system

Abstract

To provide a system for preventing a new graduate or a former graduate from failing to make a proper answer at the time of interviewing because of insufficient self-PR or corporate research in job hunting.SOLUTION: A specific processing part 290 of a data processor 12 in this system, when receiving an input of a company name and business type information desired by a user, collects a URL of a news article related to the received company name / business type, analyzes text data, and extracts an important keyword from the news article by using a natural language processing technology. Then, expected interview questions are generated and stored on the basis of the extracted keywords and company information. Then, the questions generated in the mock interview format are sequentially displayed to the users, the answers of the users to the questions are analyzed, and feedback is generated and displayed. Further, a question asked by the user in the actual interview is added to the database and reflected on the update of the next question.SELECTED DRAWING: Figure 2

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] In today's job-hunting process, many new and former graduates fail to give appropriate answers during interviews due to insufficient self-promotion and company research. In particular, the quality of career support offered by some universities and vocational schools varies, leading to job-hunting failure due to inadequate support. Furthermore, insufficient preparation for appropriate questions based on the latest company information and market trends can lead to a decline in competitiveness. There is a need for a support system that can solve these problems and enable job seekers to more appropriately prepare for interviews. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for a user to input the name of a company and information on the industry that the user is applying to, a means for collecting URLs of related news articles and analyzing the text data, a means for extracting important keywords from the news articles using natural language processing technology, a means for generating anticipated interview questions based on the keywords and company information, a means for saving the generated questions in a database, a means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers, a means for analyzing the answers and generating and displaying feedback, a means for a user to input questions asked in an actual interview, and a means for adding the input questions to a database and reflecting them in the next question update, thereby enabling job seekers to effectively prepare for interviews and improving their interview success rate.

[0006] Of course, we will provide definitions of important terms included in the claims below.

[0007] The "user information input means" is an interface for users to input the name of the company they wish to work for and information about the type of business they wish to work for.

[0008] The "means for collecting related news articles" is a technology for collecting related news articles from specified URLs.

[0009] "Text data analysis means" refers to processing technology for analyzing the text data of collected news articles and understanding and summarizing their contents.

[0010] "Natural language processing technology" is a technology that enables computers to understand human language and extract meaning.

[0011] The "means for extracting important keywords" is a technique for extracting specific keywords from the analyzed text data.

[0012] The "means for generating interview questions" is a technology for automatically generating anticipated interview questions based on the extracted keywords and company information.

[0013] The "means for storing a list of questions" is a technique for storing the generated interview questions in a database.

[0014] The "mock interview display means" is an interface for displaying saved questions to the user and conducting a mock interview.

[0015] The "means for saving user responses" is a technology for saving the responses to the mock interview entered by the user.

[0016] The "answer analysis means" is a technique for analyzing saved user answers and evaluating their content.

[0017] The "feedback generation and display means" is a technology for generating feedback based on the analysis results and displaying it to the user.

[0018] The "actual interview question input means" is an interface that allows a user to input questions asked in an actual interview into the system.

[0019] The "database addition and update means" is a technique for adding actual interview questions that have been entered to a database and updating the list of questions for the next interview. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The present invention relates to a system that allows users to effectively prepare for interviews. This system generates interview questions based on information input by the user and provides feedback through mock interviews, allowing users to prepare for actual interviews. Detailed embodiments of this system will be described below.

[0042] System configuration

[0043] Enter user information

[0044] The terminal provides the user with an interface for entering company name and industry information. The user enters the name of the company they are applying to ("ABC Co., Ltd."), the industry ("IT industry"), and the URL of a related news article, and sends it to the system.

[0045] Collection and analysis of relevant news articles

[0046] Based on the URLs sent, the server scrapes relevant news articles from the web to collect text data. The server then uses natural language processing techniques to analyze this text data and understand the content of the articles, for example by extracting important keywords and phrases from the articles.

[0047] Generate and save interview questions

[0048] The server uses the keywords extracted from the analysis results to generate interview questions related to the company and industry the candidate is applying for. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?" This question is then saved in a database.

[0049] Mock interviews

[0050] When the user presses a button to start the mock interview, the server sends a list of questions that are displayed sequentially on the device. The user enters answers to the questions in the text box and submits the answer. For example, the user might enter, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[0051] Analysis of responses and feedback

[0052] The server analyzes the user's answers using natural language processing technology and evaluates their content. Specifically, it judges the specificity and relevance of the answers. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device.

[0053] Enter questions asked in the actual interview

[0054] An interface is provided for users to provide feedback to the system about the questions they received during the actual interview. For example, the user can enter "I was asked about my specific project management experience" and submit the feedback.

[0055] Database Update

[0056] The server stores the entered actual interview questions in a database and reflects them in the question list for future mock interviews. This allows the system to always provide a question list that incorporates the latest interview question trends.

[0057] Specific examples

[0058] Let's say a user is applying to work for a company called "X Corporation" in the "financial industry." The user enters the URL of a related news article and submits it. The system retrieves the news article from the URL, analyzes it using natural language processing technology, and extracts keywords such as "X Corporation's new financial service." The system then generates a question, "What do you think about X Corporation's new financial service?" and presents it to the user through a mock interview. The system analyzes the user's answers and provides feedback such as "It would be good to mention the specific service name and features." The user then provides feedback to the system with the question they received in the actual interview, "Tell us about your experience managing specific financial projects," and the database is updated.

[0059] In this way, users can have continuously up-to-date information about their interview preparation, and the feedback provided helps users understand and improve their weaknesses.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] A user accesses the system and logs in or creates a new account.

[0063] Step 2:

[0064] The device will display a form for entering the company name, industry, and the URL of a related news article.

[0065] Step 3:

[0066] The user enters the company name "ABC Co., Ltd.", the industry "IT industry," and the URL of a related news article, and presses the send button.

[0067] Step 4:

[0068] The server receives the company name, industry, and news article URL that were sent.

[0069] Step 5:

[0070] The server scrapes related news articles from the news article URLs and collects text data.

[0071] Step 6:

[0072] The server analyzes the collected text data of news articles using natural language processing technology.

[0073] Step 7:

[0074] The server extracts important keywords and phrases from the analysis results, such as "ABC Corporation's latest project" or "technology trends."

[0075] Step 8:

[0076] The server generates questions that are likely to be asked in an interview based on the extracted keywords and company information. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?"

[0077] Step 9:

[0078] The server stores the generated questions in a database.

[0079] Step 10:

[0080] The user presses a button to start the mock interview from the mock interview menu.

[0081] Step 11:

[0082] The server loads the saved question list into a task queue and prepares it to be sent to the terminal in order.

[0083] Step 12:

[0084] The server sends the first question to the terminal and displays it. For example, it displays "What do you think about ABC Corporation's latest project?"

[0085] Step 13:

[0086] The user enters an answer in the text box and presses the submit button.

[0087] Step 14:

[0088] The server receives and stores the user's answers.

[0089] Step 15:

[0090] The server analyzes the saved user responses using natural language processing techniques.

[0091] Step 16:

[0092] The server evaluates the depth, specificity, and relevance of the response.

[0093] Step 17:

[0094] The server generates feedback based on the evaluation results, such as "Your response is not specific enough. Please provide a specific project name."

[0095] Step 18:

[0096] The server sends the feedback to the terminal for display.

[0097] Step 19:

[0098] The user accesses a form that allows them to enter questions from the actual interview into the system.

[0099] Step 20:

[0100] The user enters, for example, "I was asked about my specific project management experience" and presses the submit button.

[0101] Step 21:

[0102] The server stores the questions asked in the actual interview in a database.

[0103] Step 22:

[0104] The server updates the question list for the next and subsequent mock interviews based on the new questions.

[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] Conventional interview preparation systems have difficulty generating appropriate interview questions based on the information entered by the user, which means that they do not adequately improve the ability to respond to questions required in actual interviews. Furthermore, when providing feedback, there is a lack of specific improvements and suggestions, which makes it difficult to fully improve users' skills. Furthermore, there is no system that can reflect questions asked in actual interviews, making it difficult to provide interview practice based on the latest information.

[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: a means for inputting the name and industry information of the company the user is applying to; a means for collecting URLs of related news articles and analyzing the text data; a means for extracting important keywords from the news articles using natural language processing technology; a means for generating predicted interview questions using a generative AI model based on the keywords and company information; a means for saving the generated questions in a database; a means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers; a means for analyzing the answers using natural language processing technology and generating and displaying feedback including areas for improvement and specific suggestions; a means for the user to input questions asked in an actual interview; and a means for adding the input actual interview questions to the database and reflecting them in the next question update. This allows users to effectively prepare for interviews based on the latest and most relevant information, and the feedback can lead to concrete improvements. Furthermore, real-time information updates allow interview practice that always incorporates the latest question trends.

[0110] "User" means an individual or entity who uses the System to prepare for an interview.

[0111] "Name of desired company" is the name of the company where the user wishes to have an interview.

[0112] "Industry information" is information about the industry or economic field to which the company you are applying to belongs.

[0113] A "URL" is a uniform resource locator for a resource on the Web; it is an address that points to the relevant news article.

[0114] "Text data" is data that expresses the contents of collected news articles as digital strings of characters.

[0115] "Natural language processing technology" is a technology for processing human natural language using a computer, and is used to analyze text data.

[0116] "Keywords" are important words and phrases extracted from news articles and used to generate interview questions.

[0117] A "generative AI model" is a model that uses artificial intelligence technology to generate new text and questions.

[0118] "Interview questions" are questions related to the company or industry the user is applying for in an interview, and require the user to answer.

[0119] A "database" is an information system for collecting and managing data within a system.

[0120] The "mock interview format" refers to the display means and operation means of the system that allows practice in a format similar to a real interview.

[0121] "Feedback" is information that includes evaluation of the user's response, areas for improvement, and specific suggestions.

[0122] The "questions asked in an actual interview" are specific questions that the user was asked in an actual interview.

[0123] This invention relates to a system that allows users to effectively prepare for interviews. The system generates interview questions based on information input by the user and provides feedback through mock interviews, allowing users to prepare for actual interviews.

[0124] The system uses the following hardware and software. The hardware requires a server and a terminal; specifically, the server is a cloud server with powerful computing power (such as Amazon Web Services or Microsoft Azure). The terminal is the user's personal computer or smartphone. The software uses Python and its library BeautifulSoup for web scraping, spaCy and NLTK for natural language processing technology, and GPT-3 for the generative AI model.

[0125] First, the terminal provides the user with an interface for entering company names and industry information. The user enters the name of the company they are applying for, industry information, and the URL of a related news article, and submits it to the system. The input data is sent to the server using an HTML form or JavaScript.

[0126] The server then receives the URL sent from the device and performs web scraping using Python's BeautifulSoup library to collect text data from the news articles. The collected text data is then analyzed using natural language processing techniques (spaCy and NLTK). Specifically, processes such as tokenization, POS tagging, and named entity recognition are performed to extract important keywords and phrases.

[0127] Next, the server uses a deep learning model (a generative AI model such as GPT-3) to generate interview questions based on keywords extracted from the analysis results. For example, a question might be generated such as, "What do you think about the latest project at the company you're applying to?" The generated questions are stored in an SQL database (PostgreSQL or MySQL).

[0128] When a user starts a mock interview, the server retrieves a list of questions from the database and displays them sequentially on the device. The user enters answers to the questions in the text boxes and submits the answer. For example, the user might respond, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[0129] The server receives the user's response and analyzes it again using natural language processing technology (spaCy or GPT-3). Specifically, it evaluates the specificity, relevance, and logic of the response. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device. For example, it provides feedback such as, "Your response would be more persuasive if you provided specific examples."

[0130] Furthermore, the terminal provides the user with an interface for inputting questions from actual interviews. The user inputs "I was asked about specific project management experience" and submits the request. This actual interview question is also saved in the database and reflected in the question list for future mock interviews.

[0131] For example, the prompts for entering the company name and industry information are as follows:

[0132] "Please enter the name of the company you are applying to, the industry, and the URL of a related news article below."

[0133] The mock interview begins with a prompt such as:

[0134] "Press the button to begin the mock interview."

[0135] Example questions include:

[0136] "Please answer the following question: How do you feel about the new financial services offered by your desired company?"

[0137] This process allows users to prepare effectively for interviews based on the latest and most relevant information, and they can expect to make concrete improvements based on feedback.In addition, real-time updates of information allow users to practice interviews while always incorporating the latest question trends.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1:

[0140] The terminal provides an interface for inputting company names, industry information, and URLs of related news articles. When the user inputs the company name "Corporation," the industry "IT industry," and the URLs of related news articles into the input format and presses the send button, this information is sent to the server. The input data is sent to the server using an HTML form or JavaScript.

[0141] Input: Company name, industry information, URL of related news article

[0142] Output: Sending information to the server

[0143] Step 2:

[0144] The server receives the URL sent from the device and performs web scraping using Python's BeautifulSoup library. Specifically, it uses the requests library to retrieve HTML content from the specified URL and extracts text data from news articles.

[0145] Input: URL of related news article

[0146] Output: News article text data

[0147] Step 3:

[0148] The server analyzes the collected text data using natural language processing techniques (spaCy and NLTK libraries), specifically tokenizing, POS tagging, and named entity recognition to extract important keywords and phrases.

[0149] Input: News article text data

[0150] Output: Important keywords and phrases

[0151] Step 4:

[0152] The server generates interview questions using a generative AI model (e.g., GPT-3) based on the keywords extracted from the analysis results. Specifically, the keywords and company information are input into the model, and the generated questions are retrieved. For example, a question such as "What do you think about a certain company's latest project?" is generated.

[0153] Input: Important keywords and company information

[0154] Output: Generated interview questions

[0155] Step 5:

[0156] The server stores the generated interview questions in an SQL database (PostgreSQL or MySQL) by adding the question text and related information as new rows in a database table.

[0157] Input: Generated interview questions

[0158] Output: Questions saved in the database

[0159] Step 6:

[0160] When the user presses the start button for the mock interview, the server retrieves a list of questions from the database and displays them sequentially on the terminal. For example, a question such as "How do you feel about a certain company's new product?" may be displayed. The user enters their answer to the displayed question in the text box and presses the send button.

[0161] Input: A list of questions retrieved from the database

[0162] Output: Question displayed on terminal and user's response

[0163] Step 7:

[0164] The server receives the user's response and analyzes it using natural language processing technology. Specifically, it runs an analysis algorithm that evaluates the specificity, relevance, and logic of the response.

[0165] Input: User's answer

[0166] Output: Analysis results

[0167] Step 8:

[0168] Based on the analysis results, the server generates feedback including areas for improvement and specific suggestions. For example, it might generate feedback such as, "If you provide specific examples, it will be more persuasive." The generated feedback is displayed on the device.

[0169] Input: Analysis results

[0170] Output: Feedback displayed on the terminal

[0171] Step 9:

[0172] The terminal provides the user with an interface for inputting questions that they would have received in an actual interview. For example, the user might input, "I was asked about my specific project management experience," and press the send button.

[0173] Input: User input of questions asked in the actual interview

[0174] Output: Actual interview questions sent to the server

[0175] Step 10:

[0176] The server saves the actual interview questions sent by the user in a database. The saved questions are reflected in the question list for the next mock interview. This allows the system to always incorporate the latest question trends.

[0177] Input: Actual interview questions submitted by the user

[0178] Output: Actual interview questions stored in a database

[0179] (Application example 1)

[0180] 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."

[0181] Conventional interview preparation systems focus solely on providing interview questions and feedback, but do not address specific training or skill development in specific work or technical fields. In particular, there is a lack of efficient means for providing practical training, such as operating and troubleshooting automated equipment in factories. This makes it difficult for employees to effectively acquire the skills actually required in factories. To solve this issue, a system is needed that allows users to receive specific training related to factory operations.

[0182] 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.

[0183] In this invention, the server includes: means for inputting the name of the company and industry information for which the user is applying; means for collecting URLs of related news articles and analyzing the text data; means for extracting important keywords from the news articles using natural language processing technology; means for generating anticipated interview questions based on the keywords and company information; means for saving the generated questions in a database; means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers; means for analyzing the answers and generating and displaying feedback; means for the user to input questions asked in an actual interview; means for adding the input questions to the database and reflecting them in the next question update; means for generating and displaying training questions related to the operation of automated equipment in a factory; and means for evaluating the responses and providing feedback based on the user's answers. This allows users to receive practical operational training in a factory and effectively acquire skills directly related to actual work.

[0184] "User" refers to an individual or employee who uses the system to prepare for an interview or for factory training.

[0185] "Company name" refers to the name of the specific company for which the user is applying.

[0186] "Industry information" refers to information related to the industry or field to which a company belongs.

[0187] "Related news articles" refer to articles that describe the latest news or events related to a company or industry.

[0188] "URL" refers to Internet link information that indicates the address of a web page.

[0189] "Text data" refers to the written information obtained from news articles and text.

[0190] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[0191] "Keywords" refer to important words and phrases extracted from news articles and company information.

[0192] "Interview Questions" refers to questions that may be asked of you in a job interview.

[0193] A "database" refers to a computer system for systematically organizing and storing information.

[0194] A "mock interview" is a form of practice conducted to simulate a real interview.

[0195] "Answer" refers to the response a user gives to a question during a mock interview or training.

[0196] "Feedback" refers to information that evaluates an answer or points out areas for improvement.

[0197] "Input" refers to the act of a user providing information to a system.

[0198] "Automation equipment" refers to robots and automated machines used in factories, etc.

[0199] "Operational training" refers to training that teaches users how to operate and troubleshoot automated equipment.

[0200] "Response evaluation" refers to the act of analyzing the content of a user's response and evaluating its quality.

[0201] This invention is a system for enabling users to effectively operate and train automated equipment in factories. This system comprises the following steps:

[0202] 1. Entering user information

[0203] First, the terminal provides the user with an interface for entering company name and industry information. The user enters the company name and industry information they wish to work for and sends it to the system. For example, the user may enter "manufacturing."

[0204] 2. Collection and analysis of related news articles

[0205] Based on the submitted URL, the server scrapes relevant news articles from the web to collect text data. The server then uses natural language processing techniques to analyze this text data and understand the content of the article. For example, it extracts important keywords and phrases from the article. Specifically, it uses Python's BeautifulSoup and requests libraries to retrieve web page data, and Hugging Face's transformers library to perform natural language processing.

[0206] 3. Generate and save training questions

[0207] The server uses the keywords extracted from the analysis results to generate training questions related to the company or industry, such as "What do you think about the latest robot operation technology?" These questions are then stored in a database.

[0208] 4. Conducting mock training

[0209] When the user presses a button to start the simulation training, the server sends a list of questions to the terminal, which are displayed one after the other. The user enters answers to the questions in the text box and submits the answer. For example, the user might enter, "The latest technology is extremely important for dramatically improving production efficiency."

[0210] 5. Analysis of answers and feedback

[0211] The server analyzes the user's responses using natural language processing technology and evaluates their content. Specifically, it determines the specificity and relevance of the responses. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device. The OpenAI API is used to evaluate responses and generate appropriate feedback.

[0212] 6. Input of actual operation feedback

[0213] An interface is provided for users to provide feedback and problems they have experienced during actual operation or training to the system. For example, users can input and submit a message such as, "Please tell us about your specific troubleshooting experiences during operation."

[0214] 7. Updating the database

[0215] The server stores the inputted actual operation feedback in a database and reflects it in the question list for the next mock training session, allowing the system to always provide a question list that incorporates the latest trends in training content.

[0216] As a concrete example, consider the case where a user requests "Training in factory automation technology in the manufacturing industry." In this case, the system extracts keywords such as "automation technology" and "robot operation" from related news articles and generates the question, "What do you think about the latest trends in automation technology?" The user can enter an answer and receive feedback on their response, allowing them to effectively acquire the skills required in an actual factory.

[0217] An example prompt might look like this:

[0218] You are in the manufacturing industry and are being trained to operate automated equipment. Using information from a news article, answer the following questions:

[0219] 1. What do you think about the latest robotic manipulation technology?

[0220] 2. What is your experience troubleshooting robot operations?

[0221] This system allows users to undergo simulated training based on real-life operating situations, enabling them to effectively acquire the skills necessary for actual factory work.

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] The terminal provides the user with an interface for entering company names and industry information. The user enters the company name and industry information they wish to work for and sends it to the system. The information entered includes "company name" and "industry information." This allows the system to understand the user's specific wishes.

[0225] Step 2:

[0226] The server receives the URL sent by the user and scrapes related news articles from the web to collect text data. Specifically, it accesses web pages using Python's requests library and extracts text data using the BeautifulSoup library. The input is the "URL of the news article" and the output is the "scraped text data."

[0227] Step 3:

[0228] The server uses natural language processing technology to analyze the collected text data and understand the content of the articles. Specifically, it uses Hugging Face's transformers library to extract important keywords and phrases from the text data. The input is "text data" and the output is "important keywords and phrases."

[0229] Step 4:

[0230] The server uses the extracted keywords to generate predicted questions from training related to the company and industry. A generative AI model is used to generate "predicted questions" from "keywords" and "company information." For example, it generates a question such as "What do you think about the latest robot operation technology?" The input here is "keywords" and "company information," and the output is the "generated question."

[0231] Step 5:

[0232] The server saves the generated question in a database. The saved information is the "generated question" and is prepared for display to the user in later processing. The input is the "generated question" and the output is the "question saved in the database."

[0233] Step 6:

[0234] When the user presses a button to start the simulated training, the server sends a list of questions to the terminal in order for them to be displayed. The user receives the training questions in order, enters their answers in the text box, and sends them. The input is the "user's confirmation action," and the output is the "question displayed on the terminal" and the "user's answer."

[0235] Step 7:

[0236] The server analyzes the user's answers using natural language processing technology and evaluates their content. Specifically, it determines the specificity and relevance of the answers. It analyzes the "user's answers" using the OpenAI API and generates "evaluation results and feedback." The input is the "user's answers" and the output is "evaluation results and feedback."

[0237] Step 8:

[0238] Based on the evaluation results, the server generates feedback including areas for improvement and specific suggestions, which is displayed on the device. The user can review this feedback and use it for the next training session. The input is "evaluation results and feedback," and the output is "feedback display on the device."

[0239] Step 9:

[0240] An interface is provided that allows users to provide feedback and problems they have received during actual operations and training to the system. Users input and send specific feedback and problems. The input is "feedback from operations and training," and the output is "sending feedback data to the server."

[0241] Step 10:

[0242] The server stores the inputted actual operation feedback in a database and reflects it in the question list for the next and subsequent mock training sessions. This allows the server to provide a question list that always incorporates the latest trends in training content. The input is "feedback from the user" and the output is "feedback stored in the database."

[0243] 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.

[0244] This invention relates to a system that allows users to effectively prepare for interviews, and in particular provides an innovative system that recognizes the user's emotions and reflects them in feedback by combining an emotion engine. An embodiment of this system will be described in detail below.

[0245] System configuration

[0246] Enter user information

[0247] The terminal provides the user with an interface for entering company name and industry information. The user enters the name of the company they are applying to ("ABC Co., Ltd."), the industry ("IT industry"), and the URL of a related news article, and sends it to the system.

[0248] Collection and analysis of relevant news articles

[0249] The server scrapes relevant news articles from the web based on the submitted URL and collects text data. The server then analyzes this text data using natural language processing techniques to understand the content of the article, specifically extracting important keywords and phrases.

[0250] Generate and save interview questions

[0251] The server uses the extracted keywords to generate potential interview questions based on company information. For example, it generates a question like, "What do you think about ABC Corporation's latest project?" The generated questions are stored in a database.

[0252] Mock interviews

[0253] When a user starts a mock interview, the server sequentially sends a list of questions to the terminal and displays them. The user enters answers to the questions in the text boxes and submits the answer. For example, the user might enter, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[0254] Emotion recognition by emotion engine

[0255] During the mock interview, the device runs an emotion engine based on the user's text responses and facial expression data to recognize the user's emotions. The emotion engine recognizes emotions such as "happiness," "anxiety," and "confidence."

[0256] Analysis of responses and feedback

[0257] The server analyzes the saved user responses using natural language processing technology and evaluates them, taking into account the results of the emotion engine. Specifically, it considers the specificity and relevance of the responses as well as the user's emotional state. Based on the results, it generates feedback including areas for improvement and specific suggestions, which are displayed on the device.

[0258] Enter questions asked in the actual interview

[0259] An interface is provided for users to provide feedback to the system about the questions they received during the actual interview. For example, the user can enter "I was asked about my specific project management experience" and submit the feedback.

[0260] Database Update

[0261] The server saves the entered actual interview questions in a database and reflects them in the question list for future mock interviews, allowing the system to always provide a question list that incorporates the latest interview question trends.

[0262] Specific examples

[0263] Let's say a user is applying to work for a company called "X Corporation" in the "financial industry." The user enters the URL of a related news article and submits it. The system retrieves the news article from the URL, analyzes it using natural language processing technology, and extracts keywords such as "X Corporation's new financial service." The system then generates a question, "What do you think about X Corporation's new financial service?" and presents it to the user through a mock interview. The system analyzes the user's answer and the emotions recognized by the emotion engine, and provides feedback such as, "It would be good if you mentioned the specific name and features of the service. Also, it's good that you answered with confidence, but it would be even better if you included more specific experiences." The user then feeds back to the system the question they received in the actual interview, "Tell us about your experience managing specific financial projects," and the database is updated.

[0264] In this way, users can continuously prepare for their interviews taking into account their current information and emotional state, and the feedback provided allows users to understand and improve their weaknesses.

[0265] The processing flow will be explained below.

[0266] Of course, the specific processing flow of the system will be explained below by dividing it into steps.

[0267] Step 1:

[0268] A user accesses the system and logs in or creates a new account.

[0269] Step 2:

[0270] The device will display a form for entering the company name, industry, and the URL of a related news article.

[0271] Step 3:

[0272] The user enters the company name "ABC Co., Ltd.", the industry "IT industry," and the URL of a related news article, and presses the send button.

[0273] Step 4:

[0274] The server receives the company name, industry, and news article URL that were sent.

[0275] Step 5:

[0276] The server scrapes related news articles from the news article URLs and collects text data.

[0277] Step 6:

[0278] The server analyzes the collected text data of news articles using natural language processing technology.

[0279] Step 7:

[0280] The server extracts important keywords and phrases from the analysis results, such as "ABC Corporation's latest project" or "technology trends."

[0281] Step 8:

[0282] The server generates questions that are likely to be asked in an interview based on the extracted keywords and company information. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?"

[0283] Step 9:

[0284] The server stores the generated questions in a database.

[0285] Step 10:

[0286] The user presses a button to start the mock interview from the mock interview menu.

[0287] Step 11:

[0288] The server loads the saved question list into a task queue and prepares it to be sent to the terminal in order.

[0289] Step 12:

[0290] The server sends the first question to the terminal and displays it. For example, it displays "What do you think about ABC Corporation's latest project?"

[0291] Step 13:

[0292] The user enters an answer in the text box and presses the submit button.

[0293] Step 14:

[0294] The server receives and stores the user's answers.

[0295] Step 15:

[0296] During the mock interview, the device uses a camera and microphone to collect the user's facial expressions and voice and transmits them to the emotion engine.

[0297] Step 16:

[0298] The emotion engine on the server analyzes the user's facial expressions and voice data to recognize emotions, such as "happiness," "anxiety," and "confidence."

[0299] Step 17:

[0300] The server analyzes the saved user responses using natural language processing technology, evaluating their depth, specificity, and relevance, while also taking into account the results of the emotion engine.

[0301] Step 18:

[0302] The server generates feedback based on the analysis of the answer and the emotions recognized by the emotion engine. For example, "Your answer is not specific enough. It would be better if you mentioned a specific project name. Also, it is good that you answered with confidence, but it would be even better if you included more specific experiences."

[0303] Step 19:

[0304] The server sends the feedback to the terminal for display.

[0305] Step 20:

[0306] The user accesses a form that allows them to enter questions from the actual interview into the system.

[0307] Step 21:

[0308] The user enters, for example, "I was asked about my specific project management experience" and presses the submit button.

[0309] Step 22:

[0310] The server stores the questions asked in the actual interview in a database.

[0311] Step 23:

[0312] The server updates the question list for the next and subsequent mock interviews based on the new questions.

[0313] Example 2

[0314] 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."

[0315] Existing systems for preparing Q&A questions for potential organizations often lack sufficient information gathering and appropriate Q&A content. Furthermore, they lack feedback that takes into account the user's emotional state, making it difficult to improve performance in mock questions or actual Q&A sessions. The present invention aims to solve these problems by providing a system that allows users to effectively prepare and improve Q&A questions.

[0316] 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 inputting the name and industry information of the organization the user is interested in; means for collecting links to related information articles and analyzing text data; means for extracting important keywords from the information articles using natural language processing technology; means for generating predicted questions based on the keywords and organization information; means for saving the generated questions in a storage device; means for sequentially displaying the questions to the user in the form of mock questions and saving the user's answers; means for analyzing the answers, generating and displaying evaluations and responses; means for the user to input questions asked in actual question-and-answer sessions; means for adding the input questions to a storage device and reflecting them in the next question update; emotion recognition means for analyzing the user's answers and facial expression data and recognizing the user's emotional state; and means for including the recognition results in feedback. This enables the user to collect related information, generate questions, and provide feedback that takes emotions into account.

[0317] "User" means a person who uses the system to prepare questions and answers for a prospective organization.

[0318] "Organization name" is information that indicates the name of the company or organization that the user is applying to.

[0319] "Industry information" is information about the type of industry or business to which the organization to which the applicant belongs.

[0320] "Link" refers to a web address that points to a related article of information.

[0321] "Text data" refers to textual information obtained through scraping or analysis.

[0322] "Natural language processing technology" refers to technology for analyzing acquired text data and extracting meaningful information.

[0323] "Keywords" refer to important words or phrases extracted from text data.

[0324] "Question and answer content" refers to anticipated questions generated using natural language processing technology.

[0325] "Storage device" refers to a device for storing the generated questions and answers, answer data, and other necessary information.

[0326] "Mock question format" refers to a method in which anticipated questions are presented in a format similar to an actual questioning environment, and users respond to them.

[0327] "Answer" refers to a user's answer to a question presented in the form of a mock question.

[0328] "Evaluation and response" refers to feedback and suggestions generated based on the analyzed answer data.

[0329] "Emotion recognition means" refers to technology that analyzes a user's answers and facial expression data to recognize their emotional state.

[0330] This invention relates to a system that allows users to effectively prepare for Q&A sessions, and in particular provides an innovative system that recognizes the user's emotions and reflects them in feedback by incorporating an emotion recognition engine. An embodiment of this system will now be described in detail.

[0331] System configuration

[0332] Enter user information

[0333] The terminal provides the user with an interface for entering information about the organization's name and industry. The user enters the name of the organization they wish to apply for ("Organization XYZ"), the industry ("Technology field"), and a link to a related news article, and sends it to the system.

[0334] Collection and analysis of relevant news articles

[0335] The server scrapes relevant news articles from the web based on the submitted links and collects text data using Python's BeautifulSoup. The server then analyzes this text data using natural language processing techniques (e.g., spaCy, NLTK) to extract important keywords and phrases.

[0336] Generate and save interview questions

[0337] Based on the extracted keywords, the server uses a generative AI model (e.g., GPT-3) to generate predicted questions based on the organization information. An example of a prompt used for generation is, "Please generate questions related to 'technological innovation.'" The generated questions are saved in a storage device.

[0338] Mock question session

[0339] When a user starts a mock question, the server sequentially sends the generated list of questions to the terminal, which then displays them. The user enters answers to each question in the text box and submits it. For example, in response to the question "What do you think about the impact of new technological innovations on the market?", the user enters "I think new technological innovations will improve market competitiveness."

[0340] Emotion recognition using an emotion recognition engine

[0341] During the mock questions, the device collects the user's text responses and facial expression data, and uses an emotion recognition engine (e.g., Microsoft Azure Cognitive Services) to recognize the user's emotions. The emotion recognition engine recognizes emotions such as "happiness," "anxiety," and "confidence."

[0342] Analysis of responses and feedback

[0343] The server analyzes the user's saved answers using natural language processing technology and evaluates them taking into account the results of an emotion recognition engine. For example, it evaluates the specificity and relevance of the answer and generates feedback based on the recognized emotional state. The feedback might be something like, "It would be good to include a specific example. Also, it's good that you're answering with confidence, but it would be even better if you included a more specific experience." The generated feedback is displayed on the device.

[0344] Enter questions asked during the actual Q&A session

[0345] The terminal provides the user with an interface for feedback on the questions asked during the actual Q&A session. For example, the user can input "I was asked about my specific project management experience" and submit.

[0346] Database Update

[0347] The server saves the questions entered in the actual Q&A session in a storage device and reflects them in the Q&A list for the next mock question session onwards, allowing the system to always provide a list that incorporates the latest trends in Q&A questions.

[0348] Specific examples

[0349] For example, suppose a user is applying to work for "Organization ABC" in the "finance industry." The user inputs and submits a link to a related news article. The server retrieves the news article from the link, analyzes it using natural language processing technology, and extracts keywords such as "Organization ABC's new financial service." The server then generates a question, "How do you feel about Organization ABC's new financial service?" and provides it to the user through a mock question. The server analyzes the user's answer and the emotions recognized by the emotion recognition engine, and provides feedback such as, "It would be good if you mentioned the specific service name and features. Also, it is good that you answered with confidence, but it would be even better if you included more specific experiences." The user then feeds back the question they received in the actual Q&A session, "Tell me about your experience managing specific financial projects," to the system and updates the storage device.

[0350] In this way, users can continuously prepare questions and answers that take into account the latest information and their emotional state, and the feedback provided allows users to understand and improve their weaknesses.

[0351] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0352] Step 1: Enter user information

[0353] Input: The user enters the name of the organization they wish to apply to, industry information, and links to related news articles.

[0354] Processing: The terminal receives the entered information and confirms it through the interface.

[0355] Output: Sends the entered information to the server.

[0356] Specific operation: The device displays a web form or app input screen, and after the user enters data in the input fields for "organization name," "industry," and "news article URL," clicks the send button, and the input information is sent to the server.

[0357] Step 2: Collect and analyze relevant news articles

[0358] Input: The server receives the link information.

[0359] Processing: The server scrapes the linked webpage using Python's BeautifulSoup library to collect text data, which is then analyzed using natural language processing techniques (e.g., spaCy, NLTK) to extract important keywords and phrases.

[0360] Output: A list of parsed keywords and phrases.

[0361] How it works: The server retrieves the web page from the specified URL, extracts the text using BeautifulSoup, and then performs morphological analysis on the text data using SpaCy to extract important keywords.

[0362] Step 3: Generate and save interview questions

[0363] Input: The server receives the extracted keywords and organization information.

[0364] Processing: The server sends the keywords as a prompt to a generative AI model (e.g., GPT-3) to generate questions. An example prompt is, "Please generate questions related to 'technological innovation.'"

[0365] Output: The generated questions and answers.

[0366] Specific operation: The server sends a prompt to the generation AI model, which generates the expected question and answer content. The generated question and answer content is then saved in a storage device.

[0367] Step 4: Practice Questions

[0368] Input: The user sends a request to start the mock question.

[0369] Processing: The server retrieves the list of questions from the storage device and transmits them to the terminals in order.

[0370] Output: The question list displayed on the terminal.

[0371] Specific operation: When the user clicks the "Start mock questions" button, the server retrieves the question list from the storage device, sends it to the terminal, and displays it.

[0372] Step 5: Enter and submit your answers

[0373] Input: The user enters the answer to each question.

[0374] Processing: The terminal sends the entered answer to the server.

[0375] Output: The answer data sent to the server.

[0376] Specific operation: The terminal presents questions to the user, and when the user enters answers to each question in the text boxes and presses the send button, the terminal sends the answer data to the server.

[0377] Step 6: Emotion recognition using the emotion recognition engine

[0378] Input: The server receives the submitted answer data and facial expression data.

[0379] Processing: The server uses an emotion recognition engine (e.g., Microsoft Azure Cognitive Services) to analyze the answer data and facial expression data and recognize the user's emotions.

[0380] Output: Recognized emotional state data.

[0381] Specific operation: The device sends the user's answer data and facial expression data together, and the server passes it to the emotion recognition engine for analysis.

[0382] Step 7: Analyze responses and generate feedback

[0383] Input: The server receives answer data and recognized emotional state data.

[0384] Processing: The server analyzes the answer data using natural language processing technology and evaluates it, taking into account the emotion recognition results. Based on the evaluation results, specific feedback is generated.

[0385] Output: The generated feedback.

[0386] Specific operation: The server analyzes the answer data using natural language processing tools, evaluates the specificity, relevance, and emotional state of the content, and generates feedback. This feedback is then sent to the device.

[0387] Step 8: View your feedback

[0388] Input: Sends server-generated feedback to the device.

[0389] Processing: The device displays feedback to the user.

[0390] Output: The feedback displayed to the user.

[0391] Specific behavior: The device receives feedback from the server and displays it to the user, such as "It would be good to include a specific example. Also, it's good that you're confident in your answer, but it would be even better if you included more specific experiences."

[0392] Step 9: Enter the questions asked during the Q&A session

[0393] Input: The user inputs the question asked in the actual Q&A session.

[0394] Processing: The terminal sends the entered question to the server.

[0395] Output: The query data sent to the server.

[0396] Specific operation: The terminal displays a form for the user to input the actual question, and when the user inputs the question and presses the submit button, the terminal sends the question data to the server.

[0397] Step 10: Update the Database

[0398] Input: The server receives the actual query data that was sent.

[0399] Processing: The server saves the newly entered question in a memory device and reflects it in the question and answer list from the next time onwards.

[0400] Output: Updated question list.

[0401] Specific operation: The server saves the new question data in the storage device and updates the existing question list. The newly saved questions are used in the next mock test.

[0402] (Application example 2)

[0403] 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."

[0404] In conventional customer support preparation systems, it is difficult for representatives to fully acquire the product information and knowledge necessary for customer support, and the responsiveness and accuracy of responses to customer inquiries can be reduced. Furthermore, the emotional state of representatives can affect the quality of customer support, but there is a lack of a means to effectively manage this. The present invention aims to solve these problems and improve the efficiency and quality of customer support preparation.

[0405] 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 inputting product names and category information for which the user is responsible; means for collecting URLs of related product reviews and analyzing text data; means for extracting important keywords from the reviews using natural language processing technology; means for generating predicted customer queries based on the keywords and product information; means for saving the generated queries in a database; means for sequentially displaying the queries in a simulated customer support format and saving the user's responses; means including an emotion engine that recognizes the user's emotions during the simulated session and reflects them as feedback in the evaluation results; means for analyzing the responses and generating and displaying feedback; means for inputting queries made by the user during actual support; and means for adding the input queries to a database and reflecting them in the next query update. This allows users to acquire the latest and most effective support information, manages the emotional states of staff, and enables highly accurate customer support.

[0406] "User" means any person or entity that uses the System.

[0407] "Organization name" refers to the name of the company or organization you are applying for.

[0408] "Industry information" refers to information about the industry to which the company or organization you are applying to belongs.

[0409] "Related news articles" refer to articles that cover the latest news related to the company or industry you are applying to.

[0410] "URL" refers to the web page address where the relevant news article is published online.

[0411] "Text data" refers to the textual information of collected news articles.

[0412] "Natural language processing technology" refers to computer technology for analyzing text data and understanding its meaning.

[0413] "Key words" refer to key words and phrases extracted from news articles and used to generate interview questions.

[0414] "Interview questions" refer to questions asked of users during mock interviews or actual interviews.

[0415] "Database" refers to a system for storing data such as generated questions, user responses, and questions asked in actual interviews.

[0416] A "mock interview" refers to a simulation that allows users to practice for a real interview.

[0417] "Emotion engine" refers to a system for recognizing and analyzing users' emotions.

[0418] "Feedback" refers to evaluations and improvement suggestions generated based on the user's responses and emotional state.

[0419] ·System Programming

[0420] The system's program is written in Python and includes the following main functions:

[0421] 1. Data collection function:

[0422] The server collects the URLs of the product review web pages based on the product name and category information entered by the user. This collection process uses the requests and BeautifulSoup libraries.

[0423] 2. Data analysis function:

[0424] The server analyzes the collected text data using natural language processing techniques to extract important keywords. This analysis process utilizes the spacy and TextBlob libraries.

[0425] 3. Query generation function:

[0426] The server generates a customer query based on the analysis results and stores it in a database, using the extracted important keywords.

[0427] 4. Simulation session function:

[0428] The terminal sequentially displays queries generated in a simulated customer support format and accepts the user's answers, which are then sent from the terminal to a server and stored.

[0429] 5. Emotion recognition function:

[0430] During the simulation session, the server runs an emotion engine based on the user's responses to recognize the user's emotions. This emotion recognition is performed using the EmotionRecognizer library.

[0431] 6. Feedback generation function:

[0432] The server analyzes the saved user responses and evaluates them based on the results of the emotion engine. The feedback includes specific improvements and suggestions.

[0433] 7. Actual query input function:

[0434] Users are provided with an interface to input queries received from actual customer support into the system. The input queries are added to a database and reflected in the generation of future queries.

[0435] Processing Description

[0436] To realize the above functions, the server performs the following data processing and data calculations.

[0437] 1. Data Collection:

[0438] Scrape product reviews from a URL and retrieve them as text data. Here, requests and BeautifulSoup are used.

[0439] 2. Data Analysis:

[0440] Spacy is used to perform natural language processing on the scraped text data to extract important keywords from the reviews.

[0441] 3. Query Generation:

[0442] Generate predicted customer queries based on the extracted keywords.

[0443] 4. Mock Session:

[0444] The device displays the query to the user and accepts the user's answer, which is sent to the server and stored.

[0445] 5. Emotion recognition:

[0446] The server uses the EmotionRecognizer library to recognize emotions from the user's responses.

[0447] 6. Feedback Generation:

[0448] The content of the user's response is analyzed using TextBlob, and feedback is generated taking into account the results of emotion recognition.

[0449] 7. Actual query input and database update:

[0450] The actual customer query entered by the user is added to the database and reflected in the next query generation.

[0451] Specific examples and prompts

[0452] As a specific use case, consider a customer support representative preparing to support a new product, "Smartwatch X." In this case, the representative enters information about "Smartwatch X" into the system, collects and analyzes related reviews, and generates predicted queries based on the results, conducting mock sessions.

[0453] Example prompt sentence:

[0454] We will predict customer queries based on reviews of the "Smartwatch X" and conduct a mock customer support session. First, enter the product URL.

[0455] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0456] Step 1:

[0457] The user inputs the product name and category information for which they are responsible. The user inputs the product name "Smart Watch X" and the category "Wearable Device" into the system's input interface. The device sends this information to the server. Based on this input information, the server determines the URLs of the related reviews to be collected.

[0458] Step 2:

[0459] The server collects URLs of related product reviews and parses the text data. The server scrapes product review pages from the web based on product name and category information. This process uses the requests and BeautifulSoup libraries. The collected review text data is stored for subsequent analysis.

[0460] Step 3:

[0461] The server uses natural language processing technology to extract important keywords from reviews. The collected text data is analyzed using the spacy library to identify nouns and related important keywords. For example, "battery life" and "fitness features" are extracted. This data processing identifies important keywords.

[0462] Step 4:

[0463] The server generates predicted customer queries based on the analysis results. Based on the extracted important keywords, it generates predicted customer queries. For example, a query such as "What is the battery life of Smartwatch X?" is created. These queries are stored in a database.

[0464] Step 5:

[0465] The terminal sequentially displays queries generated in a simulated customer support format and accepts responses from the user. The terminal displays the queries received from the server to the user. The user inputs a text response to the query, and the terminal sends the response to the server. The input from the user is saved as response data.

[0466] Step 6:

[0467] The server runs an emotion engine based on the user's responses during the simulated session to recognize emotions. Using the EmotionRecognizer library, emotions such as "happiness" or "anxiety" are extracted from the user's responses. For example, if a user responds, "I think this feature is very good," "happiness" is recognized as the emotion.

[0468] Step 7:

[0469] The server analyzes the saved user answers and generates and displays feedback. It uses the TextBlob library to evaluate the positivity and subjectivity of the answer, and generates feedback taking into account the results of emotion recognition. For example, feedback such as "Your answer is positive, and including specific examples would make it even better" is generated. The feedback is displayed on the device.

[0470] Step 8:

[0471] The user inputs a query received from a real customer support service into the system. The user inputs the query received from a real customer through the interface, and the device sends it to the server. For example, a query such as "Please tell me about the waterproof performance of Smartwatch X" is input.

[0472] Step 9:

[0473] The server adds the actual query entered to the database and reflects it in the next query generation. By saving the actual query entered by the user in the database and using that data when generating the next query, it becomes possible to provide a query list that reflects the latest information.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] [Second embodiment]

[0478] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0479] 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.

[0480] 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).

[0481] 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.

[0482] 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.

[0483] 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).

[0484] 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. 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.

[0485] 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.

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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."

[0490] The present invention relates to a system that allows users to effectively prepare for interviews. This system generates interview questions based on information input by the user and provides feedback through mock interviews, allowing users to prepare for actual interviews. Detailed embodiments of this system will be described below.

[0491] System configuration

[0492] Enter user information

[0493] The terminal provides the user with an interface for entering company name and industry information. The user enters the name of the company they are applying to ("ABC Co., Ltd."), the industry ("IT industry"), and the URL of a related news article, and sends it to the system.

[0494] Collection and analysis of relevant news articles

[0495] Based on the URLs sent, the server scrapes relevant news articles from the web to collect text data. The server then uses natural language processing techniques to analyze this text data and understand the content of the articles, for example by extracting important keywords and phrases from the articles.

[0496] Generate and save interview questions

[0497] The server uses the keywords extracted from the analysis results to generate interview questions related to the company and industry the candidate is applying for. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?" This question is then saved in a database.

[0498] Mock interviews

[0499] When the user presses a button to start the mock interview, the server sends a list of questions that are displayed sequentially on the device. The user enters answers to the questions in the text box and submits the answer. For example, the user might enter, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[0500] Analysis of responses and feedback

[0501] The server analyzes the user's answers using natural language processing technology and evaluates their content. Specifically, it judges the specificity and relevance of the answers. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device.

[0502] Enter questions asked in the actual interview

[0503] An interface is provided for users to provide feedback to the system about the questions they received during the actual interview. For example, the user can enter "I was asked about my specific project management experience" and submit the feedback.

[0504] Database Update

[0505] The server stores the entered actual interview questions in a database and reflects them in the question list for future mock interviews. This allows the system to always provide a question list that incorporates the latest interview question trends.

[0506] Specific examples

[0507] Let's say a user is applying to work for a company called "X Corporation" in the "financial industry." The user enters the URL of a related news article and submits it. The system retrieves the news article from the URL, analyzes it using natural language processing technology, and extracts keywords such as "X Corporation's new financial service." The system then generates a question, "What do you think about X Corporation's new financial service?" and presents it to the user through a mock interview. The system analyzes the user's answers and provides feedback such as "It would be good to mention the specific service name and features." The user then provides feedback to the system with the question they received in the actual interview, "Tell us about your experience managing specific financial projects," and the database is updated.

[0508] In this way, users can have continuously up-to-date information about their interview preparation, and the feedback provided helps users understand and improve their weaknesses.

[0509] The processing flow will be explained below.

[0510] Step 1:

[0511] A user accesses the system and logs in or creates a new account.

[0512] Step 2:

[0513] The device will display a form for entering the company name, industry, and the URL of a related news article.

[0514] Step 3:

[0515] The user enters the company name "ABC Co., Ltd.", the industry "IT industry," and the URL of a related news article, and presses the send button.

[0516] Step 4:

[0517] The server receives the company name, industry, and news article URL that were sent.

[0518] Step 5:

[0519] The server scrapes related news articles from the news article URLs and collects text data.

[0520] Step 6:

[0521] The server analyzes the collected text data of news articles using natural language processing technology.

[0522] Step 7:

[0523] The server extracts important keywords and phrases from the analysis results, such as "ABC Corporation's latest project" or "technology trends."

[0524] Step 8:

[0525] The server generates questions that are likely to be asked in an interview based on the extracted keywords and company information. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?"

[0526] Step 9:

[0527] The server stores the generated questions in a database.

[0528] Step 10:

[0529] The user presses a button to start the mock interview from the mock interview menu.

[0530] Step 11:

[0531] The server loads the saved question list into a task queue and prepares it to be sent to the terminal in order.

[0532] Step 12:

[0533] The server sends the first question to the terminal and displays it. For example, it displays "What do you think about ABC Corporation's latest project?"

[0534] Step 13:

[0535] The user enters an answer in the text box and presses the submit button.

[0536] Step 14:

[0537] The server receives and stores the user's answers.

[0538] Step 15:

[0539] The server analyzes the saved user responses using natural language processing techniques.

[0540] Step 16:

[0541] The server evaluates the depth, specificity, and relevance of the response.

[0542] Step 17:

[0543] The server generates feedback based on the evaluation results, such as "Your response is not specific enough. Please provide a specific project name."

[0544] Step 18:

[0545] The server sends the feedback to the terminal for display.

[0546] Step 19:

[0547] The user accesses a form that allows them to enter questions from the actual interview into the system.

[0548] Step 20:

[0549] The user enters, for example, "I was asked about my specific project management experience" and presses the submit button.

[0550] Step 21:

[0551] The server stores the questions asked in the actual interview in a database.

[0552] Step 22:

[0553] The server updates the question list for the next and subsequent mock interviews based on the new questions.

[0554] Example 1

[0555] 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."

[0556] Conventional interview preparation systems have difficulty generating appropriate interview questions based on the information entered by the user, which means that they do not adequately improve the ability to respond to questions required in actual interviews. Furthermore, when providing feedback, there is a lack of specific improvements and suggestions, which makes it difficult to fully improve users' skills. Furthermore, there is no system that can reflect questions asked in actual interviews, making it difficult to provide interview practice based on the latest information.

[0557] 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.

[0558] In this invention, the server includes: a means for inputting the name and industry information of the company the user is applying to; a means for collecting URLs of related news articles and analyzing the text data; a means for extracting important keywords from the news articles using natural language processing technology; a means for generating predicted interview questions using a generative AI model based on the keywords and company information; a means for saving the generated questions in a database; a means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers; a means for analyzing the answers using natural language processing technology and generating and displaying feedback including areas for improvement and specific suggestions; a means for the user to input questions asked in an actual interview; and a means for adding the input actual interview questions to the database and reflecting them in the next question update. This allows users to effectively prepare for interviews based on the latest and most relevant information, and the feedback can lead to concrete improvements. Furthermore, real-time information updates allow interview practice that always incorporates the latest question trends.

[0559] "User" means an individual or entity who uses the System to prepare for an interview.

[0560] "Name of desired company" is the name of the company where the user wishes to have an interview.

[0561] "Industry information" is information about the industry or economic field to which the company you are applying to belongs.

[0562] A "URL" is a uniform resource locator for a resource on the Web; it is an address that points to the relevant news article.

[0563] "Text data" is data that expresses the contents of collected news articles as digital strings of characters.

[0564] "Natural language processing technology" is a technology for processing human natural language using a computer, and is used to analyze text data.

[0565] "Keywords" are important words and phrases extracted from news articles and used to generate interview questions.

[0566] A "generative AI model" is a model that uses artificial intelligence technology to generate new text and questions.

[0567] "Interview questions" are questions related to the company or industry the user is applying for in an interview, and require the user to answer.

[0568] A "database" is an information system for collecting and managing data within a system.

[0569] The "mock interview format" refers to the display means and operation means of the system that allows practice in a format similar to a real interview.

[0570] "Feedback" is information that includes evaluation of the user's response, areas for improvement, and specific suggestions.

[0571] The "questions asked in an actual interview" are specific questions that the user was asked in an actual interview.

[0572] This invention relates to a system that allows users to effectively prepare for interviews. The system generates interview questions based on information input by the user and provides feedback through mock interviews, allowing users to prepare for actual interviews.

[0573] The system uses the following hardware and software. The hardware requires a server and a terminal; specifically, the server is a cloud server with powerful computing power (such as Amazon Web Services or Microsoft Azure). The terminal is the user's personal computer or smartphone. The software uses Python and its library BeautifulSoup for web scraping, spaCy and NLTK for natural language processing technology, and GPT-3 for the generative AI model.

[0574] First, the terminal provides the user with an interface for entering company names and industry information. The user enters the name of the company they are applying for, industry information, and the URL of a related news article, and submits it to the system. The input data is sent to the server using an HTML form or JavaScript.

[0575] The server then receives the URL sent from the device and performs web scraping using Python's BeautifulSoup library to collect text data from the news articles. The collected text data is then analyzed using natural language processing techniques (spaCy and NLTK). Specifically, processes such as tokenization, POS tagging, and named entity recognition are performed to extract important keywords and phrases.

[0576] Next, the server uses a deep learning model (a generative AI model such as GPT-3) to generate interview questions based on keywords extracted from the analysis results. For example, a question might be generated such as, "What do you think about the latest project at the company you're applying to?" The generated questions are stored in an SQL database (PostgreSQL or MySQL).

[0577] When a user starts a mock interview, the server retrieves a list of questions from the database and displays them sequentially on the device. The user enters answers to the questions in the text boxes and submits the answer. For example, the user might respond, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[0578] The server receives the user's response and analyzes it again using natural language processing technology (spaCy or GPT-3). Specifically, it evaluates the specificity, relevance, and logic of the response. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device. For example, it provides feedback such as, "Your response would be more persuasive if you provided specific examples."

[0579] Furthermore, the terminal provides the user with an interface for inputting questions from actual interviews. The user inputs "I was asked about specific project management experience" and submits the request. This actual interview question is also saved in the database and reflected in the question list for future mock interviews.

[0580] For example, the prompts for entering the company name and industry information are as follows:

[0581] "Please enter the name of the company you are applying to, the industry, and the URL of a related news article below."

[0582] The mock interview begins with a prompt such as:

[0583] "Press the button to begin the mock interview."

[0584] Example questions include:

[0585] "Please answer the following question: How do you feel about the new financial services offered by your desired company?"

[0586] This process allows users to prepare effectively for interviews based on the latest and most relevant information, and they can expect to make concrete improvements based on feedback.In addition, real-time updates of information allow users to practice interviews while always incorporating the latest question trends.

[0587] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0588] Step 1:

[0589] The terminal provides an interface for inputting company names, industry information, and URLs of related news articles. When the user inputs the company name "Corporation," the industry "IT industry," and the URLs of related news articles into the input format and presses the send button, this information is sent to the server. The input data is sent to the server using an HTML form or JavaScript.

[0590] Input: Company name, industry information, URL of related news article

[0591] Output: Sending information to the server

[0592] Step 2:

[0593] The server receives the URL sent from the device and performs web scraping using Python's BeautifulSoup library. Specifically, it uses the requests library to retrieve HTML content from the specified URL and extracts text data from news articles.

[0594] Input: URL of related news article

[0595] Output: News article text data

[0596] Step 3:

[0597] The server analyzes the collected text data using natural language processing techniques (spaCy and NLTK libraries), specifically tokenizing, POS tagging, and named entity recognition to extract important keywords and phrases.

[0598] Input: News article text data

[0599] Output: Important keywords and phrases

[0600] Step 4:

[0601] The server generates interview questions using a generative AI model (e.g., GPT-3) based on the keywords extracted from the analysis results. Specifically, the keywords and company information are input into the model, and the generated questions are retrieved. For example, a question such as "What do you think about a certain company's latest project?" is generated.

[0602] Input: Important keywords and company information

[0603] Output: Generated interview questions

[0604] Step 5:

[0605] The server stores the generated interview questions in an SQL database (PostgreSQL or MySQL) by adding the question text and related information as new rows in a database table.

[0606] Input: Generated interview questions

[0607] Output: Questions saved in the database

[0608] Step 6:

[0609] When the user presses the start button for the mock interview, the server retrieves a list of questions from the database and displays them sequentially on the terminal. For example, a question such as "How do you feel about a certain company's new product?" may be displayed. The user enters their answer to the displayed question in the text box and presses the send button.

[0610] Input: A list of questions retrieved from the database

[0611] Output: Question displayed on terminal and user's response

[0612] Step 7:

[0613] The server receives the user's response and analyzes it using natural language processing technology. Specifically, it runs an analysis algorithm that evaluates the specificity, relevance, and logic of the response.

[0614] Input: User's answer

[0615] Output: Analysis results

[0616] Step 8:

[0617] Based on the analysis results, the server generates feedback including areas for improvement and specific suggestions. For example, it might generate feedback such as, "If you provide specific examples, it will be more persuasive." The generated feedback is displayed on the device.

[0618] Input: Analysis results

[0619] Output: Feedback displayed on the terminal

[0620] Step 9:

[0621] The terminal provides the user with an interface for inputting questions that they would have received in an actual interview. For example, the user might input, "I was asked about my specific project management experience," and press the send button.

[0622] Input: User input of questions asked in the actual interview

[0623] Output: Actual interview questions sent to the server

[0624] Step 10:

[0625] The server saves the actual interview questions sent by the user in a database. The saved questions are reflected in the question list for the next mock interview. This allows the system to always incorporate the latest question trends.

[0626] Input: Actual interview questions submitted by the user

[0627] Output: Actual interview questions stored in a database

[0628] (Application example 1)

[0629] 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."

[0630] Conventional interview preparation systems focus solely on providing interview questions and feedback, but do not address specific training or skill development in specific work or technical fields. In particular, there is a lack of efficient means for providing practical training, such as operating and troubleshooting automated equipment in factories. This makes it difficult for employees to effectively acquire the skills actually required in factories. To solve this issue, a system is needed that allows users to receive specific training related to factory operations.

[0631] 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.

[0632] In this invention, the server includes: means for inputting the name of the company and industry information for which the user is applying; means for collecting URLs of related news articles and analyzing the text data; means for extracting important keywords from the news articles using natural language processing technology; means for generating anticipated interview questions based on the keywords and company information; means for saving the generated questions in a database; means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers; means for analyzing the answers and generating and displaying feedback; means for the user to input questions asked in an actual interview; means for adding the input questions to the database and reflecting them in the next question update; means for generating and displaying training questions related to the operation of automated equipment in a factory; and means for evaluating the responses and providing feedback based on the user's answers. This allows users to receive practical operational training in a factory and effectively acquire skills directly related to actual work.

[0633] "User" refers to an individual or employee who uses the system to prepare for an interview or for factory training.

[0634] "Company name" refers to the name of the specific company for which the user is applying.

[0635] "Industry information" refers to information related to the industry or field to which a company belongs.

[0636] "Related news articles" refer to articles that describe the latest news or events related to a company or industry.

[0637] "URL" refers to Internet link information that indicates the address of a web page.

[0638] "Text data" refers to the written information obtained from news articles and text.

[0639] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[0640] "Keywords" refer to important words and phrases extracted from news articles and company information.

[0641] "Interview Questions" refers to questions that may be asked of you in a job interview.

[0642] A "database" refers to a computer system for systematically organizing and storing information.

[0643] A "mock interview" is a form of practice conducted to simulate a real interview.

[0644] "Answer" refers to the response a user gives to a question during a mock interview or training.

[0645] "Feedback" refers to information that evaluates an answer or points out areas for improvement.

[0646] "Input" refers to the act of a user providing information to a system.

[0647] "Automation equipment" refers to robots and automated machines used in factories, etc.

[0648] "Operational training" refers to training that teaches users how to operate and troubleshoot automated equipment.

[0649] "Response evaluation" refers to the act of analyzing the content of a user's response and evaluating its quality.

[0650] This invention is a system for enabling users to effectively operate and train automated equipment in factories. This system comprises the following steps:

[0651] 1. Entering user information

[0652] First, the terminal provides the user with an interface for entering company name and industry information. The user enters the company name and industry information they wish to work for and sends it to the system. For example, the user may enter "manufacturing."

[0653] 2. Collection and analysis of related news articles

[0654] Based on the submitted URL, the server scrapes relevant news articles from the web to collect text data. The server then uses natural language processing techniques to analyze this text data and understand the content of the article. For example, it extracts important keywords and phrases from the article. Specifically, it uses Python's BeautifulSoup and requests libraries to retrieve web page data, and Hugging Face's transformers library to perform natural language processing.

[0655] 3. Generate and save training questions

[0656] The server uses the keywords extracted from the analysis results to generate training questions related to the company or industry, such as "What do you think about the latest robot operation technology?" These questions are then stored in a database.

[0657] 4. Conducting mock training

[0658] When the user presses a button to start the simulation training, the server sends a list of questions to the terminal, which are displayed one after the other. The user enters answers to the questions in the text box and submits the answer. For example, the user might enter, "The latest technology is extremely important for dramatically improving production efficiency."

[0659] 5. Analysis of answers and feedback

[0660] The server analyzes the user's responses using natural language processing technology and evaluates their content. Specifically, it determines the specificity and relevance of the responses. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device. The OpenAI API is used to evaluate responses and generate appropriate feedback.

[0661] 6. Input of actual operation feedback

[0662] An interface is provided for users to provide feedback and problems they have experienced during actual operation or training to the system. For example, users can input and submit a message such as, "Please tell us about your specific troubleshooting experiences during operation."

[0663] 7. Updating the database

[0664] The server stores the inputted actual operation feedback in a database and reflects it in the question list for the next mock training session, allowing the system to always provide a question list that incorporates the latest trends in training content.

[0665] As a concrete example, consider the case where a user requests "Training in factory automation technology in the manufacturing industry." In this case, the system extracts keywords such as "automation technology" and "robot operation" from related news articles and generates the question, "What do you think about the latest trends in automation technology?" The user can enter an answer and receive feedback on their response, allowing them to effectively acquire the skills required in an actual factory.

[0666] An example prompt might look like this:

[0667] You are in the manufacturing industry and are being trained to operate automated equipment. Using information from a news article, answer the following questions:

[0668] 1. What do you think about the latest robotic manipulation technology?

[0669] 2. What is your experience troubleshooting robot operations?

[0670] This system allows users to undergo simulated training based on real-life operating situations, enabling them to effectively acquire the skills necessary for actual factory work.

[0671] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0672] Step 1:

[0673] The terminal provides the user with an interface for entering company names and industry information. The user enters the company name and industry information they wish to work for and sends it to the system. The information entered includes "company name" and "industry information." This allows the system to understand the user's specific wishes.

[0674] Step 2:

[0675] The server receives the URL sent by the user and scrapes related news articles from the web to collect text data. Specifically, it accesses web pages using Python's requests library and extracts text data using the BeautifulSoup library. The input is the "URL of the news article" and the output is the "scraped text data."

[0676] Step 3:

[0677] The server uses natural language processing technology to analyze the collected text data and understand the content of the articles. Specifically, it uses Hugging Face's transformers library to extract important keywords and phrases from the text data. The input is "text data" and the output is "important keywords and phrases."

[0678] Step 4:

[0679] The server uses the extracted keywords to generate predicted questions from training related to the company and industry. A generative AI model is used to generate "predicted questions" from "keywords" and "company information." For example, it generates a question such as "What do you think about the latest robot operation technology?" The input here is "keywords" and "company information," and the output is the "generated question."

[0680] Step 5:

[0681] The server saves the generated question in a database. The saved information is the "generated question" and is prepared for display to the user in later processing. The input is the "generated question" and the output is the "question saved in the database."

[0682] Step 6:

[0683] When the user presses a button to start the simulated training, the server sends a list of questions to the terminal in order for them to be displayed. The user receives the training questions in order, enters their answers in the text box, and sends them. The input is the "user's confirmation action," and the output is the "question displayed on the terminal" and the "user's answer."

[0684] Step 7:

[0685] The server analyzes the user's answers using natural language processing technology and evaluates their content. Specifically, it determines the specificity and relevance of the answers. It analyzes the "user's answers" using the OpenAI API and generates "evaluation results and feedback." The input is the "user's answers" and the output is "evaluation results and feedback."

[0686] Step 8:

[0687] Based on the evaluation results, the server generates feedback including areas for improvement and specific suggestions, which is displayed on the device. The user can review this feedback and use it for the next training session. The input is "evaluation results and feedback," and the output is "feedback display on the device."

[0688] Step 9:

[0689] An interface is provided that allows users to provide feedback and problems they have received during actual operations and training to the system. Users input and send specific feedback and problems. The input is "feedback from operations and training," and the output is "sending feedback data to the server."

[0690] Step 10:

[0691] The server stores the inputted actual operation feedback in a database and reflects it in the question list for the next and subsequent mock training sessions. This allows the server to provide a question list that always incorporates the latest trends in training content. The input is "feedback from the user" and the output is "feedback stored in the database."

[0692] 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.

[0693] This invention relates to a system that allows users to effectively prepare for interviews, and in particular provides an innovative system that recognizes the user's emotions and reflects them in feedback by combining an emotion engine. An embodiment of this system will be described in detail below.

[0694] System configuration

[0695] Enter user information

[0696] The terminal provides the user with an interface for entering company name and industry information. The user enters the name of the company they are applying to ("ABC Co., Ltd."), the industry ("IT industry"), and the URL of a related news article, and sends it to the system.

[0697] Collection and analysis of relevant news articles

[0698] The server scrapes relevant news articles from the web based on the submitted URL and collects text data. The server then analyzes this text data using natural language processing techniques to understand the content of the article, specifically extracting important keywords and phrases.

[0699] Generate and save interview questions

[0700] The server uses the extracted keywords to generate potential interview questions based on company information. For example, it generates a question like, "What do you think about ABC Corporation's latest project?" The generated questions are stored in a database.

[0701] Mock interviews

[0702] When a user starts a mock interview, the server sequentially sends a list of questions to the terminal and displays them. The user enters answers to the questions in the text boxes and submits the answer. For example, the user might enter, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[0703] Emotion recognition by emotion engine

[0704] During the mock interview, the device runs an emotion engine based on the user's text responses and facial expression data to recognize the user's emotions. The emotion engine recognizes emotions such as "happiness," "anxiety," and "confidence."

[0705] Analysis of responses and feedback

[0706] The server analyzes the saved user responses using natural language processing technology and evaluates them, taking into account the results of the emotion engine. Specifically, it considers the specificity and relevance of the responses as well as the user's emotional state. Based on the results, it generates feedback including areas for improvement and specific suggestions, which are displayed on the device.

[0707] Enter questions asked in the actual interview

[0708] An interface is provided for users to feed back to the system the questions they received in the actual interview. For example, the user can input "I was asked about my specific project management experience" and submit it.

[0709] Database Update

[0710] The server saves the entered actual interview questions in a database and reflects them in the question list for future mock interviews, allowing the system to always provide a question list that incorporates the latest interview question trends.

[0711] Specific examples

[0712] Let's say a user is applying to work for a company called "X Corporation" in the "financial industry." The user enters the URL of a related news article and submits it. The system retrieves the news article from the URL, analyzes it using natural language processing technology, and extracts keywords such as "X Corporation's new financial service." The system then generates a question, "What do you think about X Corporation's new financial service?" and presents it to the user through a mock interview. The system analyzes the user's answer and the emotions recognized by the emotion engine, and provides feedback such as, "It would be good if you mentioned the specific name and features of the service. Also, it's good that you answered with confidence, but it would be even better if you included more specific experiences." The user then feeds back to the system the question they received in the actual interview, "Tell us about your experience managing specific financial projects," and the database is updated.

[0713] In this way, users can continuously prepare for their interviews taking into account their current information and emotional state, and the feedback provided allows users to understand and improve their weaknesses.

[0714] The processing flow will be explained below.

[0715] Of course, the specific processing flow of the system will be explained below by dividing it into steps.

[0716] Step 1:

[0717] A user accesses the system and logs in or creates a new account.

[0718] Step 2:

[0719] The device will display a form for entering the company name, industry, and the URL of a related news article.

[0720] Step 3:

[0721] The user enters the company name "ABC Co., Ltd.", the industry "IT industry," and the URL of a related news article, and presses the send button.

[0722] Step 4:

[0723] The server receives the company name, industry, and news article URL that were sent.

[0724] Step 5:

[0725] The server scrapes related news articles from the news article URLs and collects text data.

[0726] Step 6:

[0727] The server analyzes the collected text data of news articles using natural language processing technology.

[0728] Step 7:

[0729] The server extracts important keywords and phrases from the analysis results, such as "ABC Corporation's latest project" or "technology trends."

[0730] Step 8:

[0731] The server generates questions that are likely to be asked in an interview based on the extracted keywords and company information. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?"

[0732] Step 9:

[0733] The server stores the generated questions in a database.

[0734] Step 10:

[0735] The user presses a button to start the mock interview from the mock interview menu.

[0736] Step 11:

[0737] The server loads the saved question list into a task queue and prepares it to be sent to the terminal in order.

[0738] Step 12:

[0739] The server sends the first question to the terminal and displays it. For example, it displays "What do you think about ABC Corporation's latest project?"

[0740] Step 13:

[0741] The user enters an answer in the text box and presses the submit button.

[0742] Step 14:

[0743] The server receives and stores the user's answers.

[0744] Step 15:

[0745] During the mock interview, the device uses a camera and microphone to collect the user's facial expressions and voice and transmits them to the emotion engine.

[0746] Step 16:

[0747] The emotion engine on the server analyzes the user's facial expressions and voice data to recognize emotions, such as "happiness," "anxiety," and "confidence."

[0748] Step 17:

[0749] The server analyzes the saved user responses using natural language processing technology, evaluating their depth, specificity, and relevance, while also taking into account the results of the emotion engine.

[0750] Step 18:

[0751] The server generates feedback based on the analysis of the answer and the emotions recognized by the emotion engine. For example, "Your answer is not specific enough. It would be better if you mentioned a specific project name. Also, it is good that you answered with confidence, but it would be even better if you included more specific experiences."

[0752] Step 19:

[0753] The server sends the feedback to the terminal for display.

[0754] Step 20:

[0755] The user accesses a form that allows them to enter questions from the actual interview into the system.

[0756] Step 21:

[0757] The user enters, for example, "I was asked about my specific project management experience" and presses the submit button.

[0758] Step 22:

[0759] The server stores the questions asked in the actual interview in a database.

[0760] Step 23:

[0761] The server updates the question list for the next and subsequent mock interviews based on the new questions.

[0762] Example 2

[0763] 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."

[0764] Existing systems for preparing Q&A questions for potential organizations often lack sufficient information gathering and appropriate Q&A content. Furthermore, they lack feedback that takes into account the user's emotional state, making it difficult to improve performance in mock questions or actual Q&A sessions. The present invention aims to solve these problems by providing a system that allows users to effectively prepare and improve Q&A questions.

[0765] 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 inputting the name and industry information of the organization the user is interested in; means for collecting links to related information articles and analyzing text data; means for extracting important keywords from the information articles using natural language processing technology; means for generating predicted questions based on the keywords and organization information; means for saving the generated questions in a storage device; means for sequentially displaying the questions to the user in the form of mock questions and saving the user's answers; means for analyzing the answers, generating and displaying evaluations and responses; means for the user to input questions asked in actual question-and-answer sessions; means for adding the input questions to a storage device and reflecting them in the next question update; emotion recognition means for analyzing the user's answers and facial expression data and recognizing the user's emotional state; and means for including the recognition results in feedback. This enables the user to collect related information, generate questions, and provide feedback that takes emotions into account.

[0766] "User" means a person who uses the system to prepare questions and answers for a prospective organization.

[0767] "Organization name" is information that indicates the name of the company or organization that the user is applying to.

[0768] "Industry information" is information about the type of industry or business to which the organization to which the applicant belongs.

[0769] "Link" refers to a web address that points to a related article of information.

[0770] "Text data" refers to textual information obtained through scraping or analysis.

[0771] "Natural language processing technology" refers to technology for analyzing acquired text data and extracting meaningful information.

[0772] "Keywords" refer to important words or phrases extracted from text data.

[0773] "Question and answer content" refers to anticipated questions generated using natural language processing technology.

[0774] "Storage device" refers to a device for storing the generated questions and answers, answer data, and other necessary information.

[0775] "Mock question format" refers to a method in which anticipated questions are presented in a format similar to an actual questioning environment, and users respond to them.

[0776] "Answer" refers to a user's answer to a question presented in the form of a mock question.

[0777] "Evaluation and response" refers to feedback and suggestions generated based on the analyzed answer data.

[0778] "Emotion recognition means" refers to technology that analyzes a user's answers and facial expression data to recognize their emotional state.

[0779] This invention relates to a system that allows users to effectively prepare for Q&A sessions, and in particular provides an innovative system that recognizes the user's emotions and reflects them in feedback by incorporating an emotion recognition engine. An embodiment of this system will now be described in detail.

[0780] System configuration

[0781] Enter user information

[0782] The terminal provides the user with an interface for entering information about the organization's name and industry. The user enters the name of the organization they wish to apply for ("Organization XYZ"), the industry ("Technology field"), and a link to a related news article, and sends it to the system.

[0783] Collection and analysis of relevant news articles

[0784] The server scrapes relevant news articles from the web based on the submitted links and collects text data using Python's BeautifulSoup. The server then analyzes this text data using natural language processing techniques (e.g., spaCy, NLTK) to extract important keywords and phrases.

[0785] Generate and save interview questions

[0786] Based on the extracted keywords, the server uses a generative AI model (e.g., GPT-3) to generate predicted questions based on the organization information. An example of a prompt used for generation is, "Please generate questions related to 'technological innovation.'" The generated questions are saved in a storage device.

[0787] Mock question session

[0788] When a user starts a mock question, the server sequentially sends the generated list of questions to the terminal, which then displays them. The user enters answers to each question in the text box and submits it. For example, in response to the question "What do you think about the impact of new technological innovations on the market?", the user enters "I think new technological innovations will improve market competitiveness."

[0789] Emotion recognition using an emotion recognition engine

[0790] During the mock questions, the device collects the user's text responses and facial expression data, and uses an emotion recognition engine (e.g., Microsoft Azure Cognitive Services) to recognize the user's emotions. The emotion recognition engine recognizes emotions such as "happiness," "anxiety," and "confidence."

[0791] Analysis of responses and feedback

[0792] The server analyzes the user's saved answers using natural language processing technology and evaluates them taking into account the results of an emotion recognition engine. For example, it evaluates the specificity and relevance of the answer and generates feedback based on the recognized emotional state. The feedback might be something like, "It would be good to include a specific example. Also, it's good that you're answering with confidence, but it would be even better if you included a more specific experience." The generated feedback is displayed on the device.

[0793] Enter questions asked during the actual Q&A session

[0794] The terminal provides the user with an interface for feedback on the questions asked during the actual Q&A session. For example, the user can input "I was asked about my specific project management experience" and submit.

[0795] Database Update

[0796] The server saves the questions entered in the actual Q&A session in a storage device and reflects them in the Q&A list for the next mock question session onwards, allowing the system to always provide a list that incorporates the latest trends in Q&A questions.

[0797] Specific examples

[0798] For example, suppose a user is applying to work for "Organization ABC" in the "finance industry." The user inputs and submits a link to a related news article. The server retrieves the news article from the link, analyzes it using natural language processing technology, and extracts keywords such as "Organization ABC's new financial service." The server then generates a question, "How do you feel about Organization ABC's new financial service?" and provides it to the user through a mock question. The server analyzes the user's answer and the emotions recognized by the emotion recognition engine, and provides feedback such as, "It would be good if you mentioned the specific service name and features. Also, it is good that you answered with confidence, but it would be even better if you included more specific experiences." The user then feeds back the question they received in the actual Q&A session, "Tell me about your experience managing specific financial projects," to the system and updates the storage device.

[0799] In this way, users can continuously prepare questions and answers that take into account the latest information and their emotional state, and the feedback provided allows users to understand and improve their weaknesses.

[0800] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0801] Step 1: Enter user information

[0802] Input: The user enters the name of the organization they wish to apply to, industry information, and links to related news articles.

[0803] Processing: The terminal receives the entered information and confirms it through the interface.

[0804] Output: Sends the entered information to the server.

[0805] Specific operation: The device displays a web form or app input screen, and after the user enters data in the input fields for "organization name," "industry," and "news article URL," clicks the send button, and the input information is sent to the server.

[0806] Step 2: Collect and analyze relevant news articles

[0807] Input: The server receives the link information.

[0808] Processing: The server scrapes the linked webpage using Python's BeautifulSoup library to collect text data, which is then analyzed using natural language processing techniques (e.g., spaCy, NLTK) to extract important keywords and phrases.

[0809] Output: A list of parsed keywords and phrases.

[0810] How it works: The server retrieves the web page from the specified URL, extracts the text using BeautifulSoup, and then performs morphological analysis on the text data using SpaCy to extract important keywords.

[0811] Step 3: Generate and save interview questions

[0812] Input: The server receives the extracted keywords and organization information.

[0813] Processing: The server sends the keywords as a prompt to a generative AI model (e.g., GPT-3) to generate questions. An example prompt is, "Please generate questions related to 'technological innovation.'"

[0814] Output: The generated questions and answers.

[0815] Specific operation: The server sends a prompt to the generation AI model, which generates the expected question and answer content. The generated question and answer content is then saved in a storage device.

[0816] Step 4: Practice Questions

[0817] Input: The user sends a request to start the mock question.

[0818] Processing: The server retrieves the list of questions from the storage device and transmits them to the terminals in order.

[0819] Output: The question list displayed on the terminal.

[0820] Specific operation: When the user clicks the "Start mock questions" button, the server retrieves the question list from the storage device, sends it to the terminal, and displays it.

[0821] Step 5: Enter and submit your answers

[0822] Input: The user enters the answer to each question.

[0823] Processing: The terminal sends the entered answer to the server.

[0824] Output: The answer data sent to the server.

[0825] Specific operation: The terminal presents questions to the user, and when the user enters answers to each question in the text boxes and presses the send button, the terminal sends the answer data to the server.

[0826] Step 6: Emotion recognition using the emotion recognition engine

[0827] Input: The server receives the submitted answer data and facial expression data.

[0828] Processing: The server uses an emotion recognition engine (e.g., Microsoft Azure Cognitive Services) to analyze the answer data and facial expression data and recognize the user's emotions.

[0829] Output: Recognized emotional state data.

[0830] Specific operation: The device sends the user's answer data and facial expression data together, and the server passes it to the emotion recognition engine for analysis.

[0831] Step 7: Analyze responses and generate feedback

[0832] Input: The server receives answer data and recognized emotional state data.

[0833] Processing: The server analyzes the answer data using natural language processing technology and evaluates it, taking into account the emotion recognition results. Based on the evaluation results, specific feedback is generated.

[0834] Output: The generated feedback.

[0835] Specific operation: The server analyzes the answer data using natural language processing tools, evaluates the specificity, relevance, and emotional state of the content, and generates feedback. This feedback is then sent to the device.

[0836] Step 8: View your feedback

[0837] Input: Sends server-generated feedback to the device.

[0838] Processing: The device displays feedback to the user.

[0839] Output: The feedback displayed to the user.

[0840] Specific behavior: The device receives feedback from the server and displays it to the user, such as "It would be good to include a specific example. Also, it's good that you're confident in your answer, but it would be even better if you included more specific experiences."

[0841] Step 9: Enter the questions asked during the Q&A session

[0842] Input: The user inputs the question asked in the actual Q&A session.

[0843] Processing: The terminal sends the entered question to the server.

[0844] Output: The query data sent to the server.

[0845] Specific operation: The terminal displays a form for the user to input the actual question, and when the user inputs the question and presses the submit button, the terminal sends the question data to the server.

[0846] Step 10: Update the Database

[0847] Input: The server receives the actual query data that was sent.

[0848] Processing: The server saves the newly entered question in a memory device and reflects it in the question and answer list from the next time onwards.

[0849] Output: Updated question list.

[0850] Specific operation: The server saves the new question data in the storage device and updates the existing question list. The newly saved questions are used in the next mock test.

[0851] (Application example 2)

[0852] 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."

[0853] In conventional customer support preparation systems, it is difficult for representatives to fully acquire the product information and knowledge necessary for customer support, and the responsiveness and accuracy of responses to customer inquiries can be reduced. Furthermore, the emotional state of representatives can affect the quality of customer support, but there is a lack of a means to effectively manage this. The present invention aims to solve these problems and improve the efficiency and quality of customer support preparation.

[0854] 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 inputting product names and category information for which the user is responsible; means for collecting URLs of related product reviews and analyzing text data; means for extracting important keywords from the reviews using natural language processing technology; means for generating predicted customer queries based on the keywords and product information; means for saving the generated queries in a database; means for sequentially displaying the queries in a simulated customer support format and saving the user's responses; means including an emotion engine that recognizes the user's emotions during the simulated session and reflects them as feedback in the evaluation results; means for analyzing the responses and generating and displaying feedback; means for inputting queries made by the user during actual support; and means for adding the input queries to a database and reflecting them in the next query update. This allows users to acquire the latest and most effective support information, manages the emotional states of staff, and enables highly accurate customer support.

[0855] "User" means any person or entity that uses the System.

[0856] "Organization name" refers to the name of the company or organization you are applying for.

[0857] "Industry information" refers to information about the industry to which the company or organization you are applying to belongs.

[0858] "Related news articles" refer to articles that cover the latest news related to the company or industry you are applying to.

[0859] "URL" refers to the web page address where the relevant news article is published online.

[0860] "Text data" refers to the textual information of collected news articles.

[0861] "Natural language processing technology" refers to computer technology for analyzing text data and understanding its meaning.

[0862] "Key words" refer to key words and phrases extracted from news articles and used to generate interview questions.

[0863] "Interview questions" refer to questions asked of users during mock interviews or actual interviews.

[0864] "Database" refers to a system for storing data such as generated questions, user responses, and questions asked in actual interviews.

[0865] A "mock interview" refers to a simulation that allows users to practice for a real interview.

[0866] "Emotion engine" refers to a system for recognizing and analyzing users' emotions.

[0867] "Feedback" refers to evaluations and improvement suggestions generated based on the user's responses and emotional state.

[0868] ·System Programming

[0869] The system's program is written in Python and includes the following main functions:

[0870] 1. Data collection function:

[0871] The server collects the URLs of the product review web pages based on the product name and category information entered by the user. This collection process uses the requests and BeautifulSoup libraries.

[0872] 2. Data analysis function:

[0873] The server analyzes the collected text data using natural language processing techniques to extract important keywords. This analysis process utilizes the spacy and TextBlob libraries.

[0874] 3. Query generation function:

[0875] The server generates a customer query based on the analysis results and stores it in a database, using the extracted important keywords.

[0876] 4. Simulation session function:

[0877] The terminal sequentially displays queries generated in a simulated customer support format and accepts the user's answers, which are then sent from the terminal to a server and stored.

[0878] 5. Emotion recognition function:

[0879] During the simulation session, the server runs an emotion engine based on the user's responses to recognize the user's emotions. This emotion recognition is performed using the EmotionRecognizer library.

[0880] 6. Feedback generation function:

[0881] The server analyzes the saved user responses and evaluates them based on the results of the emotion engine. The feedback includes specific improvements and suggestions.

[0882] 7. Actual query input function:

[0883] Users are provided with an interface to input queries received from actual customer support into the system. The input queries are added to a database and reflected in the generation of future queries.

[0884] Processing Description

[0885] To realize the above functions, the server performs the following data processing and data calculations.

[0886] 1. Data Collection:

[0887] Scrape product reviews from a URL and retrieve them as text data. Here, requests and BeautifulSoup are used.

[0888] 2. Data Analysis:

[0889] Spacy is used to perform natural language processing on the scraped text data to extract important keywords from the reviews.

[0890] 3. Query Generation:

[0891] Generate predicted customer queries based on the extracted keywords.

[0892] 4. Mock Session:

[0893] The device displays the query to the user and accepts the user's answer, which is sent to the server and stored.

[0894] 5. Emotion recognition:

[0895] The server uses the EmotionRecognizer library to recognize emotions from the user's responses.

[0896] 6. Feedback Generation:

[0897] The content of the user's response is analyzed using TextBlob, and feedback is generated taking into account the results of emotion recognition.

[0898] 7. Actual query input and database update:

[0899] The actual customer query entered by the user is added to the database and reflected in the next query generation.

[0900] Specific examples and prompts

[0901] As a specific use case, consider a customer support representative preparing to support a new product, "Smartwatch X." In this case, the representative enters information about "Smartwatch X" into the system, collects and analyzes related reviews, and generates predicted queries based on the results, conducting mock sessions.

[0902] Example prompt sentence:

[0903] We will predict customer queries based on reviews of the "Smartwatch X" and conduct a mock customer support session. First, enter the product URL.

[0904] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0905] Step 1:

[0906] The user inputs the product name and category information for which they are responsible. The user inputs the product name "Smart Watch X" and the category "Wearable Device" into the system's input interface. The device sends this information to the server. Based on this input information, the server determines the URLs of the related reviews to be collected.

[0907] Step 2:

[0908] The server collects URLs of related product reviews and parses the text data. The server scrapes product review pages from the web based on product name and category information. This process uses the requests and BeautifulSoup libraries. The collected review text data is stored for subsequent analysis.

[0909] Step 3:

[0910] The server uses natural language processing technology to extract important keywords from reviews. The collected text data is analyzed using the spacy library to identify nouns and related important keywords. For example, "battery life" and "fitness features" are extracted. This data processing identifies important keywords.

[0911] Step 4:

[0912] The server generates predicted customer queries based on the analysis results. Based on the extracted important keywords, it generates predicted customer queries. For example, a query such as "What is the battery life of Smartwatch X?" is created. These queries are stored in a database.

[0913] Step 5:

[0914] The terminal sequentially displays queries generated in a simulated customer support format and accepts responses from the user. The terminal displays the queries received from the server to the user. The user inputs a text response to the query, and the terminal sends the response to the server. The input from the user is saved as response data.

[0915] Step 6:

[0916] The server runs an emotion engine based on the user's responses during the simulated session to recognize emotions. Using the EmotionRecognizer library, emotions such as "happiness" or "anxiety" are extracted from the user's responses. For example, if a user responds, "I think this feature is very good," "happiness" is recognized as the emotion.

[0917] Step 7:

[0918] The server analyzes the saved user answers and generates and displays feedback. It uses the TextBlob library to evaluate the positivity and subjectivity of the answer, and generates feedback taking into account the results of emotion recognition. For example, feedback such as "Your answer is positive, and including specific examples would make it even better" is generated. The feedback is displayed on the device.

[0919] Step 8:

[0920] The user inputs a query received from a real customer support service into the system. The user inputs the query received from a real customer through the interface, and the device sends it to the server. For example, a query such as "Please tell me about the waterproof performance of Smartwatch X" is input.

[0921] Step 9:

[0922] The server adds the actual query entered to the database and reflects it in the next query generation. By saving the actual query entered by the user in the database and using that data when generating the next query, it becomes possible to provide a query list that reflects the latest information.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] [Third embodiment]

[0927] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0928] 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.

[0929] 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).

[0930] 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.

[0931] 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.

[0932] 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).

[0933] 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. 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.

[0934] 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.

[0935] 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.

[0936] 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.

[0937] 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.

[0938] 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."

[0939] The present invention relates to a system that allows users to effectively prepare for interviews. This system generates interview questions based on information input by the user and provides feedback through mock interviews, allowing users to prepare for actual interviews. Detailed embodiments of this system will be described below.

[0940] System configuration

[0941] Enter user information

[0942] The terminal provides the user with an interface for entering company name and industry information. The user enters the name of the company they are applying to ("ABC Co., Ltd."), the industry ("IT industry"), and the URL of a related news article, and sends it to the system.

[0943] Collection and analysis of relevant news articles

[0944] Based on the URLs sent, the server scrapes relevant news articles from the web to collect text data. The server then uses natural language processing techniques to analyze this text data and understand the content of the articles, for example by extracting important keywords and phrases from the articles.

[0945] Generate and save interview questions

[0946] The server uses the keywords extracted from the analysis results to generate interview questions related to the company and industry the candidate is applying for. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?" This question is then saved in a database.

[0947] Mock interviews

[0948] When the user presses a button to start the mock interview, the server sends a list of questions that are displayed sequentially on the device. The user enters answers to the questions in the text box and submits the answer. For example, the user might enter, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[0949] Analysis of responses and feedback

[0950] The server analyzes the user's answers using natural language processing technology and evaluates their content. Specifically, it judges the specificity and relevance of the answers. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device.

[0951] Enter questions asked in the actual interview

[0952] An interface is provided for users to provide feedback to the system about the questions they received during the actual interview. For example, the user can enter "I was asked about my specific project management experience" and submit the feedback.

[0953] Database Update

[0954] The server stores the entered actual interview questions in a database and reflects them in the question list for future mock interviews. This allows the system to always provide a question list that incorporates the latest interview question trends.

[0955] Specific examples

[0956] Let's say a user is applying to work for a company called "X Corporation" in the "financial industry." The user enters the URL of a related news article and submits it. The system retrieves the news article from the URL, analyzes it using natural language processing technology, and extracts keywords such as "X Corporation's new financial service." The system then generates a question, "What do you think about X Corporation's new financial service?" and presents it to the user through a mock interview. The system analyzes the user's answers and provides feedback such as "It would be good to mention the specific service name and features." The user then provides feedback to the system with the question they received in the actual interview, "Tell us about your experience managing specific financial projects," and the database is updated.

[0957] In this way, users can have continuously up-to-date information about their interview preparation, and the feedback provided helps users understand and improve their weaknesses.

[0958] The processing flow will be explained below.

[0959] Step 1:

[0960] A user accesses the system and logs in or creates a new account.

[0961] Step 2:

[0962] The device will display a form for entering the company name, industry, and the URL of a related news article.

[0963] Step 3:

[0964] The user enters the company name "ABC Co., Ltd.", the industry "IT industry," and the URL of a related news article, and presses the send button.

[0965] Step 4:

[0966] The server receives the company name, industry, and news article URL that were sent.

[0967] Step 5:

[0968] The server scrapes related news articles from the news article URLs and collects text data.

[0969] Step 6:

[0970] The server analyzes the collected text data of news articles using natural language processing technology.

[0971] Step 7:

[0972] The server extracts important keywords and phrases from the analysis results, such as "ABC Corporation's latest project" or "technology trends."

[0973] Step 8:

[0974] The server generates questions that are likely to be asked in an interview based on the extracted keywords and company information. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?"

[0975] Step 9:

[0976] The server stores the generated questions in a database.

[0977] Step 10:

[0978] The user presses a button to start the mock interview from the mock interview menu.

[0979] Step 11:

[0980] The server loads the saved question list into a task queue and prepares it to be sent to the terminal in order.

[0981] Step 12:

[0982] The server sends the first question to the terminal and displays it. For example, it displays "What do you think about ABC Corporation's latest project?"

[0983] Step 13:

[0984] The user enters an answer in the text box and presses the submit button.

[0985] Step 14:

[0986] The server receives and stores the user's answers.

[0987] Step 15:

[0988] The server analyzes the saved user responses using natural language processing techniques.

[0989] Step 16:

[0990] The server evaluates the depth, specificity, and relevance of the response.

[0991] Step 17:

[0992] The server generates feedback based on the evaluation results, such as "Your response is not specific enough. Please provide a specific project name."

[0993] Step 18:

[0994] The server sends the feedback to the terminal for display.

[0995] Step 19:

[0996] The user accesses a form that allows them to enter questions from the actual interview into the system.

[0997] Step 20:

[0998] The user enters, for example, "I was asked about my specific project management experience" and presses the submit button.

[0999] Step 21:

[1000] The server stores the questions asked in the actual interview in a database.

[1001] Step 22:

[1002] The server updates the question list for the next and subsequent mock interviews based on the new questions.

[1003] Example 1

[1004] 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."

[1005] Conventional interview preparation systems have difficulty generating appropriate interview questions based on the information entered by the user, which means that they do not adequately improve the ability to respond to questions required in actual interviews. Furthermore, when providing feedback, there is a lack of specific improvements and suggestions, which makes it difficult to fully improve users' skills. Furthermore, there is no system that can reflect questions asked in actual interviews, making it difficult to provide interview practice based on the latest information.

[1006] 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.

[1007] In this invention, the server includes: a means for inputting the name and industry information of the company the user is applying to; a means for collecting URLs of related news articles and analyzing the text data; a means for extracting important keywords from the news articles using natural language processing technology; a means for generating predicted interview questions using a generative AI model based on the keywords and company information; a means for saving the generated questions in a database; a means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers; a means for analyzing the answers using natural language processing technology and generating and displaying feedback including areas for improvement and specific suggestions; a means for the user to input questions asked in an actual interview; and a means for adding the input actual interview questions to the database and reflecting them in the next question update. This allows users to effectively prepare for interviews based on the latest and most relevant information, and the feedback can lead to concrete improvements. Furthermore, real-time information updates allow interview practice that always incorporates the latest question trends.

[1008] "User" means an individual or entity who uses the System to prepare for an interview.

[1009] "Name of desired company" is the name of the company where the user wishes to have an interview.

[1010] "Industry information" is information about the industry or economic field to which the company you are applying to belongs.

[1011] A "URL" is a uniform resource locator for a resource on the Web; it is an address that points to the relevant news article.

[1012] "Text data" is data that expresses the contents of collected news articles as digital strings of characters.

[1013] "Natural language processing technology" is a technology for processing human natural language using a computer, and is used to analyze text data.

[1014] "Keywords" are important words and phrases extracted from news articles and used to generate interview questions.

[1015] A "generative AI model" is a model that uses artificial intelligence technology to generate new text and questions.

[1016] "Interview questions" are questions related to the company or industry the user is applying for in an interview, and require the user to answer.

[1017] A "database" is an information system for collecting and managing data within a system.

[1018] The "mock interview format" refers to the display means and operation means of the system that allows practice in a format similar to a real interview.

[1019] "Feedback" is information that includes evaluation of the user's response, areas for improvement, and specific suggestions.

[1020] The "questions asked in an actual interview" are specific questions that the user was asked in an actual interview.

[1021] This invention relates to a system that allows users to effectively prepare for interviews. The system generates interview questions based on information input by the user and provides feedback through mock interviews, allowing users to prepare for actual interviews.

[1022] The system uses the following hardware and software. The hardware requires a server and a terminal; specifically, the server is a cloud server with powerful computing power (such as Amazon Web Services or Microsoft Azure). The terminal is the user's personal computer or smartphone. The software uses Python and its library BeautifulSoup for web scraping, spaCy and NLTK for natural language processing technology, and GPT-3 for the generative AI model.

[1023] First, the terminal provides the user with an interface for entering company names and industry information. The user enters the name of the company they are applying for, industry information, and the URL of a related news article, and submits it to the system. The input data is sent to the server using an HTML form or JavaScript.

[1024] The server then receives the URL sent from the device and performs web scraping using Python's BeautifulSoup library to collect text data from the news articles. The collected text data is then analyzed using natural language processing techniques (spaCy and NLTK). Specifically, processes such as tokenization, POS tagging, and named entity recognition are performed to extract important keywords and phrases.

[1025] Next, the server uses a deep learning model (a generative AI model such as GPT-3) to generate interview questions based on keywords extracted from the analysis results. For example, a question might be generated such as, "What do you think about the latest project at the company you're applying to?" The generated questions are stored in an SQL database (PostgreSQL or MySQL).

[1026] When a user starts a mock interview, the server retrieves a list of questions from the database and displays them sequentially on the device. The user enters answers to the questions in the text boxes and submits the answer. For example, the user might respond, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[1027] The server receives the user's response and analyzes it again using natural language processing technology (spaCy or GPT-3). Specifically, it evaluates the specificity, relevance, and logic of the response. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device. For example, it provides feedback such as, "Your response would be more persuasive if you provided specific examples."

[1028] Furthermore, the terminal provides the user with an interface for inputting questions from actual interviews. The user inputs "I was asked about specific project management experience" and submits the request. This actual interview question is also saved in the database and reflected in the question list for future mock interviews.

[1029] For example, the prompts for entering the company name and industry information are as follows:

[1030] "Please enter the name of the company you are applying to, the industry, and the URL of a related news article below."

[1031] The mock interview begins with a prompt such as:

[1032] "Press the button to begin the mock interview."

[1033] Example questions include:

[1034] "Please answer the following question: How do you feel about the new financial services offered by your desired company?"

[1035] This process allows users to prepare effectively for interviews based on the latest and most relevant information, and they can expect to make concrete improvements based on feedback.In addition, real-time updates of information allow users to practice interviews while always incorporating the latest question trends.

[1036] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1037] Step 1:

[1038] The terminal provides an interface for inputting company names, industry information, and URLs of related news articles. When the user inputs the company name "Corporation," the industry "IT industry," and the URLs of related news articles into the input format and presses the send button, this information is sent to the server. The input data is sent to the server using an HTML form or JavaScript.

[1039] Input: Company name, industry information, URL of related news article

[1040] Output: Sending information to the server

[1041] Step 2:

[1042] The server receives the URL sent from the device and performs web scraping using Python's BeautifulSoup library. Specifically, it uses the requests library to retrieve HTML content from the specified URL and extracts text data from news articles.

[1043] Input: URL of related news article

[1044] Output: News article text data

[1045] Step 3:

[1046] The server analyzes the collected text data using natural language processing techniques (spaCy and NLTK libraries), specifically tokenizing, POS tagging, and named entity recognition to extract important keywords and phrases.

[1047] Input: News article text data

[1048] Output: Important keywords and phrases

[1049] Step 4:

[1050] The server generates interview questions using a generative AI model (e.g., GPT-3) based on the keywords extracted from the analysis results. Specifically, the keywords and company information are input into the model, and the generated questions are retrieved. For example, a question such as "What do you think about a certain company's latest project?" is generated.

[1051] Input: Important keywords and company information

[1052] Output: Generated interview questions

[1053] Step 5:

[1054] The server stores the generated interview questions in an SQL database (PostgreSQL or MySQL) by adding the question text and related information as new rows in a database table.

[1055] Input: Generated interview questions

[1056] Output: Questions saved in the database

[1057] Step 6:

[1058] When the user presses the start button for the mock interview, the server retrieves a list of questions from the database and displays them sequentially on the terminal. For example, a question such as "How do you feel about a certain company's new product?" may be displayed. The user enters their answer to the displayed question in the text box and presses the send button.

[1059] Input: A list of questions retrieved from the database

[1060] Output: Question displayed on terminal and user's response

[1061] Step 7:

[1062] The server receives the user's response and analyzes it using natural language processing technology. Specifically, it runs an analysis algorithm that evaluates the specificity, relevance, and logic of the response.

[1063] Input: User's answer

[1064] Output: Analysis results

[1065] Step 8:

[1066] Based on the analysis results, the server generates feedback including areas for improvement and specific suggestions. For example, it might generate feedback such as, "If you provide specific examples, it will be more persuasive." The generated feedback is displayed on the device.

[1067] Input: Analysis results

[1068] Output: Feedback displayed on the terminal

[1069] Step 9:

[1070] The terminal provides the user with an interface for inputting questions that they would have received in an actual interview. For example, the user might input, "I was asked about my specific project management experience," and press the send button.

[1071] Input: User input of questions asked in the actual interview

[1072] Output: Actual interview questions sent to the server

[1073] Step 10:

[1074] The server saves the actual interview questions sent by the user in a database. The saved questions are reflected in the question list for the next mock interview. This allows the system to always incorporate the latest question trends.

[1075] Input: Actual interview questions submitted by the user

[1076] Output: Actual interview questions stored in a database

[1077] (Application example 1)

[1078] 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."

[1079] Conventional interview preparation systems focus solely on providing interview questions and feedback, but do not address specific training or skill development in specific work or technical fields. In particular, there is a lack of efficient means for providing practical training, such as operating and troubleshooting automated equipment in factories. This makes it difficult for employees to effectively acquire the skills actually required in factories. To solve this issue, a system is needed that allows users to receive specific training related to factory operations.

[1080] 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.

[1081] In this invention, the server includes: means for inputting the name of the company and industry information for which the user is applying; means for collecting URLs of related news articles and analyzing the text data; means for extracting important keywords from the news articles using natural language processing technology; means for generating anticipated interview questions based on the keywords and company information; means for saving the generated questions in a database; means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers; means for analyzing the answers and generating and displaying feedback; means for the user to input questions asked in an actual interview; means for adding the input questions to the database and reflecting them in the next question update; means for generating and displaying training questions related to the operation of automated equipment in a factory; and means for evaluating the responses and providing feedback based on the user's answers. This allows users to receive practical operational training in a factory and effectively acquire skills directly related to actual work.

[1082] "User" refers to an individual or employee who uses the system to prepare for an interview or for factory training.

[1083] "Company name" refers to the name of the specific company for which the user is applying.

[1084] "Industry information" refers to information related to the industry or field to which a company belongs.

[1085] "Related news articles" refer to articles that describe the latest news or events related to a company or industry.

[1086] "URL" refers to Internet link information that indicates the address of a web page.

[1087] "Text data" refers to the written information obtained from news articles and text.

[1088] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[1089] "Keywords" refer to important words and phrases extracted from news articles and company information.

[1090] "Interview Questions" refers to questions that may be asked of you in a job interview.

[1091] A "database" refers to a computer system for systematically organizing and storing information.

[1092] A "mock interview" is a form of practice conducted to simulate a real interview.

[1093] "Answer" refers to the response a user gives to a question during a mock interview or training.

[1094] "Feedback" refers to information that evaluates an answer or points out areas for improvement.

[1095] "Input" refers to the act of a user providing information to a system.

[1096] "Automation equipment" refers to robots and automated machines used in factories, etc.

[1097] "Operational training" refers to training that teaches users how to operate and troubleshoot automated equipment.

[1098] "Response evaluation" refers to the act of analyzing the content of a user's response and evaluating its quality.

[1099] This invention is a system for enabling users to effectively operate and train automated equipment in factories. This system comprises the following steps:

[1100] 1. Entering user information

[1101] First, the terminal provides the user with an interface for entering company name and industry information. The user enters the company name and industry information they wish to work for and sends it to the system. For example, the user may enter "manufacturing."

[1102] 2. Collection and analysis of related news articles

[1103] Based on the submitted URL, the server scrapes relevant news articles from the web to collect text data. The server then uses natural language processing techniques to analyze this text data and understand the content of the article. For example, it extracts important keywords and phrases from the article. Specifically, it uses Python's BeautifulSoup and requests libraries to retrieve web page data, and Hugging Face's transformers library to perform natural language processing.

[1104] 3. Generate and save training questions

[1105] The server uses the keywords extracted from the analysis results to generate training questions related to the company or industry, such as "What do you think about the latest robot operation technology?" These questions are then stored in a database.

[1106] 4. Conducting mock training

[1107] When the user presses a button to start the simulation training, the server sends a list of questions to the terminal, which are displayed one after the other. The user enters answers to the questions in the text box and submits the answer. For example, the user might enter, "The latest technology is extremely important for dramatically improving production efficiency."

[1108] 5. Analysis of answers and feedback

[1109] The server analyzes the user's responses using natural language processing technology and evaluates their content. Specifically, it determines the specificity and relevance of the responses. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device. The OpenAI API is used to evaluate responses and generate appropriate feedback.

[1110] 6. Input of actual operation feedback

[1111] An interface is provided for users to provide feedback and problems they have experienced during actual operation or training to the system. For example, users can input and submit a message such as, "Please tell us about your specific troubleshooting experiences during operation."

[1112] 7. Updating the database

[1113] The server stores the inputted actual operation feedback in a database and reflects it in the question list for the next mock training session, allowing the system to always provide a question list that incorporates the latest trends in training content.

[1114] As a concrete example, consider the case where a user requests "Training in factory automation technology in the manufacturing industry." In this case, the system extracts keywords such as "automation technology" and "robot operation" from related news articles and generates the question, "What do you think about the latest trends in automation technology?" The user can enter an answer and receive feedback on their response, allowing them to effectively acquire the skills required in an actual factory.

[1115] An example prompt might look like this:

[1116] You are in the manufacturing industry and are being trained to operate automated equipment. Using information from a news article, answer the following questions:

[1117] 1. What do you think about the latest robotic manipulation technology?

[1118] 2. What is your experience troubleshooting robot operations?

[1119] This system allows users to undergo simulated training based on real-life operating situations, enabling them to effectively acquire the skills necessary for actual factory work.

[1120] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1121] Step 1:

[1122] The terminal provides the user with an interface for entering company names and industry information. The user enters the company name and industry information they wish to work for and sends it to the system. The information entered includes "company name" and "industry information." This allows the system to understand the user's specific wishes.

[1123] Step 2:

[1124] The server receives the URL sent by the user and scrapes related news articles from the web to collect text data. Specifically, it accesses web pages using Python's requests library and extracts text data using the BeautifulSoup library. The input is the "URL of the news article" and the output is the "scraped text data."

[1125] Step 3:

[1126] The server uses natural language processing technology to analyze the collected text data and understand the content of the articles. Specifically, it uses Hugging Face's transformers library to extract important keywords and phrases from the text data. The input is "text data" and the output is "important keywords and phrases."

[1127] Step 4:

[1128] The server uses the extracted keywords to generate predicted questions from training related to the company and industry. A generative AI model is used to generate "predicted questions" from "keywords" and "company information." For example, it generates a question such as "What do you think about the latest robot operation technology?" The input here is "keywords" and "company information," and the output is the "generated question."

[1129] Step 5:

[1130] The server saves the generated question in a database. The saved information is the "generated question" and is prepared for display to the user in later processing. The input is the "generated question" and the output is the "question saved in the database."

[1131] Step 6:

[1132] When the user presses a button to start the simulated training, the server sends a list of questions to the terminal in order for them to be displayed. The user receives the training questions in order, enters their answers in the text box, and sends them. The input is the "user's confirmation action," and the output is the "question displayed on the terminal" and the "user's answer."

[1133] Step 7:

[1134] The server analyzes the user's answers using natural language processing technology and evaluates their content. Specifically, it determines the specificity and relevance of the answers. It analyzes the "user's answers" using the OpenAI API and generates "evaluation results and feedback." The input is the "user's answers" and the output is "evaluation results and feedback."

[1135] Step 8:

[1136] Based on the evaluation results, the server generates feedback including areas for improvement and specific suggestions, which is displayed on the device. The user can review this feedback and use it for the next training session. The input is "evaluation results and feedback," and the output is "feedback display on the device."

[1137] Step 9:

[1138] An interface is provided that allows users to provide feedback and problems they have received during actual operations and training to the system. Users input and send specific feedback and problems. The input is "feedback from operations and training," and the output is "sending feedback data to the server."

[1139] Step 10:

[1140] The server stores the inputted actual operation feedback in a database and reflects it in the question list for the next and subsequent mock training sessions. This allows the server to provide a question list that always incorporates the latest trends in training content. The input is "feedback from the user" and the output is "feedback stored in the database."

[1141] 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.

[1142] This invention relates to a system that allows users to effectively prepare for interviews, and in particular provides an innovative system that recognizes the user's emotions and reflects them in feedback by combining an emotion engine. An embodiment of this system will be described in detail below.

[1143] System configuration

[1144] Enter user information

[1145] The terminal provides the user with an interface for entering company name and industry information. The user enters the name of the company they are applying to ("ABC Co., Ltd."), the industry ("IT industry"), and the URL of a related news article, and sends it to the system.

[1146] Collection and analysis of relevant news articles

[1147] The server scrapes relevant news articles from the web based on the submitted URL and collects text data. The server then analyzes this text data using natural language processing techniques to understand the content of the article, specifically extracting important keywords and phrases.

[1148] Generate and save interview questions

[1149] The server uses the extracted keywords to generate potential interview questions based on company information. For example, it generates a question like, "What do you think about ABC Corporation's latest project?" The generated questions are stored in a database.

[1150] Mock interviews

[1151] When a user starts a mock interview, the server sequentially sends a list of questions to the terminal and displays them. The user enters answers to the questions in the text boxes and submits the answer. For example, the user might enter, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[1152] Emotion recognition by emotion engine

[1153] During the mock interview, the device runs an emotion engine based on the user's text responses and facial expression data to recognize the user's emotions. The emotion engine recognizes emotions such as "happiness," "anxiety," and "confidence."

[1154] Analysis of responses and feedback

[1155] The server analyzes the saved user responses using natural language processing technology and evaluates them, taking into account the results of the emotion engine. Specifically, it considers the specificity and relevance of the responses as well as the user's emotional state. Based on the results, it generates feedback including areas for improvement and specific suggestions, which are displayed on the device.

[1156] Enter questions asked in the actual interview

[1157] An interface is provided for users to feed back the questions they received in the actual interview to the system. For example, the user can input "I was asked about my specific project management experience" and submit it.

[1158] Database Update

[1159] The server saves the entered actual interview questions in a database and reflects them in the question list for future mock interviews, allowing the system to always provide a question list that incorporates the latest interview question trends.

[1160] Specific examples

[1161] Let's say a user is applying to work for a company called "X Corporation" in the "financial industry." The user enters the URL of a related news article and submits it. The system retrieves the news article from the URL, analyzes it using natural language processing technology, and extracts keywords such as "X Corporation's new financial service." The system then generates a question, "What do you think about X Corporation's new financial service?" and presents it to the user through a mock interview. The system analyzes the user's answer and the emotions recognized by the emotion engine, and provides feedback such as, "It would be good if you mentioned the specific name and features of the service. Also, it's good that you answered with confidence, but it would be even better if you included more specific experiences." The user then feeds back to the system the question they received in the actual interview, "Tell us about your experience managing specific financial projects," and the database is updated.

[1162] In this way, users can continuously prepare for their interviews taking into account their current information and emotional state, and the feedback provided allows users to understand and improve their weaknesses.

[1163] The processing flow will be explained below.

[1164] Of course, the specific processing flow of the system will be explained below by dividing it into steps.

[1165] Step 1:

[1166] A user accesses the system and logs in or creates a new account.

[1167] Step 2:

[1168] The device will display a form for entering the company name, industry, and the URL of a related news article.

[1169] Step 3:

[1170] The user enters the company name "ABC Co., Ltd.", the industry "IT industry," and the URL of a related news article, and presses the send button.

[1171] Step 4:

[1172] The server receives the company name, industry, and news article URL that were sent.

[1173] Step 5:

[1174] The server scrapes related news articles from the news article URLs and collects text data.

[1175] Step 6:

[1176] The server analyzes the collected text data of news articles using natural language processing technology.

[1177] Step 7:

[1178] The server extracts important keywords and phrases from the analysis results, such as "ABC Corporation's latest project" or "technology trends."

[1179] Step 8:

[1180] The server generates questions that are likely to be asked in an interview based on the extracted keywords and company information. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?"

[1181] Step 9:

[1182] The server stores the generated questions in a database.

[1183] Step 10:

[1184] The user presses a button to start the mock interview from the mock interview menu.

[1185] Step 11:

[1186] The server loads the saved question list into a task queue and prepares it to be sent to the terminal in order.

[1187] Step 12:

[1188] The server sends the first question to the terminal and displays it. For example, it displays "What do you think about ABC Corporation's latest project?"

[1189] Step 13:

[1190] The user enters an answer in the text box and presses the submit button.

[1191] Step 14:

[1192] The server receives and stores the user's answers.

[1193] Step 15:

[1194] During the mock interview, the device uses a camera and microphone to collect the user's facial expressions and voice and transmits them to the emotion engine.

[1195] Step 16:

[1196] The emotion engine on the server analyzes the user's facial expressions and voice data to recognize emotions, such as "happiness," "anxiety," and "confidence."

[1197] Step 17:

[1198] The server analyzes the saved user responses using natural language processing technology, evaluating their depth, specificity, and relevance, while also taking into account the results of the emotion engine.

[1199] Step 18:

[1200] The server generates feedback based on the analysis of the answer and the emotions recognized by the emotion engine. For example, "Your answer is not specific enough. It would be better if you mentioned a specific project name. Also, it is good that you answered with confidence, but it would be even better if you included more specific experiences."

[1201] Step 19:

[1202] The server sends the feedback to the terminal for display.

[1203] Step 20:

[1204] The user accesses a form that allows them to enter questions from the actual interview into the system.

[1205] Step 21:

[1206] The user enters, for example, "I was asked about my specific project management experience" and presses the submit button.

[1207] Step 22:

[1208] The server stores the questions asked in the actual interview in a database.

[1209] Step 23:

[1210] The server updates the question list for the next and subsequent mock interviews based on the new questions.

[1211] Example 2

[1212] 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."

[1213] Existing systems for preparing Q&A questions for potential organizations often lack sufficient information gathering and appropriate Q&A content. Furthermore, they lack feedback that takes into account the user's emotional state, making it difficult to improve performance in mock questions or actual Q&A sessions. The present invention aims to solve these problems by providing a system that allows users to effectively prepare and improve Q&A questions.

[1214] 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 inputting the name and industry information of the organization the user is interested in; means for collecting links to related information articles and analyzing text data; means for extracting important keywords from the information articles using natural language processing technology; means for generating predicted questions based on the keywords and organization information; means for saving the generated questions in a storage device; means for sequentially displaying the questions to the user in the form of mock questions and saving the user's answers; means for analyzing the answers, generating and displaying evaluations and responses; means for the user to input questions asked in actual question-and-answer sessions; means for adding the input questions to a storage device and reflecting them in the next question update; emotion recognition means for analyzing the user's answers and facial expression data and recognizing the user's emotional state; and means for including the recognition results in feedback. This enables the user to collect related information, generate questions, and provide feedback that takes emotions into account.

[1215] "User" means a person who uses the system to prepare questions and answers for a prospective organization.

[1216] "Organization name" is information that indicates the name of the company or organization that the user is applying to.

[1217] "Industry information" is information about the type of industry or business to which the organization to which the applicant belongs.

[1218] "Link" refers to a web address that points to a related article of information.

[1219] "Text data" refers to textual information obtained through scraping or analysis.

[1220] "Natural language processing technology" refers to technology for analyzing acquired text data and extracting meaningful information.

[1221] "Keywords" refer to important words or phrases extracted from text data.

[1222] "Question and answer content" refers to anticipated questions generated using natural language processing technology.

[1223] "Storage device" refers to a device for storing the generated questions and answers, answer data, and other necessary information.

[1224] "Mock question format" refers to a method in which anticipated questions are presented in a format similar to an actual questioning environment, and users respond to them.

[1225] "Answer" refers to a user's answer to a question presented in the form of a mock question.

[1226] "Evaluation and response" refers to feedback and suggestions generated based on the analyzed answer data.

[1227] "Emotion recognition means" refers to technology that analyzes a user's answers and facial expression data to recognize their emotional state.

[1228] This invention relates to a system that allows users to effectively prepare for Q&A sessions, and in particular provides an innovative system that recognizes the user's emotions and reflects them in feedback by incorporating an emotion recognition engine. An embodiment of this system will now be described in detail.

[1229] System configuration

[1230] Enter user information

[1231] The terminal provides the user with an interface for entering information about the organization's name and industry. The user enters the name of the organization they wish to apply for ("Organization XYZ"), the industry ("Technology field"), and a link to a related news article, and sends it to the system.

[1232] Collection and analysis of relevant news articles

[1233] The server scrapes relevant news articles from the web based on the submitted links and collects text data using Python's BeautifulSoup. The server then analyzes this text data using natural language processing techniques (e.g., spaCy, NLTK) to extract important keywords and phrases.

[1234] Generate and save interview questions

[1235] Based on the extracted keywords, the server uses a generative AI model (e.g., GPT-3) to generate predicted questions based on the organization information. An example of a prompt used for generation is, "Please generate questions related to 'technological innovation.'" The generated questions are saved in a storage device.

[1236] Mock question session

[1237] When a user starts a mock question, the server sequentially sends the generated list of questions to the terminal, which then displays them. The user enters answers to each question in the text box and submits it. For example, in response to the question "What do you think about the impact of new technological innovations on the market?", the user enters "I think new technological innovations will improve market competitiveness."

[1238] Emotion recognition using an emotion recognition engine

[1239] During the mock questions, the device collects the user's text responses and facial expression data, and uses an emotion recognition engine (e.g., Microsoft Azure Cognitive Services) to recognize the user's emotions. The emotion recognition engine recognizes emotions such as "happiness," "anxiety," and "confidence."

[1240] Analysis of responses and feedback

[1241] The server analyzes the user's saved answers using natural language processing technology and evaluates them taking into account the results of an emotion recognition engine. For example, it evaluates the specificity and relevance of the answer and generates feedback based on the recognized emotional state. The feedback might be something like, "It would be good to include a specific example. Also, it's good that you're answering with confidence, but it would be even better if you included a more specific experience." The generated feedback is displayed on the device.

[1242] Enter questions asked during the actual Q&A session

[1243] The terminal provides the user with an interface for feedback on the questions asked during the actual Q&A session. For example, the user can input "I was asked about my specific project management experience" and submit.

[1244] Database Update

[1245] The server saves the questions entered in the actual Q&A session in a storage device and reflects them in the Q&A list for the next mock question session onwards, allowing the system to always provide a list that incorporates the latest trends in Q&A questions.

[1246] Specific examples

[1247] For example, suppose a user is applying to work for "Organization ABC" in the "finance industry." The user inputs and submits a link to a related news article. The server retrieves the news article from the link, analyzes it using natural language processing technology, and extracts keywords such as "Organization ABC's new financial service." The server then generates a question, "How do you feel about Organization ABC's new financial service?" and provides it to the user through a mock question. The server analyzes the user's answer and the emotions recognized by the emotion recognition engine, and provides feedback such as, "It would be good if you mentioned the specific service name and features. Also, it is good that you answered with confidence, but it would be even better if you included more specific experiences." The user then feeds back the question they received in the actual Q&A session, "Tell me about your experience managing specific financial projects," to the system and updates the storage device.

[1248] In this way, users can continuously prepare questions and answers that take into account the latest information and their emotional state, and the feedback provided allows users to understand and improve their weaknesses.

[1249] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1250] Step 1: Enter user information

[1251] Input: The user enters the name of the organization they wish to apply to, industry information, and links to related news articles.

[1252] Processing: The terminal receives the entered information and confirms it through the interface.

[1253] Output: Sends the entered information to the server.

[1254] Specific operation: The device displays a web form or app input screen, and after the user enters data in the input fields for "organization name," "industry," and "news article URL," clicks the send button, and the input information is sent to the server.

[1255] Step 2: Collect and analyze relevant news articles

[1256] Input: The server receives the link information.

[1257] Processing: The server scrapes the linked webpage using Python's BeautifulSoup library to collect text data, which is then analyzed using natural language processing techniques (e.g., spaCy, NLTK) to extract important keywords and phrases.

[1258] Output: A list of parsed keywords and phrases.

[1259] How it works: The server retrieves the web page from the specified URL, extracts the text using BeautifulSoup, and then performs morphological analysis on the text data using SpaCy to extract important keywords.

[1260] Step 3: Generate and save interview questions

[1261] Input: The server receives the extracted keywords and organization information.

[1262] Processing: The server sends the keywords as a prompt to a generative AI model (e.g., GPT-3) to generate questions. An example prompt is, "Please generate questions related to 'technological innovation.'"

[1263] Output: The generated questions and answers.

[1264] Specific operation: The server sends a prompt to the generation AI model, which generates the expected question and answer content. The generated question and answer content is then saved in a storage device.

[1265] Step 4: Practice Questions

[1266] Input: The user sends a request to start the mock question.

[1267] Processing: The server retrieves the list of questions from the storage device and transmits them to the terminals in order.

[1268] Output: The question list displayed on the terminal.

[1269] Specific operation: When the user clicks the "Start mock questions" button, the server retrieves the question list from the storage device, sends it to the terminal, and displays it.

[1270] Step 5: Enter and submit your answers

[1271] Input: The user enters the answer to each question.

[1272] Processing: The terminal sends the entered answer to the server.

[1273] Output: The answer data sent to the server.

[1274] Specific operation: The terminal presents questions to the user, and when the user enters answers to each question in the text boxes and presses the send button, the terminal sends the answer data to the server.

[1275] Step 6: Emotion recognition using the emotion recognition engine

[1276] Input: The server receives the submitted answer data and facial expression data.

[1277] Processing: The server uses an emotion recognition engine (e.g., Microsoft Azure Cognitive Services) to analyze the answer data and facial expression data and recognize the user's emotions.

[1278] Output: Recognized emotional state data.

[1279] Specific operation: The device sends the user's answer data and facial expression data together, and the server passes it to the emotion recognition engine for analysis.

[1280] Step 7: Analyze responses and generate feedback

[1281] Input: The server receives answer data and recognized emotional state data.

[1282] Processing: The server analyzes the answer data using natural language processing technology and evaluates it, taking into account the emotion recognition results. Based on the evaluation results, specific feedback is generated.

[1283] Output: The generated feedback.

[1284] Specific operation: The server analyzes the answer data using natural language processing tools, evaluates the specificity, relevance, and emotional state of the content, and generates feedback. This feedback is then sent to the device.

[1285] Step 8: View your feedback

[1286] Input: Sends server-generated feedback to the device.

[1287] Processing: The device displays feedback to the user.

[1288] Output: The feedback displayed to the user.

[1289] Specific behavior: The device receives feedback from the server and displays it to the user, such as "It would be good to include a specific example. Also, it's good that you're confident in your answer, but it would be even better if you included more specific experiences."

[1290] Step 9: Enter the questions asked during the Q&A session

[1291] Input: The user inputs the question asked in the actual Q&A session.

[1292] Processing: The terminal sends the entered question to the server.

[1293] Output: The query data sent to the server.

[1294] Specific operation: The terminal displays a form for the user to input the actual question, and when the user inputs the question and presses the submit button, the terminal sends the question data to the server.

[1295] Step 10: Update the Database

[1296] Input: The server receives the actual query data that was sent.

[1297] Processing: The server saves the newly entered question in a memory device and reflects it in the question and answer list from the next time onwards.

[1298] Output: Updated question list.

[1299] Specific operation: The server saves the new question data in the storage device and updates the existing question list. The newly saved questions are used in the next mock test.

[1300] (Application example 2)

[1301] 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."

[1302] In conventional customer support preparation systems, it is difficult for representatives to fully acquire the product information and knowledge necessary for customer support, and the responsiveness and accuracy of responses to customer inquiries can be reduced. Furthermore, the emotional state of representatives can affect the quality of customer support, but there is a lack of a means to effectively manage this. The present invention aims to solve these problems and improve the efficiency and quality of customer support preparation.

[1303] 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 inputting product names and category information for which the user is responsible; means for collecting URLs of related product reviews and analyzing text data; means for extracting important keywords from the reviews using natural language processing technology; means for generating predicted customer queries based on the keywords and product information; means for saving the generated queries in a database; means for sequentially displaying the queries in a simulated customer support format and saving the user's responses; means including an emotion engine that recognizes the user's emotions during the simulated session and reflects them as feedback in the evaluation results; means for analyzing the responses and generating and displaying feedback; means for inputting queries made by the user during actual support; and means for adding the input queries to a database and reflecting them in the next query update. This allows users to acquire the latest and most effective support information, manages the emotional states of staff, and enables highly accurate customer support.

[1304] "User" means any person or entity that uses the System.

[1305] "Organization name" refers to the name of the company or organization you are applying for.

[1306] "Industry information" refers to information about the industry to which the company or organization you are applying to belongs.

[1307] "Related news articles" refer to articles that cover the latest news related to the company or industry you are applying to.

[1308] "URL" refers to the web page address where the relevant news article is published online.

[1309] "Text data" refers to the textual information of collected news articles.

[1310] "Natural language processing technology" refers to computer technology for analyzing text data and understanding its meaning.

[1311] "Key words" refer to key words and phrases extracted from news articles and used to generate interview questions.

[1312] "Interview questions" refer to questions asked of users during mock interviews or actual interviews.

[1313] "Database" refers to a system for storing data such as generated questions, user responses, and questions asked in actual interviews.

[1314] A "mock interview" refers to a simulation that allows users to practice for a real interview.

[1315] "Emotion engine" refers to a system for recognizing and analyzing users' emotions.

[1316] "Feedback" refers to evaluations and improvement suggestions generated based on the user's responses and emotional state.

[1317] ·System Programming

[1318] The system's program is written in Python and includes the following main functions:

[1319] 1. Data collection function:

[1320] The server collects the URLs of the product review web pages based on the product name and category information entered by the user. This collection process uses the requests and BeautifulSoup libraries.

[1321] 2. Data analysis function:

[1322] The server analyzes the collected text data using natural language processing techniques to extract important keywords. This analysis process utilizes the spacy and TextBlob libraries.

[1323] 3. Query generation function:

[1324] The server generates a customer query based on the analysis results and stores it in a database, using the extracted important keywords.

[1325] 4. Simulation session function:

[1326] The terminal sequentially displays queries generated in a simulated customer support format and accepts the user's answers, which are then sent from the terminal to a server and stored.

[1327] 5. Emotion recognition function:

[1328] During the simulation session, the server runs an emotion engine based on the user's responses to recognize the user's emotions. This emotion recognition is performed using the EmotionRecognizer library.

[1329] 6. Feedback generation function:

[1330] The server analyzes the saved user responses and evaluates them based on the results of the emotion engine. The feedback includes specific improvements and suggestions.

[1331] 7. Actual query input function:

[1332] Users are provided with an interface to input queries received from actual customer support into the system. The input queries are added to a database and reflected in the generation of future queries.

[1333] Processing Description

[1334] To realize the above functions, the server performs the following data processing and data calculations.

[1335] 1. Data Collection:

[1336] Scrape product reviews from a URL and retrieve them as text data. Here, requests and BeautifulSoup are used.

[1337] 2. Data Analysis:

[1338] Spacy is used to perform natural language processing on the scraped text data to extract important keywords from the reviews.

[1339] 3. Query Generation:

[1340] Generate predicted customer queries based on the extracted keywords.

[1341] 4. Mock Session:

[1342] The device displays the query to the user and accepts the user's answer, which is sent to the server and stored.

[1343] 5. Emotion recognition:

[1344] The server uses the EmotionRecognizer library to recognize emotions from the user's responses.

[1345] 6. Feedback Generation:

[1346] The content of the user's response is analyzed using TextBlob, and feedback is generated taking into account the results of emotion recognition.

[1347] 7. Actual query input and database update:

[1348] The actual customer query entered by the user is added to the database and reflected in the next query generation.

[1349] Specific examples and prompts

[1350] As a specific use case, consider a customer support representative preparing to support a new product, "Smartwatch X." In this case, the representative enters information about "Smartwatch X" into the system, collects and analyzes related reviews, and generates predicted queries based on the results, conducting mock sessions.

[1351] Example prompt sentence:

[1352] We will predict customer queries based on reviews of the "Smartwatch X" and conduct a mock customer support session. First, enter the product URL.

[1353] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1354] Step 1:

[1355] The user inputs the product name and category information for which they are responsible. The user inputs the product name "Smart Watch X" and the category "Wearable Device" into the system's input interface. The device sends this information to the server. Based on this input information, the server determines the URLs of the related reviews to be collected.

[1356] Step 2:

[1357] The server collects URLs of related product reviews and parses the text data. The server scrapes product review pages from the web based on product name and category information. This process uses the requests and BeautifulSoup libraries. The collected review text data is stored for subsequent analysis.

[1358] Step 3:

[1359] The server uses natural language processing technology to extract important keywords from reviews. The collected text data is analyzed using the spacy library to identify nouns and related important keywords. For example, "battery life" and "fitness features" are extracted. This data processing identifies important keywords.

[1360] Step 4:

[1361] The server generates predicted customer queries based on the analysis results. Based on the extracted important keywords, it generates predicted customer queries. For example, a query such as "What is the battery life of Smartwatch X?" is created. These queries are stored in a database.

[1362] Step 5:

[1363] The terminal sequentially displays queries generated in a simulated customer support format and accepts responses from the user. The terminal displays the queries received from the server to the user. The user inputs a text response to the query, and the terminal sends the response to the server. The input from the user is saved as response data.

[1364] Step 6:

[1365] The server runs an emotion engine based on the user's responses during the simulated session to recognize emotions. Using the EmotionRecognizer library, emotions such as "happiness" or "anxiety" are extracted from the user's responses. For example, if a user responds, "I think this feature is very good," "happiness" is recognized as the emotion.

[1366] Step 7:

[1367] The server analyzes the saved user answers and generates and displays feedback. It uses the TextBlob library to evaluate the positivity and subjectivity of the answer, and generates feedback taking into account the results of emotion recognition. For example, feedback such as "Your answer is positive, and including specific examples would make it even better" is generated. The feedback is displayed on the device.

[1368] Step 8:

[1369] The user inputs a query received from a real customer support service into the system. The user inputs the query received from a real customer through the interface, and the device sends it to the server. For example, a query such as "Please tell me about the waterproof performance of Smartwatch X" is input.

[1370] Step 9:

[1371] The server adds the actual query entered to the database and reflects it in the next query generation. By saving the actual query entered by the user in the database and using that data when generating the next query, it becomes possible to provide a query list that reflects the latest information.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] [Fourth embodiment]

[1376] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1377] 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.

[1378] 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).

[1379] 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.

[1380] 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.

[1381] 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).

[1382] 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. 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.

[1383] 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.

[1384] 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.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] 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."

[1389] The present invention relates to a system that allows users to effectively prepare for interviews. This system generates interview questions based on information input by the user and provides feedback through mock interviews, allowing users to prepare for actual interviews. Detailed embodiments of this system will be described below.

[1390] System configuration

[1391] Enter user information

[1392] The terminal provides the user with an interface for entering company name and industry information. The user enters the name of the company they are applying to ("ABC Co., Ltd."), the industry ("IT industry"), and the URL of a related news article, and sends it to the system.

[1393] Collection and analysis of relevant news articles

[1394] Based on the URLs sent, the server scrapes relevant news articles from the web to collect text data. The server then uses natural language processing techniques to analyze this text data and understand the content of the articles, for example by extracting important keywords and phrases from the articles.

[1395] Generate and save interview questions

[1396] The server uses the keywords extracted from the analysis results to generate interview questions related to the company and industry the candidate is applying for. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?" This question is then saved in a database.

[1397] Mock interviews

[1398] When the user presses a button to start the mock interview, the server sends a list of questions that are displayed sequentially on the device. The user enters answers to the questions in the text box and submits the answer. For example, the user might enter, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[1399] Analysis of responses and feedback

[1400] The server analyzes the user's answers using natural language processing technology and evaluates their content. Specifically, it judges the specificity and relevance of the answers. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device.

[1401] Enter questions asked in the actual interview

[1402] An interface is provided for users to provide feedback to the system about the questions they received during the actual interview. For example, the user can enter "I was asked about my specific project management experience" and submit the feedback.

[1403] Database Update

[1404] The server stores the entered actual interview questions in a database and reflects them in the question list for future mock interviews. This allows the system to always provide a question list that incorporates the latest interview question trends.

[1405] Specific examples

[1406] Let's say a user is applying to work for a company called "X Corporation" in the "financial industry." The user enters the URL of a related news article and submits it. The system retrieves the news article from the URL, analyzes it using natural language processing technology, and extracts keywords such as "X Corporation's new financial service." The system then generates a question, "What do you think about X Corporation's new financial service?" and presents it to the user through a mock interview. The system analyzes the user's answers and provides feedback such as "It would be good to mention the specific service name and features." The user then provides feedback to the system with the question they received in the actual interview, "Tell us about your experience managing specific financial projects," and the database is updated.

[1407] In this way, users can have continuously up-to-date information about their interview preparation, and the feedback provided helps users understand and improve their weaknesses.

[1408] The processing flow will be explained below.

[1409] Step 1:

[1410] A user accesses the system and logs in or creates a new account.

[1411] Step 2:

[1412] The device will display a form for entering the company name, industry, and the URL of a related news article.

[1413] Step 3:

[1414] The user enters the company name "ABC Co., Ltd.", the industry "IT industry," and the URL of a related news article, and presses the send button.

[1415] Step 4:

[1416] The server receives the company name, industry, and news article URL that were sent.

[1417] Step 5:

[1418] The server scrapes related news articles from the news article URLs and collects text data.

[1419] Step 6:

[1420] The server analyzes the collected text data of news articles using natural language processing technology.

[1421] Step 7:

[1422] The server extracts important keywords and phrases from the analysis results, such as "ABC Corporation's latest project" or "technology trends."

[1423] Step 8:

[1424] The server generates questions that are likely to be asked in an interview based on the extracted keywords and company information. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?"

[1425] Step 9:

[1426] The server stores the generated questions in a database.

[1427] Step 10:

[1428] The user presses a button to start the mock interview from the mock interview menu.

[1429] Step 11:

[1430] The server loads the saved question list into a task queue and prepares it to be sent to the terminal in order.

[1431] Step 12:

[1432] The server sends the first question to the terminal and displays it. For example, it displays "What do you think about ABC Corporation's latest project?"

[1433] Step 13:

[1434] The user enters an answer in the text box and presses the submit button.

[1435] Step 14:

[1436] The server receives and stores the user's answers.

[1437] Step 15:

[1438] The server analyzes the saved user responses using natural language processing techniques.

[1439] Step 16:

[1440] The server evaluates the depth, specificity, and relevance of the response.

[1441] Step 17:

[1442] The server generates feedback based on the evaluation results, such as "Your response is not specific enough. Please provide a specific project name."

[1443] Step 18:

[1444] The server sends the feedback to the terminal for display.

[1445] Step 19:

[1446] The user accesses a form that allows them to enter questions from the actual interview into the system.

[1447] Step 20:

[1448] The user enters, for example, "I was asked about my specific project management experience" and presses the submit button.

[1449] Step 21:

[1450] The server stores the questions asked in the actual interview in a database.

[1451] Step 22:

[1452] The server updates the question list for the next and subsequent mock interviews based on the new questions.

[1453] Example 1

[1454] 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."

[1455] Conventional interview preparation systems have difficulty generating appropriate interview questions based on the information entered by the user, which means that they do not adequately improve the ability to respond to questions required in actual interviews. Furthermore, when providing feedback, there is a lack of specific improvements and suggestions, which makes it difficult to fully improve users' skills. Furthermore, there is no system that can reflect questions asked in actual interviews, making it difficult to provide interview practice based on the latest information.

[1456] 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.

[1457] In this invention, the server includes: a means for inputting the name and industry information of the company the user is applying to; a means for collecting URLs of related news articles and analyzing the text data; a means for extracting important keywords from the news articles using natural language processing technology; a means for generating predicted interview questions using a generative AI model based on the keywords and company information; a means for saving the generated questions in a database; a means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers; a means for analyzing the answers using natural language processing technology and generating and displaying feedback including areas for improvement and specific suggestions; a means for the user to input questions asked in an actual interview; and a means for adding the input actual interview questions to the database and reflecting them in the next question update. This allows users to effectively prepare for interviews based on the latest and most relevant information, and the feedback can lead to concrete improvements. Furthermore, real-time information updates allow interview practice that always incorporates the latest question trends.

[1458] "User" means an individual or entity who uses the System to prepare for an interview.

[1459] "Name of desired company" is the name of the company where the user wishes to have an interview.

[1460] "Industry information" is information about the industry or economic field to which the company you are applying to belongs.

[1461] A "URL" is a uniform resource locator for a resource on the Web; it is an address that points to the relevant news article.

[1462] "Text data" is data that expresses the contents of collected news articles as digital strings of characters.

[1463] "Natural language processing technology" is a technology for processing human natural language using a computer, and is used to analyze text data.

[1464] "Keywords" are important words and phrases extracted from news articles and used to generate interview questions.

[1465] A "generative AI model" is a model that uses artificial intelligence technology to generate new text and questions.

[1466] "Interview questions" are questions related to the company or industry the user is applying for in an interview, and require the user to answer.

[1467] A "database" is an information system for collecting and managing data within a system.

[1468] The "mock interview format" refers to the display means and operation means of the system that allows practice in a format similar to a real interview.

[1469] "Feedback" is information that includes evaluation of the user's response, areas for improvement, and specific suggestions.

[1470] The "questions asked in an actual interview" are specific questions that the user was asked in an actual interview.

[1471] This invention relates to a system that allows users to effectively prepare for interviews. The system generates interview questions based on information input by the user and provides feedback through mock interviews, allowing users to prepare for actual interviews.

[1472] The system uses the following hardware and software. The hardware requires a server and a terminal; specifically, the server is a cloud server with powerful computing power (such as Amazon Web Services or Microsoft Azure). The terminal is the user's personal computer or smartphone. The software uses Python and its library BeautifulSoup for web scraping, spaCy and NLTK for natural language processing technology, and GPT-3 for the generative AI model.

[1473] First, the terminal provides the user with an interface for entering company names and industry information. The user enters the name of the company they are applying for, industry information, and the URL of a related news article, and submits it to the system. The input data is sent to the server using an HTML form or JavaScript.

[1474] The server then receives the URL sent from the device and performs web scraping using Python's BeautifulSoup library to collect text data from the news articles. The collected text data is then analyzed using natural language processing techniques (spaCy and NLTK). Specifically, processes such as tokenization, POS tagging, and named entity recognition are performed to extract important keywords and phrases.

[1475] Next, the server uses a deep learning model (a generative AI model such as GPT-3) to generate interview questions based on keywords extracted from the analysis results. For example, a question might be generated such as, "What do you think about the latest project at the company you're applying to?" The generated questions are stored in an SQL database (PostgreSQL or MySQL).

[1476] When a user starts a mock interview, the server retrieves a list of questions from the database and displays them sequentially on the device. The user enters answers to the questions in the text boxes and submits the answer. For example, the user might respond, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[1477] The server receives the user's response and analyzes it again using natural language processing technology (spaCy or GPT-3). Specifically, it evaluates the specificity, relevance, and logic of the response. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device. For example, it provides feedback such as, "Your response would be more persuasive if you provided specific examples."

[1478] Furthermore, the terminal provides the user with an interface for inputting questions from actual interviews. The user inputs "I was asked about specific project management experience" and submits the request. This actual interview question is also saved in the database and reflected in the question list for future mock interviews.

[1479] For example, the prompts for entering the company name and industry information are as follows:

[1480] "Please enter the name of the company you are applying to, the industry, and the URL of a related news article below."

[1481] The mock interview begins with a prompt such as:

[1482] "Press the button to begin the mock interview."

[1483] Example questions include:

[1484] "Please answer the following question: How do you feel about the new financial services offered by your desired company?"

[1485] This process allows users to prepare effectively for interviews based on the latest and most relevant information, and they can expect to make concrete improvements based on feedback.In addition, real-time updates of information allow users to practice interviews while always incorporating the latest question trends.

[1486] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1487] Step 1:

[1488] The terminal provides an interface for inputting company names, industry information, and URLs of related news articles. When the user inputs the company name "Corporation," the industry "IT industry," and the URLs of related news articles into the input format and presses the send button, this information is sent to the server. The input data is sent to the server using an HTML form or JavaScript.

[1489] Input: Company name, industry information, URL of related news article

[1490] Output: Sending information to the server

[1491] Step 2:

[1492] The server receives the URL sent from the device and performs web scraping using Python's BeautifulSoup library. Specifically, it uses the requests library to retrieve HTML content from the specified URL and extracts text data from news articles.

[1493] Input: URL of related news article

[1494] Output: News article text data

[1495] Step 3:

[1496] The server analyzes the collected text data using natural language processing techniques (spaCy and NLTK libraries), specifically tokenizing, POS tagging, and named entity recognition to extract important keywords and phrases.

[1497] Input: News article text data

[1498] Output: Important keywords and phrases

[1499] Step 4:

[1500] The server generates interview questions using a generative AI model (e.g., GPT-3) based on the keywords extracted from the analysis results. Specifically, the keywords and company information are input into the model, and the generated questions are retrieved. For example, a question such as "What do you think about a certain company's latest project?" is generated.

[1501] Input: Important keywords and company information

[1502] Output: Generated interview questions

[1503] Step 5:

[1504] The server stores the generated interview questions in an SQL database (PostgreSQL or MySQL) by adding the question text and related information as new rows in a database table.

[1505] Input: Generated interview questions

[1506] Output: Questions saved in the database

[1507] Step 6:

[1508] When the user presses the start button for the mock interview, the server retrieves a list of questions from the database and displays them sequentially on the terminal. For example, a question such as "How do you feel about a certain company's new product?" may be displayed. The user enters their answer to the displayed question in the text box and presses the send button.

[1509] Input: A list of questions retrieved from the database

[1510] Output: Question displayed on terminal and user's response

[1511] Step 7:

[1512] The server receives the user's response and analyzes it using natural language processing technology. Specifically, it runs an analysis algorithm that evaluates the specificity, relevance, and logic of the response.

[1513] Input: User's answer

[1514] Output: Analysis results

[1515] Step 8:

[1516] Based on the analysis results, the server generates feedback including areas for improvement and specific suggestions. For example, it might generate feedback such as, "If you provide specific examples, it will be more persuasive." The generated feedback is displayed on the device.

[1517] Input: Analysis results

[1518] Output: Feedback displayed on the terminal

[1519] Step 9:

[1520] The terminal provides the user with an interface for inputting questions that they would have received in an actual interview. For example, the user might input, "I was asked about my specific project management experience," and press the send button.

[1521] Input: User input of questions asked in the actual interview

[1522] Output: Actual interview questions sent to the server

[1523] Step 10:

[1524] The server saves the actual interview questions sent by the user in a database. The saved questions are reflected in the question list for the next mock interview. This allows the system to always incorporate the latest question trends.

[1525] Input: Actual interview questions submitted by the user

[1526] Output: Actual interview questions stored in a database

[1527] (Application example 1)

[1528] 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."

[1529] Conventional interview preparation systems focus solely on providing interview questions and feedback, but do not address specific training or skill development in specific work or technical fields. In particular, there is a lack of efficient means for providing practical training, such as operating and troubleshooting automated equipment in factories. This makes it difficult for employees to effectively acquire the skills actually required in factories. To solve this issue, a system is needed that allows users to receive specific training related to factory operations.

[1530] 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.

[1531] In this invention, the server includes: means for inputting the name of the company and industry information for which the user is applying; means for collecting URLs of related news articles and analyzing the text data; means for extracting important keywords from the news articles using natural language processing technology; means for generating anticipated interview questions based on the keywords and company information; means for saving the generated questions in a database; means for sequentially displaying the questions to the user in a mock interview format and saving the user's answers; means for analyzing the answers and generating and displaying feedback; means for the user to input questions asked in an actual interview; means for adding the input questions to the database and reflecting them in the next question update; means for generating and displaying training questions related to the operation of automated equipment in a factory; and means for evaluating the responses and providing feedback based on the user's answers. This allows users to receive practical operational training in a factory and effectively acquire skills directly related to actual work.

[1532] "User" refers to an individual or employee who uses the system to prepare for an interview or for factory training.

[1533] "Company name" refers to the name of the specific company for which the user is applying.

[1534] "Industry information" refers to information related to the industry or field to which a company belongs.

[1535] "Related news articles" refer to articles that describe the latest news or events related to a company or industry.

[1536] "URL" refers to Internet link information that indicates the address of a web page.

[1537] "Text data" refers to the written information obtained from news articles and text.

[1538] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[1539] "Keywords" refer to important words and phrases extracted from news articles and company information.

[1540] "Interview Questions" refers to questions that may be asked of you in a job interview.

[1541] A "database" refers to a computer system for systematically organizing and storing information.

[1542] A "mock interview" is a form of practice conducted to simulate a real interview.

[1543] "Answer" refers to the response a user gives to a question during a mock interview or training.

[1544] "Feedback" refers to information that evaluates an answer or points out areas for improvement.

[1545] "Input" refers to the act of a user providing information to a system.

[1546] "Automation equipment" refers to robots and automated machines used in factories, etc.

[1547] "Operational training" refers to training that teaches users how to operate and troubleshoot automated equipment.

[1548] "Response evaluation" refers to the act of analyzing the content of a user's response and evaluating its quality.

[1549] This invention is a system for enabling users to effectively operate and train automated equipment in factories. This system comprises the following steps:

[1550] 1. Entering user information

[1551] First, the terminal provides the user with an interface for entering company name and industry information. The user enters the company name and industry information they wish to work for and sends it to the system. For example, the user may enter "manufacturing."

[1552] 2. Collection and analysis of related news articles

[1553] Based on the submitted URL, the server scrapes relevant news articles from the web to collect text data. The server then uses natural language processing techniques to analyze this text data and understand the content of the article. For example, it extracts important keywords and phrases from the article. Specifically, it uses Python's BeautifulSoup and requests libraries to retrieve web page data, and Hugging Face's transformers library to perform natural language processing.

[1554] 3. Generate and save training questions

[1555] The server uses the keywords extracted from the analysis results to generate training questions related to the company or industry, such as "What do you think about the latest robot operation technology?" These questions are then stored in a database.

[1556] 4. Conducting mock training

[1557] When the user presses a button to start the simulation training, the server sends a list of questions to the terminal, which are displayed one after the other. The user enters answers to the questions in the text box and submits the answer. For example, the user might enter, "The latest technology is extremely important for dramatically improving production efficiency."

[1558] 5. Analysis of answers and feedback

[1559] The server analyzes the user's responses using natural language processing technology and evaluates their content. Specifically, it determines the specificity and relevance of the responses. Based on the evaluation results, it generates feedback including areas for improvement and specific suggestions, and displays it on the device. The OpenAI API is used to evaluate responses and generate appropriate feedback.

[1560] 6. Input of actual operation feedback

[1561] An interface is provided for users to provide feedback and problems they have experienced during actual operation or training to the system. For example, users can input and submit a message such as, "Please tell us about your specific troubleshooting experiences during operation."

[1562] 7. Updating the database

[1563] The server stores the inputted actual operation feedback in a database and reflects it in the question list for the next mock training session, allowing the system to always provide a question list that incorporates the latest trends in training content.

[1564] As a concrete example, consider the case where a user requests "Training in factory automation technology in the manufacturing industry." In this case, the system extracts keywords such as "automation technology" and "robot operation" from related news articles and generates the question, "What do you think about the latest trends in automation technology?" The user can enter an answer and receive feedback on their response, allowing them to effectively acquire the skills required in an actual factory.

[1565] An example prompt might look like this:

[1566] You are in the manufacturing industry and are being trained to operate automated equipment. Using information from a news article, answer the following questions:

[1567] 1. What do you think about the latest robotic manipulation technology?

[1568] 2. What is your experience troubleshooting robot operations?

[1569] This system allows users to undergo simulated training based on real-life operating situations, enabling them to effectively acquire the skills necessary for actual factory work.

[1570] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1571] Step 1:

[1572] The terminal provides the user with an interface for entering company names and industry information. The user enters the company name and industry information they wish to work for and sends it to the system. The information entered includes "company name" and "industry information." This allows the system to understand the user's specific wishes.

[1573] Step 2:

[1574] The server receives the URL sent by the user and scrapes related news articles from the web to collect text data. Specifically, it accesses web pages using Python's requests library and extracts text data using the BeautifulSoup library. The input is the "URL of the news article" and the output is the "scraped text data."

[1575] Step 3:

[1576] The server uses natural language processing technology to analyze the collected text data and understand the content of the articles. Specifically, it uses Hugging Face's transformers library to extract important keywords and phrases from the text data. The input is "text data" and the output is "important keywords and phrases."

[1577] Step 4:

[1578] The server uses the extracted keywords to generate predicted questions from training related to the company and industry. A generative AI model is used to generate "predicted questions" from "keywords" and "company information." For example, it generates a question such as "What do you think about the latest robot operation technology?" The input here is "keywords" and "company information," and the output is the "generated question."

[1579] Step 5:

[1580] The server saves the generated question in a database. The saved information is the "generated question" and is prepared for display to the user in later processing. The input is the "generated question" and the output is the "question saved in the database."

[1581] Step 6:

[1582] When the user presses a button to start the simulated training, the server sends a list of questions to the terminal in order for them to be displayed. The user receives the training questions in order, enters their answers in the text box, and sends them. The input is the "user's confirmation action," and the output is the "question displayed on the terminal" and the "user's answer."

[1583] Step 7:

[1584] The server analyzes the user's answers using natural language processing technology and evaluates their content. Specifically, it determines the specificity and relevance of the answers. It analyzes the "user's answers" using the OpenAI API and generates "evaluation results and feedback." The input is the "user's answers" and the output is "evaluation results and feedback."

[1585] Step 8:

[1586] Based on the evaluation results, the server generates feedback including areas for improvement and specific suggestions, which is displayed on the device. The user can review this feedback and use it for the next training session. The input is "evaluation results and feedback," and the output is "feedback display on the device."

[1587] Step 9:

[1588] An interface is provided that allows users to provide feedback and problems they have received during actual operations and training to the system. Users input and send specific feedback and problems. The input is "feedback from operations and training," and the output is "sending feedback data to the server."

[1589] Step 10:

[1590] The server stores the inputted actual operation feedback in a database and reflects it in the question list for the next and subsequent mock training sessions. This allows the server to provide a question list that always incorporates the latest trends in training content. The input is "feedback from the user" and the output is "feedback stored in the database."

[1591] 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.

[1592] This invention relates to a system that allows users to effectively prepare for interviews, and in particular provides an innovative system that recognizes the user's emotions and reflects them in feedback by combining an emotion engine. An embodiment of this system will be described in detail below.

[1593] System configuration

[1594] Enter user information

[1595] The terminal provides the user with an interface for entering company name and industry information. The user enters the name of the company they are applying to ("ABC Co., Ltd."), the industry ("IT industry"), and the URL of a related news article, and sends it to the system.

[1596] Collection and analysis of relevant news articles

[1597] The server scrapes relevant news articles from the web based on the submitted URL and collects text data. The server then analyzes this text data using natural language processing techniques to understand the content of the article, specifically extracting important keywords and phrases.

[1598] Generate and save interview questions

[1599] The server uses the extracted keywords to generate potential interview questions based on company information. For example, it generates a question like, "What do you think about ABC Corporation's latest project?" The generated questions are stored in a database.

[1600] Mock interviews

[1601] When a user starts a mock interview, the server sequentially sends a list of questions to the terminal and displays them. The user enters answers to the questions in the text boxes and submits the answer. For example, the user might enter, "The latest project will provide new value to the market, and I believe I can contribute by utilizing my skills."

[1602] Emotion recognition by emotion engine

[1603] During the mock interview, the device runs an emotion engine based on the user's text responses and facial expression data to recognize the user's emotions. The emotion engine recognizes emotions such as "happiness," "anxiety," and "confidence."

[1604] Analysis of responses and feedback

[1605] The server analyzes the saved user responses using natural language processing technology and evaluates them, taking into account the results of the emotion engine. Specifically, it considers the specificity and relevance of the responses as well as the user's emotional state. Based on the results, it generates feedback including areas for improvement and specific suggestions, which are displayed on the device.

[1606] Enter questions asked in the actual interview

[1607] An interface is provided for users to provide feedback to the system about the questions they received during the actual interview. For example, the user can enter "I was asked about my specific project management experience" and submit the feedback.

[1608] Database Update

[1609] The server saves the entered actual interview questions in a database and reflects them in the question list for future mock interviews, allowing the system to always provide a question list that incorporates the latest interview question trends.

[1610] Specific examples

[1611] Let's say a user is applying to work for a company called "X Corporation" in the "financial industry." The user enters the URL of a related news article and submits it. The system retrieves the news article from the URL, analyzes it using natural language processing technology, and extracts keywords such as "X Corporation's new financial service." The system then generates a question, "What do you think about X Corporation's new financial service?" and presents it to the user through a mock interview. The system analyzes the user's answer and the emotions recognized by the emotion engine, and provides feedback such as, "It would be good if you mentioned the specific name and features of the service. Also, it's good that you answered with confidence, but it would be even better if you included more specific experiences." The user then feeds back to the system the question they received in the actual interview, "Tell us about your experience managing specific financial projects," and the database is updated.

[1612] In this way, users can continuously prepare for their interviews taking into account their current information and emotional state, and the feedback provided allows users to understand and improve their weaknesses.

[1613] The processing flow will be explained below.

[1614] Of course, the specific processing flow of the system will be explained below by dividing it into steps.

[1615] Step 1:

[1616] A user accesses the system and logs in or creates a new account.

[1617] Step 2:

[1618] The device will display a form for entering the company name, industry, and the URL of a related news article.

[1619] Step 3:

[1620] The user enters the company name "ABC Co., Ltd.", the industry "IT industry," and the URL of a related news article, and presses the send button.

[1621] Step 4:

[1622] The server receives the company name, industry, and news article URL that were sent.

[1623] Step 5:

[1624] The server scrapes related news articles from the news article URLs and collects text data.

[1625] Step 6:

[1626] The server analyzes the collected text data of news articles using natural language processing technology.

[1627] Step 7:

[1628] The server extracts important keywords and phrases from the analysis results, such as "ABC Corporation's latest project" or "technology trends."

[1629] Step 8:

[1630] The server generates questions that are likely to be asked in an interview based on the extracted keywords and company information. For example, it generates a question such as, "What do you think about ABC Corporation's latest project?"

[1631] Step 9:

[1632] The server stores the generated questions in a database.

[1633] Step 10:

[1634] The user presses a button to start the mock interview from the mock interview menu.

[1635] Step 11:

[1636] The server loads the saved question list into a task queue and prepares it to be sent to the terminal in order.

[1637] Step 12:

[1638] The server sends the first question to the terminal and displays it. For example, it displays "What do you think about ABC Corporation's latest project?"

[1639] Step 13:

[1640] The user enters an answer in the text box and presses the submit button.

[1641] Step 14:

[1642] The server receives and stores the user's answers.

[1643] Step 15:

[1644] During the mock interview, the device uses a camera and microphone to collect the user's facial expressions and voice and transmits them to the emotion engine.

[1645] Step 16:

[1646] The emotion engine on the server analyzes the user's facial expressions and voice data to recognize emotions, such as "happiness," "anxiety," and "confidence."

[1647] Step 17:

[1648] The server analyzes the saved user responses using natural language processing technology, evaluating their depth, specificity, and relevance, while also taking into account the results of the emotion engine.

[1649] Step 18:

[1650] The server generates feedback based on the analysis of the answer and the emotions recognized by the emotion engine. For example, "Your answer is not specific enough. It would be better if you mentioned a specific project name. Also, it is good that you answered with confidence, but it would be even better if you included more specific experiences."

[1651] Step 19:

[1652] The server sends the feedback to the terminal for display.

[1653] Step 20:

[1654] The user accesses a form that allows them to enter questions from the actual interview into the system.

[1655] Step 21:

[1656] The user enters, for example, "I was asked about my specific project management experience" and presses the submit button.

[1657] Step 22:

[1658] The server stores the questions asked in the actual interview in a database.

[1659] Step 23:

[1660] The server updates the question list for the next and subsequent mock interviews based on the new questions.

[1661] Example 2

[1662] 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."

[1663] Existing systems for preparing Q&A questions for potential organizations often lack sufficient information gathering and appropriate Q&A content. Furthermore, they lack feedback that takes into account the user's emotional state, making it difficult to improve performance in mock questions or actual Q&A sessions. The present invention aims to solve these problems by providing a system that allows users to effectively prepare and improve Q&A questions.

[1664] 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 inputting the name and industry information of the organization the user is interested in; means for collecting links to related information articles and analyzing text data; means for extracting important keywords from the information articles using natural language processing technology; means for generating predicted questions based on the keywords and organization information; means for saving the generated questions in a storage device; means for sequentially displaying the questions to the user in the form of mock questions and saving the user's answers; means for analyzing the answers, generating and displaying evaluations and responses; means for the user to input questions asked in actual question-and-answer sessions; means for adding the input questions to a storage device and reflecting them in the next question update; emotion recognition means for analyzing the user's answers and facial expression data and recognizing the user's emotional state; and means for including the recognition results in feedback. This enables the user to collect related information, generate questions, and provide feedback that takes emotions into account.

[1665] "User" means a person who uses the system to prepare questions and answers for a prospective organization.

[1666] "Organization name" is information that indicates the name of the company or organization that the user is applying to.

[1667] "Industry information" is information about the type of industry or business to which the organization to which the applicant belongs.

[1668] "Link" refers to a web address that points to a related article of information.

[1669] "Text data" refers to textual information obtained through scraping or analysis.

[1670] "Natural language processing technology" refers to technology for analyzing acquired text data and extracting meaningful information.

[1671] "Keywords" refer to important words or phrases extracted from text data.

[1672] "Question and answer content" refers to anticipated questions generated using natural language processing technology.

[1673] "Storage device" refers to a device for storing the generated questions and answers, answer data, and other necessary information.

[1674] "Mock question format" refers to a method in which anticipated questions are presented in a format similar to an actual questioning environment, and users respond to them.

[1675] "Answer" refers to a user's answer to a question presented in the form of a mock question.

[1676] "Evaluation and response" refers to feedback and suggestions generated based on the analyzed answer data.

[1677] "Emotion recognition means" refers to technology that analyzes a user's answers and facial expression data to recognize their emotional state.

[1678] This invention relates to a system that allows users to effectively prepare for Q&A sessions, and in particular provides an innovative system that recognizes the user's emotions and reflects them in feedback by incorporating an emotion recognition engine. An embodiment of this system will now be described in detail.

[1679] System configuration

[1680] Enter user information

[1681] The terminal provides the user with an interface for entering information about the organization's name and industry. The user enters the name of the organization they wish to apply for ("Organization XYZ"), the industry ("Technology field"), and a link to a related news article, and sends it to the system.

[1682] Collection and analysis of relevant news articles

[1683] The server scrapes relevant news articles from the web based on the submitted links and collects text data using Python's BeautifulSoup. The server then analyzes this text data using natural language processing techniques (e.g., spaCy, NLTK) to extract important keywords and phrases.

[1684] Generate and save interview questions

[1685] Based on the extracted keywords, the server uses a generative AI model (e.g., GPT-3) to generate predicted questions based on the organization information. An example of a prompt used for generation is, "Please generate questions related to 'technological innovation.'" The generated questions are saved in a storage device.

[1686] Mock question session

[1687] When a user starts a mock question, the server sequentially sends the generated list of questions to the terminal, which then displays them. The user enters answers to each question in the text box and submits it. For example, in response to the question "What do you think about the impact of new technological innovations on the market?", the user enters "I think new technological innovations will improve market competitiveness."

[1688] Emotion recognition using an emotion recognition engine

[1689] During the mock questions, the device collects the user's text responses and facial expression data, and uses an emotion recognition engine (e.g., Microsoft Azure Cognitive Services) to recognize the user's emotions. The emotion recognition engine recognizes emotions such as "happiness," "anxiety," and "confidence."

[1690] Analysis of responses and feedback

[1691] The server analyzes the user's saved answers using natural language processing technology and evaluates them taking into account the results of an emotion recognition engine. For example, it evaluates the specificity and relevance of the answer and generates feedback based on the recognized emotional state. The feedback might be something like, "It would be good to include a specific example. Also, it's good that you're answering with confidence, but it would be even better if you included a more specific experience." The generated feedback is displayed on the device.

[1692] Enter questions asked during the actual Q&A session

[1693] The terminal provides the user with an interface for feedback on the questions asked during the actual Q&A session. For example, the user can input "I was asked about my specific project management experience" and submit.

[1694] Database Update

[1695] The server saves the questions entered in the actual Q&A session in a storage device and reflects them in the Q&A list for the next mock question session onwards, allowing the system to always provide a list that incorporates the latest trends in Q&A questions.

[1696] Specific examples

[1697] For example, suppose a user is applying to work for "Organization ABC" in the "finance industry." The user inputs and submits a link to a related news article. The server retrieves the news article from the link, analyzes it using natural language processing technology, and extracts keywords such as "Organization ABC's new financial service." The server then generates a question, "How do you feel about Organization ABC's new financial service?" and provides it to the user through a mock question. The server analyzes the user's answer and the emotions recognized by the emotion recognition engine, and provides feedback such as, "It would be good if you mentioned the specific service name and features. Also, it is good that you answered with confidence, but it would be even better if you included more specific experiences." The user then feeds back the question they received in the actual Q&A session, "Tell me about your experience managing specific financial projects," to the system and updates the storage device.

[1698] In this way, users can continuously prepare questions and answers that take into account the latest information and their emotional state, and the feedback provided allows users to understand and improve their weaknesses.

[1699] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1700] Step 1: Enter user information

[1701] Input: The user enters the name of the organization they wish to apply to, industry information, and links to related news articles.

[1702] Processing: The terminal receives the entered information and confirms it through the interface.

[1703] Output: Sends the entered information to the server.

[1704] Specific operation: The device displays a web form or app input screen, and after the user enters data in the input fields for "organization name," "industry," and "news article URL," clicks the send button, and the input information is sent to the server.

[1705] Step 2: Collect and analyze relevant news articles

[1706] Input: The server receives the link information.

[1707] Processing: The server scrapes the linked webpage using Python's BeautifulSoup library to collect text data, which is then analyzed using natural language processing techniques (e.g., spaCy, NLTK) to extract important keywords and phrases.

[1708] Output: A list of parsed keywords and phrases.

[1709] How it works: The server retrieves the web page from the specified URL, extracts the text using BeautifulSoup, and then performs morphological analysis on the text data using SpaCy to extract important keywords.

[1710] Step 3: Generate and save interview questions

[1711] Input: The server receives the extracted keywords and organization information.

[1712] Processing: The server sends the keywords as a prompt to a generative AI model (e.g., GPT-3) to generate questions. An example prompt is, "Please generate questions related to 'technological innovation.'"

[1713] Output: The generated questions and answers.

[1714] Specific operation: The server sends a prompt to the generation AI model, which generates the expected question and answer content. The generated question and answer content is then saved in a storage device.

[1715] Step 4: Practice Questions

[1716] Input: The user sends a request to start the mock question.

[1717] Processing: The server retrieves the list of questions from the storage device and transmits them to the terminals in order.

[1718] Output: The question list displayed on the terminal.

[1719] Specific operation: When the user clicks the "Start mock questions" button, the server retrieves the question list from the storage device, sends it to the terminal, and displays it.

[1720] Step 5: Enter and submit your answers

[1721] Input: The user enters the answer to each question.

[1722] Processing: The terminal sends the entered answer to the server.

[1723] Output: The answer data sent to the server.

[1724] Specific operation: The terminal presents questions to the user, and when the user enters answers to each question in the text boxes and presses the send button, the terminal sends the answer data to the server.

[1725] Step 6: Emotion recognition using the emotion recognition engine

[1726] Input: The server receives the submitted answer data and facial expression data.

[1727] Processing: The server uses an emotion recognition engine (e.g., Microsoft Azure Cognitive Services) to analyze the answer data and facial expression data and recognize the user's emotions.

[1728] Output: Recognized emotional state data.

[1729] Specific operation: The device sends the user's answer data and facial expression data together, and the server passes it to the emotion recognition engine for analysis.

[1730] Step 7: Analyze responses and generate feedback

[1731] Input: The server receives answer data and recognized emotional state data.

[1732] Processing: The server analyzes the answer data using natural language processing technology and evaluates it, taking into account the emotion recognition results. Based on the evaluation results, specific feedback is generated.

[1733] Output: The generated feedback.

[1734] Specific operation: The server analyzes the answer data using natural language processing tools, evaluates the specificity, relevance, and emotional state of the content, and generates feedback. This feedback is then sent to the device.

[1735] Step 8: View your feedback

[1736] Input: Sends server-generated feedback to the device.

[1737] Processing: The device displays feedback to the user.

[1738] Output: The feedback displayed to the user.

[1739] Specific behavior: The device receives feedback from the server and displays it to the user, such as "It would be good to include a specific example. Also, it's good that you're confident in your answer, but it would be even better if you included more specific experiences."

[1740] Step 9: Enter the questions asked during the Q&A session

[1741] Input: The user inputs the question asked in the actual Q&A session.

[1742] Processing: The terminal sends the entered question to the server.

[1743] Output: The query data sent to the server.

[1744] Specific operation: The terminal displays a form for the user to input the actual question, and when the user inputs the question and presses the submit button, the terminal sends the question data to the server.

[1745] Step 10: Update the Database

[1746] Input: The server receives the actual query data that was sent.

[1747] Processing: The server saves the newly entered question in a memory device and reflects it in the question and answer list from the next time onwards.

[1748] Output: Updated question list.

[1749] Specific operation: The server saves the new question data in the storage device and updates the existing question list. The newly saved questions are used in the next mock test.

[1750] (Application example 2)

[1751] 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."

[1752] In conventional customer support preparation systems, it is difficult for representatives to fully acquire the product information and knowledge necessary for customer support, and the responsiveness and accuracy of responses to customer inquiries can be reduced. Furthermore, the emotional state of representatives can affect the quality of customer support, but there is a lack of a means to effectively manage this. The present invention aims to solve these problems and improve the efficiency and quality of customer support preparation.

[1753] 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 inputting product names and category information for which the user is responsible; means for collecting URLs of related product reviews and analyzing text data; means for extracting important keywords from the reviews using natural language processing technology; means for generating predicted customer queries based on the keywords and product information; means for saving the generated queries in a database; means for sequentially displaying the queries in a simulated customer support format and saving the user's responses; means including an emotion engine that recognizes the user's emotions during the simulated session and reflects them as feedback in the evaluation results; means for analyzing the responses and generating and displaying feedback; means for inputting queries made by the user during actual support; and means for adding the input queries to a database and reflecting them in the next query update. This allows users to acquire the latest and most effective support information, manages the emotional states of staff, and enables highly accurate customer support.

[1754] "User" means any person or entity that uses the System.

[1755] "Organization name" refers to the name of the company or organization you are applying for.

[1756] "Industry information" refers to information about the industry to which the company or organization you are applying to belongs.

[1757] "Related news articles" refer to articles that cover the latest news related to the company or industry you are applying to.

[1758] "URL" refers to the web page address where the relevant news article is published online.

[1759] "Text data" refers to the textual information of collected news articles.

[1760] "Natural language processing technology" refers to computer technology for analyzing text data and understanding its meaning.

[1761] "Key words" refer to key words and phrases extracted from news articles and used to generate interview questions.

[1762] "Interview questions" refer to questions asked of users during mock interviews or actual interviews.

[1763] "Database" refers to a system for storing data such as generated questions, user responses, and questions asked in actual interviews.

[1764] A "mock interview" refers to a simulation that allows users to practice for a real interview.

[1765] "Emotion engine" refers to a system for recognizing and analyzing users' emotions.

[1766] "Feedback" refers to evaluations and improvement suggestions generated based on the user's responses and emotional state.

[1767] ·System Programming

[1768] The system's program is written in Python and includes the following main functions:

[1769] 1. Data collection function:

[1770] The server collects the URLs of the product review web pages based on the product name and category information entered by the user. This collection process uses the requests and BeautifulSoup libraries.

[1771] 2. Data analysis function:

[1772] The server analyzes the collected text data using natural language processing techniques to extract important keywords. This analysis process utilizes the spacy and TextBlob libraries.

[1773] 3. Query generation function:

[1774] The server generates a customer query based on the analysis results and stores it in a database, using the extracted important keywords.

[1775] 4. Simulation session function:

[1776] The terminal sequentially displays queries generated in a simulated customer support format and accepts the user's answers, which are then sent from the terminal to a server and stored.

[1777] 5. Emotion recognition function:

[1778] During the simulation session, the server runs an emotion engine based on the user's responses to recognize the user's emotions. This emotion recognition is performed using the EmotionRecognizer library.

[1779] 6. Feedback generation function:

[1780] The server analyzes the saved user responses and evaluates them based on the results of the emotion engine. The feedback includes specific improvements and suggestions.

[1781] 7. Actual query input function:

[1782] Users are provided with an interface to input queries received from actual customer support into the system. The input queries are added to a database and reflected in the generation of future queries.

[1783] Processing Description

[1784] To realize the above functions, the server performs the following data processing and data calculations.

[1785] 1. Data Collection:

[1786] Scrape product reviews from a URL and retrieve them as text data. Here, requests and BeautifulSoup are used.

[1787] 2. Data Analysis:

[1788] Spacy is used to perform natural language processing on the scraped text data to extract important keywords from the reviews.

[1789] 3. Query Generation:

[1790] Generate predicted customer queries based on the extracted keywords.

[1791] 4. Mock Session:

[1792] The device displays the query to the user and accepts the user's answer, which is sent to the server and stored.

[1793] 5. Emotion recognition:

[1794] The server uses the EmotionRecognizer library to recognize emotions from the user's responses.

[1795] 6. Feedback Generation:

[1796] The content of the user's response is analyzed using TextBlob, and feedback is generated taking into account the results of emotion recognition.

[1797] 7. Actual query input and database update:

[1798] The actual customer query entered by the user is added to the database and reflected in the next query generation.

[1799] Specific examples and prompts

[1800] As a specific use case, consider a customer support representative preparing to support a new product, "Smartwatch X." In this case, the representative enters information about "Smartwatch X" into the system, collects and analyzes related reviews, and generates predicted queries based on the results, conducting mock sessions.

[1801] Example prompt sentence:

[1802] We will predict customer queries based on reviews of the "Smartwatch X" and conduct a mock customer support session. First, enter the product URL.

[1803] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1804] Step 1:

[1805] The user inputs the product name and category information for which they are responsible. The user inputs the product name "Smart Watch X" and the category "Wearable Device" into the system's input interface. The device sends this information to the server. Based on this input information, the server determines the URLs of the related reviews to be collected.

[1806] Step 2:

[1807] The server collects URLs of related product reviews and parses the text data. The server scrapes product review pages from the web based on product name and category information. This process uses the requests and BeautifulSoup libraries. The collected review text data is stored for subsequent analysis.

[1808] Step 3:

[1809] The server uses natural language processing technology to extract important keywords from reviews. The collected text data is analyzed using the spacy library to identify nouns and related important keywords. For example, "battery life" and "fitness features" are extracted. This data processing identifies important keywords.

[1810] Step 4:

[1811] The server generates predicted customer queries based on the analysis results. Based on the extracted important keywords, it generates predicted customer queries. For example, a query such as "What is the battery life of Smartwatch X?" is created. These queries are stored in a database.

[1812] Step 5:

[1813] The terminal sequentially displays queries generated in a simulated customer support format and accepts responses from the user. The terminal displays the queries received from the server to the user. The user inputs a text response to the query, and the terminal sends the response to the server. The input from the user is saved as response data.

[1814] Step 6:

[1815] The server runs an emotion engine based on the user's responses during the simulated session to recognize emotions. Using the EmotionRecognizer library, emotions such as "happiness" or "anxiety" are extracted from the user's responses. For example, if a user responds, "I think this feature is very good," "happiness" is recognized as the emotion.

[1816] Step 7:

[1817] The server analyzes the saved user answers and generates and displays feedback. It uses the TextBlob library to evaluate the positivity and subjectivity of the answer, and generates feedback taking into account the results of emotion recognition. For example, feedback such as "Your answer is positive, and including specific examples would make it even better" is generated. The feedback is displayed on the device.

[1818] Step 8:

[1819] The user inputs a query received from a real customer support service into the system. The user inputs the query received from a real customer through the interface, and the device sends it to the server. For example, a query such as "Please tell me about the waterproof performance of Smartwatch X" is input.

[1820] Step 9:

[1821] The server adds the actual query entered to the database and reflects it in the next query generation. By saving the actual query entered by the user in the database and using that data when generating the next query, it becomes possible to provide a query list that reflects the latest information.

[1822] 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.

[1823] 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.

[1824] 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.

[1825] 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.

[1826] 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.

[1827] 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.

[1828] 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).

[1829] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of ...

Claims

1. A means for the user to input the name of the company and industry information he / she wishes to apply for; A means of collecting URLs of related news articles and analyzing the text data; A means of extracting important keywords from news articles using natural language processing technology; A means for generating predicted interview questions based on the keywords and company information; means for storing the generated questions in a database; a means for sequentially displaying the questions to a user in a mock interview format and saving the user's answers; means for analyzing the responses and generating and displaying feedback; A means for a user to input questions asked in an actual interview; a means for adding the input question to a database and reflecting the input question in the next question update; A system including:

2. The system according to claim 1 , wherein the system analyzes the user's response using natural language processing technology and generates feedback based on the analysis results.

3. 2. The system of claim 1, wherein the system continuously adds input questions asked in actual interviews to the database and updates the question list.

Images