system

Abstract

We provide the system. [Solution] Information processing circuit means that generates relevant dialogue-style questions based on the requests of the interviewer, An autonomous device having voice input / output capabilities receives voice input from an interviewer and converts it into a text signal using a voice recognition circuit. An evaluation circuit means that analyzes a text signal and provides methods for evaluating and improving its content, An output circuit means for notifying the interviewer of the evaluation results and improvement methods, A training support system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Regarding the need to efficiently conduct high-quality preparation for interviews, there is a problem that there is a shortage of professional interviewers and coaches. Furthermore, in conventional interview practice, there is a problem that it is difficult to appropriately customize questions and provide detailed feedback. Therefore, there is a demand for providing practical interview practice optimized for individual interview practice participants.

Means for Solving the Problems

[0005] The present invention solves the aforementioned problems by providing a system that includes an information processing device that generates relevant interview questions based on the requests of interview trainees, a speech recognition device that receives voice input from interview trainees and converts it into text data, an evaluation device that analyzes the text data and provides content evaluation and improvement points, and a notification device that notifies interview trainees of the evaluation results and improvement points. With the present invention, interview trainees can efficiently prepare for interviews with high quality through individually optimized question sets and specific feedback.

[0006] "Interview practice participant" refers to an individual who uses the system of the present invention for the purpose of preparing for an interview.

[0007] An "information processing device" refers to a device that has the function of generating relevant interview questions based on the requests of the interviewer and providing a set of questions.

[0008] A "voice recognition device" refers to a device that has the function of converting voice data input from interviewees into text data.

[0009] An "evaluation device" refers to a device that analyzes text data and evaluates its content to generate specific feedback for interviewees.

[0010] A "notification device" refers to a device that effectively notifies interviewers of the feedback generated by the evaluation device. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. The communication I / F manages 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), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the 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.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0025] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] The present invention provides a system for interview trainees to effectively prepare for interviews. This system generates relevant interview questions in response to the trainee's requests, presents them audibly, accepts user responses, and provides appropriate feedback. Specific embodiments of the present invention are described below.

[0033] First, the user enters their interview practice request on a terminal. The user specifies their desired industry and job type and prepares practice questions based on the topic. Based on this, the server uses a generation AI to generate appropriate interview questions. These questions are customized in terms of difficulty and content to meet the user's requirements.

[0034] Next, the device presents a question to the user verbally. The user can then answer verbally. The device converts the user's response into text using speech recognition technology. The converted text is then sent to the server.

[0035] The server analyzes the received text data using natural language processing technology and evaluates the user's response. Based on the analysis results, the evaluation device determines the quality of the response and generates areas for improvement and examples of good responses. This feedback is detailed and specific, enabling users to prepare better responses.

[0036] Finally, the device notifies the user of feedback via voice or text, allowing them to reflect on their answers and gain guidance for further improvement. This system supports continuous practice so that users can perform at their best in interviews.

[0037] For example, if a user requests a "sales interview," the server generates questions related to sales. For instance, it might generate a question like, "Please tell us about the sales targets you have achieved in the past." When the user answers, the answer is evaluated, and feedback is provided, such as, "It would be even better if you included specific numerical data." Through this process, users can prepare persuasive answers that include concrete examples.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user enters a request to start a mock interview via their device. The user specifies the industry and job type they want to practice for and selects their preferred interview format.

[0041] Step 2:

[0042] The server receives the user's request and retrieves appropriate question data by referring to a database corresponding to the specified industry and job type. Based on the retrieved data, it uses AI to generate interview questions.

[0043] Step 3:

[0044] The terminal receives questions from the server and presents them to the user verbally. Speech synthesis technology is used to ensure the user understands the questions naturally.

[0045] Step 4:

[0046] The user responds to the presented questions verbally. The user attempts to structure and express their thoughts.

[0047] Step 5:

[0048] The device receives the user's voice response and converts it into text data using its speech recognition function. This text data is then sent to the server.

[0049] Step 6:

[0050] The server analyzes the text data it receives. Natural language processing techniques are applied to evaluate the keywords, logical structure, and expressiveness of the responses. Furthermore, areas for improvement and inconsistencies that need to be pointed out in the responses are identified.

[0051] Step 7:

[0052] The server generates feedback based on the analysis results. This feedback includes what was good about the response, areas for improvement, and specific examples of improvements.

[0053] Step 8:

[0054] The device receives feedback and notifies the user. The user reviews the feedback, pays attention to areas for improvement, and continues practicing.

[0055] Step 9:

[0056] Users can receive feedback, improve their answers, and try the same question again or a new one. By repeating this process, users gradually improve their interview skills.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] Currently, systems for effective interview practice do not adequately meet the specific needs of users. In particular, there is a lack of systems that can appropriately customize interview content and questions according to specific industries and job types, and provide accurate feedback on user responses. Furthermore, there is a growing need for systems that can effectively analyze voice input and evaluate user responses using natural language processing.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes a computing device means that generates relevant inquiries based on requests from the user, a speech recognition device means that receives voice input from the user and converts it into text data, and an evaluation device means that analyzes the text data and provides content evaluation and improvement points. This makes it possible for users to receive appropriate interview questions tailored to their industry and job type, and to obtain specific and effective feedback on their answers.

[0062] "User" refers to an individual or organization that uses computing devices and related systems to conduct interview practice.

[0063] "Requests" refer to the specific wishes and conditions regarding interview practice that the user communicates to the computing device.

[0064] "Inquiry" refers to interview-related questions generated by the computer based on the user's request.

[0065] A "computer" refers to a central processing unit that receives user requests, generates queries, and interacts with other system components.

[0066] "Voice input" refers to information provided by the user through voice.

[0067] "Character data" refers to information in text format converted from voice input by a speech recognition device.

[0068] A "speech recognition device" refers to a machine or software that receives speech input and converts it into text data.

[0069] An "evaluation device" refers to a device or software that has the function of analyzing text data provided by a speech recognition device, evaluating its content, and generating areas for improvement.

[0070] "Notification device" refers to a machine or function that communicates evaluation results and areas for improvement to the user in voice or text format.

[0071] "Natural language processing technology" refers to artificial intelligence technology that analyzes the meaning contained in text data and understands the syntactic structure, content, and context of a sentence.

[0072] "Domain" refers to the specific industry or field that the user focuses on during interview practice.

[0073] "Work" refers to a series of activities or tasks related to a specific job or function.

[0074] This invention provides a system to support effective preparation for users who wish to practice for interviews. The system includes the ability to generate highly customized interview questions and to analyze and evaluate the user's voice input.

[0075] The user uses a terminal to input a request for interview practice. The user specifies the desired area or job and provides prompts to the system. For example, if the user enters the prompt "Generate sales job questions," questions related to that specific job will be generated.

[0076] Upon receiving a user request, the server uses its computing power and a generative AI model to generate relevant questions. This generation process utilizes various databases and pre-trained natural language processing models. The generated interview questions are those that best fit the conditions specified by the user.

[0077] Next, the device uses speech synthesis technology to present questions to the user verbally. A typical speech synthesis technology that utilizes this technology is a commonly used voice output function.

[0078] The user answers the presented questions verbally. The terminal converts these answers into text data using speech recognition software and sends the results to the server. Various commercially available speech recognition APIs are used for the speech recognition technology.

[0079] The server analyzes the received text data using natural language processing technology and evaluates the response. Based on the analysis results, detailed and specific feedback is generated that the user needs to improve.

[0080] Finally, the device notifies the user of the evaluation results and feedback. This feedback is displayed in either audio or text format. This allows the user to reflect on their answers and gain guidance for more effective presentations in interviews.

[0081] This system provides practical support for interview preparation and helps users approach interviews with confidence.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The user enters a request for interview practice using a terminal. This request includes the desired job or area of ​​work. The entered request is sent to the server in the form of a prompt message. The input data consists of the job or area of ​​work specified by the user, and interview questions are generated based on this.

[0085] Step 2:

[0086] The server generates relevant interview questions using a generative AI model based on the received prompt. The server parses the input request and invokes the AI ​​model to generate customized questions accordingly. The output is a set of questions appropriately tailored based on the user's request. This process leverages past question examples stored in the database and the generative capabilities of the AI ​​model.

[0087] Step 3:

[0088] The interview questions generated by the server are sent to the terminal. The terminal uses speech synthesis technology to present the questions to the user verbally. Specifically, the question text is converted into speech output using a speech synthesis API and played through the speaker.

[0089] Step 4:

[0090] The user answers the presented questions verbally via the microphone. These answers are recorded on the device. The recorded audio is input to the device and prepared as data for processing in the next stage.

[0091] Step 5:

[0092] The device converts the user's voice responses into text data using speech recognition technology. It analyzes audio files as input and outputs text data. This process is performed in real time, and the generated text is sent to the server.

[0093] Step 6:

[0094] The server analyzes the received text data using natural language processing technology and evaluates the user's response. Based on the input text, it evaluates the sentence structure, appropriateness of content, and logical structure, and generates feedback data as a result. Predefined evaluation criteria are applied to the evaluation.

[0095] Step 7:

[0096] The server sends the evaluation results and generated improvement feedback to the terminal. The terminal notifies the user of this feedback. This feedback can be delivered via speech synthesis or displayed as text on the screen. The user can then use this feedback to improve their interview responses.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] Conventional interview practice systems have limitations in providing feedback to user voice input, making it difficult to provide customized practice tailored to specific industries or job types. Furthermore, to efficiently support user skill improvement, it is important to utilize autonomous devices that allow for readily accessible interview practice.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes an information processing circuit means that generates relevant dialogue-style questions based on the requests of the interview trainee, a speech recognition circuit means that receives voice input from the interview trainee and converts it into a text signal, and an evaluation circuit means that analyzes the text signal and provides methods for evaluating and improving its content. This makes it possible for interview trainees to efficiently improve skills relevant to specific jobs and industries through dialogue-style practice using the autonomous device.

[0102] An "interview trainee" refers to an individual who practices for an interview, with the aim of improving their ability to answer questions related to a specific industry or job.

[0103] An "autonomous device" refers to a mechanical device equipped with voice input / output capabilities that supports interview practice by interacting with the user, and is used in homes and facilities.

[0104] An "information processing circuit" refers to a circuit that performs calculations to generate relevant dialogue-style questions based on the requests of the interviewee.

[0105] A "voice recognition circuit" refers to a circuit that converts the voice input of an interviewee received by an autonomous device into a text signal.

[0106] An "evaluation circuit" refers to a circuit that analyzes the text signal converted by the speech recognition circuit and provides evaluation and improvement methods for its content.

[0107] "Text signal" refers to the character information generated as a result of the speech recognition circuit converting the voice input of the interviewee.

[0108] This invention provides a system for supporting the skill improvement of interviewers using autonomous devices. This system includes an information processing circuit, a speech recognition circuit, and an evaluation circuit, each of which works in cooperation with the others.

[0109] The server generates relevant conversational questions in its information processing circuit in response to the interviewer's requests. By using a generative AI model, it is possible to efficiently create questions specific to the interviewer's job and industry. For example, when generating questions related to a sales position, the AI ​​model is instructed with the prompt, "Please create five questions for a sales interview."

[0110] When a user answers a question by voice, the device's voice input / output function converts the voice into text signals via a speech recognition circuit. These converted text signals are sent to a server, where an evaluation circuit analyzes the content and suggests ways to improve it. Natural language processing technology (e.g., spaCy) is used for this analysis.

[0111] The evaluation results and areas for improvement are communicated to the interviewer via their device. This feedback provides guidance for interviewers to easily prepare for interviews at home or elsewhere, supporting skill improvement. For example, if a user includes numerical data in their answer, they will receive feedback such as, "Specific numerical data makes your answer more persuasive."

[0112] By using this system, interview candidates can effectively improve their skills tailored to specific jobs and industries through interactive practice using autonomous devices.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The user enters a request for interview practice into the terminal. By specifically specifying the desired job and industry, the request data sent to the server is formed. This request data serves as the basis for generating prompt messages.

[0116] Step 2:

[0117] The server receives the request data and uses its information processing circuitry to generate prompt statements for the AI ​​model. Based on these prompt statements, the AI ​​model creates relevant, conversational questions about a specific job or industry. The generated questions become output data ready to be converted into speech format.

[0118] Step 3:

[0119] The generated question is transmitted to the terminal, which uses speech synthesis technology to present the question to the user verbally. The user answers the presented question verbally. This process generates voice input data. The voice input data is then awaiting processing by the speech recognition circuit.

[0120] Step 4:

[0121] The terminal receives the user's voice input and converts it into a text signal using a speech recognition circuit. This voice-to-text conversion organizes the text data into the format necessary for analysis, and the resulting text data is sent to the server.

[0122] Step 5:

[0123] The server sends the received text data to an evaluation circuit, where it is analyzed using natural language processing technology. This analysis evaluates the user's response and generates information regarding the evaluation and areas for improvement. This result becomes feedback data.

[0124] Step 6:

[0125] The device receives feedback data and notifies the user via voice or text using a notification device. By receiving this feedback, the user can gain specific guidance for improving the quality of their responses. The ultimate output is reflection and skill improvement through feedback.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] This invention provides a system that incorporates emotion recognition functionality into an interview practice system, enabling it to provide personalized feedback while considering the user's emotional state. This system generates relevant questions based on the interview practice request, processes the user's voice input, and recognizes emotional characteristics using an emotion engine.

[0128] Specifically, users input a request to begin interview practice via their device, specifying their desired industry and job type, which generates questions on the server. These questions are dynamically generated by a generation AI and adjusted to meet the user's needs.

[0129] The device presents the user with generated questions via voice. The user is expected to respond to these questions verbally while considering the question. The user's voice input is converted into text data by the device and then sent to the server. Here, the voice data is analyzed by an emotion engine to extract the user's emotional characteristics.

[0130] On the server, the evaluation device performs analysis using natural language processing technology based on text data. Furthermore, emotional characteristics obtained by the emotion engine are referenced in this analysis process. As a result, the evaluation device generates feedback that corresponds to the user's emotional state. The feedback includes content that takes the user's emotional state into consideration, so that the user can practice with confidence.

[0131] The device ultimately notifies the user of feedback and analyzed sentiment data. This notification can be in audio or text format, and the user can use it to improve their responses. For example, if the sentiment engine detects that the user is nervous, the notification may include advice on how to relax. This allows the user to improve their responses in a better state of mind and enhance their performance during the actual interview.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user enters a request to start a practice interview into the terminal. Here, the user specifies the industry and job type they want to practice for and selects the desired interview format.

[0135] Step 2:

[0136] The server receives a request from the user and retrieves relevant question data by referencing a database corresponding to the specified industry and job type. Using generation AI, appropriate interview questions are generated based on the retrieved data.

[0137] Step 3:

[0138] The terminal receives questions from the server and presents them to the user verbally. Speech synthesis technology is used to deliver the questions to the user in a natural-sounding manner.

[0139] Step 4:

[0140] Users will answer the presented questions verbally. Users should strive to organize their experiences and thoughts and answer clearly.

[0141] Step 5:

[0142] The device receives the user's voice response and converts it into text data using speech recognition. Additionally, an emotion engine is run to sense the user's tone and pace, extracting emotional characteristics.

[0143] Step 6:

[0144] The server analyzes the received text data using natural language processing techniques. This analysis includes identifying keywords in the text data, evaluating the logical consistency of the responses, and analyzing their expressiveness. Furthermore, emotional characteristics generated by an emotion engine are incorporated into the analysis.

[0145] Step 7:

[0146] The server generates feedback based on the analysis results. Particular attention is paid to the user's emotional state, and the feedback includes not only suggestions for improving answers, but also advice on mental preparation for the interview.

[0147] Step 8:

[0148] The device notifies the user of the generated feedback and sentiment analysis results. The notifications are provided in both audio and text formats, allowing the user to gain specific insights for improvement from the feedback.

[0149] Step 9:

[0150] Users review and improve their answers based on feedback. If necessary, they practice interviews again using the same process, gradually improving their interview skills.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0153] In modern interview practice, not only high-quality responses to questions but also the interviewee's emotional state are crucial. However, while conventional interview practice systems can evaluate audio content, they have struggled to provide feedback that takes the user's emotional state into account. Therefore, there is a need to provide individually optimized feedback to support improved performance in actual interviews.

[0154] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0155] In this invention, the server includes an information processing device that generates relevant interview questions based on the request of the interviewer, an emotion recognition device that extracts emotional characteristics from voice data, and a feedback device that generates feedback corresponding to the emotional state. This makes it possible to provide individualized feedback that takes into account the emotional state of the interviewer.

[0156] An "interview trainee" refers to a person who uses a system to practice and improve their interview skills.

[0157] A "request" refers to an action or input that indicates to the system the interviewer's intention to begin interview practice.

[0158] An "information processing device" refers to a device that processes information to generate relevant interview questions based on the requests of the interviewee.

[0159] A "voice recognition device" refers to a device that receives voice input from interviewees and converts it into text data.

[0160] An "evaluation device" refers to a device that analyzes text data and provides interviewers with an evaluation of its content and suggestions for improvement.

[0161] A "notification device" refers to a device that has the function of notifying interviewers of their evaluation results and areas for improvement.

[0162] An "emotion recognition device" refers to a device that has the function of extracting emotional characteristics from audio data and identifying the emotional state of the interviewer.

[0163] A "feedback device" refers to a device that has the function of generating and providing feedback according to the emotional state of the interviewee.

[0164] This invention relates to an embodiment of an interview practice system that takes into account the emotional state of the interviewee. The system begins with a server generating relevant questions based on user requests, utilizing a generative AI model. Specifically, a general-purpose text generation algorithm is used as the generative AI model.

[0165] The terminal uses a speech synthesis engine to present questions sent from the server to the user verbally. For speech synthesis, general-purpose speech processing software is used, for example. The user is expected to respond to these verbal questions via microphone input.

[0166] The user's voice response is converted into text data by a speech recognition device on the terminal. This conversion can utilize common speech recognition technologies; for example, voice-to-text APIs provided on many platforms are available.

[0167] The converted text and audio data are processed on a server, and the user's emotional characteristics are extracted by an emotion recognition device. This analysis utilizes emotion analysis software to infer emotional states from voice tone and word choices.

[0168] The evaluation device on the server analyzes text data using natural language processing techniques. Then, referencing the emotional characteristics obtained from the emotion recognition device, the feedback device generates user-specific feedback. This feedback includes specific advice for the user to take steps to improve their performance.

[0169] The device ultimately notifies the user of the generated feedback and analysis results. These notifications can be in voice or text format, allowing the user to improve their responses.

[0170] For example, when a user aiming for a sales position answers the question "Please introduce yourself," if the emotion recognition device detects the user's tension, the server generates feedback such as "Relax and emphasize your strengths."

[0171] An example of a prompt message would be, "I want to start practicing for a sales interview. I want to practice my self-introduction. Please use the generative AI model to create questions and provide an overall evaluation with emotional feedback." This allows users to experience the system's entire feedback cycle.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] A user requests a practice interview. The user launches a dedicated application on their device and enters information about the industry and job type they wish to practice for. The entered information is sent to the server as a request. This request serves as the basis for the server to generate interview questions.

[0175] Step 2:

[0176] The server generates relevant interview questions. The server receives user requests and generates appropriate questions using a generation AI model. Based on the entered industry and job information, it dynamically outputs customized questions by utilizing existing question templates and generation algorithms.

[0177] Step 3:

[0178] The terminal presents the generated question to the user in audio. The terminal receives the question in text format from the server and converts it into audio format using a speech synthesis engine. This converted audio is then output to the user through the speaker.

[0179] Step 4:

[0180] The user responds by voice. After listening to the question presented on the device, the user speaks their answer into the microphone. This voice is processed immediately by the device.

[0181] Step 5:

[0182] The terminal converts voice input into text. The terminal uses speech recognition software to convert the user's voice input into text data. This process converts voice data as input into text data as output.

[0183] Step 6:

[0184] The server analyzes the voice data and performs emotion recognition. The server receives voice and text data transmitted from the terminal and extracts emotional features using an emotion recognition device. In this process, the user's emotional state is identified based on factors such as voice tone, speaking speed, and word emphasis.

[0185] Step 7:

[0186] The server analyzes text data and generates feedback. The server's evaluation device uses natural language processing technology to analyze the text data and generate feedback tailored to the user's emotional state. The analysis results and emotion recognition data are integrated to output areas for improvement and specific advice for the user.

[0187] Step 8:

[0188] The device notifies the user of the feedback. The device receives feedback generated from the server and notifies the user in voice or text format. The user can use this feedback to improve their interview skills.

[0189] (Application Example 2)

[0190] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] In interview preparation, traditional methods make it difficult to obtain feedback that takes into account the interviewee's emotional state, and emotions such as nervousness and anxiety can particularly affect performance during the actual interview. Furthermore, when practicing at home, it is not easy to obtain objective feedback or advice that takes emotions into account, thus limiting the capabilities of conventional methods. This aims to address these issues.

[0192] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0193] In this invention, the server includes an information processing device that generates relevant interview questions based on the interviewer's requests, a speech recognition device that receives voice input from the interviewer and converts it into text data, and an emotion recognition device that allows the information processing device to analyze the interviewer's emotional state and generate feedback accordingly. This enables more effective interview preparation, even when the interviewer practices at home, by receiving feedback that takes their emotional state into account.

[0194] An "information processing device" is a device that generates relevant interview questions based on the requests of the interviewee, and further analyzes their emotional state to generate feedback.

[0195] A "voice recognition device" is a device that receives voice input from interviewees and converts it into text data.

[0196] An "evaluation device" is a device that analyzes text data and provides evaluations and suggestions for improvement regarding its content.

[0197] An "emotion recognition device" is a device that extracts emotional characteristics from the voice data of interviewees and generates feedback based on the results.

[0198] A "notification device" is a device used to notify interviewers of evaluation results, areas for improvement, and feedback based on their emotional state.

[0199] The system for implementing this invention has the following configuration: When an interview trainee inputs a request, the server generates relevant interview questions using a generative AI model. These questions are customized according to the interview trainee's desired industry and job type. The questions are sent to the user's terminal and presented to the interview trainee as audio.

[0200] The user answers the presented questions verbally. The terminal converts this voice input into text data using speech recognition technology. The converted data is sent to a server, where an evaluation device analyzes the answers using natural language processing technology. Software such as Google® Cloud Natural Language API is used for the analysis. The server also uses an emotion recognition device to extract emotional characteristics from the interviewer's voice data. Microsoft® Azure® Emotion API is used for this purpose.

[0201] Based on the evaluation results, the server generates feedback tailored to the evaluation results and emotional characteristics. This feedback includes content that helps the interviewer continue practicing with confidence and is received via the device in audio or text format. The user can use this feedback to improve their answers.

[0202] For example, if a speech recognition system generates a question such as "Please answer the following question," and analyzes the interviewer's response, an emotion recognition device might generate feedback such as "Try taking a deep breath to relax" if it detects the interviewer's tension. Furthermore, the generative AI model optimizes the feedback content using a prompt such as, "If the system recognizes that the user is nervous, how should it provide support to help them relax?"

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server receives a request for interview practice from the user's terminal. This request includes information about the desired industry and job type. The server uses a generative AI model to generate relevant interview questions based on this information. The generated questions are then sent to the user's terminal.

[0206] Step 2:

[0207] The user receives interview questions displayed on the device via voice. The user answers the questions aloud, and the device captures the audio data. Using speech recognition software, this audio data is converted into text data. The converted text data is sent to the server.

[0208] Step 3:

[0209] The server inputs the received text data into the evaluation device, which then analyzes the data using natural language processing technologies such as the Google Cloud Natural Language API. This analysis evaluates the content of the responses and extracts areas for improvement. The evaluation results are stored on the server.

[0210] Step 4:

[0211] Simultaneously, the server transmits the audio data to an emotion recognition device. The emotion recognition device extracts the user's emotional characteristics using tools such as the Microsoft Azure Emotion API. This process determines emotional states such as tension and confidence levels.

[0212] Step 5:

[0213] The server uses the evaluation results and emotional characteristics to input prompt statements into an AI model that generates feedback. An example of a prompt statement is, "If you recognize that the user is feeling anxious, how would you provide support to help them relax?" The feedback includes suggestions for improving the answer and advice tailored to the emotional state.

[0214] Step 6:

[0215] The server sends the generated feedback to the user's device. The device notifies the user of the received feedback via voice or text. The user can then use this feedback to improve their answers and continue practicing their interview skills in a better state.

[0216] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0217] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0218] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0222] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0223] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0224] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0225] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0226] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0227] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0228] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0229] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0230] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0231] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0232] The present invention provides a system for interview trainees to effectively prepare for interviews. This system generates relevant interview questions in response to the trainee's requests, presents them audibly, accepts user responses, and provides appropriate feedback. Specific embodiments of the present invention are described below.

[0233] First, the user enters their interview practice request on a terminal. The user specifies their desired industry and job type and prepares practice questions based on the topic. Based on this, the server uses a generation AI to generate appropriate interview questions. These questions are customized in terms of difficulty and content to meet the user's requirements.

[0234] Next, the device presents a question to the user verbally. The user can then answer verbally. The device converts the user's response into text using speech recognition technology. The converted text is then sent to the server.

[0235] The server analyzes the received text data using natural language processing technology and evaluates the user's response. Based on the analysis results, the evaluation device determines the quality of the response and generates areas for improvement and examples of good responses. This feedback is detailed and specific, enabling users to prepare better responses.

[0236] Finally, the device notifies the user of feedback via voice or text, allowing them to reflect on their answers and gain guidance for further improvement. This system supports continuous practice so that users can perform at their best in interviews.

[0237] For example, if a user requests a "sales interview," the server generates questions related to sales. For instance, it might generate a question like, "Please tell us about the sales targets you have achieved in the past." When the user answers, the answer is evaluated, and feedback is provided, such as, "It would be even better if you included specific numerical data." Through this process, users can prepare persuasive answers that include concrete examples.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The user enters a request to start a mock interview via their device. The user specifies the industry and job type they want to practice for and selects their preferred interview format.

[0241] Step 2:

[0242] The server receives the user's request and retrieves appropriate question data by referring to a database corresponding to the specified industry and job type. Based on the retrieved data, it uses AI to generate interview questions.

[0243] Step 3:

[0244] The terminal receives questions from the server and presents them to the user verbally. Speech synthesis technology is used to ensure the user understands the questions naturally.

[0245] Step 4:

[0246] The user responds to the presented questions verbally. The user attempts to structure and express their thoughts.

[0247] Step 5:

[0248] The device receives the user's voice response and converts it into text data using its speech recognition function. This text data is then sent to the server.

[0249] Step 6:

[0250] The server analyzes the text data it receives. Natural language processing techniques are applied to evaluate the keywords, logical structure, and expressiveness of the responses. Furthermore, areas for improvement and inconsistencies that need to be pointed out in the responses are identified.

[0251] Step 7:

[0252] The server generates feedback based on the analysis results. This feedback includes what was good about the response, areas for improvement, and specific examples of improvements.

[0253] Step 8:

[0254] The device receives feedback and notifies the user. The user reviews the feedback, pays attention to areas for improvement, and continues practicing.

[0255] Step 9:

[0256] Users can receive feedback, improve their answers, and try the same question again or a new one. By repeating this process, users gradually improve their interview skills.

[0257] (Example 1)

[0258] Next, we will describe Example 1. 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."

[0259] Currently, systems for effective interview practice do not adequately meet the specific needs of users. In particular, there is a lack of systems that can appropriately customize interview content and questions according to specific industries and job types, and provide accurate feedback on user responses. Furthermore, there is a growing need for systems that can effectively analyze voice input and evaluate user responses using natural language processing.

[0260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0261] In this invention, the server includes a computing device means that generates relevant inquiries based on requests from the user, a speech recognition device means that receives voice input from the user and converts it into text data, and an evaluation device means that analyzes the text data and provides content evaluation and improvement points. This makes it possible for users to receive appropriate interview questions tailored to their industry and job type, and to obtain specific and effective feedback on their answers.

[0262] "User" refers to an individual or organization that uses computing devices and related systems to conduct interview practice.

[0263] "Requests" refer to the specific wishes and conditions regarding interview practice that the user communicates to the computing device.

[0264] "Inquiry" refers to interview-related questions generated by the computer based on the user's request.

[0265] A "computer" refers to a central processing unit that receives user requests, generates queries, and interacts with other system components.

[0266] "Voice input" refers to information provided by the user through voice.

[0267] "Character data" refers to information in text format converted from voice input by a speech recognition device.

[0268] A "speech recognition device" refers to a machine or software that receives speech input and converts it into text data.

[0269] An "evaluation device" refers to a device or software that has the function of analyzing text data provided by a speech recognition device, evaluating its content, and generating areas for improvement.

[0270] "Notification device" refers to a machine or function that communicates evaluation results and areas for improvement to the user in voice or text format.

[0271] "Natural language processing technology" refers to artificial intelligence technology that analyzes the meaning contained in text data and understands the syntactic structure, content, and context of a sentence.

[0272] "Domain" refers to the specific industry or field that the user focuses on during interview practice.

[0273] "Work" refers to a series of activities or tasks related to a specific job or function.

[0274] This invention provides a system to support effective preparation for users who wish to practice for interviews. The system includes the ability to generate highly customized interview questions and to analyze and evaluate the user's voice input.

[0275] The user uses a terminal to input a request for interview practice. The user specifies the desired area or job and provides prompts to the system. For example, if the user enters the prompt "Generate sales job questions," questions related to that specific job will be generated.

[0276] Upon receiving a user request, the server uses its computing power and a generative AI model to generate relevant questions. This generation process utilizes various databases and pre-trained natural language processing models. The generated interview questions are those that best fit the conditions specified by the user.

[0277] Next, the device uses speech synthesis technology to present questions to the user verbally. A typical speech synthesis technology that utilizes this technology is a commonly used voice output function.

[0278] The user answers the presented questions verbally. The terminal converts these answers into text data using speech recognition software and sends the results to the server. Various commercially available speech recognition APIs are used for the speech recognition technology.

[0279] The server analyzes the received text data using natural language processing technology and evaluates the response. Based on the analysis results, detailed and specific feedback is generated that the user needs to improve.

[0280] Finally, the device notifies the user of the evaluation results and feedback. This feedback is displayed in either audio or text format. This allows the user to reflect on their answers and gain guidance for more effective presentations in interviews.

[0281] This system provides practical support for interview preparation and helps users approach interviews with confidence.

[0282] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0283] Step 1:

[0284] The user uses the terminal to input a request for interview practice. This request includes the desired business or area. The input request is sent to the server in the form of a prompt sentence. The input data includes the business or area specified by the user, and based on this, interview questions are generated.

[0285] Step 2:

[0286] Based on the received prompt sentence, the server uses the generation AI model to generate relevant interview questions. The server analyzes the input request and calls the AI model to generate customized questions accordingly. The output is a set of questions appropriately adjusted based on the user's request. In this process, past question examples stored in the database and the generation ability of the AI model are utilized.

[0287] Step 3:

[0288] The interview questions generated by the server are sent to the terminal. The terminal uses voice synthesis technology to present the questions to the user in voice. Specifically, the question text is converted into voice output by the voice synthesis API and made to flow through the speaker.

[0289] Step 4:

[0290] For the presented questions, the user answers in voice through the microphone. This answer is recorded by the terminal. The recorded voice is input into the terminal and prepared as data to be processed in the next stage.

[0291] Step 5:

[0292] The device converts the user's voice responses into text data using speech recognition technology. It analyzes audio files as input and outputs text data. This process is performed in real time, and the generated text is sent to the server.

[0293] Step 6:

[0294] The server analyzes the received text data using natural language processing technology and evaluates the user's response. Based on the input text, it evaluates the sentence structure, appropriateness of content, and logical structure, and generates feedback data as a result. Predefined evaluation criteria are applied to the evaluation.

[0295] Step 7:

[0296] The server sends the evaluation results and generated improvement feedback to the terminal. The terminal notifies the user of this feedback. This feedback can be delivered via speech synthesis or displayed as text on the screen. The user can then use this feedback to improve their interview responses.

[0297] (Application Example 1)

[0298] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0299] Conventional interview practice systems have limitations in providing feedback to user voice input, making it difficult to provide customized practice tailored to specific industries or job types. Furthermore, to efficiently support user skill improvement, it is important to utilize autonomous devices that allow for readily accessible interview practice.

[0300] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0301] In this invention, the server includes information processing circuit means for generating relevant dialogue-form questions based on the requests of the interview trainee, speech recognition circuit means for a self-governing device having a speech input / output function to receive the speech input from the interview trainee and convert it into a text signal, and evaluation circuit means for analyzing the text signal and providing a method for evaluating and improving the content. As a result, through dialogue-form practice using the self-governing device, the interview trainee can efficiently improve skills suitable for specific jobs and industries.

[0302] The "interview trainee" refers to an individual who practices for an interview test, aiming to improve the ability to respond to questions related to a specific industry or job.

[0303] The "self-governing device" refers to a mechanical device equipped with a speech input / output function that supports interview practice by interacting with the user and is used within a home or facility.

[0304] The "information processing circuit" refers to a circuit that performs arithmetic processing for generating relevant dialogue-form questions based on the requests of the interview trainee.

[0305] The "speech recognition circuit" refers to a circuit for converting the speech input of the interview trainee received by the self-governing device into a text signal.

[0306] The "evaluation circuit" refers to a circuit that analyzes the text signal converted by the speech recognition circuit and provides a method for evaluating and improving the content.

[0307] The "text signal" refers to the character information generated as a result of the speech recognition circuit converting the speech input of the interview trainee.

[0308] This invention provides a system for assisting in improving the skills of interview trainees using a self-governing device. This system includes an information processing circuit, a speech recognition circuit, and an evaluation circuit, and each circuit operates in cooperation with each other.

[0309] The server generates relevant conversational questions in its information processing circuit in response to the interviewer's requests. By using a generative AI model, it is possible to efficiently create questions specific to the interviewer's job and industry. For example, when generating questions related to a sales position, the AI ​​model is instructed with the prompt, "Please create five questions for a sales interview."

[0310] When a user answers a question by voice, the device's voice input / output function converts the voice into text signals via a speech recognition circuit. These converted text signals are sent to a server, where an evaluation circuit analyzes the content and suggests ways to improve it. Natural language processing technology (e.g., spaCy) is used for this analysis.

[0311] The evaluation results and areas for improvement are communicated to the interviewer via their device. This feedback provides guidance for interviewers to easily prepare for interviews at home or elsewhere, supporting skill improvement. For example, if a user includes numerical data in their answer, they will receive feedback such as, "Specific numerical data makes your answer more persuasive."

[0312] By using this system, interview candidates can effectively improve their skills tailored to specific jobs and industries through interactive practice using autonomous devices.

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The user enters a request for interview practice into the terminal. By specifically specifying the desired job and industry, the request data sent to the server is formed. This request data serves as the basis for generating prompt messages.

[0316] Step 2:

[0317] The server receives the request data and uses its information processing circuitry to generate prompt statements for the AI ​​model. Based on these prompt statements, the AI ​​model creates relevant, conversational questions about a specific job or industry. The generated questions become output data ready to be converted into speech format.

[0318] Step 3:

[0319] The generated question is transmitted to the terminal, which uses speech synthesis technology to present the question to the user verbally. The user answers the presented question verbally. This process generates voice input data. The voice input data is then awaiting processing by the speech recognition circuit.

[0320] Step 4:

[0321] The terminal receives the user's voice input and converts it into a text signal using a speech recognition circuit. This voice-to-text conversion organizes the text data into the format necessary for analysis, and the resulting text data is sent to the server.

[0322] Step 5:

[0323] The server sends the received text data to an evaluation circuit, where it is analyzed using natural language processing technology. This analysis evaluates the user's response and generates information regarding the evaluation and areas for improvement. This result becomes feedback data.

[0324] Step 6:

[0325] The device receives feedback data and notifies the user via voice or text using a notification device. By receiving this feedback, the user can gain specific guidance for improving the quality of their responses. The ultimate output is reflection and skill improvement through feedback.

[0326] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0327] This invention provides a system that incorporates emotion recognition functionality into an interview practice system, enabling it to provide personalized feedback while considering the user's emotional state. This system generates relevant questions based on the interview practice request, processes the user's voice input, and recognizes emotional characteristics using an emotion engine.

[0328] Specifically, users input a request to begin interview practice via their device, specifying their desired industry and job type, which generates questions on the server. These questions are dynamically generated by a generation AI and adjusted to meet the user's needs.

[0329] The device presents the user with generated questions via voice. The user is expected to respond to these questions verbally while considering the question. The user's voice input is converted into text data by the device and then sent to the server. Here, the voice data is analyzed by an emotion engine to extract the user's emotional characteristics.

[0330] On the server, the evaluation device performs analysis using natural language processing technology based on text data. Furthermore, emotional characteristics obtained by the emotion engine are referenced in this analysis process. As a result, the evaluation device generates feedback that corresponds to the user's emotional state. The feedback includes content that takes the user's emotional state into consideration, so that the user can practice with confidence.

[0331] The device ultimately notifies the user of feedback and analyzed sentiment data. This notification can be in audio or text format, and the user can use it to improve their responses. For example, if the sentiment engine detects that the user is nervous, the notification may include advice on how to relax. This allows the user to improve their responses in a better state of mind and enhance their performance during the actual interview.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The user enters a request to start a practice interview into the terminal. Here, the user specifies the industry and job type they want to practice for and selects the desired interview format.

[0335] Step 2:

[0336] The server receives a request from the user and retrieves relevant question data by referencing a database corresponding to the specified industry and job type. Using generation AI, appropriate interview questions are generated based on the retrieved data.

[0337] Step 3:

[0338] The terminal receives questions from the server and presents them to the user verbally. Speech synthesis technology is used to convey the questions to the user in a natural-sounding manner.

[0339] Step 4:

[0340] Users will answer the presented questions verbally. Users should strive to organize their experiences and thoughts and answer clearly.

[0341] Step 5:

[0342] The device receives the user's voice response and converts it into text data using speech recognition. Additionally, an emotion engine is run to sense the user's tone and pace, extracting emotional characteristics.

[0343] Step 6:

[0344] The server analyzes the received text data using natural language processing techniques. This analysis includes identifying keywords in the text data, evaluating the logical consistency of the responses, and analyzing their expressiveness. Furthermore, emotional characteristics generated by an emotion engine are incorporated into the analysis.

[0345] Step 7:

[0346] The server generates feedback based on the analysis results. Particular attention is paid to the user's emotional state, and the feedback includes not only suggestions for improving answers, but also advice on mental preparation for the interview.

[0347] Step 8:

[0348] The device notifies the user of the generated feedback and sentiment analysis results. The notifications are provided in both audio and text formats, allowing the user to gain specific insights for improvement from the feedback.

[0349] Step 9:

[0350] Users review and improve their answers based on feedback. If necessary, they practice interviews again using the same process, gradually improving their interview skills.

[0351] (Example 2)

[0352] Next, we will describe Example 2. 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".

[0353] In modern interview practice, not only high-quality responses to questions but also the interviewee's emotional state are crucial. However, while conventional interview practice systems can evaluate audio content, they have struggled to provide feedback that takes the user's emotional state into account. Therefore, there is a need to provide individually optimized feedback to support improved performance in actual interviews.

[0354] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0355] In this invention, the server includes an information processing device that generates relevant interview questions based on the request of the interviewer, an emotion recognition device that extracts emotional characteristics from voice data, and a feedback device that generates feedback corresponding to the emotional state. This makes it possible to provide individualized feedback that takes into account the emotional state of the interviewer.

[0356] An "interview trainee" refers to a person who uses a system to practice and improve their interview skills.

[0357] A "request" refers to an action or input that indicates to the system the interviewer's intention to begin interview practice.

[0358] An "information processing device" refers to a device that processes information to generate relevant interview questions based on the requests of the interviewee.

[0359] A "voice recognition device" refers to a device that receives voice input from interviewees and converts it into text data.

[0360] An "evaluation device" refers to a device that analyzes text data and provides interviewers with an evaluation of its content and suggestions for improvement.

[0361] A "notification device" refers to a device that has the function of notifying interviewers of their evaluation results and areas for improvement.

[0362] An "emotion recognition device" refers to a device that has the function of extracting emotional characteristics from audio data and identifying the emotional state of the interviewer.

[0363] A "feedback device" refers to a device that generates and provides feedback according to the emotional state of the interviewee.

[0364] This invention relates to an embodiment of an interview practice system that takes into account the emotional state of the interviewee. The system begins with a server generating relevant questions based on user requests, utilizing a generative AI model. Specifically, a general-purpose text generation algorithm is used as the generative AI model.

[0365] The terminal uses a speech synthesis engine to present questions sent from the server to the user verbally. For speech synthesis, general-purpose speech processing software is used, for example. The user is expected to respond to these verbal questions via microphone input.

[0366] The user's voice response is converted into text data by a speech recognition device on the terminal. This conversion can utilize common speech recognition technologies; for example, voice-to-text APIs provided on many platforms are available.

[0367] The converted text and audio data are processed on a server, and the user's emotional characteristics are extracted by an emotion recognition device. This analysis utilizes emotion analysis software to infer emotional states from voice tone and word choices.

[0368] The evaluation device on the server analyzes text data using natural language processing techniques. Then, referencing the emotional characteristics obtained from the emotion recognition device, the feedback device generates user-specific feedback. This feedback includes specific advice for the user to take steps to improve their performance.

[0369] The device ultimately notifies the user of the generated feedback and analysis results. These notifications can be in voice or text format, allowing the user to use them to improve their responses.

[0370] As a concrete example, when a user aiming for a sales position answers the question "Please introduce yourself," if the emotion recognition device detects the user's tension, the server generates feedback such as "Relax and emphasize your strengths."

[0371] An example of a prompt message would be, "I want to start practicing for a sales interview. I want to practice my self-introduction. Please use the generative AI model to create questions and provide an overall evaluation with emotional feedback." This allows users to experience the system's entire feedback cycle.

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] A user requests a practice interview. The user launches a dedicated application on their device and enters information about the industry and job type they wish to practice for. The entered information is sent to the server as a request. This request serves as the basic data for the server to generate interview questions.

[0375] Step 2:

[0376] The server generates relevant interview questions. The server receives user requests and generates appropriate questions using a generation AI model. Based on the entered industry and job information, it dynamically outputs customized questions by utilizing existing question templates and generation algorithms.

[0377] Step 3:

[0378] The terminal presents the generated question to the user in audio. The terminal receives the question in text format from the server and converts it into audio format using a speech synthesis engine. This converted audio is then output to the user through the speaker.

[0379] Step 4:

[0380] The user responds by voice. After listening to the question presented on the device, the user speaks their answer into the microphone. This voice is processed immediately by the device.

[0381] Step 5:

[0382] The terminal converts voice input into text. The terminal uses speech recognition software to convert the user's voice input into text data. This process converts voice data as input into text data as output.

[0383] Step 6:

[0384] The server analyzes the voice data and performs emotion recognition. The server receives voice and text data transmitted from the terminal and extracts emotional features using an emotion recognition device. In this process, the user's emotional state is identified based on factors such as voice tone, speaking speed, and word emphasis.

[0385] Step 7:

[0386] The server analyzes text data and generates feedback. The server's evaluation device uses natural language processing technology to analyze the text data and generate feedback tailored to the user's emotional state. The analysis results and emotion recognition data are integrated to output areas for improvement and specific advice for the user.

[0387] Step 8:

[0388] The device notifies the user of the feedback. The device receives feedback generated from the server and notifies the user in voice or text format. The user can use this feedback to improve their interview skills.

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0391] In interview preparation, traditional methods make it difficult to obtain feedback that takes into account the interviewee's emotional state, and emotions such as nervousness and anxiety can particularly affect performance during the actual interview. Furthermore, when practicing at home, it is not easy to obtain objective feedback or advice that takes emotions into account, thus limiting the capabilities of conventional methods. This aims to address these issues.

[0392] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0393] In this invention, the server includes an information processing device that generates relevant interview questions based on the interviewer's requests, a speech recognition device that receives voice input from the interviewer and converts it into text data, and an emotion recognition device that allows the information processing device to analyze the interviewer's emotional state and generate feedback accordingly. This enables more effective interview preparation, even when the interviewer practices at home, by receiving feedback that takes their emotional state into account.

[0394] An "information processing device" is a device that generates relevant interview questions based on the requests of the interviewee, and further analyzes their emotional state to generate feedback.

[0395] A "voice recognition device" is a device that receives voice input from interviewees and converts it into text data.

[0396] An "evaluation device" is a device that analyzes text data and provides evaluations and suggestions for improvement regarding its content.

[0397] An "emotion recognition device" is a device that extracts emotional characteristics from the voice data of interviewees and generates feedback based on the results.

[0398] A "notification device" is a device used to notify interviewers of evaluation results, areas for improvement, and feedback based on their emotional state.

[0399] The system for implementing this invention has the following configuration: When an interview trainee inputs a request, the server generates relevant interview questions using a generative AI model. These questions are customized according to the interview trainee's desired industry and job type. The questions are sent to the user's terminal and presented to the interview trainee as audio.

[0400] The user answers the presented questions verbally. The terminal converts this voice input into text data using speech recognition technology. The converted data is sent to a server, where an evaluation device analyzes the answers using natural language processing technology. Software such as the Google Cloud Natural Language API is used for the analysis. The server also uses an emotion recognition device to extract emotional characteristics from the interviewer's voice data. Microsoft Azure Emotion API is used for this purpose.

[0401] Based on the evaluation results, the server generates feedback tailored to the evaluation results and emotional characteristics. This feedback includes content that helps the interviewer continue practicing with confidence and is received via the device in audio or text format. The user can use this feedback to improve their answers.

[0402] For example, if a speech recognition system generates a question such as "Please answer the following question," and analyzes the interviewer's response, an emotion recognition device might generate feedback such as "Try taking a deep breath to relax" if it detects the interviewer's tension. Furthermore, the generative AI model optimizes the feedback content using a prompt such as, "If the system recognizes that the user is nervous, how should it provide support to help them relax?"

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] The server receives a request for interview practice from the user's terminal. This request includes information about the desired industry and job type. The server uses a generative AI model to generate relevant interview questions based on this information. The generated questions are then sent to the user's terminal.

[0406] Step 2:

[0407] The user receives interview questions displayed on the device via voice. The user answers the questions aloud, and the device captures the audio data. Using speech recognition software, this audio data is converted into text data. The converted text data is sent to the server.

[0408] Step 3:

[0409] The server inputs the received text data into the evaluation device, which then analyzes the data using natural language processing technologies such as the Google Cloud Natural Language API. This analysis evaluates the content of the responses and extracts areas for improvement. The evaluation results are stored on the server.

[0410] Step 4:

[0411] Simultaneously, the server transmits the audio data to an emotion recognition device. The emotion recognition device extracts the user's emotional characteristics using tools such as the Microsoft Azure Emotion API. This process determines emotional states such as tension and confidence levels.

[0412] Step 5:

[0413] The server uses the evaluation results and emotional characteristics to input prompt statements into an AI model that generates feedback. An example of a prompt statement is, "If you recognize that the user is feeling anxious, how would you provide support to help them relax?" The feedback includes suggestions for improving the answer and advice tailored to the emotional state.

[0414] Step 6:

[0415] The server sends the generated feedback to the user's device. The device notifies the user of the received feedback via voice or text. The user can then use this feedback to improve their answers and continue practicing their interview skills in a better state.

[0416] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0417] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0418] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0422] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0423] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0424] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0426] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0427] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0428] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0429] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0430] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0431] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0432] The present invention provides a system for interview trainees to effectively prepare for interviews. This system generates relevant interview questions in response to the trainee's requests, presents them audibly, accepts user responses, and provides appropriate feedback. Specific embodiments of the present invention are described below.

[0433] First, the user enters their interview practice request on a terminal. The user specifies their desired industry and job type and prepares practice questions based on the topic. Based on this, the server uses a generation AI to generate appropriate interview questions. These questions are customized in terms of difficulty and content to meet the user's requirements.

[0434] Next, the device presents a question to the user verbally. The user can then answer verbally. The device converts the user's response into text using speech recognition technology. The converted text is then sent to the server.

[0435] The server analyzes the received text data using natural language processing technology and evaluates the user's response. Based on the analysis results, the evaluation device determines the quality of the response and generates areas for improvement and examples of good responses. This feedback is detailed and specific, enabling users to prepare better responses.

[0436] Finally, the device notifies the user of feedback via voice or text, allowing them to reflect on their answers and gain guidance for further improvement. This system supports continuous practice so that users can perform at their best in interviews.

[0437] For example, if a user requests a "sales interview," the server generates questions related to sales. For instance, it might generate a question like, "Please tell us about the sales targets you have achieved in the past." When the user answers, the answer is evaluated, and feedback is provided, such as, "It would be even better if you included specific numerical data." Through this process, users can prepare persuasive answers that include concrete examples.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The user enters a request to start a mock interview via their device. The user specifies the industry and job type they want to practice for and selects their preferred interview format.

[0441] Step 2:

[0442] The server receives the user's request and retrieves appropriate question data by referring to a database corresponding to the specified industry and job type. Based on the retrieved data, it uses AI to generate interview questions.

[0443] Step 3:

[0444] The terminal receives questions from the server and presents them to the user verbally. Speech synthesis technology is used to ensure the user understands the questions naturally.

[0445] Step 4:

[0446] The user responds to the presented questions verbally. The user attempts to structure and express their thoughts.

[0447] Step 5:

[0448] The device receives the user's voice response and converts it into text data using its speech recognition function. This text data is then sent to the server.

[0449] Step 6:

[0450] The server analyzes the text data it receives. Natural language processing techniques are applied to evaluate the keywords, logical structure, and expressiveness of the responses. Furthermore, areas for improvement and inconsistencies that need to be pointed out in the responses are identified.

[0451] Step 7:

[0452] The server generates feedback based on the analysis results. This feedback includes what was good about the response, areas for improvement, and specific examples of improvements.

[0453] Step 8:

[0454] The device receives feedback and notifies the user. The user reviews the feedback, pays attention to areas for improvement, and continues practicing.

[0455] Step 9:

[0456] Users can receive feedback, improve their answers, and try the same question again or a new one. By repeating this process, users gradually improve their interview skills.

[0457] (Example 1)

[0458] Next, we will describe Example 1. 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."

[0459] Currently, systems for effective interview practice do not adequately meet the specific needs of users. In particular, there is a lack of systems that can appropriately customize interview content and questions according to specific industries and job types, and provide accurate feedback on user responses. Furthermore, there is a growing need for systems that can effectively analyze voice input and evaluate user responses using natural language processing.

[0460] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0461] In this invention, the server includes a computing device means that generates relevant inquiries based on requests from the user, a speech recognition device means that receives voice input from the user and converts it into text data, and an evaluation device means that analyzes the text data and provides content evaluation and improvement points. This makes it possible for users to receive appropriate interview questions tailored to their industry and job type, and to obtain specific and effective feedback on their answers.

[0462] "User" refers to an individual or organization that uses computing devices and related systems to conduct interview practice.

[0463] "Requests" refer to the specific wishes and conditions regarding interview practice that the user communicates to the computing device.

[0464] "Inquiry" refers to interview-related questions generated by the computer based on the user's request.

[0465] A "computer" refers to a central processing unit that receives user requests, generates queries, and interacts with other system components.

[0466] "Voice input" refers to information provided by the user through voice.

[0467] "Character data" refers to information in text format converted from voice input by a speech recognition device.

[0468] A "speech recognition device" refers to a machine or software that receives speech input and converts it into text data.

[0469] An "evaluation device" refers to a device or software that has the function of analyzing text data provided by a speech recognition device, evaluating its content, and generating areas for improvement.

[0470] "Notification device" refers to a machine or function that communicates evaluation results and areas for improvement to the user in voice or text format.

[0471] "Natural language processing technology" refers to artificial intelligence technology that analyzes the meaning contained in text data and understands the syntactic structure, content, and context of a sentence.

[0472] "Domain" refers to the specific industry or field that the user focuses on during interview practice.

[0473] "Work" refers to a series of activities or tasks related to a specific job or function.

[0474] This invention provides a system to support effective preparation for users who wish to practice for interviews. The system includes the ability to generate highly customized interview questions and to analyze and evaluate the user's voice input.

[0475] The user uses a terminal to input a request for interview practice. The user specifies the desired area or job and provides prompts to the system. For example, if the user enters the prompt "Generate sales job questions," questions related to that specific job will be generated.

[0476] Upon receiving a user request, the server uses its computing power and a generative AI model to generate relevant questions. This generation process utilizes various databases and pre-trained natural language processing models. The generated interview questions are those that best fit the conditions specified by the user.

[0477] Next, the device uses speech synthesis technology to present questions to the user verbally. A typical speech synthesis technology that utilizes this technology is a commonly used voice output function.

[0478] The user answers the presented questions verbally. The terminal converts these answers into text data using speech recognition software and sends the results to the server. Various commercially available speech recognition APIs are used for the speech recognition technology.

[0479] The server analyzes the received text data using natural language processing technology and evaluates the response. Based on the analysis results, detailed and specific feedback is generated that the user needs to improve.

[0480] Finally, the device notifies the user of the evaluation results and feedback. This feedback is displayed in either audio or text format. This allows the user to reflect on their answers and gain guidance for more effective presentations in interviews.

[0481] This system provides practical support for interview preparation and helps users approach interviews with confidence.

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] The user enters a request for interview practice using a terminal. This request includes the desired job or area of ​​work. The entered request is sent to the server in the form of a prompt message. The input data consists of the job or area of ​​work specified by the user, and interview questions are generated based on this.

[0485] Step 2:

[0486] The server generates relevant interview questions using a generative AI model based on the received prompt. The server parses the input request and invokes the AI ​​model to generate customized questions accordingly. The output is a set of questions appropriately tailored based on the user's request. This process leverages past question examples stored in the database and the generative capabilities of the AI ​​model.

[0487] Step 3:

[0488] The interview questions generated by the server are sent to the terminal. The terminal uses speech synthesis technology to present the questions to the user verbally. Specifically, the question text is converted into speech output using a speech synthesis API and played through the speaker.

[0489] Step 4:

[0490] The user answers the presented questions verbally via the microphone. These answers are recorded on the device. The recorded audio is input to the device and prepared as data for processing in the next stage.

[0491] Step 5:

[0492] The device converts the user's voice responses into text data using speech recognition technology. It analyzes audio files as input and outputs text data. This process is performed in real time, and the generated text is sent to the server.

[0493] Step 6:

[0494] The server analyzes the received text data using natural language processing technology and evaluates the user's response. Based on the input text, it evaluates the sentence structure, appropriateness of content, and logical structure, and generates feedback data as a result. Predefined evaluation criteria are applied to the evaluation.

[0495] Step 7:

[0496] The server sends the evaluation results and generated improvement feedback to the terminal. The terminal notifies the user of this feedback. This feedback can be delivered via speech synthesis or displayed as text on the screen. The user can then use this feedback to improve their interview responses.

[0497] (Application Example 1)

[0498] Next, we will explain Application Example 1. In the following explanation, 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."

[0499] Conventional interview practice systems have limitations in providing feedback to user voice input, making it difficult to provide customized practice tailored to specific industries or job types. Furthermore, to efficiently support user skill improvement, it is important to utilize autonomous devices that allow for readily accessible interview practice.

[0500] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0501] In this invention, the server includes an information processing circuit means that generates relevant dialogue-style questions based on the requests of the interview trainee, a speech recognition circuit means that receives voice input from the interview trainee and converts it into a text signal, and an evaluation circuit means that analyzes the text signal and provides methods for evaluating and improving its content. This makes it possible for interview trainees to efficiently improve skills relevant to specific jobs and industries through dialogue-style practice using the autonomous device.

[0502] An "interview trainee" refers to an individual who practices for an interview, with the aim of improving their ability to answer questions related to a specific industry or job.

[0503] An "autonomous device" refers to a mechanical device equipped with voice input / output capabilities that supports interview practice by interacting with the user, and is used in homes and facilities.

[0504] An "information processing circuit" refers to a circuit that performs calculations to generate relevant dialogue-style questions based on the requests of the interviewee.

[0505] A "voice recognition circuit" refers to a circuit that converts the voice input received by an autonomous device from an interviewer into text signals.

[0506] An "evaluation circuit" refers to a circuit that analyzes the text signal converted by the speech recognition circuit and provides evaluation and improvement methods for its content.

[0507] "Text signal" refers to the character information generated as a result of the speech recognition circuit converting the voice input of the interviewee.

[0508] This invention provides a system for supporting the skill improvement of interviewers using autonomous devices. This system includes an information processing circuit, a speech recognition circuit, and an evaluation circuit, each of which works in cooperation with the others.

[0509] The server generates relevant conversational questions in its information processing circuit in response to the interviewer's requests. By using a generative AI model, it is possible to efficiently create questions specific to the interviewer's job and industry. For example, when generating questions related to a sales position, the AI ​​model is instructed with the prompt, "Please create five questions for a sales interview."

[0510] When a user answers a question by voice, the device's voice input / output function converts the voice into text signals via a speech recognition circuit. These converted text signals are sent to a server, where an evaluation circuit analyzes the content and suggests ways to improve it. Natural language processing technology (e.g., spaCy) is used for this analysis.

[0511] The evaluation results and areas for improvement are communicated to the interviewer via their device. This feedback provides guidance for interviewers to easily prepare for interviews at home or elsewhere, supporting skill improvement. For example, if a user includes numerical data in their answer, they will receive feedback such as, "Specific numerical data makes your answer more persuasive."

[0512] By using this system, interview candidates can effectively improve their skills tailored to specific jobs and industries through interactive practice using autonomous devices.

[0513] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0514] Step 1:

[0515] The user enters a request for interview practice into the terminal. By specifically specifying the desired job and industry, the request data sent to the server is formed. This request data serves as the basis for generating prompt messages.

[0516] Step 2:

[0517] The server receives the request data and uses its information processing circuitry to generate prompt statements for the AI ​​model. Based on these prompt statements, the AI ​​model creates relevant, conversational questions about a specific job or industry. The generated questions become output data ready to be converted into speech format.

[0518] Step 3:

[0519] The generated question is transmitted to the terminal, which uses speech synthesis technology to present the question to the user verbally. The user answers the presented question verbally. This process generates voice input data. The voice input data is then awaiting processing by the speech recognition circuit.

[0520] Step 4:

[0521] The terminal receives the user's voice input and converts it into a text signal using a speech recognition circuit. This voice-to-text conversion organizes the text data into the format necessary for analysis, and the resulting text data is sent to the server.

[0522] Step 5:

[0523] The server sends the received text data to an evaluation circuit, where it is analyzed using natural language processing technology. This analysis evaluates the user's response and generates information regarding the evaluation and areas for improvement. This result becomes feedback data.

[0524] Step 6:

[0525] The device receives feedback data and notifies the user via voice or text using a notification device. By receiving this feedback, the user can gain specific guidance for improving the quality of their responses. The ultimate output is reflection and skill improvement through feedback.

[0526] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0527] This invention provides a system that incorporates emotion recognition functionality into an interview practice system, enabling it to provide personalized feedback while considering the user's emotional state. This system generates relevant questions based on the interview practice request, processes the user's voice input, and recognizes emotional characteristics using an emotion engine.

[0528] Specifically, users input a request to begin interview practice via their device, specifying their desired industry and job type, which generates questions on the server. These questions are dynamically generated by a generation AI and adjusted to meet the user's needs.

[0529] The device presents the user with generated questions via voice. The user is expected to respond to these questions verbally while considering the question. The user's voice input is converted into text data by the device and then sent to the server. Here, the voice data is analyzed by an emotion engine to extract the user's emotional characteristics.

[0530] On the server, the evaluation device performs analysis using natural language processing technology based on text data. Furthermore, emotional characteristics obtained by the emotion engine are referenced in this analysis process. As a result, the evaluation device generates feedback that corresponds to the user's emotional state. The feedback includes content that takes the user's emotional state into consideration, so that the user can practice with confidence.

[0531] The device ultimately notifies the user of feedback and analyzed sentiment data. This notification can be in audio or text format, and the user can use it to improve their responses. For example, if the sentiment engine detects that the user is nervous, the notification may include advice on how to relax. This allows the user to improve their responses in a better state of mind and enhance their performance during the actual interview.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The user enters a request to start a practice interview into the terminal. Here, the user specifies the industry and job type they want to practice for and selects the desired interview format.

[0535] Step 2:

[0536] The server receives a request from the user and retrieves relevant question data by referencing a database corresponding to the specified industry and job type. Using generation AI, appropriate interview questions are generated based on the retrieved data.

[0537] Step 3:

[0538] The terminal receives questions from the server and presents them to the user verbally. Speech synthesis technology is used to convey the questions to the user in a natural-sounding manner.

[0539] Step 4:

[0540] Users will answer the presented questions verbally. Users should strive to organize their experiences and thoughts and answer clearly.

[0541] Step 5:

[0542] The device receives the user's voice response and converts it into text data using speech recognition. Additionally, an emotion engine is run to sense the user's tone and pace, extracting emotional characteristics.

[0543] Step 6:

[0544] The server analyzes the received text data using natural language processing techniques. This analysis includes identifying keywords in the text data, evaluating the logical consistency of the responses, and analyzing their expressiveness. Furthermore, emotional characteristics generated by an emotion engine are incorporated into the analysis.

[0545] Step 7:

[0546] The server generates feedback based on the analysis results. Particular attention is paid to the user's emotional state, and the feedback includes not only suggestions for improving answers, but also advice on mental preparation for the interview.

[0547] Step 8:

[0548] The device notifies the user of the generated feedback and sentiment analysis results. The notifications are provided in both audio and text formats, allowing the user to gain specific insights for improvement from the feedback.

[0549] Step 9:

[0550] Users review and improve their answers based on feedback. If necessary, they practice interviews again using the same process, gradually improving their interview skills.

[0551] (Example 2)

[0552] Next, we will describe Example 2. 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."

[0553] In modern interview practice, not only high-quality responses to questions but also the interviewee's emotional state are crucial. However, while conventional interview practice systems can evaluate audio content, they have struggled to provide feedback that takes the user's emotional state into account. Therefore, there is a need to provide individually optimized feedback to support improved performance in actual interviews.

[0554] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0555] In this invention, the server includes an information processing device that generates relevant interview questions based on the request of the interviewer, an emotion recognition device that extracts emotional characteristics from voice data, and a feedback device that generates feedback corresponding to the emotional state. This makes it possible to provide individualized feedback that takes into account the emotional state of the interviewer.

[0556] An "interview trainee" refers to a person who uses a system to practice and improve their interview skills.

[0557] A "request" refers to an action or input that indicates to the system the interviewer's intention to begin interview practice.

[0558] An "information processing device" refers to a device that processes information to generate relevant interview questions based on the requests of the interviewee.

[0559] A "voice recognition device" refers to a device that receives voice input from interviewees and converts it into text data.

[0560] An "evaluation device" refers to a device that analyzes text data and provides interviewers with an evaluation of its content and suggestions for improvement.

[0561] A "notification device" refers to a device that has the function of notifying interviewers of their evaluation results and areas for improvement.

[0562] An "emotion recognition device" refers to a device that has the function of extracting emotional characteristics from audio data and identifying the emotional state of the interviewer.

[0563] A "feedback device" refers to a device that generates and provides feedback according to the emotional state of the interviewee.

[0564] This invention relates to an embodiment of an interview practice system that takes into account the emotional state of the interviewee. The system begins with a server generating relevant questions based on user requests, utilizing a generative AI model. Specifically, a general-purpose text generation algorithm is used as the generative AI model.

[0565] The terminal uses a speech synthesis engine to present questions sent from the server to the user verbally. For speech synthesis, general-purpose speech processing software is used, for example. The user is expected to respond to these verbal questions via microphone input.

[0566] The user's voice response is converted into text data by a speech recognition device on the terminal. This conversion can utilize common speech recognition technologies; for example, voice-to-text APIs provided on many platforms are available.

[0567] The converted text and audio data are processed on a server, and the user's emotional characteristics are extracted by an emotion recognition device. This analysis utilizes emotion analysis software to infer emotional states from voice tone and word choices.

[0568] The evaluation device on the server analyzes text data using natural language processing techniques. Then, referencing the emotional characteristics obtained from the emotion recognition device, the feedback device generates user-specific feedback. This feedback includes specific advice for the user to take steps to improve their performance.

[0569] The device ultimately notifies the user of the generated feedback and analysis results. These notifications can be in voice or text format, allowing the user to use them to improve their responses.

[0570] As a concrete example, when a user aiming for a sales position answers the question "Please introduce yourself," if the emotion recognition device detects the user's tension, the server generates feedback such as "Relax and emphasize your strengths."

[0571] An example of a prompt message would be, "I want to start practicing for a sales interview. I want to practice my self-introduction. Please use the generative AI model to create questions and provide an overall evaluation with emotional feedback." This allows users to experience the system's entire feedback cycle.

[0572] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0573] Step 1:

[0574] A user requests a practice interview. The user launches a dedicated application on their device and enters information about the industry and job type they wish to practice for. The entered information is sent to the server as a request. This request serves as the basic data for the server to generate interview questions.

[0575] Step 2:

[0576] The server generates relevant interview questions. The server receives user requests and generates appropriate questions using a generation AI model. Based on the entered industry and job information, it dynamically outputs customized questions by utilizing existing question templates and generation algorithms.

[0577] Step 3:

[0578] The terminal presents the generated question to the user in audio. The terminal receives the question in text format from the server and converts it into audio format using a speech synthesis engine. This converted audio is then output to the user through the speaker.

[0579] Step 4:

[0580] The user responds by voice. After listening to the question presented on the device, the user speaks their answer into the microphone. This voice is processed immediately by the device.

[0581] Step 5:

[0582] The terminal converts voice input into text. The terminal uses speech recognition software to convert the user's voice input into text data. This process converts voice data as input into text data as output.

[0583] Step 6:

[0584] The server analyzes the voice data and performs emotion recognition. The server receives voice and text data transmitted from the terminal and extracts emotional features using an emotion recognition device. In this process, the user's emotional state is identified based on factors such as voice tone, speaking speed, and word emphasis.

[0585] Step 7:

[0586] The server analyzes text data and generates feedback. The server's evaluation device uses natural language processing technology to analyze the text data and generate feedback tailored to the user's emotional state. The analysis results and emotion recognition data are integrated to output areas for improvement and specific advice for the user.

[0587] Step 8:

[0588] The device notifies the user of the feedback. The device receives feedback generated from the server and notifies the user in voice or text format. The user can use this feedback to improve their interview skills.

[0589] (Application Example 2)

[0590] Next, we will explain application example 2. In the following explanation, 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."

[0591] In interview preparation, traditional methods make it difficult to obtain feedback that takes into account the interviewee's emotional state, and emotions such as nervousness and anxiety can particularly affect performance during the actual interview. Furthermore, when practicing at home, it is not easy to obtain objective feedback or advice that takes emotions into account, thus limiting the capabilities of conventional methods. This aims to address these issues.

[0592] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0593] In this invention, the server includes an information processing device that generates relevant interview questions based on the interviewer's requests, a speech recognition device that receives voice input from the interviewer and converts it into text data, and an emotion recognition device that allows the information processing device to analyze the interviewer's emotional state and generate feedback accordingly. This enables more effective interview preparation, even when the interviewer practices at home, by receiving feedback that takes their emotional state into account.

[0594] An "information processing device" is a device that generates relevant interview questions based on the requests of the interviewee, and further analyzes their emotional state to generate feedback.

[0595] A "voice recognition device" is a device that receives voice input from interviewees and converts it into text data.

[0596] An "evaluation device" is a device that analyzes text data and provides evaluations and suggestions for improvement regarding its content.

[0597] An "emotion recognition device" is a device that extracts emotional characteristics from the voice data of interviewees and generates feedback based on the results.

[0598] A "notification device" is a device used to notify interviewers of evaluation results, areas for improvement, and feedback based on their emotional state.

[0599] The system for implementing this invention has the following configuration: When an interview trainee inputs a request, the server generates relevant interview questions using a generative AI model. These questions are customized according to the interview trainee's desired industry and job type. The questions are sent to the user's terminal and presented to the interview trainee as audio.

[0600] The user answers the presented questions verbally. The terminal converts this voice input into text data using speech recognition technology. The converted data is sent to a server, where an evaluation device analyzes the answers using natural language processing technology. Software such as the Google Cloud Natural Language API is used for the analysis. The server also uses an emotion recognition device to extract emotional characteristics from the interviewer's voice data. Microsoft Azure Emotion API is used for this purpose.

[0601] Based on the evaluation results, the server generates feedback tailored to the evaluation results and emotional characteristics. This feedback includes content that helps the interviewer continue practicing with confidence and is received via the device in audio or text format. The user can use this feedback to improve their answers.

[0602] For example, if a speech recognition system generates a question such as "Please answer the following question," and analyzes the interviewer's response, an emotion recognition device might generate feedback such as "Try taking a deep breath to relax" if it detects the interviewer's tension. Furthermore, the generative AI model optimizes the feedback content using a prompt such as, "If the system recognizes that the user is nervous, how should it provide support to help them relax?"

[0603] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0604] Step 1:

[0605] The server receives a request for interview practice from the user's terminal. This request includes information about the desired industry and job type. The server uses a generative AI model to generate relevant interview questions based on this information. The generated questions are then sent to the user's terminal.

[0606] Step 2:

[0607] The user receives interview questions displayed on the device via voice. The user answers the questions aloud, and the device captures the audio data. Using speech recognition software, this audio data is converted into text data. The converted text data is sent to the server.

[0608] Step 3:

[0609] The server inputs the received text data into the evaluation device, which then analyzes the data using natural language processing technologies such as the Google Cloud Natural Language API. This analysis evaluates the content of the responses and extracts areas for improvement. The evaluation results are stored on the server.

[0610] Step 4:

[0611] Simultaneously, the server transmits the audio data to an emotion recognition device. The emotion recognition device extracts the user's emotional characteristics using tools such as the Microsoft Azure Emotion API. This process determines emotional states such as tension and confidence levels.

[0612] Step 5:

[0613] The server uses the evaluation results and emotional characteristics to input prompt statements into an AI model that generates feedback. An example of a prompt statement is, "If you recognize that the user is feeling anxious, how would you provide support to help them relax?" The feedback includes suggestions for improving the answer and advice tailored to the emotional state.

[0614] Step 6:

[0615] The server sends the generated feedback to the user's device. The device notifies the user of the received feedback via voice or text. The user can then use this feedback to improve their answers and continue practicing their interview skills in a better state.

[0616] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0617] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0618] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0619] [Fourth Embodiment]

[0620] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0621] As shown in Figure 7, the 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.

[0622] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0623] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0624] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0625] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0626] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0627] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0628] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0629] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0630] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0631] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0632] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0633] The present invention provides a system for interview trainees to effectively prepare for interviews. This system generates relevant interview questions in response to the trainee's requests, presents them audibly, accepts user responses, and provides appropriate feedback. Specific embodiments of the present invention are described below.

[0634] First, the user enters their interview practice request on a terminal. The user specifies their desired industry and job type and prepares practice questions based on the topic. Based on this, the server uses a generation AI to generate appropriate interview questions. These questions are customized in terms of difficulty and content to meet the user's requirements.

[0635] Next, the device presents a question to the user verbally. The user can then answer verbally. The device converts the user's response into text using speech recognition technology. The converted text is then sent to the server.

[0636] The server analyzes the received text data using natural language processing technology and evaluates the user's response. Based on the analysis results, the evaluation device determines the quality of the response and generates areas for improvement and examples of good responses. This feedback is detailed and specific, enabling users to prepare better responses.

[0637] Finally, the device notifies the user of feedback via voice or text, allowing them to reflect on their answers and gain guidance for further improvement. This system supports continuous practice so that users can perform at their best in interviews.

[0638] For example, if a user requests a "sales interview," the server generates questions related to sales. For instance, it might generate a question like, "Please tell us about the sales targets you have achieved in the past." When the user answers, the answer is evaluated, and feedback is provided, such as, "It would be even better if you included specific numerical data." Through this process, users can prepare persuasive answers that include concrete examples.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] The user enters a request to start a mock interview via their device. The user specifies the industry and job type they want to practice for and selects their preferred interview format.

[0642] Step 2:

[0643] The server receives the user's request and retrieves appropriate question data by referring to a database corresponding to the specified industry and job type. Based on the retrieved data, it uses a generation AI to generate interview questions.

[0644] Step 3:

[0645] The terminal receives questions from the server and presents them to the user verbally. Speech synthesis technology is used to ensure the user understands the questions naturally.

[0646] Step 4:

[0647] The user responds to the presented questions verbally. The user attempts to structure and express their thoughts.

[0648] Step 5:

[0649] The device receives the user's voice response and converts it into text data using its speech recognition function. This text data is then sent to the server.

[0650] Step 6:

[0651] The server analyzes the text data it receives. Natural language processing techniques are applied to evaluate the keywords, logical structure, and expressiveness of the responses. Furthermore, areas for improvement and inconsistencies that need to be pointed out in the responses are identified.

[0652] Step 7:

[0653] The server generates feedback based on the analysis results. This feedback includes what was good about the response, areas for improvement, and specific examples of improvements.

[0654] Step 8:

[0655] The device receives feedback and notifies the user. The user reviews the feedback, pays attention to areas for improvement, and continues practicing.

[0656] Step 9:

[0657] Users can receive feedback, improve their answers, and try the same question again or a new one. By repeating this process, users gradually improve their interview skills.

[0658] (Example 1)

[0659] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0660] Currently, systems for effective interview practice do not adequately meet the specific needs of users. In particular, there is a lack of systems that can appropriately customize interview content and questions according to specific industries and job types, and provide accurate feedback on user responses. Furthermore, there is a growing need for systems that can effectively analyze voice input and evaluate user responses using natural language processing.

[0661] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0662] In this invention, the server includes a computing device means that generates relevant inquiries based on requests from the user, a speech recognition device means that receives voice input from the user and converts it into text data, and an evaluation device means that analyzes the text data and provides content evaluation and improvement points. This makes it possible for users to receive appropriate interview questions tailored to their industry and job type, and to obtain specific and effective feedback on their answers.

[0663] "User" refers to an individual or organization that uses computing devices and related systems to conduct interview practice.

[0664] "Requests" refer to the specific wishes and conditions regarding interview practice that the user communicates to the computing device.

[0665] "Inquiry" refers to interview-related questions generated by the computer based on the user's request.

[0666] A "computer" refers to a central processing unit that receives user requests, generates queries, and interacts with other system components.

[0667] "Voice input" refers to information provided by the user through voice.

[0668] "Character data" refers to information in text format converted from voice input by a speech recognition device.

[0669] A "speech recognition device" refers to a machine or software that receives speech input and converts it into text data.

[0670] An "evaluation device" refers to a device or software that has the function of analyzing text data provided by a speech recognition device, evaluating its content, and generating areas for improvement.

[0671] "Notification device" refers to a machine or function that communicates evaluation results and areas for improvement to the user in voice or text format.

[0672] "Natural language processing technology" refers to artificial intelligence technology that analyzes the meaning contained in text data and understands the syntactic structure, content, and context of a sentence.

[0673] "Domain" refers to the specific industry or field that the user focuses on during interview practice.

[0674] "Work" refers to a series of activities or tasks related to a specific job or function.

[0675] This invention provides a system to support effective preparation for users who wish to practice for interviews. The system includes the ability to generate highly customized interview questions and to analyze and evaluate the user's voice input.

[0676] The user uses a terminal to input a request for interview practice. The user specifies the desired area or job and provides prompts to the system. For example, if the user enters the prompt "Generate sales job questions," questions related to that specific job will be generated.

[0677] Upon receiving a user request, the server uses its computing power and a generative AI model to generate relevant questions. This generation process utilizes various databases and pre-trained natural language processing models. The generated interview questions are those that best fit the conditions specified by the user.

[0678] Next, the device uses speech synthesis technology to present questions to the user verbally. A typical speech synthesis technology that utilizes this technology is a commonly used voice output function.

[0679] The user answers the presented questions verbally. The terminal converts these answers into text data using speech recognition software and sends the results to the server. Various commercially available speech recognition APIs are used for the speech recognition technology.

[0680] The server analyzes the received text data using natural language processing technology and evaluates the response. Based on the analysis results, detailed and specific feedback is generated that the user needs to improve.

[0681] Finally, the device notifies the user of the evaluation results and feedback. This feedback is displayed in either audio or text format. This allows the user to reflect on their answers and gain guidance for more effective presentations in interviews.

[0682] This system provides practical support for interview preparation and helps users approach interviews with confidence.

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The user enters a request for interview practice using a terminal. This request includes the desired job or area of ​​work. The entered request is sent to the server in the form of a prompt message. The input data consists of the job or area of ​​work specified by the user, and interview questions are generated based on this.

[0686] Step 2:

[0687] The server generates relevant interview questions using a generative AI model based on the received prompt. The server parses the input request and invokes the AI ​​model to generate customized questions accordingly. The output is a set of questions appropriately tailored based on the user's request. This process leverages past question examples stored in the database and the generative capabilities of the AI ​​model.

[0688] Step 3:

[0689] The interview questions generated by the server are sent to the terminal. The terminal uses speech synthesis technology to present the questions to the user verbally. Specifically, the question text is converted into speech output using a speech synthesis API and played through the speaker.

[0690] Step 4:

[0691] The user answers the presented questions verbally via the microphone. These answers are recorded on the device. The recorded audio is input to the device and prepared as data for processing in the next stage.

[0692] Step 5:

[0693] The device converts the user's voice responses into text data using speech recognition technology. It analyzes audio files as input and outputs text data. This process is performed in real time, and the generated text is sent to the server.

[0694] Step 6:

[0695] The server analyzes the received text data using natural language processing technology and evaluates the user's response. Based on the input text, it evaluates the sentence structure, appropriateness of content, and logical structure, and generates feedback data as a result. Predefined evaluation criteria are applied to the evaluation.

[0696] Step 7:

[0697] The server sends the evaluation results and generated improvement feedback to the terminal. The terminal notifies the user of this feedback. This feedback can be delivered via speech synthesis or displayed as text on the screen. The user can then use this feedback to improve their interview responses.

[0698] (Application Example 1)

[0699] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0700] Conventional interview practice systems have limitations in providing feedback to user voice input, making it difficult to provide customized practice tailored to specific industries or job types. Furthermore, to efficiently support user skill improvement, it is important to utilize autonomous devices that allow for readily accessible interview practice.

[0701] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0702] In this invention, the server includes an information processing circuit means that generates relevant dialogue-style questions based on the requests of the interview trainee, a speech recognition circuit means that receives voice input from the interview trainee and converts it into a text signal, and an evaluation circuit means that analyzes the text signal and provides methods for evaluating and improving its content. This makes it possible for interview trainees to efficiently improve skills relevant to specific jobs and industries through dialogue-style practice using the autonomous device.

[0703] An "interview trainee" refers to an individual who practices for an interview, with the aim of improving their ability to answer questions related to a specific industry or job.

[0704] An "autonomous device" refers to a mechanical device equipped with voice input / output capabilities that supports interview practice by interacting with the user, and is used in homes and facilities.

[0705] An "information processing circuit" refers to a circuit that performs calculations to generate relevant dialogue-style questions based on the requests of the interviewee.

[0706] A "voice recognition circuit" refers to a circuit that converts the voice input received by an autonomous device from an interviewer into text signals.

[0707] An "evaluation circuit" refers to a circuit that analyzes the text signal converted by the speech recognition circuit and provides evaluation and improvement methods for its content.

[0708] "Text signal" refers to the character information generated as a result of the speech recognition circuit converting the voice input of the interviewee.

[0709] This invention provides a system for supporting the skill improvement of interviewers using autonomous devices. This system includes an information processing circuit, a speech recognition circuit, and an evaluation circuit, each of which works in cooperation with the others.

[0710] The server generates relevant conversational questions in its information processing circuit in response to the interviewer's requests. By using a generative AI model, it is possible to efficiently create questions specific to the interviewer's job and industry. For example, when generating questions related to a sales position, the AI ​​model is instructed with the prompt, "Please create five questions for a sales interview."

[0711] When a user answers a question by voice, the device's voice input / output function converts the voice into text signals via a speech recognition circuit. These converted text signals are sent to a server, where an evaluation circuit analyzes the content and suggests ways to improve it. Natural language processing technology (e.g., spaCy) is used for this analysis.

[0712] The evaluation results and areas for improvement are communicated to the interviewer via their device. This feedback provides guidance for interviewers to easily prepare for interviews at home or elsewhere, supporting skill improvement. For example, if a user includes numerical data in their answer, they will receive feedback such as, "Specific numerical data makes your answer more persuasive."

[0713] By using this system, interview candidates can effectively improve their skills tailored to specific jobs and industries through interactive practice using autonomous devices.

[0714] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0715] Step 1:

[0716] The user enters a request for interview practice into the terminal. By specifically specifying the desired job and industry, the request data sent to the server is formed. This request data serves as the basis for generating prompt messages.

[0717] Step 2:

[0718] The server receives the request data and uses its information processing circuitry to generate prompt statements for the AI ​​model. Based on these prompt statements, the AI ​​model creates relevant, conversational questions about a specific job or industry. The generated questions become output data ready to be converted into speech format.

[0719] Step 3:

[0720] The generated question is transmitted to the terminal, which uses speech synthesis technology to present the question to the user verbally. The user answers the presented question verbally. This process generates voice input data. The voice input data is then awaiting processing by the speech recognition circuit.

[0721] Step 4:

[0722] The terminal receives the user's voice input and converts it into a text signal using a speech recognition circuit. This voice-to-text conversion organizes the text data into the format necessary for analysis, and the resulting text data is sent to the server.

[0723] Step 5:

[0724] The server sends the received text data to an evaluation circuit, where it is analyzed using natural language processing technology. This analysis evaluates the user's response and generates information regarding the evaluation and areas for improvement. This result becomes feedback data.

[0725] Step 6:

[0726] The device receives feedback data and notifies the user via voice or text using a notification device. By receiving this feedback, the user can gain specific guidance for improving the quality of their responses. The ultimate output is reflection and skill improvement through feedback.

[0727] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0728] This invention provides a system that incorporates emotion recognition functionality into an interview practice system, enabling it to provide personalized feedback while considering the user's emotional state. This system generates relevant questions based on the interview practice request, processes the user's voice input, and recognizes emotional characteristics using an emotion engine.

[0729] Specifically, users input a request to begin interview practice via their device, specifying their desired industry and job type, which generates questions on the server. These questions are dynamically generated by a generation AI and adjusted to meet the user's needs.

[0730] The device presents the user with generated questions via voice. The user is expected to respond to these questions verbally while considering the question. The user's voice input is converted into text data by the device and then sent to the server. Here, the voice data is analyzed by an emotion engine to extract the user's emotional characteristics.

[0731] On the server, the evaluation device performs analysis using natural language processing technology based on text data. Furthermore, emotional characteristics obtained by the emotion engine are referenced in this analysis process. As a result, the evaluation device generates feedback that corresponds to the user's emotional state. The feedback includes content that takes the user's emotional state into consideration, so that the user can practice with confidence.

[0732] The device ultimately notifies the user of feedback and analyzed sentiment data. This notification can be in audio or text format, and the user can use it to improve their responses. For example, if the sentiment engine detects that the user is nervous, the notification may include advice on how to relax. This allows the user to improve their responses in a better state of mind and enhance their performance during the actual interview.

[0733] The following describes the processing flow.

[0734] Step 1:

[0735] The user enters a request to start a practice interview into the terminal. Here, the user specifies the industry and job type they want to practice for and selects the desired interview format.

[0736] Step 2:

[0737] The server receives a request from the user and retrieves relevant question data by referencing a database corresponding to the specified industry and job type. Using generation AI, appropriate interview questions are generated based on the retrieved data.

[0738] Step 3:

[0739] The terminal receives questions from the server and presents them to the user verbally. Speech synthesis technology is used to convey the questions to the user in a natural-sounding manner.

[0740] Step 4:

[0741] Users will answer the presented questions verbally. Users should strive to organize their experiences and thoughts and answer clearly.

[0742] Step 5:

[0743] The device receives the user's voice response and converts it into text data using speech recognition. Additionally, an emotion engine is run to sense the user's tone and pace, extracting emotional characteristics.

[0744] Step 6:

[0745] The server analyzes the received text data using natural language processing techniques. This analysis includes identifying keywords in the text data, evaluating the logical consistency of the responses, and analyzing their expressiveness. Furthermore, emotional characteristics generated by an emotion engine are incorporated into the analysis.

[0746] Step 7:

[0747] The server generates feedback based on the analysis results. Particular attention is paid to the user's emotional state, and the feedback includes not only suggestions for improving answers, but also advice on mental preparation for the interview.

[0748] Step 8:

[0749] The device notifies the user of the generated feedback and sentiment analysis results. The notifications are provided in both audio and text formats, allowing the user to gain specific insights for improvement from the feedback.

[0750] Step 9:

[0751] Users review and improve their answers based on feedback. If necessary, they practice interviews again using the same process, gradually improving their interview skills.

[0752] (Example 2)

[0753] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0754] In modern interview practice, not only high-quality responses to questions but also the interviewee's emotional state are crucial. However, while conventional interview practice systems can evaluate audio content, they have struggled to provide feedback that takes the user's emotional state into account. Therefore, there is a need to provide individually optimized feedback to support improved performance in actual interviews.

[0755] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0756] In this invention, the server includes an information processing device that generates relevant interview questions based on the request of the interviewer, an emotion recognition device that extracts emotional characteristics from voice data, and a feedback device that generates feedback corresponding to the emotional state. This makes it possible to provide individualized feedback that takes into account the emotional state of the interviewer.

[0757] An "interview trainee" refers to a person who uses a system to practice and improve their interview skills.

[0758] A "request" refers to an action or input that indicates to the system the interviewer's intention to begin interview practice.

[0759] An "information processing device" refers to a device that processes information to generate relevant interview questions based on the requests of the interviewee.

[0760] A "voice recognition device" refers to a device that receives voice input from interviewees and converts it into text data.

[0761] An "evaluation device" refers to a device that analyzes text data and provides interviewers with an evaluation of its content and suggestions for improvement.

[0762] A "notification device" refers to a device that has the function of notifying interviewers of their evaluation results and areas for improvement.

[0763] An "emotion recognition device" refers to a device that has the function of extracting emotional characteristics from audio data and identifying the emotional state of the interviewer.

[0764] A "feedback device" refers to a device that generates and provides feedback according to the emotional state of the interviewee.

[0765] This invention relates to an embodiment of an interview practice system that takes into account the emotional state of the interviewee. The system begins with a server generating relevant questions based on user requests, utilizing a generative AI model. Specifically, a general-purpose text generation algorithm is used as the generative AI model.

[0766] The terminal uses a speech synthesis engine to present questions sent from the server to the user verbally. For speech synthesis, general-purpose speech processing software is used, for example. The user is expected to respond to these verbal questions via microphone input.

[0767] The user's voice response is converted into text data by a speech recognition device on the terminal. This conversion can utilize common speech recognition technologies; for example, voice-to-text APIs provided on many platforms are available.

[0768] The converted text and audio data are processed on a server, and the user's emotional characteristics are extracted by an emotion recognition device. This analysis utilizes emotion analysis software to infer emotional states from voice tone and word choices.

[0769] The evaluation device on the server analyzes text data using natural language processing techniques. Then, referencing the emotional characteristics obtained from the emotion recognition device, the feedback device generates user-specific feedback. This feedback includes specific advice for the user to take steps to improve their performance.

[0770] The device ultimately notifies the user of the generated feedback and analysis results. These notifications can be in voice or text format, allowing the user to use them to improve their responses.

[0771] As a concrete example, when a user aiming for a sales position answers the question "Please introduce yourself," if the emotion recognition device detects the user's tension, the server generates feedback such as "Relax and emphasize your strengths."

[0772] An example of a prompt message would be, "I want to start practicing for a sales interview. I want to practice my self-introduction. Please use the generative AI model to create questions and provide an overall evaluation with emotional feedback." This allows users to experience the system's entire feedback cycle.

[0773] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0774] Step 1:

[0775] A user requests a practice interview. The user launches a dedicated application on their device and enters information about the industry and job type they wish to practice for. The entered information is sent to the server as a request. This request serves as the basic data for the server to generate interview questions.

[0776] Step 2:

[0777] The server generates relevant interview questions. The server receives user requests and generates appropriate questions using a generation AI model. Based on the entered industry and job information, it dynamically outputs customized questions by utilizing existing question templates and generation algorithms.

[0778] Step 3:

[0779] The terminal presents the generated question to the user in audio. The terminal receives the question in text format from the server and converts it into audio format using a speech synthesis engine. This converted audio is then output to the user through the speaker.

[0780] Step 4:

[0781] The user responds by voice. After listening to the question presented on the device, the user speaks their answer into the microphone. This voice is processed immediately by the device.

[0782] Step 5:

[0783] The terminal converts voice input into text. The terminal uses speech recognition software to convert the user's voice input into text data. This process converts voice data as input into text data as output.

[0784] Step 6:

[0785] The server analyzes the voice data and performs emotion recognition. The server receives voice and text data transmitted from the terminal and extracts emotional features using an emotion recognition device. In this process, the user's emotional state is identified based on factors such as voice tone, speaking speed, and word emphasis.

[0786] Step 7:

[0787] The server analyzes text data and generates feedback. The server's evaluation device uses natural language processing technology to analyze the text data and generate feedback tailored to the user's emotional state. The analysis results and emotion recognition data are integrated to output areas for improvement and specific advice for the user.

[0788] Step 8:

[0789] The device notifies the user of the feedback. The device receives feedback generated from the server and notifies the user in voice or text format. The user can use this feedback to improve their interview skills.

[0790] (Application Example 2)

[0791] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0792] In interview preparation, traditional methods make it difficult to obtain feedback that takes into account the interviewee's emotional state, and emotions such as nervousness and anxiety can particularly affect performance during the actual interview. Furthermore, when practicing at home, it is not easy to obtain objective feedback or advice that takes emotions into account, thus limiting the capabilities of conventional methods. This aims to address these issues.

[0793] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0794] In this invention, the server includes an information processing device that generates relevant interview questions based on the interviewer's requests, a speech recognition device that receives voice input from the interviewer and converts it into text data, and an emotion recognition device that allows the information processing device to analyze the interviewer's emotional state and generate feedback accordingly. This enables more effective interview preparation, even when the interviewer practices at home, by receiving feedback that takes their emotional state into account.

[0795] An "information processing device" is a device that generates relevant interview questions based on the requests of the interviewee, and further analyzes their emotional state to generate feedback.

[0796] A "voice recognition device" is a device that receives voice input from interviewees and converts it into text data.

[0797] An "evaluation device" is a device that analyzes text data and provides evaluations and suggestions for improvement regarding its content.

[0798] An "emotion recognition device" is a device that extracts emotional characteristics from the voice data of interviewees and generates feedback based on the results.

[0799] A "notification device" is a device used to notify interviewers of evaluation results, areas for improvement, and feedback based on their emotional state.

[0800] The system for implementing this invention has the following configuration: When an interview trainee inputs a request, the server generates relevant interview questions using a generative AI model. These questions are customized according to the interview trainee's desired industry and job type. The questions are sent to the user's terminal and presented to the interview trainee as audio.

[0801] The user answers the presented questions verbally. The terminal converts this voice input into text data using speech recognition technology. The converted data is sent to a server, where an evaluation device analyzes the answers using natural language processing technology. Software such as the Google Cloud Natural Language API is used for the analysis. The server also uses an emotion recognition device to extract emotional characteristics from the interviewer's voice data. Microsoft Azure Emotion API is used for this purpose.

[0802] Based on the evaluation results, the server generates feedback tailored to the evaluation results and emotional characteristics. This feedback includes content that helps the interviewer continue practicing with confidence and is received via the device in audio or text format. The user can use this feedback to improve their answers.

[0803] For example, if a speech recognition system generates a question such as "Please answer the following question," and analyzes the interviewer's response, an emotion recognition device might generate feedback such as "Try taking a deep breath to relax" if it detects the interviewer's tension. Furthermore, the generative AI model optimizes the feedback content using a prompt such as, "If the system recognizes that the user is nervous, how should it provide support to help them relax?"

[0804] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0805] Step 1:

[0806] The server receives a request for interview practice from the user's terminal. This request includes information about the desired industry and job type. The server uses a generative AI model to generate relevant interview questions based on this information. The generated questions are then sent to the user's terminal.

[0807] Step 2:

[0808] The user receives interview questions displayed on the device via voice. The user answers the questions aloud, and the device captures the audio data. Using speech recognition software, this audio data is converted into text data. The converted text data is sent to the server.

[0809] Step 3:

[0810] The server inputs the received text data into the evaluation device, which then analyzes the data using natural language processing technologies such as the Google Cloud Natural Language API. This analysis evaluates the content of the responses and extracts areas for improvement. The evaluation results are stored on the server.

[0811] Step 4:

[0812] Simultaneously, the server transmits the audio data to an emotion recognition device. The emotion recognition device extracts the user's emotional characteristics using tools such as the Microsoft Azure Emotion API. This process determines emotional states such as tension and confidence levels.

[0813] Step 5:

[0814] The server uses the evaluation results and emotional characteristics to input prompt statements into an AI model that generates feedback. An example of a prompt statement is, "If you recognize that the user is feeling anxious, how would you provide support to help them relax?" The feedback includes suggestions for improving the answer and advice tailored to the emotional state.

[0815] Step 6:

[0816] The server sends the generated feedback to the user's device. The device notifies the user of the received feedback via voice or text. The user can then use this feedback to improve their answers and continue practicing their interview skills in a better state.

[0817] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0818] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0819] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0820] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0821] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0822] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0823] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0824] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0825] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0826] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0827] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0828] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0829] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0830] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0831] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0832] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0833] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0834] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0835] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0836] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0837] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0838] The following is further disclosed regarding the embodiments described above.

[0839] (Claim 1)

[0840] Information processing device means for generating relevant interview questions based on the requests of the interviewer,

[0841] A speech recognition device means that receives voice input from interviewers and converts it into text data,

[0842] An evaluation device means that analyzes text data and provides content evaluation and improvement suggestions,

[0843] A notification device means for informing the interviewer of the evaluation results and areas for improvement,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, wherein the information processing device customizes the questions according to the industry or job type specified by the interviewer.

[0847] (Claim 3)

[0848] The system according to claim 1, wherein the evaluation device uses natural language processing technology when analyzing text data.

[0849] "Example 1"

[0850] (Claim 1)

[0851] A computing device means that generates related queries based on requests from the user,

[0852] A speech recognition device means that receives voice input from the user and converts it into text data,

[0853] An evaluation device means that analyzes text data and provides content evaluation and improvement points,

[0854] A notification device means for notifying the user of evaluation results and areas for improvement,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, wherein the computing device adjusts queries according to the area or task specified by the user.

[0858] (Claim 3)

[0859] The system according to claim 1, wherein the evaluation device uses natural language processing technology when analyzing character data.

[0860] "Application Example 1"

[0861] (Claim 1)

[0862] Information processing circuit means that generates relevant dialogue-style questions based on the requests of the interviewer,

[0863] An autonomous device having voice input / output capabilities receives voice input from an interviewer and converts it into a text signal using a voice recognition circuit.

[0864] An evaluation circuit means that analyzes a text signal and provides methods for evaluating and improving its content,

[0865] An output circuit means for notifying the interviewer of the evaluation results and improvement methods,

[0866] A training support system that includes this.

[0867] (Claim 2)

[0868] The training support system according to claim 1, wherein the information processing circuit changes the questions according to the job or industry specified by the interview trainee.

[0869] (Claim 3)

[0870] The training support system according to claim 1, wherein the evaluation circuit utilizes natural language processing technology when analyzing text signals.

[0871] "Example 2 of combining an emotion engine"

[0872] (Claim 1)

[0873] Information processing device means for generating relevant interview questions based on the requests of the interviewer,

[0874] A speech recognition device means that receives voice input from interviewers and converts it into text data,

[0875] An evaluation device means that analyzes text data and provides content evaluation and improvement suggestions,

[0876] A notification device means for informing the interviewer of the evaluation results and areas for improvement,

[0877] An emotion recognition device means for extracting emotional features from audio data,

[0878] A feedback device means that generates feedback according to the emotional state,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, wherein the information processing device customizes the questions according to the industry or job type specified by the interviewer.

[0882] (Claim 3)

[0883] The system according to claim 1, wherein the evaluation device uses natural language processing technology when analyzing text data.

[0884] "Application example 2 when combining with an emotional engine"

[0885] (Claim 1)

[0886] Information processing device means for generating relevant interview questions based on the requests of the interviewer,

[0887] A speech recognition device means that receives voice input from interviewers and converts it into text data,

[0888] An evaluation device means that analyzes text data and provides content evaluation and improvement suggestions,

[0889] An information processing device includes an emotion recognition device means that analyzes the emotional state of the interviewer and generates feedback according to the results,

[0890] A notification device means for informing the interviewer of evaluation results, areas for improvement, and feedback based on emotional state,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, wherein the information processing device customizes questions according to the industry or job type specified by the interviewer and generates feedback that takes into account the emotional state.

[0894] (Claim 3)

[0895] The system according to claim 1, wherein the evaluation device uses natural language processing technology when analyzing text data and adjusts the feedback based on the emotional state. [Explanation of Symbols]

[0896] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information processing circuit means that generates relevant dialogue-style questions based on the requests of the interviewer, An autonomous device having voice input / output capabilities receives voice input from an interviewer and converts it into a text signal using a voice recognition circuit. An evaluation circuit means that analyzes a text signal and provides methods for evaluating and improving its content, An output circuit means for notifying the interviewer of the evaluation results and improvement methods, A training support system that includes this.

2. The training support system according to claim 1, wherein the information processing circuit changes the questions according to the job or industry specified by the interview trainee.

3. The training support system according to claim 1, wherein the evaluation circuit utilizes natural language processing technology when analyzing text signals.

Images