results quickly have been posed. Manual evaluation consumes a large amount of time and human resources, and it is difficult to ensure fairness. Furthermore, if candidates do not have time to thoroughly consider their answers, they may not receive an appropriate evaluation.

[0918] 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.

[0919] In this invention, the server includes means for verifying authentication information entered by a user via a terminal on the server, means for transmitting test questions from the server to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an artificial intelligence on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, and means for evaluating the submitted answers with the artificial intelligence on the server, generating feedback together with the evaluation results and transmitting it to the terminal. This allows candidates to be evaluated efficiently and fairly, and test results to be obtained quickly.

[0920] "Authentication Information" means information provided by a user to prove his or her identity, and typically includes a user ID and password.

[0921] A "server" is a computer system that processes data and provides services over a network.

[0922] A "terminal" is a device operated by a user, and includes a personal computer, a tablet, a smartphone, and the like.

[0923] "Exam Questions" means questions or tasks designed to assess a candidate's abilities or knowledge.

[0924] An "answer prompt" is text or instructions that assist the user in entering an answer to a test question.

[0925] "Artificial intelligence" refers to computer programs that mimic human intelligence to learn and solve problems.

[0926] "Evaluation" is the process of judging the appropriateness and comprehensiveness of submitted answers and generating scores and feedback.

[0927] "Feedback" refers to advice or comments provided to the user based on the evaluation results.

[0928] overview

[0929] This invention relates to a system in which candidates use artificial intelligence (AI) to answer questions during employment examinations, and the answers are evaluated by AI. The system consists of a terminal, a server, and an AI module, and provides users with a fair and prompt evaluation.

[0930] System configuration

[0931] The system is implemented with the following main components:

[0932] 1. Terminal

[0933] The terminal is a device for user access, and includes a personal computer, tablet, smartphone, etc. The terminal displays a login screen, a screen displaying test questions, and an interface for inputting answer prompts.

[0934] 2. Server

[0935] The server plays a key role in verifying user credentials, sending test questions to the device, and generating and evaluating answers using artificial intelligence. An AI module is installed on the server, which generates and evaluates answers based on prompt input.

[0936] 3. AI Module

[0937] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users, and is responsible for evaluating the final answers submitted and generating scores and feedback. A pre-trained generative AI model (e.g., GPT-3) is used.

[0938] Program processing

[0939] 1. User authentication

[0940] The user enters authentication information (user ID and password) on the login screen displayed on the terminal. This information is sent from the terminal to the server. The server compares it with the database, and if authentication is successful, it sends a list of test questions to the terminal.

[0941] 2. Display of exam questions

[0942] The test question list sent from the server is displayed on the terminal, and the user selects the questions to answer from the displayed test questions.

[0943] 3. Enter the answer prompt

[0944] The user checks the test questions displayed on the terminal and inputs the answer prompt, for example, "Explain the basic principles of programming." This prompt is sent from the terminal to the server.

[0945] 4. AI-generated answers

[0946] The AI ​​module on the server uses a generative AI model to generate an answer based on the prompt received from the user, for example, "The fundamental principles of programming include algorithms, data structures, modularization, and error handling." This answer is then sent back from the server to the device.

[0947] 5. User decides on the final answer

[0948] The user checks the answers generated by the AI ​​on their device, and if necessary, makes corrections to determine the final answer, which is then sent from the device to the server.

[0949] 6. Rating and Feedback on Answers

[0950] The AI ​​module on the server evaluates the final answer and generates a score and feedback (for example, a score of 90) that is sent to the device. The feedback also includes specific advice and comments.

[0951] Specific examples

[0952] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user enters the answer prompt "Explain the basic principles of programming," and the server passes this to the AI ​​module. The AI ​​generates an answer: "The basic principles of programming include algorithms, data structures, modularization, and error handling," and sends it back to the terminal. When the user decides on a final answer and submits it to the server, the AI ​​evaluates it and sends 90 points and feedback to the terminal. This process allows the user to generate answers efficiently and have them evaluated fairly.

[0953] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0954] Program processing flow

[0955] Step 1: Perform user authentication

[0956] The user enters their user ID and password into the login screen on the terminal. This input information is sent to the server as an HTTP request. The server compares the received authentication information with the database, and if authentication is successful, sends a successful authentication response to the terminal. The input is "user123" and "password", and the output is a message indicating successful authentication. Specifically, the server searches the database using the user ID as a key and compares it with the corresponding password.

[0957] Step 2: View the exam questions

[0958] The server sends a pre-set list of test questions to the terminal along with a response of successful authentication. The terminal displays the received test questions on the screen, and the user selects questions to answer from the list. The input is an authentication success message, and the output is a list of test questions. Specifically, the server retrieves the list from a database or configuration file that stores test question data, and sends it to the terminal.

[0959] Step 3: Enter the answer prompts

[0960] The user checks the test questions displayed on the terminal and enters the answer prompt. For example, they enter "Explain the basic principles of programming" and press the send button. The terminal sends this input as an HTTP request to the server. The input is the answer prompt, "Explain the basic principles of programming," and the output is a confirmation of sending the prompt to the server. Specifically, the terminal constructs form data and sends it to the server.

[0961] Step 4: AI-generated answers

[0962] The server passes the prompt received from the device to the AI ​​module. The AI ​​module uses the generative AI model to generate an answer based on the prompt. For example, if the prompt is "Explain the basic principles of programming," the AI ​​generates the answer "The basic principles of programming include algorithms, data structures, modularization, and error handling." The generated answer is sent back from the server to the device. The input is the prompt, and the output is the generated answer. Specifically, the AI ​​module performs natural language processing to generate an answer.

[0963] Step 5: User decides on final answer

[0964] The user checks the AI-generated answer received on their device and makes corrections as necessary. The final answer is sent to the server by pressing the send button. The input is the AI-generated answer and the user's corrections, and the output is the final answer. Specifically, the user edits the answer using a text editor and resubmits it to the server.

[0965] Step 6: Rate and give feedback on your answers

[0966] The server passes the received final answer back to the AI ​​module. The AI ​​module evaluates the answer and generates feedback along with the evaluation result. For example, if the answer is appropriate and comprehensive, feedback of 90 points will be generated. This is sent from the server to the terminal and displayed to the user. The input is the final answer, and the output is the evaluation result and feedback. Specifically, the AI ​​module evaluates based on the set evaluation criteria and generates feedback.

[0967] (Application example 1)

[0968] 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."

[0969] In conventional factory robot operation training, operator candidates are evaluated by human evaluators, which can lead to problems of lack of fairness and speed. Furthermore, there is a lack of systems for efficiently training in operation procedures. This can lead to extended training periods and inefficient operation, negatively impacting corporate productivity.

[0970] 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.

[0971] In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting a training task from the server to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for a generating AI on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, and means for evaluating the submitted answers with the generating AI on the server and transmitting the evaluation results to the terminal, thereby enabling fair and prompt training evaluation and efficient acquisition of operating procedures.

[0972] A "terminal" is a device used by a user for access, such as a smartphone, tablet, or personal computer.

[0973] "Authentication information" refers to the information a user uses to log in to a system, and typically consists of a user ID and password.

[0974] A "server" is a computer system that is connected to a network and performs functions such as user authentication, data processing, and AI evaluation.

[0975] "Training tasks" refer to instructions and problems sent from the server to train potential operators in robot operation.

[0976] An "answer prompt" is a specific question or instruction that a user enters to answer a training task.

[0977] "Generative AI" is an AI model that has the ability to generate answers based on answer prompts from a user and to evaluate those answers.

[0978] The "evaluation result" is the evaluation made by the generating AI on the user's final answer, and is provided to the user as a score or feedback.

[0979] This invention relates to a factory robot operation training evaluation system in which operator candidates answer training questions with the help of AI, and the AI ​​evaluates their answers. This system is composed of a terminal, a server, and a generative AI. Each component and its operation are described in detail below.

[0980] 1. System Configuration

[0981] 1.1 Terminal

[0982] A terminal is a device that users access, such as a smartphone, tablet, or personal computer. The terminal provides a user authentication screen, a display screen for training tasks, and an input interface for answer prompts.

[0983] 1.2 Server

[0984] The server is a computer system connected to the network that authenticates users, provides training assignments, generates answers, and evaluates them. The server has a database that stores user authentication information, training assignments, and evaluation results.

[0985] 1.3 Generative Artificial Intelligence

[0986] Generative AI is an AI model implemented on a server that generates answers based on prompts sent by users and evaluates the final answers submitted. Specifically, a generative AI model (e.g., OpenAI's GPT model) is used.

[0987] 2. Operational Details

[0988] 2.1 User Authentication

[0989] The user enters authentication information (user ID and password) via the terminal. This information is sent from the terminal to the server, which then verifies it against a database. If authentication is successful, the server sends the user a training assignment.

[0990] 2.2 Displaying training tasks and generating response prompts

[0991] The training tasks sent from the server are displayed on the terminal and the user confirms them. The user inputs answer prompts for the training tasks and sends them from the terminal to the server.

[0992] Prompt Sentence Examples

[0993] "Please explain the basic operating procedure for a factory robot. Specifically, how to accurately place part A at position X."

[0994] 2.3 Answer generation and display using AI

[0995] The server-based AI generates an answer based on the user's prompts. The generated answer is then sent back to the terminal and displayed to the user. The user can then review the displayed answer, modify it as necessary, and determine the final answer.

[0996] 2.4 Submission and evaluation of final answers

[0997] When the user submits the final answer to the server, the server-based AI evaluates the answer, and the evaluation results (e.g., score and feedback) are sent to the terminal and provided to the user.

[0998] Specific examples

[0999] When an operator candidate logs into the system using a smartphone, the server performs authentication, and if successful, a training task is sent to the terminal: "Please explain the basic operating procedures for a factory robot. Specifically, please state the steps for placing part A at position X." The candidate enters the answer prompt, "Steps for placing part A at position X," and the server passes this prompt to the generating artificial intelligence. The procedure generated by the AI ​​is checked, and the candidate makes corrections and submits it to the server as the final answer, which the AI ​​evaluates and provides a score and feedback.

[1000] In this way, the system according to the present invention enables operator candidates to be effectively trained with the assistance of AI, and enables fair and rapid evaluation.

[1001] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1002] Step 1:

[1003] The user enters authentication information (user ID and password) via the terminal. The terminal sends this authentication information to the server. The server receives the authentication information and authenticates the user by checking it against a database. If authentication is successful, the server sends a training task to the terminal.

[1004] Input: User ID, Password

[1005] Output: Authentication results, training tasks

[1006] Step 2:

[1007] The training task sent by the server is displayed on the terminal. The user checks the training task through the terminal and inputs an answer prompt. The terminal sends this answer prompt to the server.

[1008] Input: Training task, response prompt

[1009] Output: Answer prompt

[1010] Step 3:

[1011] The server passes the answer prompt received from the terminal to the generative AI model and requests it to generate an answer. The generative AI model generates an answer based on the prompt and returns the result to the server. The server then sends the generated answer to the terminal.

[1012] Input:Answer prompt

[1013] Output: The generated answer

[1014] Step 4:

[1015] The user checks the answer generated by the generative AI model displayed on the terminal, corrects the answer as necessary, and submits it to the server from the terminal as the final answer.

[1016] Input: Generated answers, user corrections

[1017] Output: Final answer

[1018] Step 5:

[1019] The server passes the final answer to the generative AI model and requests an evaluation. The generative AI model evaluates the final answer and returns the evaluation result to the server. The server then sends the evaluation result to the terminal.

[1020] Input: Final answer

[1021] Output: Evaluation results

[1022] Step 6:

[1023] The evaluation results are displayed on the terminal. The user checks the evaluation results and understands the results of the training. The server records the evaluation results in a database for future reference.

[1024] Input: Evaluation result

[1025] Output: Record of evaluation results

[1026] In this way, a system is realized that allows users to train efficiently with the support of AI and have their results evaluated fairly and quickly.

[1027] 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.

[1028] overview

[1029] This invention relates to a system in which candidates use AI and an emotion engine to answer questions during employment tests, and the answers are evaluated by AI. This system is composed of a terminal, a server, an AI module, and an emotion engine, and provides users with fair and prompt evaluations and feedback based on their emotions.

[1030] System configuration

[1031] The system is implemented with the following main components:

[1032] 1. Terminal

[1033] This is a device that users access, such as a PC, tablet, or smartphone. The device displays the login screen, the test question screen, and an interface for entering answer prompts.

[1034] 2. Server

[1035] It verifies the user's authentication information, sends the test questions to the device, and uses AI and emotion engines to generate and evaluate answers.

[1036] 3. AI Module

[1037] It is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users, and is responsible for evaluating the final answers submitted and generating scores and feedback.

[1038] 4. Emotion Engine

[1039] This is a program that analyzes the user's emotions and adjusts the AI's response generation and error messages according to those emotions.

[1040] Program processing

[1041] User operations

[1042] The user enters authentication information (user ID and password) on the login screen. This information is sent from the terminal to the server. The server verifies the authentication information, and if the user is legitimate, a list of test questions is sent to the user terminal. If authentication fails, the emotion engine analyzes the user's emotions and generates an appropriate error message.

[1043] Server authentication and test question transmission

[1044] The server checks the authentication information against a database, and only if successful does it send the test questions to the terminal. The test questions are preset, and the user selects the questions to answer from this list.

[1045] Generate answer prompts

[1046] The user checks the test questions displayed on the terminal and inputs the answer prompts. For example, if the user inputs a prompt such as "Explain the basic principles of programming," the terminal sends this prompt to the server.

[1047] AI-based answer generation and emotion engine usage

[1048] The AI ​​module on the server receives prompts from the user and generates an answer based on the prompts. The generated answer (e.g., "The basic principles of programming include algorithms, data structures, modularization, and error handling") is then sent back to the device. At the same time, the emotion engine analyzes the user's emotions and adjusts the answer accordingly.

[1049] User decides the final answer

[1050] The user checks the answers generated by the AI ​​and decides on the final answer based on the content. If necessary, the user can modify the answer and submit it to the server as the final answer.

[1051] Evaluating answers

[1052] The final answer submitted is then evaluated by the AI ​​module on the server. The AI ​​module evaluates the appropriateness and comprehensiveness of the answer and generates a score and feedback. For example, if a score of 90 is given, the evaluation result and the analysis results from the emotion engine are also recorded.

[1053] Generate an error message when authentication fails

[1054] If the authentication information is incorrect, the emotion engine analyzes the user's emotion, generates an appropriate error message according to that emotion, and sends it to the terminal.

[1055] Specific examples

[1056] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user enters the answer prompt "Explain the basic principles of programming," and the server passes this prompt to the AI ​​module. The AI ​​generates an answer and sends it back to the terminal. At the same time, the emotion engine analyzes the user's emotions and adjusts the expression of the answer based on the user's emotions. When the user decides on a final answer and submits it to the server, the server's AI evaluates it and provides the user with a score (e.g., 90 points) and feedback. The emotion engine's analysis results are also added to the evaluation result and recorded. If authentication fails, the emotion engine adjusts the error message and displays it to the user.

[1057] In this way, the system of the present invention allows users to answer test questions with the help of AI and an emotion engine, quickly and fairly evaluate the answers, and provide feedback based on the user's emotions.

[1058] The processing flow will be explained below.

[1059] Step 1:

[1060] The user enters the user ID "user123" and password "password" on the login screen of the device and presses the login button.

[1061] Step 2:

[1062] The terminal sends the authentication information entered by the user to the server.

[1063] Step 3:

[1064] The server checks the user ID and password against a database.

[1065] Step 4:

[1066] If the server is successful in the authentication, it prepares a list of test questions and sends it to the terminal.

[1067] Step 5:

[1068] If the server fails the authentication, it uses an emotion engine to analyze the user's emotion, generates an appropriate error message, and sends it to the terminal.

[1069] Step 6:

[1070] The terminal receives the test question list and displays it to the user.

[1071] Step 7:

[1072] The user selects any test question and presses the start button.

[1073] Step 8:

[1074] The terminal requests the selected test question from the server and receives details of the question.

[1075] Step 9:

[1076] The terminal displays test questions to the user and provides an interface for entering answer prompts.

[1077] Step 10:

[1078] The user inputs the answer prompt "Explain the basic principles of programming."

[1079] Step 11:

[1080] The terminal sends the entered prompt to the server.

[1081] Step 12:

[1082] The server receives the prompt and passes it to the AI ​​module.

[1083] Step 13:

[1084] The AI ​​(server) generates an answer based on the prompt: "Fundamental principles of programming include algorithms, data structures, modularity, and error handling."

[1085] Step 14:

[1086] The emotion engine (server) analyzes the user's emotions and determines whether the generated answers need to be adjusted.

[1087] Step 15:

[1088] The server sends back to the device an answer generated and adjusted by the AI ​​module and emotion engine.

[1089] Step 16:

[1090] The device receives the answers generated by the AI ​​and emotion engine and displays them to the user.

[1091] Step 17:

[1092] The user checks the AI's answer, corrects it as necessary, and decides on the final answer.

[1093] Step 18:

[1094] The user presses a button to submit the final answer.

[1095] Step 19:

[1096] The terminal sends the user's final answer to the server.

[1097] Step 20:

[1098] The server passes the final answer back to the AI ​​module for evaluation.

[1099] Step 21:

[1100] The AI ​​(server) evaluates the answer, determines that the answer is appropriate and comprehensive, and assigns a score (e.g., 90 points).

[1101] Step 22:

[1102] The emotion engine (server) analyzes the user's emotions regarding the evaluation results and adjusts the feedback.

[1103] Step 23:

[1104] The server records the evaluation results and feedback and sends them to the terminal.

[1105] Step 24:

[1106] The terminal displays the evaluation results to the user.

[1107] Example 2

[1108] 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."

[1109] In conventional recruitment testing systems, it was difficult to quickly and fairly evaluate the answers entered by candidates, and it was also difficult to provide feedback that took into account the candidates' emotions.It was also a challenge to provide an appropriate error message when authentication failed.

[1110] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting test questions to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an AI module on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, means for the AI ​​module on the server to evaluate the submitted answers and transmit the evaluation results to the terminal, and an emotion engine means for analyzing the user's emotions and adjusting the expression of the answers based on the emotions. This makes it possible to quickly and fairly evaluate the answers entered by the user and provide feedback that takes the candidate's emotions into consideration. It is also possible to provide an appropriate error message if authentication fails.

[1111] A "user" is an individual or entity that accesses the system through a terminal, enters authentication information, and answers exam questions.

[1112] A "terminal" is a device through which a user accesses the system, and includes a PC, tablet, smartphone, etc.

[1113] "Server" is a central computer system that verifies user credentials, transmits test questions, and uses AI modules and emotion engines to generate and evaluate answers.

[1114] "Authentication information" means information such as a user ID and password that enables a user to legitimately access a system.

[1115] A "quiz question" is a question or challenge sent by a server for a user to answer, for assessment purposes.

[1116] An "answer prompt" is a command or question that a user enters in response to a test question.

[1117] "AI Module" means an artificial intelligence program implemented on a server that generates answers based on user response prompts and evaluates the final answers submitted.

[1118] The "emotion engine" is a program that analyzes the user's emotions and adjusts the AI ​​module's response and error messages based on those emotions.

[1119] "Evaluation Results" refers to the score and feedback provided by the AI ​​module to evaluate the user's final answer based on its appropriateness and comprehensiveness.

[1120] An "error message" is a notification message that is generated by the server using the emotion engine when user authentication fails, and that is based on the user's emotion.

[1121] This invention relates to a system in which candidates use AI and an emotion engine to answer questions during employment examinations, and the answers are evaluated by AI. This system is composed of a terminal, a server, an AI module, and an emotion engine, and provides users with fair and prompt evaluations and feedback according to their emotions.

[1122] System configuration

[1123] 1. Terminal

[1124] The terminal is the device through which the user accesses the test, such as a PC, tablet, or smartphone. The terminal displays a login screen, a screen displaying test questions, and an interface for entering answer prompts.

[1125] 2. Server

[1126] The server is a central computer system that verifies user credentials, sends test questions to the terminal, and uses AI modules and emotion engines to generate and evaluate answers.

[1127] 3. AI Module

[1128] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by the user and is also responsible for evaluating the final answers submitted and generating scores and feedback.

[1129] 4. Emotion Engine

[1130] The emotion engine is a program that analyzes the user's emotions and adjusts the AI ​​module's response generation and error message display based on those emotions.

[1131] Hardware and software used

[1132] Hardware: PCs, tablets, smartphones

[1133] Software: Server, AI module, emotion engine

[1134] Examples: AI platforms and sentiment analysis APIs implemented on virtual machines

[1135] Specific examples

[1136] The user enters the login information "user123" and "password" and attempts to log in. The server receives this information and checks it against the database. If authentication is successful, the test question "Explain the basic principles of programming" is sent to the terminal.

[1137] The user checks the test questions displayed on the terminal and enters the answer prompt, "Explain the basic principles of programming." The terminal sends this prompt to the server, which passes it to the server's AI module.

[1138] The AI ​​module generates answers based on the prompts, explaining that "fundamental principles of programming include algorithms, data structures, modularization, and error handling." The generated answers are then sent back to the device from the server.

[1139] At the same time, the emotion engine analyzes the user's emotions, and if the user is feeling anxious, for example, it will add a phrase such as "Don't worry, you can solve this problem if you understand it well" and display it.

[1140] The user checks the generated answers, makes corrections as necessary, and decides on the final answer, which is then submitted to the server from the terminal.

[1141] The server then passes the submitted final answer back to the AI ​​module, generates an evaluation score (e.g., 90 points) and feedback, and sends it to the device. The evaluation result also records the analysis results of the emotion engine.

[1142] If authentication fails, the emotion engine analyzes the user's emotions and generates an error message such as "The password you entered is incorrect. Please try again." and sends it to the terminal, providing the user with appropriate feedback.

[1143] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1144] Step 1:

[1145] The user enters authentication information (user ID and password) on the login screen of the terminal. The terminal sends this input information to the server. The input is the user ID and password, and the output is the authentication information sent to the server.

[1146] Step 2:

[1147] The server compares the received authentication information with the database to confirm whether the user is a legitimate user. For example, it retrieves the corresponding user ID and password record from the database and matches it with the entered information. If authentication is successful, the server sends a list of test questions to the terminal. The input is authentication information, and the output is the authentication results and a list of test questions. If there is a mismatch, the emotion engine generates an error message based on the user's emotion and sends it to the terminal.

[1148] Step 3:

[1149] The terminal displays the test questions sent from the server and the user selects the questions to answer. The terminal takes the user's selection as input and sends the selection information to the server. The input is the selection of the test question, and the output is the transmission of the selection information.

[1150] Step 4:

[1151] The user inputs an answer prompt to the multiple-choice question displayed on the terminal. For example, they input "Explain the basic principles of programming." The terminal sends this prompt to the server. The input is the answer prompt, and the output is the sending of the prompt.

[1152] Step 5:

[1153] The server passes the received prompt to the AI ​​module, which then generates an answer based on the prompt. For example, it might generate, "The fundamental principles of programming include algorithms, data structures, modularization, and error handling." The generated answer is then sent back to the terminal. The input is the prompt, and the output is the generated answer.

[1154] Step 6:

[1155] At the same time, the emotion engine analyzes the user's emotions. For example, if the user is anxious, the emotion engine adds a phrase such as "Don't worry, you can solve this problem if you understand it well" to the answer. The input is the user's emotional data, and the output is the adjusted answer. The adjusted answer is then sent back to the device from the server.

[1156] Step 7:

[1157] The user checks the generated answer on the terminal, corrects it if necessary, and decides on the final answer. The corrected final answer is then submitted to the server. The input is the corrected answer, and the output is the transmission of the final answer.

[1158] Step 8:

[1159] The server then passes the submitted final answer back to the AI ​​module, which then evaluates it based on its appropriateness and comprehensiveness. For example, it generates a score of 90. The generated evaluation result and feedback are sent from the server to the device. The input is the final answer, and the output is the evaluation result and feedback.

[1160] Step 9:

[1161] The server records the analysis results of the emotion engine along with the evaluation results to check whether the user's emotions match the server's feedback. The input is the evaluation results and emotion data, and the output is the recorded data.

[1162] Step 10:

[1163] If authentication fails, the server's emotion engine analyzes the user's emotion and generates an appropriate error message based on that emotion. The server then sends this error message to the terminal and displays it to the user. The input is authentication information and emotion data, and the output is an error message.

[1164] In this way, the system allows users to answer test questions with the help of AI and an emotion engine, quickly and fairly evaluates the answers, and provides feedback based on the user's emotions.

[1165] (Application example 2)

[1166] 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."

[1167] In recent years, advances in autonomous driving technology have led to increased demand for passenger safety and comfort. However, conventional autonomous vehicles lack effective means for responding appropriately to passenger questions and resolving their concerns and doubts. This can result in lower passenger satisfaction and a loss of trust in the safety of the vehicle. Therefore, there is a need for a system that can quickly and appropriately respond to passenger questions and adjust feedback by analyzing passenger emotions.

[1168] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting test questions to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an AI on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, means for an AI on the server to evaluate the submitted answers and send the evaluation results to the terminal, and means for analyzing the user's emotions using an emotion analysis engine and adjusting feedback based on the generated answers. This makes it possible to quickly and accurately generate answers to passenger questions and further analyze the passenger's emotions based on the answers to provide appropriate feedback.

[1169] "Means for the server to verify the authentication information entered by the user via the terminal" refers to a function that allows the server to obtain the authentication information entered by the user (e.g., user ID and password) and verify it against pre-set authentication data to perform authentication.

[1170] "Means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful" is a function that allows the server to send test questions to the terminal for a user who has been successfully authenticated and display them.

[1171] The "means for transmitting an answer prompt input by a user from a terminal to a server" is a function for transmitting an answer prompt input by a user to a terminal to a server.

[1172] "Means for AI on the server to generate an answer based on the prompt and return the generated answer to the terminal" refers to a function that allows artificial intelligence (AI) on the server to analyze the prompt, create an answer based on that, and return that answer to the user's terminal.

[1173] "Means for displaying the generated answer to the user and submitting the answer determined as the final answer from the terminal to the server" is a function for displaying the generated answer on the user's terminal, allowing the user to check the answer, determine it as the final answer, and submit it from the terminal to the server.

[1174] "Means for evaluating submitted answers using AI on the server and sending the evaluation results to the terminal" refers to a function for evaluating the final answer submitted by the user using AI on the server and sending the evaluation results to the user's terminal.

[1175] "Means for analyzing a user's emotions using an emotion analysis engine and adjusting feedback based on the generated answer" refers to a function that uses an emotion analysis engine to analyze emotions from the user's facial expressions, voice data, etc., and adjusts the expression and content of the generated answer according to those emotions to provide feedback.

[1176] The system for implementing this invention incorporates AI and an emotion engine into the user interface of an autonomous vehicle. The system components include a terminal, a server, an AI module, and an emotion engine. This section provides a detailed description of each component and how they work together.

[1177] 1. Terminal

[1178] The device could be an infotainment system installed in the autonomous vehicle or a passenger's smartphone or tablet. Users use this device to access the system, enter login information, ask questions, and confirm answers.

[1179] 2. Server

[1180] The server, which can be located in the cloud or in the vehicle, has the following main functions:

[1181] Credentials validation

[1182] Submitting exam questions

[1183] Receiving answer prompts

[1184] AI-powered answer generation

[1185] Sentiment analysis and feedback adjustment

[1186] User response rating

[1187] 3. AI Module

[1188] The AI ​​module uses a generative AI model, such as OpenAI's GPT-4, to generate answers based on prompts entered by the user and send the answers back to the device via a server.

[1189] 4. Emotion Engine

[1190] The emotion engine uses Microsoft Azure's Emotion API and other tools to analyze the user's voice tone and facial expression data to understand the user's emotions in real time. The analyzed emotion data is used to adjust the expression and content of the generated answers.

[1191] Specific examples

[1192] 1. The user enters their login information into the terminal, which is verified by the server. If authentication is successful, the next step is performed.

[1193] 2. The user types a question into the terminal, such as "How long will it take to get to my destination?" The prompt is sent to the server.

[1194] 3. The server's AI module analyzes the prompt and generates an answer such as, "Based on current traffic conditions, about 30 minutes."

[1195] 4. The emotion engine analyzes the user's emotions (e.g., anxiety) and adds feedback to the response as needed, such as "Don't worry, we'll get you to your destination safely."

[1196] 5. The final answer is displayed on the terminal and the user confirms it.

[1197] Prompt Sentence Examples

[1198] "Please tell me how long it will take to get to your destination."

[1199] "Tell me about this car's safety features."

[1200] This system will allow passengers to have any questions or concerns about self-driving vehicles resolved, allowing them to ride with peace of mind.

[1201] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1202] Step 1:

[1203] The user enters authentication information (user ID and password) via the terminal. The terminal sends this to the server. The server receives the authentication information entered by the user and verifies it against the information in the database. If authentication is successful, it sends the test questions to the terminal.

[1204] Input: User ID, Password

[1205] Data processing: The server checks the authentication information against a database

[1206] Output: Authentication success or failure message

[1207] Step 2:

[1208] When the server detects successful authentication, it sends the test questions to the user's terminal, where they are displayed and the user confirms them.

[1209] Input: Authentication success message

[1210] Data processing: Sending exam questions

[1211] Output: Display of exam questions

[1212] Step 3:

[1213] The user inputs answer prompts for the test questions into the terminal, which then sends the prompts to the server.

[1214] Input:Answer prompt

[1215] Data Processing: Send Prompt

[1216] Output: Send prompt to server

[1217] Step 4:

[1218] An AI module on the server analyzes the prompts sent by the user and generates appropriate answers, which are then sent back to the device.

[1219] Input:Answer prompt

[1220] Data processing: prompt analysis and answer generation

[1221] Output: The generated answer

[1222] Step 5:

[1223] The generated answer is displayed on the device. At the same time, the emotion engine analyzes the user's facial expressions and voice data to generate emotional data. This emotional data is sent to the AI ​​module and used to adjust the expression of the answer.

[1224] Input: User's facial expression data, voice data

[1225] Data processing: sentiment analysis, feedback adjustment

[1226] Output: Adjusted answer

[1227] Step 6:

[1228] The adjusted answer is displayed on the terminal. The user checks the displayed answer and, if necessary, modifies and decides on the final answer. The final answer is then submitted to the server.

[1229] Input: Adjusted answer, user confirmation

[1230] Data processing: determining and sending the final answer

[1231] Output: Final response sent

[1232] Step 7:

[1233] The server evaluates the submitted final answer again using the AI ​​module and generates an evaluation result, which is sent to the terminal and displayed to the user.

[1234] Input: Final answer

[1235] Data processing: Evaluation analysis

[1236] Output: Generating and sending evaluation results

[1237] 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.

[1238] 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.

[1239] 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.

[1240] [Fourth embodiment]

[1241] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1242] 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.

[1243] 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).

[1244] 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.

[1245] 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.

[1246] 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).

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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."

[1254] overview

[1255] This invention relates to a system in which candidates use AI to answer questions during employment examinations and the answers are evaluated by AI. This system is composed of terminals, a server, and AI, and provides users with a fair and prompt evaluation.

[1256] System configuration

[1257] The system is implemented with the following main components:

[1258] 1. Terminal

[1259] This is a device that users access, such as a PC, tablet, or smartphone. The device displays the login screen, the test question screen, and an interface for entering answer prompts.

[1260] 2. Server

[1261] The server plays a key role in verifying user authentication information, sending test questions to the device, and generating and evaluating answers using AI. The server is equipped with an AI module that generates and evaluates answers based on prompts.

[1262] 3. AI Module

[1263] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users and is also responsible for evaluating the final answers submitted and generating scores and feedback.

[1264] Program processing

[1265] User operations

[1266] The user enters authentication information (user ID and password) on the login screen. This information is sent from the terminal to the server. The server verifies the authentication information, and if the user is legitimate, a list of test questions is sent to the user terminal.

[1267] Server authentication and test question transmission

[1268] The server checks the authentication information against a database, and only if successful does it send the test questions to the terminal. The test questions are preset, and the user selects the questions to answer from this list.

[1269] Generate answer prompts

[1270] The user checks the test questions displayed on the terminal and inputs the answer prompts. For example, if the user inputs a prompt such as "Explain the basic principles of programming," the terminal sends the prompt to the server.

[1271] AI-powered answer generation

[1272] The AI ​​module on the server receives prompts from the user and generates an answer based on the prompts. The answer (e.g., "The fundamental principles of programming include algorithms, data structures, modularization, and error handling") is then sent back to the device.

[1273] User decides the final answer

[1274] The user checks the answers generated by the AI ​​and decides on the final answer based on the content. If necessary, the user can modify the answer and submit it to the server as the final answer.

[1275] Evaluating answers

[1276] The final answer submitted is then evaluated by the AI ​​module on the server. The AI ​​module evaluates the appropriateness and comprehensiveness of the answer and generates a score and feedback. For example, if a score of 90 is given, this is sent to the terminal along with the evaluation result.

[1277] Specific examples

[1278] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user then enters the answer prompt "Explain the basic principles of programming," and the server passes this prompt to the AI ​​module. The AI ​​generates an answer and sends it back to the terminal. When the user decides on the final answer and submits it to the server, the server's AI evaluates it and provides the user with a score and feedback.

[1279] In this way, the system according to the present invention allows users to answer test questions with the help of AI and have their answers evaluated quickly and fairly.

[1280] The processing flow will be explained below.

[1281] Step 1:

[1282] The user enters the user ID "user123" and password "password" on the login screen of the device and presses the login button.

[1283] Step 2:

[1284] The terminal sends the authentication information entered by the user to the server.

[1285] Step 3:

[1286] The server checks the user ID and password against an authentication database.

[1287] Step 4:

[1288] If the server is successful in the authentication, it prepares a test question list and sends it to the terminal, otherwise it sends an error message to the terminal.

[1289] Step 5:

[1290] The terminal receives the test question list and displays it to the user.

[1291] Step 6:

[1292] The user selects any test question and presses the start button.

[1293] Step 7:

[1294] The terminal requests the selected test question from the server and receives details of the question.

[1295] Step 8:

[1296] The terminal displays test questions to the user and provides an interface for entering answer prompts.

[1297] Step 9:

[1298] The user inputs the answer prompt "Explain the basic principles of programming."

[1299] Step 10:

[1300] The terminal sends the entered prompt to the server.

[1301] Step 11:

[1302] The server receives the prompt and passes it to the AI ​​module.

[1303] Step 12:

[1304] Based on the prompt, the AI ​​(server) generates an answer: "The fundamental principles of programming include algorithms, data structures, modularization, and error handling" and sends it back to the terminal via the server.

[1305] Step 13:

[1306] The device receives the AI-generated answer and displays it to the user.

[1307] Step 14:

[1308] The user checks the AI's answer, corrects it as necessary, and decides on the final answer.

[1309] Step 15:

[1310] The user presses a button to submit the final answer.

[1311] Step 16:

[1312] The terminal sends the user's final answer to the server.

[1313] Step 17:

[1314] The server passes the final answer back to the AI ​​module for evaluation.

[1315] Step 18:

[1316] The AI ​​(server) evaluates the answer, determines that the answer is appropriate and comprehensive, and assigns a score (e.g., 90 points).

[1317] Step 19:

[1318] The server records the evaluation results and feedback and sends them to the device.

[1319] Step 20:

[1320] The terminal displays the evaluation results to the user.

[1321] Example 1

[1322] 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."

[1323] In traditional recruitment tests, the challenges of evaluating candidates fairly and providing results quickly have been posed. Manual evaluation consumes a large amount of time and human resources, and it is difficult to ensure fairness. Furthermore, if candidates do not have time to thoroughly consider their answers, they may not receive an appropriate evaluation.

[1324] 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.

[1325] In this invention, the server includes means for verifying authentication information entered by a user via a terminal on the server, means for transmitting test questions from the server to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an artificial intelligence on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, and means for evaluating the submitted answers with the artificial intelligence on the server, generating feedback together with the evaluation results and transmitting it to the terminal. This allows candidates to be evaluated efficiently and fairly, and test results to be obtained quickly.

[1326] "Authentication Information" means information provided by a user to prove his or her identity, and typically includes a user ID and password.

[1327] A "server" is a computer system that processes data and provides services over a network.

[1328] A "terminal" is a device operated by a user, and includes a personal computer, a tablet, a smartphone, and the like.

[1329] "Exam Questions" means questions or tasks designed to assess a candidate's abilities or knowledge.

[1330] An "answer prompt" is text or instructions that assist the user in entering an answer to a test question.

[1331] "Artificial intelligence" refers to computer programs that mimic human intelligence to learn and solve problems.

[1332] "Evaluation" is the process of judging the appropriateness and comprehensiveness of submitted answers and generating scores and feedback.

[1333] "Feedback" refers to advice or comments provided to the user based on the evaluation results.

[1334] overview

[1335] This invention relates to a system in which candidates use artificial intelligence (AI) to answer questions during employment examinations, and the answers are evaluated by AI. The system consists of a terminal, a server, and an AI module, and provides users with a fair and prompt evaluation.

[1336] System configuration

[1337] The system is implemented with the following main components:

[1338] 1. Terminal

[1339] The terminal is a device for user access, and includes a personal computer, tablet, smartphone, etc. The terminal displays a login screen, a screen displaying test questions, and an interface for inputting answer prompts.

[1340] 2. Server

[1341] The server plays a key role in verifying user credentials, sending test questions to the device, and generating and evaluating answers using artificial intelligence. An AI module is installed on the server, which generates and evaluates answers based on prompt input.

[1342] 3. AI Module

[1343] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users, and is responsible for evaluating the final answers submitted and generating scores and feedback. A pre-trained generative AI model (e.g., GPT-3) is used.

[1344] Program processing

[1345] 1. User authentication

[1346] The user enters authentication information (user ID and password) on the login screen displayed on the terminal. This information is sent from the terminal to the server. The server compares it with the database, and if authentication is successful, it sends a list of test questions to the terminal.

[1347] 2. Display of exam questions

[1348] The test question list sent from the server is displayed on the terminal, and the user selects the questions to answer from the displayed test questions.

[1349] 3. Enter the answer prompt

[1350] The user checks the test questions displayed on the terminal and inputs the answer prompt, for example, "Explain the basic principles of programming." This prompt is sent from the terminal to the server.

[1351] 4. AI-generated answers

[1352] The AI ​​module on the server uses a generative AI model to generate an answer based on the prompt received from the user, for example, "The fundamental principles of programming include algorithms, data structures, modularization, and error handling." This answer is then sent back from the server to the device.

[1353] 5. User decides on the final answer

[1354] The user checks the answers generated by the AI ​​on their device, and if necessary, makes corrections to determine the final answer, which is then sent from the device to the server.

[1355] 6. Rating and Feedback on Answers

[1356] The AI ​​module on the server evaluates the final answer and generates a score and feedback (for example, a score of 90) that is sent to the device. The feedback also includes specific advice and comments.

[1357] Specific examples

[1358] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user enters the answer prompt "Explain the basic principles of programming," and the server passes this to the AI ​​module. The AI ​​generates an answer: "The basic principles of programming include algorithms, data structures, modularization, and error handling," and sends it back to the terminal. When the user decides on a final answer and submits it to the server, the AI ​​evaluates it and sends 90 points and feedback to the terminal. This process allows the user to generate answers efficiently and have them evaluated fairly.

[1359] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1360] Program processing flow

[1361] Step 1: Perform user authentication

[1362] The user enters their user ID and password into the login screen on the terminal. This input information is sent to the server as an HTTP request. The server compares the received authentication information with the database, and if authentication is successful, sends a successful authentication response to the terminal. The input is "user123" and "password", and the output is a message indicating successful authentication. Specifically, the server searches the database using the user ID as a key and compares it with the corresponding password.

[1363] Step 2: View the exam questions

[1364] The server sends a pre-set list of test questions to the terminal along with a response of successful authentication. The terminal displays the received test questions on the screen, and the user selects questions to answer from the list. The input is an authentication success message, and the output is a list of test questions. Specifically, the server retrieves the list from a database or configuration file that stores test question data, and sends it to the terminal.

[1365] Step 3: Enter the answer prompts

[1366] The user checks the test questions displayed on the terminal and enters the answer prompt. For example, they enter "Explain the basic principles of programming" and press the send button. The terminal sends this input as an HTTP request to the server. The input is the answer prompt, "Explain the basic principles of programming," and the output is a confirmation of sending the prompt to the server. Specifically, the terminal constructs form data and sends it to the server.

[1367] Step 4: AI-generated answers

[1368] The server passes the prompt received from the device to the AI ​​module. The AI ​​module uses the generative AI model to generate an answer based on the prompt. For example, if the prompt is "Explain the basic principles of programming," the AI ​​generates the answer "The basic principles of programming include algorithms, data structures, modularization, and error handling." The generated answer is sent back from the server to the device. The input is the prompt, and the output is the generated answer. Specifically, the AI ​​module performs natural language processing to generate an answer.

[1369] Step 5: User decides on final answer

[1370] The user checks the AI-generated answer received on their device and makes corrections as necessary. The final answer is sent to the server by pressing the send button. The input is the AI-generated answer and the user's corrections, and the output is the final answer. Specifically, the user edits the answer using a text editor and resubmits it to the server.

[1371] Step 6: Rate and give feedback on your answers

[1372] The server passes the received final answer back to the AI ​​module. The AI ​​module evaluates the answer and generates feedback along with the evaluation result. For example, if the answer is appropriate and comprehensive, feedback of 90 points will be generated. This is sent from the server to the terminal and displayed to the user. The input is the final answer, and the output is the evaluation result and feedback. Specifically, the AI ​​module evaluates based on the set evaluation criteria and generates feedback.

[1373] (Application example 1)

[1374] 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."

[1375] In conventional factory robot operation training, operator candidates are evaluated by human evaluators, which can lead to problems of lack of fairness and speed. Furthermore, there is a lack of systems for efficiently training in operation procedures. This can lead to extended training periods and inefficient operation, negatively impacting corporate productivity.

[1376] 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.

[1377] In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting a training task from the server to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for a generating AI on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, and means for evaluating the submitted answers with the generating AI on the server and transmitting the evaluation results to the terminal, thereby enabling fair and prompt training evaluation and efficient acquisition of operating procedures.

[1378] A "terminal" is a device used by a user for access, such as a smartphone, tablet, or personal computer.

[1379] "Authentication information" refers to the information a user uses to log in to a system, and typically consists of a user ID and password.

[1380] A "server" is a computer system that is connected to a network and performs functions such as user authentication, data processing, and AI evaluation.

[1381] "Training tasks" refer to instructions and problems sent from the server to train potential operators in robot operation.

[1382] An "answer prompt" is a specific question or instruction that a user enters to answer a training task.

[1383] "Generative AI" is an AI model that has the ability to generate answers based on answer prompts from a user and to evaluate those answers.

[1384] The "evaluation result" is the evaluation made by the generating AI on the user's final answer, and is provided to the user as a score or feedback.

[1385] This invention relates to a factory robot operation training evaluation system in which operator candidates answer training questions with the help of AI, and the AI ​​evaluates their answers. This system is composed of a terminal, a server, and a generative AI. Each component and its operation are described in detail below.

[1386] 1. System Configuration

[1387] 1.1 Terminal

[1388] A terminal is a device that users access, such as a smartphone, tablet, or personal computer. The terminal provides a user authentication screen, a display screen for training tasks, and an input interface for answer prompts.

[1389] 1.2 Server

[1390] The server is a computer system connected to the network that authenticates users, provides training assignments, generates answers, and evaluates them. The server has a database that stores user authentication information, training assignments, and evaluation results.

[1391] 1.3 Generative Artificial Intelligence

[1392] Generative AI is an AI model implemented on a server that generates answers based on prompts sent by users and evaluates the final answers submitted. Specifically, a generative AI model (e.g., OpenAI's GPT model) is used.

[1393] 2. Operational Details

[1394] 2.1 User Authentication

[1395] The user enters authentication information (user ID and password) via the terminal. This information is sent from the terminal to the server, which then verifies it against a database. If authentication is successful, the server sends the user a training assignment.

[1396] 2.2 Displaying training tasks and generating response prompts

[1397] The training tasks sent from the server are displayed on the terminal and the user confirms them. The user inputs answer prompts for the training tasks and sends them from the terminal to the server.

[1398] Prompt Sentence Examples

[1399] "Please explain the basic operating procedure for a factory robot. Specifically, how to accurately place part A at position X."

[1400] 2.3 Answer generation and display using AI

[1401] The server-based AI generates an answer based on the user's prompts. The generated answer is then sent back to the terminal and displayed to the user. The user can then review the displayed answer, modify it as necessary, and determine the final answer.

[1402] 2.4 Submission and evaluation of final answers

[1403] When the user submits the final answer to the server, the server-based AI evaluates the answer, and the evaluation results (e.g., score and feedback) are sent to the terminal and provided to the user.

[1404] Specific examples

[1405] When an operator candidate logs into the system using a smartphone, the server performs authentication, and if successful, a training task is sent to the terminal: "Please explain the basic operating procedures for a factory robot. Specifically, please state the steps for placing part A at position X." The candidate enters the answer prompt, "Steps for placing part A at position X," and the server passes this prompt to the generating artificial intelligence. The procedure generated by the AI ​​is checked, and the candidate makes corrections and submits it to the server as the final answer, which the AI ​​evaluates and provides a score and feedback.

[1406] In this way, the system according to the present invention enables operator candidates to be effectively trained with the assistance of AI, and enables fair and rapid evaluation.

[1407] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1408] Step 1:

[1409] The user enters authentication information (user ID and password) via the terminal. The terminal sends this authentication information to the server. The server receives the authentication information and authenticates the user by checking it against a database. If authentication is successful, the server sends a training task to the terminal.

[1410] Input: User ID, Password

[1411] Output: Authentication results, training tasks

[1412] Step 2:

[1413] The training task sent by the server is displayed on the terminal. The user checks the training task through the terminal and inputs an answer prompt. The terminal sends this answer prompt to the server.

[1414] Input: Training task, response prompt

[1415] Output: Answer prompt

[1416] Step 3:

[1417] The server passes the answer prompt received from the terminal to the generative AI model and requests it to generate an answer. The generative AI model generates an answer based on the prompt and returns the result to the server. The server then sends the generated answer to the terminal.

[1418] Input:Answer prompt

[1419] Output: The generated answer

[1420] Step 4:

[1421] The user checks the answer generated by the generative AI model displayed on the terminal, corrects the answer as necessary, and submits it to the server from the terminal as the final answer.

[1422] Input: Generated answers, user corrections

[1423] Output: Final answer

[1424] Step 5:

[1425] The server passes the final answer to the generative AI model and requests an evaluation. The generative AI model evaluates the final answer and returns the evaluation result to the server. The server then sends the evaluation result to the terminal.

[1426] Input: Final answer

[1427] Output: Evaluation results

[1428] Step 6:

[1429] The evaluation results are displayed on the terminal. The user checks the evaluation results and understands the results of the training. The server records the evaluation results in a database for future reference.

[1430] Input: Evaluation result

[1431] Output: Record of evaluation results

[1432] In this way, a system is realized that allows users to train efficiently with the support of AI and have their results evaluated fairly and quickly.

[1433] 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.

[1434] overview

[1435] This invention relates to a system in which candidates use AI and an emotion engine to answer questions during employment tests, and the answers are evaluated by AI. This system is composed of a terminal, a server, an AI module, and an emotion engine, and provides users with fair and prompt evaluations and feedback based on their emotions.

[1436] System configuration

[1437] The system is implemented with the following main components:

[1438] 1. Terminal

[1439] This is a device that users access, such as a PC, tablet, or smartphone. The device displays the login screen, the test question screen, and an interface for entering answer prompts.

[1440] 2. Server

[1441] It verifies the user's authentication information, sends the test questions to the device, and uses AI and emotion engines to generate and evaluate answers.

[1442] 3. AI Module

[1443] It is an artificial intelligence program implemented on a server that generates answers based on prompts sent by users, and is responsible for evaluating the final answers submitted and generating scores and feedback.

[1444] 4. Emotion Engine

[1445] This is a program that analyzes the user's emotions and adjusts the AI's response generation and error messages according to those emotions.

[1446] Program processing

[1447] User operations

[1448] The user enters authentication information (user ID and password) on the login screen. This information is sent from the terminal to the server. The server verifies the authentication information, and if the user is legitimate, a list of test questions is sent to the user terminal. If authentication fails, the emotion engine analyzes the user's emotions and generates an appropriate error message.

[1449] Server authentication and test question transmission

[1450] The server checks the authentication information against a database, and only if successful does it send the test questions to the terminal. The test questions are preset, and the user selects the questions to answer from this list.

[1451] Generate answer prompts

[1452] The user checks the test questions displayed on the terminal and inputs the answer prompts. For example, if the user inputs a prompt such as "Explain the basic principles of programming," the terminal sends this prompt to the server.

[1453] AI-based answer generation and emotion engine usage

[1454] The AI ​​module on the server receives prompts from the user and generates an answer based on the prompts. The generated answer (e.g., "The basic principles of programming include algorithms, data structures, modularization, and error handling") is then sent back to the device. At the same time, the emotion engine analyzes the user's emotions and adjusts the answer accordingly.

[1455] User decides the final answer

[1456] The user checks the answers generated by the AI ​​and decides on the final answer based on the content. If necessary, the user can modify the answer and submit it to the server as the final answer.

[1457] Evaluating answers

[1458] The final answer submitted is then evaluated by the AI ​​module on the server. The AI ​​module evaluates the appropriateness and comprehensiveness of the answer and generates a score and feedback. For example, if a score of 90 is given, the evaluation result and the analysis results from the emotion engine are also recorded.

[1459] Generate an error message when authentication fails

[1460] If the authentication information is incorrect, the emotion engine analyzes the user's emotion, generates an appropriate error message according to that emotion, and sends it to the terminal.

[1461] Specific examples

[1462] When a user logs in by entering the login information "user123" and "password," the server performs authentication, and if successful, sends the test question "Please explain the basic principles of programming" to the terminal. The user enters the answer prompt "Explain the basic principles of programming," and the server passes this prompt to the AI ​​module. The AI ​​generates an answer and sends it back to the terminal. At the same time, the emotion engine analyzes the user's emotions and adjusts the expression of the answer based on the user's emotions. When the user decides on a final answer and submits it to the server, the server's AI evaluates it and provides the user with a score (e.g., 90 points) and feedback. The emotion engine's analysis results are also added to the evaluation result and recorded. If authentication fails, the emotion engine adjusts the error message and displays it to the user.

[1463] In this way, the system of the present invention allows users to answer test questions with the help of AI and an emotion engine, quickly and fairly evaluate the answers, and provide feedback based on the user's emotions.

[1464] The processing flow will be explained below.

[1465] Step 1:

[1466] The user enters the user ID "user123" and password "password" on the login screen of the device and presses the login button.

[1467] Step 2:

[1468] The terminal sends the authentication information entered by the user to the server.

[1469] Step 3:

[1470] The server checks the user ID and password against a database.

[1471] Step 4:

[1472] If the server is successful in the authentication, it prepares a list of test questions and sends it to the terminal.

[1473] Step 5:

[1474] If the server fails the authentication, it uses an emotion engine to analyze the user's emotion, generates an appropriate error message, and sends it to the terminal.

[1475] Step 6:

[1476] The terminal receives the test question list and displays it to the user.

[1477] Step 7:

[1478] The user selects any test question and presses the start button.

[1479] Step 8:

[1480] The terminal requests the selected test question from the server and receives details of the question.

[1481] Step 9:

[1482] The terminal displays test questions to the user and provides an interface for entering answer prompts.

[1483] Step 10:

[1484] The user inputs the answer prompt "Explain the basic principles of programming."

[1485] Step 11:

[1486] The terminal sends the entered prompt to the server.

[1487] Step 12:

[1488] The server receives the prompt and passes it to the AI ​​module.

[1489] Step 13:

[1490] The AI ​​(server) generates an answer based on the prompt: "Fundamental principles of programming include algorithms, data structures, modularity, and error handling."

[1491] Step 14:

[1492] The emotion engine (server) analyzes the user's emotions and determines whether the generated answers need to be adjusted.

[1493] Step 15:

[1494] The server sends back to the device an answer generated and adjusted by the AI ​​module and emotion engine.

[1495] Step 16:

[1496] The device receives the answers generated by the AI ​​and emotion engine and displays them to the user.

[1497] Step 17:

[1498] The user checks the AI's answer, corrects it as necessary, and decides on the final answer.

[1499] Step 18:

[1500] The user presses a button to submit the final answer.

[1501] Step 19:

[1502] The terminal sends the user's final answer to the server.

[1503] Step 20:

[1504] The server passes the final answer back to the AI ​​module for evaluation.

[1505] Step 21:

[1506] The AI ​​(server) evaluates the answer, determines that the answer is appropriate and comprehensive, and assigns a score (e.g., 90 points).

[1507] Step 22:

[1508] The emotion engine (server) analyzes the user's emotions regarding the evaluation results and adjusts the feedback.

[1509] Step 23:

[1510] The server records the evaluation results and feedback and sends them to the terminal.

[1511] Step 24:

[1512] The terminal displays the evaluation results to the user.

[1513] Example 2

[1514] 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."

[1515] In conventional recruitment testing systems, it was difficult to quickly and fairly evaluate the answers entered by candidates, and it was also difficult to provide feedback that took into account the candidates' emotions.It was also a challenge to provide an appropriate error message when authentication failed.

[1516] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting test questions to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an AI module on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, means for the AI ​​module on the server to evaluate the submitted answers and transmit the evaluation results to the terminal, and an emotion engine means for analyzing the user's emotions and adjusting the expression of the answers based on the emotions. This makes it possible to quickly and fairly evaluate the answers entered by the user and provide feedback that takes the candidate's emotions into consideration. It is also possible to provide an appropriate error message if authentication fails.

[1517] A "user" is an individual or entity that accesses the system through a terminal, enters authentication information, and answers exam questions.

[1518] A "terminal" is a device through which a user accesses the system, and includes a PC, tablet, smartphone, etc.

[1519] "Server" is a central computer system that verifies user credentials, transmits test questions, and uses AI modules and emotion engines to generate and evaluate answers.

[1520] "Authentication information" means information such as a user ID and password that enables a user to legitimately access a system.

[1521] A "quiz question" is a question or challenge sent by a server for a user to answer, for assessment purposes.

[1522] An "answer prompt" is a command or question that a user enters in response to a test question.

[1523] "AI Module" means an artificial intelligence program implemented on a server that generates answers based on user response prompts and evaluates the final answers submitted.

[1524] The "emotion engine" is a program that analyzes the user's emotions and adjusts the AI ​​module's response and error messages based on those emotions.

[1525] "Evaluation Results" refers to the score and feedback provided by the AI ​​module to evaluate the user's final answer based on its appropriateness and comprehensiveness.

[1526] An "error message" is a notification message that is generated by the server using the emotion engine when user authentication fails, and that is based on the user's emotion.

[1527] This invention relates to a system in which candidates use AI and an emotion engine to answer questions during employment examinations, and the answers are evaluated by AI. This system is composed of a terminal, a server, an AI module, and an emotion engine, and provides users with fair and prompt evaluations and feedback according to their emotions.

[1528] System configuration

[1529] 1. Terminal

[1530] The terminal is the device through which the user accesses the test, such as a PC, tablet, or smartphone. The terminal displays a login screen, a screen displaying test questions, and an interface for entering answer prompts.

[1531] 2. Server

[1532] The server is a central computer system that verifies user credentials, sends test questions to the terminal, and uses AI modules and emotion engines to generate and evaluate answers.

[1533] 3. AI Module

[1534] The AI ​​module is an artificial intelligence program implemented on a server that generates answers based on prompts sent by the user and is also responsible for evaluating the final answers submitted and generating scores and feedback.

[1535] 4. Emotion Engine

[1536] The emotion engine is a program that analyzes the user's emotions and adjusts the AI ​​module's response generation and error message display based on those emotions.

[1537] Hardware and software used

[1538] Hardware: PCs, tablets, smartphones

[1539] Software: Server, AI module, emotion engine

[1540] Examples: AI platforms and sentiment analysis APIs implemented on virtual machines

[1541] Specific examples

[1542] The user enters the login information "user123" and "password" and attempts to log in. The server receives this information and checks it against the database. If authentication is successful, the test question "Explain the basic principles of programming" is sent to the terminal.

[1543] The user checks the test questions displayed on the terminal and enters the answer prompt, "Explain the basic principles of programming." The terminal sends this prompt to the server, which passes it to the server's AI module.

[1544] The AI ​​module generates answers based on the prompts, explaining that "fundamental principles of programming include algorithms, data structures, modularization, and error handling." The generated answers are then sent back to the device from the server.

[1545] At the same time, the emotion engine analyzes the user's emotions, and if the user is feeling anxious, for example, it will add a phrase such as "Don't worry, you can solve this problem if you understand it well" and display it.

[1546] The user checks the generated answers, makes corrections as necessary, and decides on the final answer, which is then submitted to the server from the terminal.

[1547] The server then passes the submitted final answer back to the AI ​​module, generates an evaluation score (e.g., 90 points) and feedback, and sends it to the device. The evaluation result also records the analysis results of the emotion engine.

[1548] If authentication fails, the emotion engine analyzes the user's emotions and generates an error message such as "The password you entered is incorrect. Please try again." and sends it to the terminal, providing the user with appropriate feedback.

[1549] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1550] Step 1:

[1551] The user enters authentication information (user ID and password) on the login screen of the terminal. The terminal sends this input information to the server. The input is the user ID and password, and the output is the authentication information sent to the server.

[1552] Step 2:

[1553] The server compares the received authentication information with the database to confirm whether the user is a legitimate user. For example, it retrieves the corresponding user ID and password record from the database and matches it with the entered information. If authentication is successful, the server sends a list of test questions to the terminal. The input is authentication information, and the output is the authentication results and a list of test questions. If there is a mismatch, the emotion engine generates an error message based on the user's emotion and sends it to the terminal.

[1554] Step 3:

[1555] The terminal displays the test questions sent from the server and the user selects the questions to answer. The terminal takes the user's selection as input and sends the selection information to the server. The input is the selection of the test question, and the output is the transmission of the selection information.

[1556] Step 4:

[1557] The user inputs an answer prompt to the multiple-choice question displayed on the terminal. For example, they input "Explain the basic principles of programming." The terminal sends this prompt to the server. The input is the answer prompt, and the output is the sending of the prompt.

[1558] Step 5:

[1559] The server passes the received prompt to the AI ​​module, which then generates an answer based on the prompt. For example, it might generate, "The fundamental principles of programming include algorithms, data structures, modularization, and error handling." The generated answer is then sent back to the terminal. The input is the prompt, and the output is the generated answer.

[1560] Step 6:

[1561] At the same time, the emotion engine analyzes the user's emotions. For example, if the user is anxious, the emotion engine adds a phrase such as "Don't worry, you can solve this problem if you understand it well" to the answer. The input is the user's emotional data, and the output is the adjusted answer. The adjusted answer is then sent back to the device from the server.

[1562] Step 7:

[1563] The user checks the generated answer on the terminal, corrects it if necessary, and decides on the final answer. The corrected final answer is then submitted to the server. The input is the corrected answer, and the output is the transmission of the final answer.

[1564] Step 8:

[1565] The server then passes the submitted final answer back to the AI ​​module, which then evaluates it based on its appropriateness and comprehensiveness. For example, it generates a score of 90. The generated evaluation result and feedback are sent from the server to the device. The input is the final answer, and the output is the evaluation result and feedback.

[1566] Step 9:

[1567] The server records the analysis results of the emotion engine along with the evaluation results to check whether the user's emotions match the server's feedback. The input is the evaluation results and emotion data, and the output is the recorded data.

[1568] Step 10:

[1569] If authentication fails, the server's emotion engine analyzes the user's emotion and generates an appropriate error message based on that emotion. The server then sends this error message to the terminal and displays it to the user. The input is authentication information and emotion data, and the output is an error message.

[1570] In this way, the system allows users to answer test questions with the help of AI and an emotion engine, quickly and fairly evaluates the answers, and provides feedback based on the user's emotions.

[1571] (Application example 2)

[1572] 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."

[1573] In recent years, advances in autonomous driving technology have led to increased demand for passenger safety and comfort. However, conventional autonomous vehicles lack effective means for responding appropriately to passenger questions and resolving their concerns and doubts. This can result in lower passenger satisfaction and a loss of trust in the safety of the vehicle. Therefore, there is a need for a system that can quickly and appropriately respond to passenger questions and adjust feedback by analyzing passenger emotions.

[1574] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for verifying authentication information entered by a user via a terminal, means for transmitting test questions to the terminal to be displayed to the user if authentication is successful, means for transmitting answer prompts entered by the user from the terminal to the server, means for an AI on the server to generate answers based on the prompts and return the generated answers to the terminal, means for displaying the generated answers to the user and submitting an answer determined as a final answer from the terminal to the server, means for an AI on the server to evaluate the submitted answers and send the evaluation results to the terminal, and means for analyzing the user's emotions using an emotion analysis engine and adjusting feedback based on the generated answers. This makes it possible to quickly and accurately generate answers to passenger questions and further analyze the passenger's emotions based on the answers to provide appropriate feedback.

[1575] "Means for the server to verify the authentication information entered by the user via the terminal" refers to a function that allows the server to obtain the authentication information entered by the user (e.g., user ID and password) and verify it against pre-set authentication data to perform authentication.

[1576] "Means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful" is a function that allows the server to send test questions to the terminal for a user who has been successfully authenticated and display them.

[1577] The "means for transmitting an answer prompt input by a user from a terminal to a server" is a function for transmitting an answer prompt input by a user to a terminal to a server.

[1578] "Means for AI on the server to generate an answer based on the prompt and return the generated answer to the terminal" refers to a function that allows artificial intelligence (AI) on the server to analyze the prompt, create an answer based on that, and return that answer to the user's terminal.

[1579] "Means for displaying the generated answer to the user and submitting the answer determined as the final answer from the terminal to the server" is a function for displaying the generated answer on the user's terminal, allowing the user to check the answer, determine it as the final answer, and submit it from the terminal to the server.

[1580] "Means for evaluating submitted answers using AI on the server and sending the evaluation results to the terminal" refers to a function for evaluating the final answer submitted by the user using AI on the server and sending the evaluation results to the user's terminal.

[1581] "Means for analyzing a user's emotions using an emotion analysis engine and adjusting feedback based on the generated answer" refers to a function that uses an emotion analysis engine to analyze emotions from the user's facial expressions, voice data, etc., and adjusts the expression and content of the generated answer according to those emotions to provide feedback.

[1582] The system for implementing this invention incorporates AI and an emotion engine into the user interface of an autonomous vehicle. The system components include a terminal, a server, an AI module, and an emotion engine. This section provides a detailed description of each component and how they work together.

[1583] 1. Terminal

[1584] The device could be an infotainment system installed in the autonomous vehicle or a passenger's smartphone or tablet. Users use this device to access the system, enter login information, ask questions, and confirm answers.

[1585] 2. Server

[1586] The server, which can be located in the cloud or in the vehicle, has the following main functions:

[1587] Credentials validation

[1588] Submitting exam questions

[1589] Receiving answer prompts

[1590] AI-powered answer generation

[1591] Sentiment analysis and feedback adjustment

[1592] User response rating

[1593] 3. AI Module

[1594] The AI ​​module uses a generative AI model, such as OpenAI's GPT-4, to generate answers based on prompts entered by the user and send the answers back to the device via a server.

[1595] 4. Emotion Engine

[1596] The emotion engine uses Microsoft Azure's Emotion API and other tools to analyze the user's voice tone and facial expression data to understand the user's emotions in real time. The analyzed emotion data is used to adjust the expression and content of the generated answers.

[1597] Specific examples

[1598] 1. The user enters their login information into the terminal, which is verified by the server. If authentication is successful, the next step is performed.

[1599] 2. The user types a question into the terminal, such as "How long will it take to get to my destination?" The prompt is sent to the server.

[1600] 3. The server's AI module analyzes the prompt and generates an answer such as, "Based on current traffic conditions, about 30 minutes."

[1601] 4. The emotion engine analyzes the user's emotions (e.g., anxiety) and adds feedback to the response as needed, such as "Don't worry, we'll get you to your destination safely."

[1602] 5. The final answer is displayed on the terminal and the user confirms it.

[1603] Prompt Sentence Examples

[1604] "Please tell me how long it will take to get to your destination."

[1605] "Tell me about this car's safety features."

[1606] This system will allow passengers to have any questions or concerns about self-driving vehicles resolved, allowing them to ride with peace of mind.

[1607] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1608] Step 1:

[1609] The user enters authentication information (user ID and password) via the terminal. The terminal sends this to the server. The server receives the authentication information entered by the user and verifies it against the information in the database. If authentication is successful, it sends the test questions to the terminal.

[1610] Input: User ID, Password

[1611] Data processing: The server checks the authentication information against a database

[1612] Output: Authentication success or failure message

[1613] Step 2:

[1614] When the server detects successful authentication, it sends the test questions to the user's terminal, where they are displayed and the user confirms them.

[1615] Input: Authentication success message

[1616] Data processing: Sending exam questions

[1617] Output: Display of exam questions

[1618] Step 3:

[1619] The user inputs answer prompts for the test questions into the terminal, which then sends the prompts to the server.

[1620] Input:Answer prompt

[1621] Data Processing: Send Prompt

[1622] Output: Send prompt to server

[1623] Step 4:

[1624] An AI module on the server analyzes the prompts sent by the user and generates appropriate answers, which are then sent back to the device.

[1625] Input:Answer prompt

[1626] Data processing: prompt analysis and answer generation

[1627] Output: The generated answer

[1628] Step 5:

[1629] The generated answer is displayed on the device. At the same time, the emotion engine analyzes the user's facial expressions and voice data to generate emotional data. This emotional data is sent to the AI ​​module and used to adjust the expression of the answer.

[1630] Input: User's facial expression data, voice data

[1631] Data processing: sentiment analysis, feedback adjustment

[1632] Output: Adjusted answer

[1633] Step 6:

[1634] The adjusted answer is displayed on the terminal. The user checks the displayed answer and, if necessary, modifies and decides on the final answer. The final answer is then submitted to the server.

[1635] Input: Adjusted answer, user confirmation

[1636] Data processing: determining and sending the final answer

[1637] Output: Final response sent

[1638] Step 7:

[1639] The server evaluates the submitted final answer again using the AI ​​module and generates an evaluation result, which is sent to the terminal and displayed to the user.

[1640] Input: Final answer

[1641] Data processing: Evaluation analysis

[1642] Output: Generating and sending evaluation results

[1643] 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.

[1644] 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.

[1645] 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.

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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).

[1650] 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.

[1651] 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."

[1652] 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.

[1653] 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).

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] The following is further disclosed regarding the above embodiment.

[1665] (Claim 1)

[1666] means for verifying authentication information input by a user via a terminal at a server;

[1667] means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful;

[1668] means for transmitting answer prompts to be input by the user from the terminal to the server;

[1669] A means for the AI ​​on the server to generate an answer based on the prompt and return the generated answer to the terminal;

[1670] means for displaying the generated answers to the user and submitting the answer determined as the final answer from the terminal to the server;

[1671] A means for evaluating the submitted answers using AI on the server and sending the evaluation results to the terminal;

[1672] A system including:

[1673] (Claim 2)

[1674] 10. The system of claim 1, further comprising means for recording the evaluation results on a server.

[1675] (Claim 3)

[1676] 10. The system of claim 1, further comprising: means for sending an error message to the terminal if the authentication fails.

[1677] "Example 1"

[1678] (Claim 1)

[1679] means for verifying authentication information input by a user via a terminal at a server;

[1680] means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful;

[1681] means for transmitting answer prompts to be input by the user from the terminal to the server;

[1682] a means for the artificial intelligence on the server to generate an answer based on the prompt and return the generated answer to the terminal;

[1683] means for displaying the generated answers to the user and submitting the answer determined as the final answer from the terminal to the server;

[1684] A means for evaluating the submitted answers using artificial intelligence on a server, generating feedback together with the evaluation results, and transmitting the feedback to the terminal;

[1685] A system including:

[1686] (Claim 2)

[1687] 10. The system of claim 1, further comprising means for recording the evaluation results and feedback on a server.

[1688] (Claim 3)

[1689] 10. The system of claim 1, further comprising: means for sending an error message to the terminal if the authentication fails.

[1690] "Application Example 1"

[1691] (Claim 1)

[1692] means for verifying authentication information input by a user via a terminal at a server;

[1693] means for transmitting a training task from the server to the terminal to be displayed to the user if authentication is successful;

[1694] means for transmitting answer prompts to be input by the user from the terminal to the server;

[1695] A generating artificial intelligence on the server generates an answer based on the prompt and sends the generated answer back to the terminal;

[1696] means for displaying the generated answers to the user and submitting the answer determined as the final answer from the terminal to the server;

[1697] A means for evaluating the submitted answers using a generating artificial intelligence on a server and transmitting the evaluation results to the terminal;

[1698] A system including:

[1699] (Claim 2)

[1700] 10. The system of claim 1, further comprising means for recording the evaluation results on a server.

[1701] (Claim 3)

[1702] 10. The system of claim 1, further comprising: means for sending an error message to the terminal if the authentication fails.

[1703] "Example 2: Combining Emotion Engines"

[1704] (Claim 1)

[1705] means for verifying authentication information input by a user via a terminal at a server;

[1706] means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful;

[1707] means for transmitting answer prompts to be input by the user from the terminal to the server;

[1708] a means for the AI ​​module on the server to generate an answer based on the prompt and return the generated answer to the terminal;

[1709] means for displaying the generated answers to the user and submitting the answer determined as the final answer from the terminal to the server;

[1710] A means for evaluating the submitted answers with an AI module on a server and transmitting the evaluation results to the terminal;

[1711] an emotion engine means for analyzing the emotion of the user and adjusting the expression of the answer based on the emotion;

[1712] A system including:

[1713] (Claim 2)

[1714] 10. The system of claim 1, further comprising means for recording the evaluation results on a server.

[1715] (Claim 3)

[1716] 2. The system according to claim 1, further comprising means for analyzing a user's emotion when authentication fails, and sending an error message to the terminal based on the emotion.

[1717] "Application example 2 when combining emotion engines"

[1718] (Claim 1)

[1719] means for verifying authentication information input by a user via a terminal at a server;

[1720] means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful;

[1721] means for transmitting answer prompts to be input by the user from the terminal to the server;

[1722] A means for the AI ​​on the server to generate an answer based on the prompt and return the generated answer to the terminal;

[1723] means for displaying the generated answers to the user and submitting the answer determined as the final answer from the terminal to the server;

[1724] A means for evaluating the submitted answers using AI on the server and sending the evaluation results to the terminal;

[1725] means for analyzing the user's emotions using a sentiment analysis engine and adjusting the feedback based on the generated answers;

[1726] A system including:

[1727] (Claim 2)

[1728] 10. The system of claim 1, further comprising means for recording the evaluation results on a server.

[1729] (Claim 3)

[1730] 10. The system of claim 1, further comprising: means for sending an error message to the terminal if the authentication fails. [Explanation of symbols]

[1731] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for verifying authentication information input by a user via a terminal at a server; means for transmitting test questions from the server to the terminal to be displayed to the user when authentication is successful; means for transmitting answer prompts to be input by the user from the terminal to the server; A means for the AI ​​on the server to generate an answer based on the prompt and return the generated answer to the terminal; means for displaying the generated answers to the user and submitting the answer determined as the final answer from the terminal to the server; A means for evaluating the submitted answers using AI on the server and sending the evaluation results to the terminal; A system including:

2. 10. The system of claim 1, further comprising means for recording the evaluation results on a server.

3. 2. The system of claim 1, further comprising: means for sending an error message to the terminal if the authentication fails.

Images