system

Abstract

Provide a system. 【Solution means】 Means for receiving user authentication information and performing authentication, Means for receiving user voice and video data in real time, Means for analyzing the received voice data and converting it into text data, Means for analyzing the received video data and obtaining non-verbal communication information, Means for evaluating the user's answer based on the analysis result and calculating a score, Means for providing real-time feedback based on the evaluation result, Means for saving the user's results and providing industry and career suggestions, A system including.

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, the method 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] In conventional interview practice, the opportunities for interviews are limited, and it has been difficult to objectively grasp one's own strengths and weaknesses. Also, it has been difficult to obtain specific feedback in line with the evaluation criteria of companies and universities, and there has been a problem that it is difficult to take efficient countermeasures. Furthermore, there has been a lack of specific guidance and direction for improving skills suitable for a specific industry or career.

Means for Solving the Problems

[0005] This invention provides a system that allows users to practice interviews online. Based on the user's authentication information, it retrieves evaluation criteria for selected companies and universities from a database and prepares for mock interviews. It also receives real-time audio and video data transmitted from the user's terminal, analyzes the audio data using natural language processing technology to convert it into text data, and further analyzes the video data to obtain non-verbal communication information. Based on these analysis results, it evaluates the user's responses, calculates a score, and provides real-time feedback based on the evaluation results. Furthermore, it provides a system that saves the user's interview results and has a function to suggest the most suitable industry and career based on the analysis.

[0006] A "user" refers to an individual who uses the system to practice mock interviews.

[0007] "Authentication information" refers to the login information and identification data that a user needs to access the system.

[0008] "Audio data" refers to the sounds a user makes during an interview, and is the data that will be analyzed.

[0009] "Video data" refers to video footage that represents the user's appearance and movements, and is data used to analyze non-verbal information.

[0010] "Natural language processing technology" is a technology that converts speech into text format and analyzes its content.

[0011] "Non-verbal communication information" refers to information other than words, such as a user's facial expressions, gaze, and posture.

[0012] "Evaluation" is the process of quantifying or qualitatively analyzing a user's interview performance based on analyzed audio and video data.

[0013] "Feedback" refers to information including evaluation results and suggestions for improvement provided based on the user's interview results.

[0014] "Industry and career suggestions" refer to information that recommends suitable job types and areas of expertise, taking into account the user's strengths and aptitudes. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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.

[0019] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. 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.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] To implement this invention, the user must first log in to the system. By accessing the portal site and entering authentication information, the server verifies and authenticates the user. This authentication allows the evaluation criteria of the company or university selected by the user to be retrieved from the database.

[0037] When a user begins a mock interview, their device activates its camera and microphone, capturing the user's audio and video in real time. The captured data is streamed from the user's device to the server.

[0038] The server converts the received audio data into text data using speech recognition technology. This text data is then analyzed using natural language processing technology to evaluate its logic and the relevance of its content. Simultaneously, video data is analyzed to evaluate the user's facial expressions, gaze, and posture, and nonverbal communication information is extracted.

[0039] These analysis results are used to comprehensively evaluate user performance and are scored by the server. The evaluation results are fed back to the user in real time and displayed on the screen. Based on this feedback, users can understand their strengths and weaknesses and use them to improve.

[0040] Furthermore, the server uses algorithms to analyze the user's analysis results in order to suggest suitable industries and career paths. This information is then provided to the user to support their future career choices.

[0041] As a concrete example, during a user's interview practice, an assessment of their suitability is also conducted to determine whether their answers match the ideal candidate profile sought by the company. If a user's answers are vague or lack specificity, the server provides feedback suggesting they "make their answers more specific."

[0042] This system allows users to more effectively improve themselves through mock interviews and hone the skills required by the industry and companies.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user accesses the online platform and enters their authentication information on the login screen. Account authentication is performed based on the user's input.

[0046] Step 2:

[0047] The server verifies the user's authentication, and if successful, retrieves evaluation criteria data for the company or university selected by the user from the database.

[0048] Step 3:

[0049] When the user initiates the mock interview, the device activates the user's camera and microphone and begins capturing the user's video and audio data in real time.

[0050] Step 4:

[0051] The terminal streams the captured video and audio data to the server in real time. The server receives this data.

[0052] Step 5:

[0053] The server converts the received audio data into text data using speech recognition technology. The text is then analyzed using natural language processing technology to evaluate the logic and relevance of its content.

[0054] Step 6:

[0055] The server analyzes the video data and extracts and evaluates nonverbal communication information such as the user's facial expressions, gaze, and posture.

[0056] Step 7:

[0057] The server comprehensively evaluates the data obtained from audio and video analysis and scores the user's mock interview performance.

[0058] Step 8:

[0059] The server generates real-time feedback for the user based on the evaluation results and immediately provides it to the user via the terminal.

[0060] Step 9:

[0061] The server analyzes suitable industries and career paths based on the user's evaluation results and generates suggestions using an algorithm.

[0062] Step 10:

[0063] The server provides the suggested results to the user via the terminal, allowing the user to use them to help them choose their career path.

[0064] (Example 1)

[0065] 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."

[0066] In modern job hunting and promotion exams, job seekers and employees are required to accurately assess and improve their own abilities. However, traditional mock interviews and evaluation processes make it difficult to obtain efficient and objective feedback in real time. Therefore, there is a need to develop systems that support the improvement of users' abilities.

[0067] 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.

[0068] In this invention, the server includes means for receiving and authenticating user authentication information, means for receiving user voice and video data in real time, means for analyzing the received voice data and converting it into text data, means for analyzing the received video data and obtaining nonverbal communication information, means for evaluating the user's responses based on the analysis results and calculating a score, means for providing feedback based on the evaluation results in real time, and means for generating prompts using a generative AI model and providing individualized advice to the user. This makes it possible to effectively and immediately evaluate the user's abilities and provide individually optimized improvement suggestions.

[0069] "Authentication information" refers to information used to verify a user's identity, and typically includes a username and password.

[0070] "Voice data" refers to data that is recorded in digital format from the voice spoken by the user and used for analysis.

[0071] "Video data" refers to digital data that includes visual information such as the user's movements and facial expressions captured by a camera.

[0072] "Means of converting to text data" refers to a processing system that uses speech recognition technology to convert audio data into text format.

[0073] "Nonverbal communication information" refers to communication elements conveyed through means other than words, such as facial expressions, posture, and eye contact.

[0074] "Analysis results" refer to the results of an analysis of data regarding user characteristics and abilities obtained through the processing of audio and video data.

[0075] "Feedback based on evaluation results" refers to advice and suggestions given to users based on analysis results, and is information intended to encourage self-improvement.

[0076] "Suitable job areas and career paths" refers to the analysis results indicating the industry and career path that best suits the user's abilities and characteristics.

[0077] "Generating prompts using a generative AI model" and providing them to the user refers to using AI technology to dynamically create instructions or questions based on specific conditions.

[0078] "Individualized advice" refers to specialized improvement suggestions and guidance based on the user's unique evaluation results.

[0079] The following describes embodiments for carrying out the invention.

[0080] In this system, users first access a portal site and log in by entering their authentication information. The server receives this authentication information and authenticates the user by comparing it with the database. In particular, the hardware used for this process would likely include a web server and an authentication protocol such as HTTPS.

[0081] After authentication, when the user begins a mock interview, the user's device activates its camera and microphone to capture audio and video in real time. Typical personal computers and smartphones are used as the hardware for this process.

[0082] The captured data is streamed from the user's terminal to the server, where speech recognition technology is applied to the received audio data. Speech recognition software such as Google® Speech-to-Text API is used here. The audio data is converted to text data, and the server further analyzes the content using natural language processing techniques. Libraries such as Python's NLTK and spaCy are utilized in this process.

[0083] The server uses OpenCV to analyze the video data and evaluate the user's facial expressions, gaze, and posture. This allows for the extraction of nonverbal communication information.

[0084] The server evaluates the user's performance based on these analysis results and generates prompts using a generative AI model. Through these prompts, it provides personalized advice to the user. The evaluation results and feedback are displayed on the user's terminal, allowing the user to identify areas for improvement.

[0085] For example, the server generates a prompt message such as, "Please tell me the procedure for analyzing the evaluation criteria of a user's mock interview using a generative AI model," and presents it to the user.

[0086] In this way, through this system, users can receive more detailed and accurate feedback, which helps them to improve their skills. Furthermore, the server uses the analysis results to suggest suitable industries and career paths, supporting the user's career choices.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The user accesses the portal site and enters their username and password as authentication information on the login screen. The server receives the entered authentication information and authenticates the user by comparing it with the information stored in the database. If successful, the server can retrieve evaluation criteria data for companies and universities based on the user's permissions.

[0090] Step 2:

[0091] When a user begins a mock interview, they click the start button on the device. The device activates the camera and microphone and captures the user's audio and video in real time. The device compresses the captured data and streams it to the server. The input audio and video data is sent to the server and forms the basis for the next processing step.

[0092] Step 3:

[0093] The server converts the received audio data into text using the Google Speech-to-Text API. This conversion outputs the text information obtained from the audio data as text data to be analyzed. Specifically, the content spoken by the user is extracted as text information.

[0094] Step 4:

[0095] The server analyzes text data using natural language processing techniques. Python's NLTK and spaCy are used to evaluate the logic and relevance of the user's statements. Based on the input text data, the analyzed data is output, and this analysis result serves as the basis for the evaluation.

[0096] Step 5:

[0097] The server analyzes the received video data using OpenCV to evaluate the user's physical characteristics such as facial expressions, gaze, and posture. Nonverbal communication information is extracted based on the input video data, and this information is added to the evaluation results.

[0098] Step 6:

[0099] The server integrates the audio and video analysis results and uses a generative AI model to evaluate the user's mock interview performance. Based on this, it calculates a score, generates prompts, and creates personalized advice. The calculated evaluation score and generated advice are output.

[0100] Step 7:

[0101] The server sends the generated evaluation score and advice to the user's terminal. The user can immediately see this feedback on the terminal screen and understand what areas need improvement. Suggestions for suitable industries and career paths are also displayed simultaneously, supporting the user in their future career choices.

[0102] (Application Example 1)

[0103] 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."

[0104] In today's labor market, it is difficult for individual job seekers to make career choices that align with their aptitudes. Furthermore, there is a lack of effective means for job seekers to practice for interviews, understand their strengths and weaknesses, and efficiently advance their future career development. Therefore, there is a need for a system that provides more appropriate feedback and enables job seekers to grow autonomously.

[0105] 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.

[0106] In this invention, the server includes means for receiving and authenticating user authentication information; means for receiving user voice and video data in real time; means for analyzing the received voice data and converting it into text data; means for analyzing the received video data and acquiring nonverbal communication information; means for evaluating the user's responses based on the analysis results and calculating a score; means for providing feedback based on the evaluation results in real time; means for saving the user's results and making industry and career suggestions; and means for conducting mock interviews with the user using a robot to support career development. As a result, job seekers can receive evaluations and feedback based on their individual characteristics, enabling more effective self-improvement and suitable occupational choices in career development.

[0107] "User authentication information" refers to unique identification information provided by a user to obtain permission to access the system.

[0108] "Audio and video data" refers to information that records the user's speech and physical movements, and is the basis for understanding, including nonverbal communication, through its analysis.

[0109] "Receiving in real time" means acquiring information for processing or analysis without delay the moment it is generated.

[0110] "Converting to text data" is the process of changing audio information into the form of characters or sentences, making it easier to analyze and search.

[0111] "Nonverbal communication information" refers to elements of communication obtained through nonverbal cues such as facial expressions, posture, and eye contact.

[0112] Providing feedback means evaluating and suggesting areas for improvement in the user's actions and responses, and returning information that can be used for future improvements.

[0113] "Supporting career development" means helping users find the right direction in their career choices and skill development, and assisting them in their growth.

[0114] A "robot" refers to a machine or device that collects information and provides feedback through interaction with users or mock interviews.

[0115] This invention is a system that effectively supports users in their career development through mock interviews. As an embodiment, the system is implemented as an application mounted on a consumer robot. This system is constructed as follows:

[0116] First, the user logs into the system via a robot. This uses biometric authentication methods such as voice recognition or facial recognition. Once authentication is successful, the robot's camera and microphone activate, capturing the user's voice and video data in real time. This data is then transmitted to the server via the user's device.

[0117] The server uses the Google Cloud Speech-to-Text API to convert audio data into text and analyzes the text data using the Hugging Face Transformers library. Additionally, OpenCV is used to analyze facial expressions, gaze, and posture in video data to obtain nonverbal communication information.

[0118] The analysis results evaluate the user's responses and provide real-time feedback to the user. For example, the robot points out ambiguities in the user's answers and advises them to be more specific. The server also suggests career paths to the user based on the collected data. To do this, the server uses a specific algorithm to evaluate occupational aptitude.

[0119] For example, if a user expresses interest in a sales position, the robot might ask a question such as, "Please tell me about your past successful experiences as a team leader." After the user responds, the system analyzes the content and, if necessary, provides feedback such as, "Providing specific numbers will make your response more persuasive." The system also suggests skill sets suitable for a sales position.

[0120] An example of a prompt for a generative AI model is: "Start a mock interview to prepare for your interview. Ask the hypothetical questions and generate specific advice for improvement based on the user's answers." This prompt instructs the generative AI model, which is responsible for natural language processing, to generate feedback for the user.

[0121] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0122] Step 1:

[0123] Users log in to the system via a robot using voice or facial recognition. Voice or image data is input, and authentication is performed based on a biometric authentication algorithm. Upon successful authentication, access is granted.

[0124] Step 2:

[0125] The user terminal activates the robot's camera and microphone, capturing the user's voice and video data in real time. The captured voice and video data are sent to the server as input. This data serves as foundational data for analyzing the user's actions and statements.

[0126] Step 3:

[0127] The server uses the Google Cloud Speech-to-Text API to convert audio data into text data. In this step, the audio waveform is input, converted into text as a string by speech recognition technology, and becomes output data for analysis.

[0128] Step 4:

[0129] The server uses the Hugging Face Transformers library to process text data using natural language processing and analyze the logic and meaning of user statements. Text data is input, and information regarding relevance and logic is output based on analysis using natural language processing technology.

[0130] Step 5:

[0131] The server uses OpenCV to analyze video data and evaluate the user's facial expressions, gaze, and posture. Video data is input, and based on image processing technology, facial expression analysis and posture estimation are performed, and evaluation information based on these is output.

[0132] Step 6:

[0133] The server comprehensively evaluates the user's responses based on the analysis results and calculates a score. Here, the text analysis results and video analysis results are input, and an evaluation algorithm calculates an overall performance score, which is then output.

[0134] Step 7:

[0135] The server provides real-time feedback based on the calculated evaluation results. This feedback is output to the user's terminal and communicated to the user via screen or audio. The feedback includes specific areas for improvement and advice.

[0136] Step 8:

[0137] The server makes industry and career suggestions based on the user's analysis results. The analysis results are input, an algorithm is used to analyze the user's aptitude, and the results are output in the form of optimal industry and job type suggestions. These suggestions are used to help the user in their long-term career development.

[0138] 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.

[0139] To implement this invention, the user must first log in to an online platform and enter their authentication information. The server verifies this information and, after granting the user access, retrieves the evaluation criteria for the company or university selected by the user.

[0140] When a user begins a mock interview, their device activates its camera and microphone, sending audio and video data to the server in real time. The server converts the received audio data into text using speech recognition technology and analyzes it using natural language processing technology. Here, the content of the text and the logical structure of the utterances are evaluated.

[0141] The server uses video analysis technology to detect the user's facial expressions, gaze, and posture from the received video data and evaluates them as nonverbal communication information.

[0142] A notable feature is that the server further uses an emotion engine to infer the user's emotional state from the received video data. This emotion recognition identifies basic emotions such as joy, anger, and surprise based on changes in the user's facial expressions and voice.

[0143] Taking all these factors into consideration, the server quantifies the user's performance in the mock interview and generates real-time feedback. Importantly, this feedback is customized based on data obtained through emotion recognition. For example, if the user shows signs of anxiety, the server may offer specific advice such as, "Try to relax and answer the questions."

[0144] Furthermore, the server accumulates these analysis results and makes industry and career path suggestions to understand the user's strengths and weaknesses. Sentimental data is also used in these suggestions, allowing the server to recommend areas where the user is more interested and enjoys to act.

[0145] Specifically, for example, if a user is interested in a sales position, and the system detects that they smile frequently, it can provide positive feedback such as, "It appears you are good at building relationships with customers in a sales role."

[0146] In this way, this system enables more effective and personalized interview training through a comprehensive evaluation that includes the user's emotions.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] The user accesses the online platform, enters and submits their login credentials. The server receives this information, compares it against the database, and performs authentication.

[0150] Step 2:

[0151] If authentication is successful, the server retrieves evaluation criteria corresponding to the company or university selected by the user from the database and prepares the interview.

[0152] Step 3:

[0153] When a user clicks the button to start a mock interview, their device activates its camera and microphone and begins capturing the user's voice and video in real time.

[0154] Step 4:

[0155] The device streams the captured audio and video data to the server in real time. The server receives this data.

[0156] Step 5:

[0157] The server analyzes the received audio data using speech recognition software and converts it into text data. This text is then further analyzed using natural language processing techniques to evaluate its logic and the relevance of its content.

[0158] Step 6:

[0159] The server processes the video data using video analysis technology, capturing the user's facial expressions, gaze, and posture to obtain nonverbal communication information.

[0160] Step 7:

[0161] The server's emotion engine identifies the user's emotions from video and audio data and determines their emotional state, such as joy or anxiety.

[0162] Step 8:

[0163] The server integrates data obtained from natural language processing, video analysis, and emotion recognition to numerically evaluate the user's overall interview performance.

[0164] Step 9:

[0165] The server generates real-time feedback based on the evaluation results, incorporating advice tailored to the user's emotional state into the feedback.

[0166] Step 10:

[0167] The server sends the generated feedback to the terminal, which then displays it on the screen to communicate it to the user.

[0168] Step 11:

[0169] The server stores the user's interview analysis results and uses algorithms to generate industry and career path suggestions, preparing them to be displayed to the user.

[0170] (Example 2)

[0171] 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 as the "terminal".

[0172] Despite advancements in information technology, there is a lack of features that allow users to receive real-time feedback and individualized evaluation during mock interviews. Conventional mock interview systems struggle to provide feedback that takes emotional states into account, failing to fully utilize users' emotions and nonverbal communication, resulting in limited training effectiveness.

[0173] 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.

[0174] In this invention, the server includes means for authenticating the user to access information resources, means for receiving the user's voice and video information in real time, and means for inferring the user's emotional state using emotion recognition technology. This enables the user to receive personalized feedback that takes emotions into account in real time.

[0175] "Authentication for users to access information resources" refers to the process of verifying that a user logs into a system and has legitimate credentials.

[0176] "Audio and video information" refers to audio data generated by the user through their device and video data captured by the camera during a mock interview.

[0177] "Receiving in real time" means that audio and video information is sent to the server as soon as it is generated and processed without delay.

[0178] "Using emotion recognition technology to infer a user's emotional state" is a process that analyzes the characteristics of audio and video to identify the user's current emotions (joy, surprise, anxiety, etc.).

[0179] "Personalized feedback" refers to providing advice and suggestions in real time that are tailored to the user's characteristics and emotional state.

[0180] "Nonverbal information" refers to information conveyed through means other than voice or text, and specifically includes aspects of communication such as facial expressions, eye contact, and posture.

[0181] This system is designed to allow users to conduct mock interviews and receive real-time feedback. Several key hardware and software technologies are used to implement the invention.

[0182] The user accesses the online platform using their device and enters their authentication information. Upon successful authentication, the user can begin the mock interview. As the mock interview begins, the device activates its built-in camera and microphone and starts capturing audio and video information. This information is encoded in real time and sent to the server via the appropriate streaming protocol.

[0183] The server uses speech recognition technology, such as Google Cloud Speech-to-Text, to convert received audio data into text data. It also uses natural language processing (NLP) techniques to analyze the content and logical structure of this text data, gaining deeper insights. For example, it can analyze pitch and tone patterns from the audio data to evaluate the user's speaking style.

[0184] Furthermore, the server analyzes video data using video processing tools such as OpenCV and Dlib to extract non-verbal information such as the user's facial expressions, gaze, and posture. Emotion recognition technology infers emotions from the user's facial expressions and voice, and generates sophisticated feedback based on that.

[0185] Feedback is provided to the user in real time, and if an anxious expression is detected, specific advice such as "Try to answer while relaxed" is given. Furthermore, a score is calculated based on the user's interview performance, and career path suggestions are made.

[0186] For example, if a user is interested in a sales position, and the system detects that they smile frequently, it can provide feedback such as, "You appear to be skilled at building relationships with customers in a sales role." This system helps users identify their skills and strengths, supporting them in making the most suitable career choices.

[0187] An example of a prompt is, "I want to start preparing for a mock interview and identify my strengths in a sales role." Based on this, the generating AI model will provide advice tailored to the user.

[0188] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0189] Step 1:

[0190] The user accesses the online platform on their device and enters their authentication credentials. The device sends these credentials to the server. The server verifies the entered information against its database to confirm legitimate access. The input consists of a username and password, and the output indicates whether authentication was successful or unsuccessful. This step grants the user permission to proceed to the next step.

[0191] Step 2:

[0192] Upon successful authentication, the device displays an interface prompting the user to begin a mock interview. Once the user starts the interview, the device activates its camera and microphone. It captures audio and video in real time and sends it to the server. The input is audio and video data, and the output is an encoded multimedia stream.

[0193] Step 3:

[0194] The server inputs the received audio data into the speech recognition engine and converts it into text data. Here, the waveform data extracted from the audio is converted into features, and the spoken content is output as a string. The input is audio data, and the output is text data.

[0195] Step 4:

[0196] The server analyzes the converted text data using natural language processing techniques. During this process, it analyzes the grammatical structure and vocabulary of the text, and evaluates the logic and consistency of the utterances. Furthermore, it sends the text data to a generative AI model for further analysis by the AI. The input is text data, and the output is the evaluation result of the utterance content.

[0197] Step 5:

[0198] The server inputs video data into a video analysis engine to evaluate the user's facial expressions, gaze, and posture. It extracts frames from the video and applies face recognition and posture estimation algorithms. The input is video data, and the output is non-verbal information.

[0199] Step 6:

[0200] The server uses emotion recognition capabilities to infer the user's emotional state from audio and video. Specifically, it analyzes the tone of voice and changes in facial expressions in the video to identify what emotions the user is experiencing. The input is audio and video data, and the output is the emotion recognition result.

[0201] Step 7:

[0202] The server comprehensively evaluates and scores the user's mock interview performance based on accumulated data. This involves integrating the results of voice analysis, video analysis, and emotion recognition to generate a numerical score. Inputs include text evaluation, nonverbal information, and emotion data, while output is the score.

[0203] Step 8:

[0204] The server generates feedback based on the user's emotional state and mock interview score, and sends it to the terminal in real time. For example, if the user appears anxious, advice such as "Try to relax and answer the questions" will be displayed. The input is the score and emotional data, and the output is the feedback message.

[0205] (Application Example 2)

[0206] 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".

[0207] In modern job hunting, there is a need to provide mock interview opportunities that closely resemble actual interviews, thereby supporting the improvement of individual interview performance. In particular, providing a system that can be easily used in a home environment and that offers diverse feedback is a key challenge.

[0208] 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.

[0209] In this invention, the server includes means for receiving and authenticating user authentication information, means for receiving user audio and video data in real time, means for analyzing the received audio data and converting it into text data, and means for using an application installed on a home support robot to advance a simulated scenario. This enables the provision of real-time and personalized feedback during simulated interviews in a home environment, thereby improving interview skills in job hunting.

[0210] "User authentication information" refers to the information necessary to identify a user and the data used to grant legitimate access to the system.

[0211] "Audio and video data" refers to digital data used to record and analyze user speech and actions in real time.

[0212] "Converting to text data" refers to the process of converting audio data into text using speech recognition technology.

[0213] "Non-verbal communication information" refers to information expressed through means other than words, such as a user's facial expressions, gaze, and posture.

[0214] "Calculating a score" means evaluating the analyzed user responses and expressing them as a quantitative score.

[0215] "Providing information in real time" means transmitting information without delay by providing immediate feedback during the user's activity.

[0216] "Industry and job suggestions" is a process that provides users with suitable industry and job options based on their results.

[0217] A "home support robot" is a robot designed to assist users in their daily lives within the home and provide various forms of support.

[0218] "Proceeding through a simulated scenario" refers to the process of providing users with a hypothetical scenario that closely resembles a real-world situation and engaging in interaction with it.

[0219] The system for realizing this invention is first implemented in which a user uses a home-use support robot at home to conduct a mock interview. When a user requests a mock interview, the robot begins to acquire the user's voice and video in real time using a high-resolution camera and microphone. The user's authentication information is registered in the system in advance, and access is granted through the login process.

[0220] The server uses the Google Cloud Speech-to-Text API to convert user speech into text data. It also analyzes video data using the OpenCV library to evaluate the user's facial expressions, gaze, and posture, and obtains nonverbal communication information based on the results. Furthermore, it uses NLTK for natural language processing to analyze the content of the user's speech. Throughout this process, the server performs evaluations in real time based on the analyzed data and calculates a score.

[0221] Based on the resulting evaluation, users are provided with appropriate feedback in real time. Sentiment analysis is performed using the Affectiva SDK, and the user's emotional state is reflected in the feedback. For example, if the user is feeling tense, supportive comments such as "Relax and continue" will be provided.

[0222] The system saves the results of the user's mock interviews and later suggests suitable industries and job roles. This allows the user to find direction for further improving their skills in their job search.

[0223] For example, if a user aspiring to a sales position displays many smiles, the system might provide feedback such as, "You have an aptitude for building customer relationships within a sales role."

[0224] Example prompt: "If a user aspiring to a sales position smiles frequently, what kind of feedback would be appropriate?"

[0225] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0226] Step 1:

[0227] The user logs into the home assistance robot.

[0228] Input: User authentication information.

[0229] Process: The robot sends authentication information to the server to verify the user's identity.

[0230] Output: Authentication complete, and the user can now access the system.

[0231] Step 2:

[0232] The mock interview begins, and the robot activates its camera and microphone.

[0233] Input: User's instruction to start a mock interview.

[0234] Processing: The device activates the camera and microphone and begins acquiring audio and video data.

[0235] Output: Audio and video data are transmitted to the server in real time.

[0236] Step 3:

[0237] The server converts the audio data into text data.

[0238] Input: User voice data received in real time.

[0239] Processing: The server uses the Google Cloud Speech-to-Text API to convert the audio data into text.

[0240] Output: Text data is generated and sent to the next processing step.

[0241] Step 4:

[0242] The server analyzes the video data and extracts nonverbal communication information.

[0243] Input: User video data received in real time.

[0244] Processing: The server uses OpenCV to analyze the video data and evaluate facial expressions, gaze, and posture.

[0245] Output: Nonverbal communication information is extracted.

[0246] Step 5:

[0247] The server evaluates the user's response based on the analysis results.

[0248] Input: Text data and nonverbal communication information.

[0249] Processing: The server uses natural language processing and evaluation algorithms to quantify the user's responses.

[0250] Output: Scores and ratings for the user's responses are generated.

[0251] Step 6:

[0252] The server provides real-time feedback.

[0253] Input: User scores, ratings, and sentiment information.

[0254] Processing: The server analyzes emotions using the Affectiva SDK and customizes the feedback content.

[0255] Output: Real-time feedback is provided to the user.

[0256] Step 7:

[0257] The server stores the user's interview results and makes industry and job-related suggestions.

[0258] Input: User scores and rating data.

[0259] Processing: The server stores the collected data, analyzes trends, and suggests suitable career paths to the user.

[0260] Output: Industry and job suggestions are generated and presented to the user.

[0261] 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.

[0262] 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.

[0263] 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.

[0264] [Second Embodiment]

[0265] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0266] 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.

[0267] 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).

[0268] 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.

[0269] 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.

[0270] 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).

[0271] 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.

[0272] 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.

[0273] 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.

[0274] 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.

[0275] 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.

[0276] 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".

[0277] To implement this invention, the user must first log in to the system. By accessing the portal site and entering authentication information, the server verifies and authenticates the user. This authentication allows the evaluation criteria of the company or university selected by the user to be retrieved from the database.

[0278] When a user begins a mock interview, their device activates its camera and microphone, capturing the user's audio and video in real time. The captured data is streamed from the user's device to the server.

[0279] The server converts the received voice data into text data using voice recognition technology. This text data is further analyzed using natural language processing technology to evaluate logic and content relevance. At the same time, video data is analyzed to evaluate the user's expression, gaze, and posture, and extract non-verbal communication information.

[0280] These analysis results are used to comprehensively evaluate the user's performance and are scored by the server. The evaluation results are feedback to the user in real-time and displayed on the screen. The user can grasp their strengths and weaknesses based on this feedback and use it for improvement.

[0281] In addition, the server analyzes this information using an algorithm to propose suitable industries and career paths based on the user's analysis results. This result is provided to the user to support future career choices.

[0282] As a specific example, during a user's interview practice, an appropriateness evaluation is also conducted, such as whether the content of the answer matches the image of the talent required by the company. If there are ambiguous or lacking parts in the user's answer, feedback such as "Make your answer more specific" is provided from the server.

[0283] With this system, the user can more effectively improve themselves through simulated interviews and hone the skills required by the industry and companies.

[0284] The following explains the processing flow.

[0285] Step 1:

[0286] The user accesses the online platform and enters authentication information on the login screen. Account authentication is performed based on the user's input.

[0287] <� Step 2:

[0288] The server verifies the user's authentication, and if successful, retrieves evaluation criteria data for the company or university selected by the user from the database.

[0289] Step 3:

[0290] When the user initiates the mock interview, the device activates the user's camera and microphone and begins capturing the user's video and audio data in real time.

[0291] Step 4:

[0292] The terminal streams the captured video and audio data to the server in real time. The server receives this data.

[0293] Step 5:

[0294] The server converts the received audio data into text data using speech recognition technology. The text is then analyzed using natural language processing technology to evaluate the logic and relevance of its content.

[0295] Step 6:

[0296] The server analyzes the video data and extracts and evaluates nonverbal communication information such as the user's facial expressions, gaze, and posture.

[0297] Step 7:

[0298] The server comprehensively evaluates the data obtained from audio and video analysis and scores the user's mock interview performance.

[0299] Step 8:

[0300] The server generates real-time feedback for the user based on the evaluation results and immediately provides it to the user via the terminal.

[0301] Step 9:

[0302] The server analyzes suitable industries and careers based on the user's evaluation results and generates its proposal through an algorithm.

[0303] Step 10:

[0304] The server provides the proposal result to the user through the terminal so that the user can utilize it when making their career choice.

[0305] (Example 1)

[0306] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0307] In modern job hunting activities and promotion examinations, job seekers and employees are required to accurately understand and improve their own abilities. However, in conventional mock interviews and evaluation processes, it is difficult to obtain efficient and objective feedback in real time. Therefore, the development of a system to support the improvement of user abilities is required.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0309] In this invention, the server includes means for receiving and authenticating the user's authentication information, means for receiving the user's voice and video data in real time, means for analyzing the received voice data and converting it into text data, means for analyzing the received video data and obtaining non-verbal communication information, means for evaluating the user's answer based on the analysis result and calculating a score, means for providing feedback based on the evaluation result in real time, and means for generating a prompt using a generative AI model and providing individual advice to the user. Thereby, it becomes possible to effectively and immediately evaluate the user's ability and provide an individually optimized improvement plan.

[0310] "Authentication information" refers to information used to verify a user's identity, and typically includes a username and password.

[0311] "Voice data" refers to data that is recorded in digital format from the voice spoken by the user and used for analysis.

[0312] "Video data" refers to digital data that includes visual information such as the user's movements and facial expressions captured by a camera.

[0313] "Means of converting to text data" refers to a processing system that uses speech recognition technology to convert audio data into text format.

[0314] "Nonverbal communication information" refers to communication elements conveyed through means other than words, such as facial expressions, posture, and eye contact.

[0315] "Analysis results" refer to the results of an analysis of data regarding user characteristics and abilities obtained through the processing of audio and video data.

[0316] "Feedback based on evaluation results" refers to advice and suggestions given to users based on analysis results, and is information intended to encourage self-improvement.

[0317] "Suitable job areas and career paths" refers to the analysis results indicating the industry and career path that best suits the user's abilities and characteristics.

[0318] "Generating prompts using a generative AI model" and providing them to the user refers to using AI technology to dynamically create instructions or questions based on specific conditions.

[0319] "Individualized advice" refers to specialized improvement suggestions and guidance based on the user's unique evaluation results.

[0320] The following describes embodiments for carrying out the invention.

[0321] In this system, users first access a portal site and log in by entering their authentication information. The server receives this authentication information and authenticates the user by comparing it with the database. In particular, the hardware used for this process would likely include a web server and an authentication protocol such as HTTPS.

[0322] After authentication, when the user begins a mock interview, the user's device activates its camera and microphone to capture audio and video in real time. Typical personal computers and smartphones are used as the hardware for this process.

[0323] The captured data is streamed from the user's terminal to the server, where speech recognition technology is applied to the received audio data. Speech recognition software such as the Google Speech-to-Text API is used here. The audio data is converted to text data, and the server further analyzes the content using natural language processing techniques. Libraries such as Python's NLTK and spaCy are utilized in this process.

[0324] The server uses OpenCV to analyze the video data and evaluate the user's facial expressions, gaze, and posture. This allows for the extraction of nonverbal communication information.

[0325] The server evaluates the user's performance based on these analysis results and generates prompts using a generative AI model. Through these prompts, it provides personalized advice to the user. The evaluation results and feedback are displayed on the user's terminal, allowing the user to identify areas for improvement.

[0326] For example, the server generates a prompt message such as, "Please tell me the procedure for analyzing the evaluation criteria of a user's mock interview using a generative AI model," and presents it to the user.

[0327] In this way, through this system, users can receive more detailed and accurate feedback, which helps them to improve their skills. Furthermore, the server uses the analysis results to suggest suitable industries and career paths, supporting the user's career choices.

[0328] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0329] Step 1:

[0330] The user accesses the portal site and enters their username and password as authentication information on the login screen. The server receives the entered authentication information and authenticates the user by comparing it with the information stored in the database. If successful, the server can retrieve evaluation criteria data for companies and universities based on the user's permissions.

[0331] Step 2:

[0332] When a user begins a mock interview, they click the start button on the device. The device activates the camera and microphone and captures the user's audio and video in real time. The device compresses the captured data and streams it to the server. The input audio and video data is sent to the server and forms the basis for the next processing step.

[0333] Step 3:

[0334] The server converts the received audio data into text using the Google Speech-to-Text API. This conversion outputs the text information obtained from the audio data as text data to be analyzed. Specifically, the content spoken by the user is extracted as text information.

[0335] Step 4:

[0336] The server analyzes text data using natural language processing techniques. Python's NLTK and spaCy are used to evaluate the logic and relevance of the user's statements. Based on the input text data, the analyzed data is output, and this analysis result serves as the basis for the evaluation.

[0337] Step 5:

[0338] The server analyzes the received video data using OpenCV to evaluate the user's physical characteristics such as facial expressions, gaze, and posture. Nonverbal communication information is extracted based on the input video data, and this information is added to the evaluation results.

[0339] Step 6:

[0340] The server integrates the audio and video analysis results and uses a generative AI model to evaluate the user's mock interview performance. Based on this, it calculates a score, generates prompts, and creates personalized advice. The calculated evaluation score and generated advice are output.

[0341] Step 7:

[0342] The server sends the generated evaluation score and advice to the user's terminal. The user can immediately see this feedback on the terminal screen and understand what areas need improvement. Suggestions for suitable industries and career paths are also displayed simultaneously, supporting the user in their future career choices.

[0343] (Application Example 1)

[0344] 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."

[0345] In today's labor market, it is difficult for individual job seekers to make career choices that align with their aptitudes. Furthermore, there is a lack of effective means for job seekers to practice for interviews, understand their strengths and weaknesses, and efficiently advance their future career development. Therefore, there is a need for a system that provides more appropriate feedback and enables job seekers to grow autonomously.

[0346] 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.

[0347] In this invention, the server includes means for receiving and authenticating user authentication information; means for receiving user voice and video data in real time; means for analyzing the received voice data and converting it into text data; means for analyzing the received video data and acquiring nonverbal communication information; means for evaluating the user's responses based on the analysis results and calculating a score; means for providing feedback based on the evaluation results in real time; means for saving the user's results and making industry and career suggestions; and means for conducting mock interviews with the user using a robot to support career development. As a result, job seekers can receive evaluations and feedback based on their individual characteristics, enabling more effective self-improvement and suitable occupational choices in career development.

[0348] "User authentication information" refers to unique identification information provided by a user to obtain permission to access the system.

[0349] "Audio and video data" refers to information that records the user's speech and physical movements, and is the basis for understanding, including nonverbal communication, through its analysis.

[0350] "Receiving in real time" means acquiring information for processing or analysis without delay the moment it is generated.

[0351] "Converting to text data" is the process of changing audio information into the form of characters or sentences, making it easier to analyze and search.

[0352] "Nonverbal communication information" refers to elements of communication obtained through nonverbal cues such as facial expressions, posture, and eye contact.

[0353] Providing feedback means evaluating and suggesting areas for improvement in the user's actions and responses, and returning information that can be used for future improvements.

[0354] "Supporting career development" means helping users find the right direction in their career choices and skill development, and assisting them in their growth.

[0355] A "robot" refers to a machine or device that collects information and provides feedback through interaction with users or mock interviews.

[0356] This invention is a system that effectively supports users in their career development through mock interviews. As an embodiment, the system is implemented as an application mounted on a consumer robot. This system is constructed as follows:

[0357] First, the user logs into the system via a robot. This uses biometric authentication methods such as voice recognition or facial recognition. Once authentication is successful, the robot's camera and microphone activate, capturing the user's voice and video data in real time. This data is then transmitted to the server via the user's device.

[0358] The server uses the Google Cloud Speech-to-Text API to convert audio data into text and analyzes the text data using the Hugging Face Transformers library. Additionally, OpenCV is used to analyze facial expressions, gaze, and posture in video data to obtain nonverbal communication information.

[0359] The analysis results evaluate the user's responses and provide real-time feedback to the user. For example, the robot points out ambiguities in the user's answers and advises them to be more specific. The server also suggests career paths to the user based on the collected data. To do this, the server uses a specific algorithm to evaluate occupational aptitude.

[0360] For example, if a user expresses interest in a sales position, the robot might ask a question such as, "Please tell me about your past successful experiences as a team leader." After the user responds, the system analyzes the content and, if necessary, provides feedback such as, "Providing specific numbers will make your response more persuasive." The system also suggests skill sets suitable for a sales position.

[0361] An example of a prompt for a generative AI model is: "Start a mock interview to prepare for your interview. Ask the hypothetical questions and generate specific advice for improvement based on the user's answers." This prompt instructs the generative AI model, which is responsible for natural language processing, to generate feedback for the user.

[0362] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0363] Step 1:

[0364] Users log in to the system via a robot using voice or facial recognition. Voice or image data is input, and authentication is performed based on a biometric authentication algorithm. Upon successful authentication, access is granted.

[0365] Step 2:

[0366] The user terminal activates the robot's camera and microphone, capturing the user's voice and video data in real time. The captured voice and video data are sent to the server as input. This data serves as foundational data for analyzing the user's actions and statements.

[0367] Step 3:

[0368] The server uses the Google Cloud Speech-to-Text API to convert audio data into text data. In this step, the audio waveform is input, converted into text as a string by speech recognition technology, and becomes output data for analysis.

[0369] Step 4:

[0370] The server uses the Hugging Face Transformers library to process text data using natural language processing and analyze the logic and meaning of user statements. Text data is input, and information regarding relevance and logic is output based on analysis using natural language processing technology.

[0371] Step 5:

[0372] The server uses OpenCV to analyze video data and evaluate the user's facial expressions, gaze, and posture. Video data is input, and based on image processing technology, facial expression analysis and posture estimation are performed, and evaluation information based on these is output.

[0373] Step 6:

[0374] The server comprehensively evaluates the user's responses based on the analysis results and calculates a score. Here, the text analysis results and video analysis results are input, and an evaluation algorithm calculates an overall performance score, which is then output.

[0375] Step 7:

[0376] The server provides real-time feedback based on the calculated evaluation results. This feedback is output to the user's terminal and communicated to the user via screen or audio. The feedback includes specific areas for improvement and advice.

[0377] Step 8:

[0378] The server makes industry and career suggestions based on the user's analysis results. The analysis results are input, an algorithm is used to analyze the user's aptitude, and the results are output in the form of optimal industry and job type suggestions. These suggestions are used to help the user in their long-term career development.

[0379] 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.

[0380] To implement this invention, the user must first log in to an online platform and enter their authentication information. The server verifies this information and, after granting the user access, retrieves the evaluation criteria for the company or university selected by the user.

[0381] When a user begins a mock interview, their device activates its camera and microphone, sending audio and video data to the server in real time. The server converts the received audio data into text using speech recognition technology and analyzes it using natural language processing technology. Here, the content of the text and the logical structure of the utterances are evaluated.

[0382] The server uses video analysis technology to detect the user's facial expressions, gaze, and posture from the received video data and evaluates them as nonverbal communication information.

[0383] A notable feature is that the server further uses an emotion engine to infer the user's emotional state from the received video data. This emotion recognition identifies basic emotions such as joy, anger, and surprise based on changes in the user's facial expressions and voice.

[0384] Taking all these factors into consideration, the server quantifies the user's performance in the mock interview and generates real-time feedback. Importantly, this feedback is customized based on data obtained through emotion recognition. For example, if the user shows signs of anxiety, the server may offer specific advice such as, "Try to relax and answer the questions."

[0385] Furthermore, the server accumulates these analysis results and makes industry and career path suggestions to understand the user's strengths and weaknesses. Sentimental data is also used in these suggestions, allowing the server to recommend areas where the user is more interested and enjoys to act.

[0386] Specifically, for example, if a user is interested in a sales position, and the system detects that they smile frequently, it can provide positive feedback such as, "It appears you are good at building relationships with customers in a sales role."

[0387] In this way, this system enables more effective and personalized interview training through a comprehensive evaluation that includes the user's emotions.

[0388] The following describes the processing flow.

[0389] Step 1:

[0390] The user accesses the online platform, enters and submits their login credentials. The server receives this information, compares it against the database, and performs authentication.

[0391] Step 2:

[0392] If authentication is successful, the server retrieves evaluation criteria corresponding to the company or university selected by the user from the database and prepares the interview.

[0393] Step 3:

[0394] When a user clicks the button to start a mock interview, their device activates its camera and microphone and begins capturing the user's voice and video in real time.

[0395] Step 4:

[0396] The device streams the captured audio and video data to the server in real time. The server receives this data.

[0397] Step 5:

[0398] The server analyzes the received audio data using speech recognition software and converts it into text data. This text is then further analyzed using natural language processing techniques to evaluate its logic and the relevance of its content.

[0399] Step 6:

[0400] The server processes the video data using video analysis technology, capturing the user's facial expressions, gaze, and posture to obtain nonverbal communication information.

[0401] Step 7:

[0402] The server's emotion engine identifies the user's emotions from video and audio data and determines their emotional state, such as joy or anxiety.

[0403] Step 8:

[0404] The server integrates data obtained from natural language processing, video analysis, and emotion recognition to numerically evaluate the user's overall interview performance.

[0405] Step 9:

[0406] The server generates real-time feedback based on the evaluation results, incorporating advice tailored to the user's emotional state into the feedback.

[0407] Step 10:

[0408] The server sends the generated feedback to the terminal, which then displays it on the screen to communicate it to the user.

[0409] Step 11:

[0410] The server stores the user's interview analysis results and uses algorithms to generate industry and career path suggestions, preparing them to be displayed to the user.

[0411] (Example 2)

[0412] 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".

[0413] Despite advancements in information technology, there is a lack of features that allow users to receive real-time feedback and individualized evaluation during mock interviews. Conventional mock interview systems struggle to provide feedback that takes emotional states into account, failing to fully utilize users' emotions and nonverbal communication, resulting in limited training effectiveness.

[0414] 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.

[0415] In this invention, the server includes means for authenticating the user to access information resources, means for receiving the user's voice and video information in real time, and means for inferring the user's emotional state using emotion recognition technology. This enables the user to receive personalized feedback that takes emotions into account in real time.

[0416] "Authentication for users to access information resources" refers to the process of verifying that a user logs into a system and has legitimate credentials.

[0417] "Audio and video information" refers to audio data generated by the user through their device and video data captured by the camera during a mock interview.

[0418] "Receiving in real time" means that audio and video information is sent to the server as soon as it is generated and processed without delay.

[0419] "Using emotion recognition technology to infer a user's emotional state" is a process that analyzes the characteristics of audio and video to identify the user's current emotions (joy, surprise, anxiety, etc.).

[0420] "Personalized feedback" refers to providing advice and suggestions in real time that are tailored to the user's characteristics and emotional state.

[0421] "Nonverbal information" refers to information conveyed through means other than voice or text, and specifically includes aspects of communication such as facial expressions, eye contact, and posture.

[0422] This system is designed to allow users to conduct mock interviews and receive real-time feedback. Several key hardware and software technologies are used to implement the invention.

[0423] The user accesses the online platform using their device and enters their authentication information. Upon successful authentication, the user can begin the mock interview. As the mock interview begins, the device activates its built-in camera and microphone and starts capturing audio and video information. This information is encoded in real time and sent to the server via the appropriate streaming protocol.

[0424] The server uses speech recognition technology, such as Google Cloud Speech-to-Text, to convert received audio data into text data. It also uses natural language processing (NLP) techniques to analyze the content and logical structure of this text data, gaining deeper insights. For example, it can analyze pitch and tone patterns from the audio data to evaluate the user's speaking style.

[0425] Furthermore, the server analyzes video data using video processing tools such as OpenCV and Dlib to extract non-verbal information such as the user's facial expressions, gaze, and posture. Emotion recognition technology infers emotions from the user's facial expressions and voice, and generates sophisticated feedback based on that.

[0426] Feedback is provided to the user in real time, and if an anxious expression is detected, specific advice such as "Try to answer while relaxed" is given. Furthermore, a score is calculated based on the user's interview performance, and career path suggestions are made.

[0427] For example, if a user is interested in a sales position, and the system detects that they smile frequently, it can provide feedback such as, "You appear to be skilled at building relationships with customers in a sales role." This system helps users identify their skills and strengths, supporting them in making the most suitable career choices.

[0428] An example of a prompt is, "I want to start preparing for a mock interview and identify my strengths in a sales role." Based on this, the generating AI model will provide advice tailored to the user.

[0429] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0430] Step 1:

[0431] The user accesses the online platform on their device and enters their authentication credentials. The device sends these credentials to the server. The server verifies the entered information against its database to confirm legitimate access. The input consists of a username and password, and the output indicates whether authentication was successful or unsuccessful. This step grants the user permission to proceed to the next step.

[0432] Step 2:

[0433] Upon successful authentication, the device displays an interface prompting the user to begin a mock interview. Once the user starts the interview, the device activates its camera and microphone. It captures audio and video in real time and sends it to the server. The input is audio and video data, and the output is an encoded multimedia stream.

[0434] Step 3:

[0435] The server inputs the received audio data into the speech recognition engine and converts it into text data. Here, the waveform data extracted from the audio is converted into features, and the spoken content is output as a string. The input is audio data, and the output is text data.

[0436] Step 4:

[0437] The server analyzes the converted text data using natural language processing techniques. During this process, it analyzes the grammatical structure and vocabulary of the text, and evaluates the logic and consistency of the utterances. Furthermore, it sends the text data to a generative AI model for further analysis by the AI. The input is text data, and the output is the evaluation result of the utterance content.

[0438] Step 5:

[0439] The server inputs video data into a video analysis engine to evaluate the user's facial expressions, gaze, and posture. It extracts frames from the video and applies face recognition and posture estimation algorithms. The input is video data, and the output is non-verbal information.

[0440] Step 6:

[0441] The server uses emotion recognition capabilities to infer the user's emotional state from audio and video. Specifically, it analyzes the tone of voice and changes in facial expressions in the video to identify what emotions the user is experiencing. The input is audio and video data, and the output is the emotion recognition result.

[0442] Step 7:

[0443] The server comprehensively evaluates and scores the user's mock interview performance based on accumulated data. This involves integrating the results of voice analysis, video analysis, and emotion recognition to generate a numerical score. Inputs include text evaluation, nonverbal information, and emotion data, while output is the score.

[0444] Step 8:

[0445] The server generates feedback based on the user's emotional state and mock interview score, and sends it to the terminal in real time. For example, if the user appears anxious, advice such as "Try to relax and answer the questions" will be displayed. The input is the score and emotional data, and the output is the feedback message.

[0446] (Application Example 2)

[0447] 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 as the "terminal".

[0448] In modern job hunting, there is a need to provide mock interview opportunities that closely resemble actual interviews, thereby supporting the improvement of individual interview performance. In particular, providing a system that can be easily used in a home environment and that offers diverse feedback is a key challenge.

[0449] 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.

[0450] In this invention, the server includes means for receiving and authenticating user authentication information, means for receiving user audio and video data in real time, means for analyzing the received audio data and converting it into text data, and means for using an application installed on a home support robot to advance a simulated scenario. This enables the provision of real-time and personalized feedback during simulated interviews in a home environment, thereby improving interview skills in job hunting.

[0451] "User authentication information" refers to the information necessary to identify a user and the data used to grant legitimate access to the system.

[0452] "Audio and video data" refers to digital data used to record and analyze user speech and actions in real time.

[0453] "Converting to text data" refers to the process of converting audio data into text using speech recognition technology.

[0454] "Non-verbal communication information" refers to information expressed through means other than words, such as a user's facial expressions, gaze, and posture.

[0455] "Calculating a score" means evaluating the analyzed user responses and expressing them as a quantitative score.

[0456] "Providing information in real time" means transmitting information without delay by providing immediate feedback during the user's activity.

[0457] "Industry and job suggestions" is a process that provides users with suitable industry and job options based on their results.

[0458] A "home support robot" is a robot designed to assist users in their daily lives within the home and provide various forms of support.

[0459] "Proceeding through a simulated scenario" refers to the process of providing users with a hypothetical scenario that closely resembles a real-world situation and engaging in interaction with it.

[0460] The system for realizing this invention is first implemented in which a user uses a home-use support robot at home to conduct a mock interview. When a user requests a mock interview, the robot begins to acquire the user's voice and video in real time using a high-resolution camera and microphone. The user's authentication information is registered in the system in advance, and access is granted through the login process.

[0461] The server uses the Google Cloud Speech-to-Text API to convert user speech into text data. It also analyzes video data using the OpenCV library to evaluate the user's facial expressions, gaze, and posture, and obtains nonverbal communication information based on the results. Furthermore, it uses NLTK for natural language processing to analyze the content of the user's speech. Throughout this process, the server performs evaluations in real time based on the analyzed data and calculates a score.

[0462] Based on the resulting evaluation, users are provided with appropriate feedback in real time. Sentiment analysis is performed using the Affectiva SDK, and the user's emotional state is reflected in the feedback. For example, if the user is feeling tense, supportive comments such as "Relax and continue" will be provided.

[0463] The system saves the results of the user's mock interviews and later suggests suitable industries and job roles. This allows the user to find direction for further improving their skills in their job search.

[0464] For example, if a user aspiring to a sales position displays many smiles, the system might provide feedback such as, "You have an aptitude for building customer relationships within a sales role."

[0465] Example prompt: "If a user aspiring to a sales position smiles frequently, what kind of feedback would be appropriate?"

[0466] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0467] Step 1:

[0468] The user logs into the home assistance robot.

[0469] Input: User authentication information.

[0470] Process: The robot sends authentication information to the server to verify the user's identity.

[0471] Output: Authentication complete, and the user can now access the system.

[0472] Step 2:

[0473] The mock interview begins, and the robot activates its camera and microphone.

[0474] Input: User's instruction to start a mock interview.

[0475] Processing: The device activates the camera and microphone and begins acquiring audio and video data.

[0476] Output: Audio and video data are transmitted to the server in real time.

[0477] Step 3:

[0478] The server converts the audio data into text data.

[0479] Input: User voice data received in real time.

[0480] Processing: The server uses the Google Cloud Speech-to-Text API to convert the audio data into text.

[0481] Output: Text data is generated and sent to the next processing step.

[0482] Step 4:

[0483] The server analyzes the video data and extracts nonverbal communication information.

[0484] Input: User video data received in real time.

[0485] Processing: The server uses OpenCV to analyze the video data and evaluate facial expressions, gaze, and posture.

[0486] Output: Nonverbal communication information is extracted.

[0487] Step 5:

[0488] The server evaluates the user's response based on the analysis results.

[0489] Input: Text data and nonverbal communication information.

[0490] Processing: The server uses natural language processing and evaluation algorithms to quantify the user's responses.

[0491] Output: Scores and ratings for the user's responses are generated.

[0492] Step 6:

[0493] The server provides real-time feedback.

[0494] Input: User scores, ratings, and sentiment information.

[0495] Processing: The server analyzes emotions using the Affectiva SDK and customizes the feedback content.

[0496] Output: Real-time feedback is provided to the user.

[0497] Step 7:

[0498] The server stores the user's interview results and makes industry and job-related suggestions.

[0499] Input: User scores and rating data.

[0500] Processing: The server stores the collected data, analyzes trends, and suggests suitable career paths to the user.

[0501] Output: Industry and job suggestions are generated and presented to the user.

[0502] 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.

[0503] 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.

[0504] 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.

[0505] [Third Embodiment]

[0506] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0507] 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.

[0508] 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).

[0509] 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.

[0510] 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.

[0511] 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).

[0512] 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.

[0513] 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.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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".

[0518] To implement this invention, the user must first log in to the system. By accessing the portal site and entering authentication information, the server verifies and authenticates the user. This authentication allows the evaluation criteria of the company or university selected by the user to be retrieved from the database.

[0519] When a user begins a mock interview, their device activates its camera and microphone, capturing the user's audio and video in real time. The captured data is streamed from the user's device to the server.

[0520] The server converts the received audio data into text data using speech recognition technology. This text data is then analyzed using natural language processing technology to evaluate its logic and the relevance of its content. Simultaneously, video data is analyzed to evaluate the user's facial expressions, gaze, and posture, and nonverbal communication information is extracted.

[0521] These analysis results are used to comprehensively evaluate user performance and are scored by the server. The evaluation results are fed back to the user in real time and displayed on the screen. Based on this feedback, users can understand their strengths and weaknesses and use them to improve.

[0522] Furthermore, the server uses algorithms to analyze the user's analysis results in order to suggest suitable industries and career paths. This information is then provided to the user to support their future career choices.

[0523] As a concrete example, during a user's interview practice, an assessment of their suitability is also conducted to determine whether their answers match the ideal candidate profile sought by the company. If a user's answers are vague or lack specificity, the server provides feedback suggesting they "make their answers more specific."

[0524] This system allows users to more effectively improve themselves through mock interviews and hone the skills required by the industry and companies.

[0525] The following describes the processing flow.

[0526] Step 1:

[0527] The user accesses the online platform and enters their authentication information on the login screen. Account authentication is performed based on the user's input.

[0528] Step 2:

[0529] The server verifies the user's authentication, and if successful, retrieves evaluation criteria data for the company or university selected by the user from the database.

[0530] Step 3:

[0531] When the user initiates the mock interview, the device activates the user's camera and microphone and begins capturing the user's video and audio data in real time.

[0532] Step 4:

[0533] The terminal streams the captured video and audio data to the server in real time. The server receives this data.

[0534] Step 5:

[0535] The server converts the received audio data into text data using speech recognition technology. The text is then analyzed using natural language processing technology to evaluate the logic and relevance of its content.

[0536] Step 6:

[0537] The server analyzes the video data and extracts and evaluates nonverbal communication information such as the user's facial expressions, gaze, and posture.

[0538] Step 7:

[0539] The server comprehensively evaluates the data obtained from audio and video analysis and scores the user's mock interview performance.

[0540] Step 8:

[0541] The server generates real-time feedback for the user based on the evaluation results and immediately provides it to the user via the terminal.

[0542] Step 9:

[0543] The server analyzes suitable industries and career paths based on the user's evaluation results and generates suggestions using an algorithm.

[0544] Step 10:

[0545] The server provides the suggested results to the user via the terminal, allowing the user to use them to help them choose their career path.

[0546] (Example 1)

[0547] 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."

[0548] In modern job hunting and promotion exams, job seekers and employees are required to accurately assess and improve their own abilities. However, traditional mock interviews and evaluation processes make it difficult to obtain efficient and objective feedback in real time. Therefore, there is a need to develop systems that support the improvement of users' abilities.

[0549] 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.

[0550] In this invention, the server includes means for receiving and authenticating user authentication information, means for receiving user voice and video data in real time, means for analyzing the received voice data and converting it into text data, means for analyzing the received video data and obtaining nonverbal communication information, means for evaluating the user's responses based on the analysis results and calculating a score, means for providing feedback based on the evaluation results in real time, and means for generating prompts using a generative AI model and providing individualized advice to the user. This makes it possible to effectively and immediately evaluate the user's abilities and provide individually optimized improvement suggestions.

[0551] "Authentication information" refers to information used to verify a user's identity, and typically includes a username and password.

[0552] "Voice data" refers to data that is recorded in digital format from the voice spoken by the user and used for analysis.

[0553] "Video data" refers to digital data that includes visual information such as the user's movements and facial expressions captured by a camera.

[0554] "Means of converting to text data" refers to a processing system that uses speech recognition technology to convert audio data into text format.

[0555] "Nonverbal communication information" refers to communication elements conveyed through means other than words, such as facial expressions, posture, and eye contact.

[0556] "Analysis results" refer to the results of an analysis of data regarding user characteristics and abilities obtained through the processing of audio and video data.

[0557] "Feedback based on evaluation results" refers to advice and suggestions given to users based on analysis results, and is information intended to encourage self-improvement.

[0558] "Suitable job areas and career paths" refers to the analysis results indicating the industry and career path that best suits the user's abilities and characteristics.

[0559] "Generating prompts using a generative AI model" and providing them to the user refers to using AI technology to dynamically create instructions or questions based on specific conditions.

[0560] "Individualized advice" refers to specialized improvement suggestions and guidance based on the user's unique evaluation results.

[0561] The following describes embodiments for carrying out the invention.

[0562] In this system, users first access a portal site and log in by entering their authentication information. The server receives this authentication information and authenticates the user by comparing it with the database. In particular, the hardware used for this process would likely include a web server and an authentication protocol such as HTTPS.

[0563] After authentication, when the user begins a mock interview, the user's device activates its camera and microphone to capture audio and video in real time. Typical personal computers and smartphones are used as the hardware for this process.

[0564] The captured data is streamed from the user's terminal to the server, where speech recognition technology is applied to the received audio data. Speech recognition software such as the Google Speech-to-Text API is used here. The audio data is converted to text data, and the server further analyzes the content using natural language processing techniques. Libraries such as Python's NLTK and spaCy are utilized in this process.

[0565] The server uses OpenCV to analyze the video data and evaluate the user's facial expressions, gaze, and posture. This allows for the extraction of nonverbal communication information.

[0566] The server evaluates the user's performance based on these analysis results and generates prompts using a generative AI model. Through these prompts, it provides personalized advice to the user. The evaluation results and feedback are displayed on the user's terminal, allowing the user to identify areas for improvement.

[0567] For example, the server generates a prompt message such as, "Please tell me the procedure for analyzing the evaluation criteria of a user's mock interview using a generative AI model," and presents it to the user.

[0568] In this way, through this system, users can receive more detailed and accurate feedback, which helps them to improve their skills. Furthermore, the server uses the analysis results to suggest suitable industries and career paths, supporting the user's career choices.

[0569] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0570] Step 1:

[0571] The user accesses the portal site and enters their username and password as authentication information on the login screen. The server receives the entered authentication information and authenticates the user by comparing it with the information stored in the database. If successful, the server can retrieve evaluation criteria data for companies and universities based on the user's permissions.

[0572] Step 2:

[0573] When a user begins a mock interview, they click the start button on the device. The device activates the camera and microphone and captures the user's audio and video in real time. The device compresses the captured data and streams it to the server. The input audio and video data is sent to the server and forms the basis for the next processing step.

[0574] Step 3:

[0575] The server converts the received audio data into text using the Google Speech-to-Text API. This conversion outputs the text information obtained from the audio data as text data to be analyzed. Specifically, the content spoken by the user is extracted as text information.

[0576] Step 4:

[0577] The server analyzes text data using natural language processing techniques. Python's NLTK and spaCy are used to evaluate the logic and relevance of the user's statements. Based on the input text data, the analyzed data is output, and this analysis result serves as the basis for the evaluation.

[0578] Step 5:

[0579] The server analyzes the received video data using OpenCV to evaluate the user's physical characteristics such as facial expressions, gaze, and posture. Nonverbal communication information is extracted based on the input video data, and this information is added to the evaluation results.

[0580] Step 6:

[0581] The server integrates the audio and video analysis results and uses a generative AI model to evaluate the user's mock interview performance. Based on this, it calculates a score, generates prompts, and creates personalized advice. The calculated evaluation score and generated advice are output.

[0582] Step 7:

[0583] The server sends the generated evaluation score and advice to the user's terminal. The user can immediately see this feedback on the terminal screen and understand what areas need improvement. Suggestions for suitable industries and career paths are also displayed simultaneously, supporting the user in their future career choices.

[0584] (Application Example 1)

[0585] 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."

[0586] In today's labor market, it is difficult for individual job seekers to make career choices that align with their aptitudes. Furthermore, there is a lack of effective means for job seekers to practice for interviews, understand their strengths and weaknesses, and efficiently advance their future career development. Therefore, there is a need for a system that provides more appropriate feedback and enables job seekers to grow autonomously.

[0587] 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.

[0588] In this invention, the server includes means for receiving and authenticating user authentication information; means for receiving user voice and video data in real time; means for analyzing the received voice data and converting it into text data; means for analyzing the received video data and acquiring nonverbal communication information; means for evaluating the user's responses based on the analysis results and calculating a score; means for providing feedback based on the evaluation results in real time; means for saving the user's results and making industry and career suggestions; and means for conducting mock interviews with the user using a robot to support career development. As a result, job seekers can receive evaluations and feedback based on their individual characteristics, enabling more effective self-improvement and suitable occupational choices in career development.

[0589] "User authentication information" refers to unique identification information provided by a user to obtain permission to access the system.

[0590] "Audio and video data" refers to information that records the user's speech and physical movements, and is the basis for understanding, including nonverbal communication, through its analysis.

[0591] "Receiving in real time" means acquiring information for processing or analysis without delay the moment it is generated.

[0592] "Converting to text data" is the process of changing audio information into the form of characters or sentences, making it easier to analyze and search.

[0593] "Nonverbal communication information" refers to elements of communication obtained through nonverbal cues such as facial expressions, posture, and eye contact.

[0594] Providing feedback means evaluating and suggesting areas for improvement in the user's actions and responses, and returning information that can be used for future improvements.

[0595] "Supporting career development" means helping users find the right direction in their career choices and skill development, and assisting them in their growth.

[0596] A "robot" refers to a machine or device that collects information and provides feedback through interaction with users or mock interviews.

[0597] This invention is a system that effectively supports users in their career development through mock interviews. As an embodiment, the system is implemented as an application mounted on a consumer robot. This system is constructed as follows:

[0598] First, the user logs into the system via a robot. This uses biometric authentication methods such as voice recognition or facial recognition. Once authentication is successful, the robot's camera and microphone activate, capturing the user's voice and video data in real time. This data is then transmitted to the server via the user's device.

[0599] The server uses the Google Cloud Speech-to-Text API to convert audio data into text and analyzes the text data using the Hugging Face Transformers library. Additionally, OpenCV is used to analyze facial expressions, gaze, and posture in video data to obtain nonverbal communication information.

[0600] The analysis results evaluate the user's responses and provide real-time feedback to the user. For example, the robot points out ambiguities in the user's answers and advises them to be more specific. The server also suggests career paths to the user based on the collected data. To do this, the server uses a specific algorithm to evaluate occupational aptitude.

[0601] For example, if a user expresses interest in a sales position, the robot might ask a question such as, "Please tell me about your past successful experiences as a team leader." After the user responds, the system analyzes the content and, if necessary, provides feedback such as, "Providing specific numbers will make your response more persuasive." The system also suggests skill sets suitable for a sales position.

[0602] An example of a prompt for a generative AI model is: "Start a mock interview to prepare for your interview. Ask the hypothetical questions and generate specific advice for improvement based on the user's answers." This prompt instructs the generative AI model, which is responsible for natural language processing, to generate feedback for the user.

[0603] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0604] Step 1:

[0605] Users log in to the system via a robot using voice or facial recognition. Voice or image data is input, and authentication is performed based on a biometric authentication algorithm. Upon successful authentication, access is granted.

[0606] Step 2:

[0607] The user terminal activates the robot's camera and microphone, capturing the user's voice and video data in real time. The captured voice and video data are sent to the server as input. This data serves as foundational data for analyzing the user's actions and statements.

[0608] Step 3:

[0609] The server uses the Google Cloud Speech-to-Text API to convert audio data into text data. In this step, the audio waveform is input, converted into text as a string by speech recognition technology, and becomes output data for analysis.

[0610] Step 4:

[0611] The server uses the Hugging Face Transformers library to process text data using natural language processing and analyze the logic and meaning of user statements. Text data is input, and information regarding relevance and logic is output based on analysis using natural language processing technology.

[0612] Step 5:

[0613] The server uses OpenCV to analyze video data and evaluate the user's facial expressions, gaze, and posture. Video data is input, and based on image processing technology, facial expression analysis and posture estimation are performed, and evaluation information based on these is output.

[0614] Step 6:

[0615] The server comprehensively evaluates the user's responses based on the analysis results and calculates a score. Here, the text analysis results and video analysis results are input, and an evaluation algorithm calculates an overall performance score, which is then output.

[0616] Step 7:

[0617] The server provides real-time feedback based on the calculated evaluation results. This feedback is output to the user's terminal and communicated to the user via screen or audio. The feedback includes specific areas for improvement and advice.

[0618] Step 8:

[0619] The server makes industry and career suggestions based on the user's analysis results. The analysis results are input, an algorithm is used to analyze the user's aptitude, and the results are output in the form of optimal industry and job type suggestions. These suggestions are used to help the user in their long-term career development.

[0620] 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.

[0621] To implement this invention, the user must first log in to an online platform and enter their authentication information. The server verifies this information and, after granting the user access, retrieves the evaluation criteria for the company or university selected by the user.

[0622] When a user begins a mock interview, their device activates its camera and microphone, sending audio and video data to the server in real time. The server converts the received audio data into text using speech recognition technology and analyzes it using natural language processing technology. Here, the content of the text and the logical structure of the utterances are evaluated.

[0623] The server uses video analysis technology to detect the user's facial expressions, gaze, and posture from the received video data and evaluates them as nonverbal communication information.

[0624] A notable feature is that the server further uses an emotion engine to infer the user's emotional state from the received video data. This emotion recognition identifies basic emotions such as joy, anger, and surprise based on changes in the user's facial expressions and voice.

[0625] Taking all these factors into consideration, the server quantifies the user's performance in the mock interview and generates real-time feedback. Importantly, this feedback is customized based on data obtained through emotion recognition. For example, if the user shows signs of anxiety, the server may offer specific advice such as, "Try to relax and answer the questions."

[0626] Furthermore, the server accumulates these analysis results and makes industry and career path suggestions to understand the user's strengths and weaknesses. Sentimental data is also used in these suggestions, allowing the server to recommend areas where the user is more interested and enjoys to act.

[0627] Specifically, for example, if a user is interested in a sales position, and the system detects that they smile frequently, it can provide positive feedback such as, "It appears you are good at building relationships with customers in a sales role."

[0628] In this way, this system enables more effective and personalized interview training through a comprehensive evaluation that includes the user's emotions.

[0629] The following describes the processing flow.

[0630] Step 1:

[0631] The user accesses the online platform, enters and submits their login credentials. The server receives this information, compares it against the database, and performs authentication.

[0632] Step 2:

[0633] If authentication is successful, the server retrieves evaluation criteria corresponding to the company or university selected by the user from the database and prepares the interview.

[0634] Step 3:

[0635] When a user clicks the button to start a mock interview, their device activates its camera and microphone and begins capturing the user's voice and video in real time.

[0636] Step 4:

[0637] The device streams the captured audio and video data to the server in real time. The server receives this data.

[0638] Step 5:

[0639] The server analyzes the received audio data using speech recognition software and converts it into text data. This text is then further analyzed using natural language processing techniques to evaluate its logic and the relevance of its content.

[0640] Step 6:

[0641] The server processes the video data using video analysis technology, capturing the user's facial expressions, gaze, and posture to obtain nonverbal communication information.

[0642] Step 7:

[0643] The server's emotion engine identifies the user's emotions from video and audio data and determines their emotional state, such as joy or anxiety.

[0644] Step 8:

[0645] The server integrates data obtained from natural language processing, video analysis, and emotion recognition to numerically evaluate the user's overall interview performance.

[0646] Step 9:

[0647] The server generates real-time feedback based on the evaluation results, incorporating advice tailored to the user's emotional state into the feedback.

[0648] Step 10:

[0649] The server sends the generated feedback to the terminal, which then displays it on the screen to communicate it to the user.

[0650] Step 11:

[0651] The server stores the user's interview analysis results and uses algorithms to generate industry and career path suggestions, preparing them to be displayed to the user.

[0652] (Example 2)

[0653] 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."

[0654] Despite advancements in information technology, there is a lack of features that allow users to receive real-time feedback and individualized evaluation during mock interviews. Conventional mock interview systems struggle to provide feedback that takes emotional states into account, failing to fully utilize users' emotions and nonverbal communication, resulting in limited training effectiveness.

[0655] 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.

[0656] In this invention, the server includes means for authenticating the user to access information resources, means for receiving the user's voice and video information in real time, and means for inferring the user's emotional state using emotion recognition technology. This enables the user to receive personalized feedback that takes emotions into account in real time.

[0657] "Authentication for users to access information resources" refers to the process of verifying that a user logs into a system and has legitimate credentials.

[0658] "Audio and video information" refers to audio data generated by the user through their device and video data captured by the camera during a mock interview.

[0659] "Receiving in real time" means that audio and video information is sent to the server as soon as it is generated and processed without delay.

[0660] "Using emotion recognition technology to infer a user's emotional state" is a process that analyzes the characteristics of audio and video to identify the user's current emotions (joy, surprise, anxiety, etc.).

[0661] "Personalized feedback" refers to providing advice and suggestions in real time that are tailored to the user's characteristics and emotional state.

[0662] "Nonverbal information" refers to information conveyed through means other than voice or text, and specifically includes aspects of communication such as facial expressions, eye contact, and posture.

[0663] This system is designed to allow users to conduct mock interviews and receive real-time feedback. Several key hardware and software technologies are used to implement the invention.

[0664] The user accesses the online platform using their device and enters their authentication information. Upon successful authentication, the user can begin the mock interview. As the mock interview begins, the device activates its built-in camera and microphone and starts capturing audio and video information. This information is encoded in real time and sent to the server via the appropriate streaming protocol.

[0665] The server uses speech recognition technology, such as Google Cloud Speech-to-Text, to convert received audio data into text data. It also uses natural language processing (NLP) techniques to analyze the content and logical structure of this text data, gaining deeper insights. For example, it can analyze pitch and tone patterns from the audio data to evaluate the user's speaking style.

[0666] Furthermore, the server analyzes video data using video processing tools such as OpenCV and Dlib to extract non-verbal information such as the user's facial expressions, gaze, and posture. Emotion recognition technology infers emotions from the user's facial expressions and voice, and generates sophisticated feedback based on that.

[0667] Feedback is provided to the user in real time, and if an anxious expression is detected, specific advice such as "Try to answer while relaxed" is given. Furthermore, a score is calculated based on the user's interview performance, and career path suggestions are made.

[0668] For example, if a user is interested in a sales position, and the system detects that they smile frequently, it can provide feedback such as, "You appear to be skilled at building relationships with customers in a sales role." This system helps users identify their skills and strengths, supporting them in making the most suitable career choices.

[0669] An example of a prompt is, "I want to start preparing for a mock interview and identify my strengths in a sales role." Based on this, the generating AI model will provide advice tailored to the user.

[0670] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0671] Step 1:

[0672] The user accesses the online platform on their device and enters their authentication credentials. The device sends these credentials to the server. The server verifies the entered information against its database to confirm legitimate access. The input consists of a username and password, and the output indicates whether authentication was successful or unsuccessful. This step grants the user permission to proceed to the next step.

[0673] Step 2:

[0674] Upon successful authentication, the device displays an interface prompting the user to begin a mock interview. Once the user starts the interview, the device activates its camera and microphone. It captures audio and video in real time and sends it to the server. The input is audio and video data, and the output is an encoded multimedia stream.

[0675] Step 3:

[0676] The server inputs the received audio data into the speech recognition engine and converts it into text data. Here, the waveform data extracted from the audio is converted into features, and the spoken content is output as a string. The input is audio data, and the output is text data.

[0677] Step 4:

[0678] The server analyzes the converted text data using natural language processing techniques. During this process, it analyzes the grammatical structure and vocabulary of the text, and evaluates the logic and consistency of the utterances. Furthermore, it sends the text data to a generative AI model for further analysis by the AI. The input is text data, and the output is the evaluation result of the utterance content.

[0679] Step 5:

[0680] The server inputs video data into a video analysis engine to evaluate the user's facial expressions, gaze, and posture. It extracts frames from the video and applies face recognition and posture estimation algorithms. The input is video data, and the output is non-verbal information.

[0681] Step 6:

[0682] The server uses emotion recognition capabilities to infer the user's emotional state from audio and video. Specifically, it analyzes the tone of voice and changes in facial expressions in the video to identify what emotions the user is experiencing. The input is audio and video data, and the output is the emotion recognition result.

[0683] Step 7:

[0684] The server comprehensively evaluates and scores the user's mock interview performance based on accumulated data. This involves integrating the results of voice analysis, video analysis, and emotion recognition to generate a numerical score. Inputs include text evaluation, nonverbal information, and emotion data, while output is the score.

[0685] Step 8:

[0686] The server generates feedback based on the user's emotional state and mock interview score, and sends it to the terminal in real time. For example, if the user appears anxious, advice such as "Try to relax and answer the questions" will be displayed. The input is the score and emotional data, and the output is the feedback message.

[0687] (Application Example 2)

[0688] 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."

[0689] In modern job hunting, there is a need to provide mock interview opportunities that closely resemble actual interviews, thereby supporting the improvement of individual interview performance. In particular, providing a system that can be easily used in a home environment and that offers diverse feedback is a key challenge.

[0690] 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.

[0691] In this invention, the server includes means for receiving and authenticating user authentication information, means for receiving user audio and video data in real time, means for analyzing the received audio data and converting it into text data, and means for using an application installed on a home support robot to advance a simulated scenario. This enables the provision of real-time and personalized feedback during simulated interviews in a home environment, thereby improving interview skills in job hunting.

[0692] "User authentication information" refers to the information necessary to identify a user and the data used to grant legitimate access to the system.

[0693] "Audio and video data" refers to digital data used to record and analyze user speech and actions in real time.

[0694] "Converting to text data" refers to the process of converting audio data into text using speech recognition technology.

[0695] "Non-verbal communication information" refers to information expressed through means other than words, such as a user's facial expressions, gaze, and posture.

[0696] "Calculating a score" means evaluating the analyzed user responses and expressing them as a quantitative score.

[0697] "Providing information in real time" means transmitting information without delay by providing immediate feedback during the user's activity.

[0698] "Industry and job suggestions" is a process that provides users with suitable industry and job options based on their results.

[0699] A "home support robot" is a robot designed to assist users in their daily lives within the home and provide various forms of support.

[0700] "Proceeding through a simulated scenario" refers to the process of providing users with a hypothetical scenario that closely resembles a real-world situation and engaging in interaction with it.

[0701] The system for realizing this invention is first implemented in which a user uses a home-use support robot at home to conduct a mock interview. When a user requests a mock interview, the robot begins to acquire the user's voice and video in real time using a high-resolution camera and microphone. The user's authentication information is registered in the system in advance, and access is granted through the login process.

[0702] The server uses the Google Cloud Speech-to-Text API to convert user speech into text data. It also analyzes video data using the OpenCV library to evaluate the user's facial expressions, gaze, and posture, and obtains nonverbal communication information based on the results. Furthermore, it uses NLTK for natural language processing to analyze the content of the user's speech. Throughout this process, the server performs evaluations in real time based on the analyzed data and calculates a score.

[0703] Based on the resulting evaluation, users are provided with appropriate feedback in real time. Sentiment analysis is performed using the Affectiva SDK, and the user's emotional state is reflected in the feedback. For example, if the user is feeling tense, supportive comments such as "Relax and continue" will be provided.

[0704] The system saves the results of the user's mock interviews and later suggests suitable industries and job roles. This allows the user to find direction for further improving their skills in their job search.

[0705] For example, if a user aspiring to a sales position displays many smiles, the system might provide feedback such as, "You have an aptitude for building customer relationships within a sales role."

[0706] Example prompt: "If a user aspiring to a sales position smiles frequently, what kind of feedback would be appropriate?"

[0707] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0708] Step 1:

[0709] The user logs into the home assistance robot.

[0710] Input: User authentication information.

[0711] Process: The robot sends authentication information to the server to verify the user's identity.

[0712] Output: Authentication complete, and the user can now access the system.

[0713] Step 2:

[0714] The mock interview begins, and the robot activates its camera and microphone.

[0715] Input: User's instruction to start a mock interview.

[0716] Processing: The device activates the camera and microphone and begins acquiring audio and video data.

[0717] Output: Audio and video data are transmitted to the server in real time.

[0718] Step 3:

[0719] The server converts the audio data into text data.

[0720] Input: User voice data received in real time.

[0721] Processing: The server uses the Google Cloud Speech-to-Text API to convert the audio data into text.

[0722] Output: Text data is generated and sent to the next processing step.

[0723] Step 4:

[0724] The server analyzes the video data and extracts nonverbal communication information.

[0725] Input: User video data received in real time.

[0726] Processing: The server uses OpenCV to analyze the video data and evaluate facial expressions, gaze, and posture.

[0727] Output: Nonverbal communication information is extracted.

[0728] Step 5:

[0729] The server evaluates the user's response based on the analysis results.

[0730] Input: Text data and nonverbal communication information.

[0731] Processing: The server uses natural language processing and evaluation algorithms to quantify the user's responses.

[0732] Output: Scores and ratings for the user's responses are generated.

[0733] Step 6:

[0734] The server provides real-time feedback.

[0735] Input: User scores, ratings, and sentiment information.

[0736] Processing: The server analyzes emotions using the Affectiva SDK and customizes the feedback content.

[0737] Output: Real-time feedback is provided to the user.

[0738] Step 7:

[0739] The server stores the user's interview results and makes industry and job-related suggestions.

[0740] Input: User scores and rating data.

[0741] Processing: The server stores the collected data, analyzes trends, and suggests suitable career paths to the user.

[0742] Output: Industry and job suggestions are generated and presented to the user.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] [Fourth Embodiment]

[0747] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0748] 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.

[0749] 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).

[0750] 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.

[0751] 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.

[0752] 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).

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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".

[0760] To implement this invention, the user must first log in to the system. By accessing the portal site and entering authentication information, the server verifies and authenticates the user. This authentication allows the evaluation criteria of the company or university selected by the user to be retrieved from the database.

[0761] When a user begins a mock interview, their device activates its camera and microphone, capturing the user's audio and video in real time. The captured data is streamed from the user's device to the server.

[0762] The server converts the received audio data into text data using speech recognition technology. This text data is then analyzed using natural language processing technology to evaluate its logic and the relevance of its content. Simultaneously, video data is analyzed to evaluate the user's facial expressions, gaze, and posture, and nonverbal communication information is extracted.

[0763] These analysis results are used to comprehensively evaluate user performance and are scored by the server. The evaluation results are fed back to the user in real time and displayed on the screen. Based on this feedback, users can understand their strengths and weaknesses and use them to improve.

[0764] Furthermore, the server uses algorithms to analyze the user's analysis results in order to suggest suitable industries and career paths. This information is then provided to the user to support their future career choices.

[0765] As a concrete example, during a user's interview practice, an assessment of their suitability is also conducted to determine whether their answers match the ideal candidate profile sought by the company. If a user's answers are vague or lack specificity, the server provides feedback suggesting they "make their answers more specific."

[0766] This system allows users to more effectively improve themselves through mock interviews and hone the skills required by the industry and companies.

[0767] The following describes the processing flow.

[0768] Step 1:

[0769] The user accesses the online platform and enters their authentication information on the login screen. Account authentication is performed based on the user's input.

[0770] Step 2:

[0771] The server verifies the user's authentication, and if successful, retrieves evaluation criteria data for the company or university selected by the user from the database.

[0772] Step 3:

[0773] When the user initiates the mock interview, the device activates the user's camera and microphone and begins capturing the user's video and audio data in real time.

[0774] Step 4:

[0775] The terminal streams the captured video and audio data to the server in real time. The server receives this data.

[0776] Step 5:

[0777] The server converts the received audio data into text data using speech recognition technology. The text is then analyzed using natural language processing technology to evaluate the logic and relevance of its content.

[0778] Step 6:

[0779] The server analyzes the video data and extracts and evaluates nonverbal communication information such as the user's facial expressions, gaze, and posture.

[0780] Step 7:

[0781] The server comprehensively evaluates the data obtained from audio and video analysis and scores the user's mock interview performance.

[0782] Step 8:

[0783] The server generates real-time feedback for the user based on the evaluation results and immediately provides it to the user via the terminal.

[0784] Step 9:

[0785] The server analyzes suitable industries and career paths based on the user's evaluation results and generates suggestions using an algorithm.

[0786] Step 10:

[0787] The server provides the suggested results to the user via the terminal, allowing the user to use them to help them choose their career path.

[0788] (Example 1)

[0789] 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".

[0790] In modern job hunting and promotion exams, job seekers and employees are required to accurately assess and improve their own abilities. However, traditional mock interviews and evaluation processes make it difficult to obtain efficient and objective feedback in real time. Therefore, there is a need to develop systems that support the improvement of users' abilities.

[0791] 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.

[0792] In this invention, the server includes means for receiving and authenticating user authentication information, means for receiving user voice and video data in real time, means for analyzing the received voice data and converting it into text data, means for analyzing the received video data and obtaining nonverbal communication information, means for evaluating the user's responses based on the analysis results and calculating a score, means for providing feedback based on the evaluation results in real time, and means for generating prompts using a generative AI model and providing individualized advice to the user. This makes it possible to effectively and immediately evaluate the user's abilities and provide individually optimized improvement suggestions.

[0793] "Authentication information" refers to information used to verify a user's identity, and typically includes a username and password.

[0794] "Voice data" refers to data that is recorded in digital format from the voice spoken by the user and used for analysis.

[0795] "Video data" refers to digital data that includes visual information such as the user's movements and facial expressions captured by a camera.

[0796] "Means of converting to text data" refers to a processing system that uses speech recognition technology to convert audio data into text format.

[0797] "Nonverbal communication information" refers to communication elements conveyed through means other than words, such as facial expressions, posture, and eye contact.

[0798] "Analysis results" refer to the results of an analysis of data regarding user characteristics and abilities obtained through the processing of audio and video data.

[0799] "Feedback based on evaluation results" refers to advice and suggestions given to users based on analysis results, and is information intended to encourage self-improvement.

[0800] "Suitable job areas and career paths" refers to the analysis results indicating the industry and career path that best suits the user's abilities and characteristics.

[0801] "Generating prompts using a generative AI model" and providing them to the user refers to using AI technology to dynamically create instructions or questions based on specific conditions.

[0802] "Individualized advice" refers to specialized improvement suggestions and guidance based on the user's unique evaluation results.

[0803] The following describes embodiments for carrying out the invention.

[0804] In this system, users first access a portal site and log in by entering their authentication information. The server receives this authentication information and authenticates the user by comparing it with the database. In particular, the hardware used for this process would likely include a web server and an authentication protocol such as HTTPS.

[0805] After authentication, when the user begins a mock interview, the user's device activates its camera and microphone to capture audio and video in real time. Typical personal computers and smartphones are used as the hardware for this process.

[0806] The captured data is streamed from the user's terminal to the server, where speech recognition technology is applied to the received audio data. Speech recognition software such as the Google Speech-to-Text API is used here. The audio data is converted to text data, and the server further analyzes the content using natural language processing techniques. Libraries such as Python's NLTK and spaCy are utilized in this process.

[0807] The server uses OpenCV to analyze the video data and evaluate the user's facial expressions, gaze, and posture. This allows for the extraction of nonverbal communication information.

[0808] The server evaluates the user's performance based on these analysis results and generates prompts using a generative AI model. Through these prompts, it provides personalized advice to the user. The evaluation results and feedback are displayed on the user's terminal, allowing the user to identify areas for improvement.

[0809] For example, the server generates a prompt message such as, "Please tell me the procedure for analyzing the evaluation criteria of a user's mock interview using a generative AI model," and presents it to the user.

[0810] In this way, through this system, users can receive more detailed and accurate feedback, which helps them to improve their skills. Furthermore, the server uses the analysis results to suggest suitable industries and career paths, supporting the user's career choices.

[0811] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0812] Step 1:

[0813] The user accesses the portal site and enters their username and password as authentication information on the login screen. The server receives the entered authentication information and authenticates the user by comparing it with the information stored in the database. If successful, the server can retrieve evaluation criteria data for companies and universities based on the user's permissions.

[0814] Step 2:

[0815] When a user begins a mock interview, they click the start button on the device. The device activates the camera and microphone and captures the user's audio and video in real time. The device compresses the captured data and streams it to the server. The input audio and video data is sent to the server and forms the basis for the next processing step.

[0816] Step 3:

[0817] The server converts the received audio data into text using the Google Speech-to-Text API. This conversion outputs the text information obtained from the audio data as text data to be analyzed. Specifically, the content spoken by the user is extracted as text information.

[0818] Step 4:

[0819] The server analyzes text data using natural language processing techniques. Python's NLTK and spaCy are used to evaluate the logic and relevance of the user's statements. Based on the input text data, the analyzed data is output, and this analysis result serves as the basis for the evaluation.

[0820] Step 5:

[0821] The server analyzes the received video data using OpenCV to evaluate the user's physical characteristics such as facial expressions, gaze, and posture. Nonverbal communication information is extracted based on the input video data, and this information is added to the evaluation results.

[0822] Step 6:

[0823] The server integrates the audio and video analysis results and uses a generative AI model to evaluate the user's mock interview performance. Based on this, it calculates a score, generates prompts, and creates personalized advice. The calculated evaluation score and generated advice are output.

[0824] Step 7:

[0825] The server sends the generated evaluation score and advice to the user's terminal. The user can immediately see this feedback on the terminal screen and understand what areas need improvement. Suggestions for suitable industries and career paths are also displayed simultaneously, supporting the user in their future career choices.

[0826] (Application Example 1)

[0827] 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".

[0828] In today's labor market, it is difficult for individual job seekers to make career choices that align with their aptitudes. Furthermore, there is a lack of effective means for job seekers to practice for interviews, understand their strengths and weaknesses, and efficiently advance their future career development. Therefore, there is a need for a system that provides more appropriate feedback and enables job seekers to grow autonomously.

[0829] 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.

[0830] In this invention, the server includes means for receiving and authenticating user authentication information; means for receiving user voice and video data in real time; means for analyzing the received voice data and converting it into text data; means for analyzing the received video data and acquiring nonverbal communication information; means for evaluating the user's responses based on the analysis results and calculating a score; means for providing feedback based on the evaluation results in real time; means for saving the user's results and making industry and career suggestions; and means for conducting mock interviews with the user using a robot to support career development. As a result, job seekers can receive evaluations and feedback based on their individual characteristics, enabling more effective self-improvement and suitable occupational choices in career development.

[0831] "User authentication information" refers to unique identification information provided by a user to obtain permission to access the system.

[0832] "Audio and video data" refers to information that records the user's speech and physical movements, and is the basis for understanding, including nonverbal communication, through its analysis.

[0833] "Receiving in real time" means acquiring information for processing or analysis without delay the moment it is generated.

[0834] "Converting to text data" is the process of changing audio information into the form of characters or sentences, making it easier to analyze and search.

[0835] "Nonverbal communication information" refers to elements of communication obtained through nonverbal cues such as facial expressions, posture, and eye contact.

[0836] Providing feedback means evaluating and suggesting areas for improvement in the user's actions and responses, and returning information that can be used for future improvements.

[0837] "Supporting career development" means helping users find the right direction in their career choices and skill development, and assisting them in their growth.

[0838] A "robot" refers to a machine or device that collects information and provides feedback through interaction with users or mock interviews.

[0839] This invention is a system that effectively supports users in their career development through mock interviews. As an embodiment, the system is implemented as an application mounted on a consumer robot. This system is constructed as follows:

[0840] First, the user logs into the system via a robot. This uses biometric authentication methods such as voice recognition or facial recognition. Once authentication is successful, the robot's camera and microphone activate, capturing the user's voice and video data in real time. This data is then transmitted to the server via the user's device.

[0841] The server uses the Google Cloud Speech-to-Text API to convert audio data into text and analyzes the text data using the Hugging Face Transformers library. Additionally, OpenCV is used to analyze facial expressions, gaze, and posture in video data to obtain nonverbal communication information.

[0842] The analysis results evaluate the user's responses and provide real-time feedback to the user. For example, the robot points out ambiguities in the user's answers and advises them to be more specific. The server also suggests career paths to the user based on the collected data. To do this, the server uses a specific algorithm to evaluate occupational aptitude.

[0843] For example, if a user expresses interest in a sales position, the robot might ask a question such as, "Please tell me about your past successful experiences as a team leader." After the user responds, the system analyzes the content and, if necessary, provides feedback such as, "Providing specific numbers will make your response more persuasive." The system also suggests skill sets suitable for a sales position.

[0844] An example of a prompt for a generative AI model is: "Start a mock interview to prepare for your interview. Ask the hypothetical questions and generate specific advice for improvement based on the user's answers." This prompt instructs the generative AI model, which is responsible for natural language processing, to generate feedback for the user.

[0845] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0846] Step 1:

[0847] Users log in to the system via a robot using voice or facial recognition. Voice or image data is input, and authentication is performed based on a biometric authentication algorithm. Upon successful authentication, access is granted.

[0848] Step 2:

[0849] The user terminal activates the robot's camera and microphone, capturing the user's voice and video data in real time. The captured voice and video data are sent to the server as input. This data serves as foundational data for analyzing the user's actions and statements.

[0850] Step 3:

[0851] The server uses the Google Cloud Speech-to-Text API to convert audio data into text data. In this step, the audio waveform is input, converted into text as a string by speech recognition technology, and becomes output data for analysis.

[0852] Step 4:

[0853] The server uses the Hugging Face Transformers library to process text data using natural language processing and analyze the logic and meaning of user statements. Text data is input, and information regarding relevance and logic is output based on analysis using natural language processing technology.

[0854] Step 5:

[0855] The server uses OpenCV to analyze video data and evaluate the user's facial expressions, gaze, and posture. Video data is input, and based on image processing technology, facial expression analysis and posture estimation are performed, and evaluation information based on these is output.

[0856] Step 6:

[0857] The server comprehensively evaluates the user's responses based on the analysis results and calculates a score. Here, the text analysis results and video analysis results are input, and an evaluation algorithm calculates an overall performance score, which is then output.

[0858] Step 7:

[0859] The server provides real-time feedback based on the calculated evaluation results. This feedback is output to the user's terminal and communicated to the user via screen or audio. The feedback includes specific areas for improvement and advice.

[0860] Step 8:

[0861] The server makes industry and career suggestions based on the user's analysis results. The analysis results are input, an algorithm is used to analyze the user's aptitude, and the results are output in the form of optimal industry and job type suggestions. These suggestions are used to help the user in their long-term career development.

[0862] 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.

[0863] To implement this invention, the user must first log in to an online platform and enter their authentication information. The server verifies this information and, after granting the user access, retrieves the evaluation criteria for the company or university selected by the user.

[0864] When a user begins a mock interview, their device activates its camera and microphone, sending audio and video data to the server in real time. The server converts the received audio data into text using speech recognition technology and analyzes it using natural language processing technology. Here, the content of the text and the logical structure of the utterances are evaluated.

[0865] The server uses video analysis technology to detect the user's facial expressions, gaze, and posture from the received video data and evaluates them as nonverbal communication information.

[0866] A notable feature is that the server further uses an emotion engine to infer the user's emotional state from the received video data. This emotion recognition identifies basic emotions such as joy, anger, and surprise based on changes in the user's facial expressions and voice.

[0867] Taking all these factors into consideration, the server quantifies the user's performance in the mock interview and generates real-time feedback. Importantly, this feedback is customized based on data obtained through emotion recognition. For example, if the user shows signs of anxiety, the server may offer specific advice such as, "Try to relax and answer the questions."

[0868] Furthermore, the server accumulates these analysis results and makes industry and career path suggestions to understand the user's strengths and weaknesses. Sentimental data is also used in these suggestions, allowing the server to recommend areas where the user is more interested and enjoys to act.

[0869] Specifically, for example, if a user is interested in a sales position, and the system detects that they smile frequently, it can provide positive feedback such as, "It appears you are good at building relationships with customers in a sales role."

[0870] In this way, this system enables more effective and personalized interview training through a comprehensive evaluation that includes the user's emotions.

[0871] The following describes the processing flow.

[0872] Step 1:

[0873] The user accesses the online platform, enters and submits their login credentials. The server receives this information, compares it against the database, and performs authentication.

[0874] Step 2:

[0875] If authentication is successful, the server retrieves evaluation criteria corresponding to the company or university selected by the user from the database and prepares the interview.

[0876] Step 3:

[0877] When a user clicks the button to start a mock interview, their device activates its camera and microphone and begins capturing the user's voice and video in real time.

[0878] Step 4:

[0879] The device streams the captured audio and video data to the server in real time. The server receives this data.

[0880] Step 5:

[0881] The server analyzes the received audio data using speech recognition software and converts it into text data. This text is then further analyzed using natural language processing techniques to evaluate its logic and the relevance of its content.

[0882] Step 6:

[0883] The server processes the video data using video analysis technology, capturing the user's facial expressions, gaze, and posture to obtain nonverbal communication information.

[0884] Step 7:

[0885] The server's emotion engine identifies the user's emotions from video and audio data and determines their emotional state, such as joy or anxiety.

[0886] Step 8:

[0887] The server integrates data obtained from natural language processing, video analysis, and emotion recognition to numerically evaluate the user's overall interview performance.

[0888] Step 9:

[0889] The server generates real-time feedback based on the evaluation results, incorporating advice tailored to the user's emotional state into the feedback.

[0890] Step 10:

[0891] The server sends the generated feedback to the terminal, which then displays it on the screen to communicate it to the user.

[0892] Step 11:

[0893] The server stores the user's interview analysis results and uses algorithms to generate industry and career path suggestions, preparing them to be displayed to the user.

[0894] (Example 2)

[0895] 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".

[0896] Despite advancements in information technology, there is a lack of features that allow users to receive real-time feedback and individualized evaluation during mock interviews. Conventional mock interview systems struggle to provide feedback that takes emotional states into account, failing to fully utilize users' emotions and nonverbal communication, resulting in limited training effectiveness.

[0897] 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.

[0898] In this invention, the server includes means for authenticating the user to access information resources, means for receiving the user's voice and video information in real time, and means for inferring the user's emotional state using emotion recognition technology. This enables the user to receive personalized feedback that takes emotions into account in real time.

[0899] "Authentication for users to access information resources" refers to the process of verifying that a user logs into a system and has legitimate credentials.

[0900] "Audio and video information" refers to audio data generated by the user through their device and video data captured by the camera during a mock interview.

[0901] "Receiving in real time" means that audio and video information is sent to the server as soon as it is generated and processed without delay.

[0902] "Using emotion recognition technology to infer a user's emotional state" is a process that analyzes the characteristics of audio and video to identify the user's current emotions (joy, surprise, anxiety, etc.).

[0903] "Personalized feedback" refers to providing advice and suggestions in real time that are tailored to the user's characteristics and emotional state.

[0904] "Nonverbal information" refers to information conveyed through means other than voice or text, and specifically includes aspects of communication such as facial expressions, eye contact, and posture.

[0905] This system is designed to allow users to conduct mock interviews and receive real-time feedback. Several key hardware and software technologies are used to implement the invention.

[0906] The user accesses the online platform using their device and enters their authentication information. Upon successful authentication, the user can begin the mock interview. As the mock interview begins, the device activates its built-in camera and microphone and starts capturing audio and video information. This information is encoded in real time and sent to the server via the appropriate streaming protocol.

[0907] The server uses speech recognition technology, such as Google Cloud Speech-to-Text, to convert received audio data into text data. It also uses natural language processing (NLP) techniques to analyze the content and logical structure of this text data, gaining deeper insights. For example, it can analyze pitch and tone patterns from the audio data to evaluate the user's speaking style.

[0908] Furthermore, the server analyzes video data using video processing tools such as OpenCV and Dlib to extract non-verbal information such as the user's facial expressions, gaze, and posture. Emotion recognition technology infers emotions from the user's facial expressions and voice, and generates sophisticated feedback based on that.

[0909] Feedback is provided to the user in real time, and if an anxious expression is detected, specific advice such as "Try to answer while relaxed" is given. Furthermore, a score is calculated based on the user's interview performance, and career path suggestions are made.

[0910] For example, if a user is interested in a sales position, and the system detects that they smile frequently, it can provide feedback such as, "You appear to be skilled at building relationships with customers in a sales role." This system helps users identify their skills and strengths, supporting them in making the most suitable career choices.

[0911] An example of a prompt is, "I want to start preparing for a mock interview and identify my strengths in a sales role." Based on this, the generating AI model will provide advice tailored to the user.

[0912] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0913] Step 1:

[0914] The user accesses the online platform on their device and enters their authentication credentials. The device sends these credentials to the server. The server verifies the entered information against its database to confirm legitimate access. The input consists of a username and password, and the output indicates whether authentication was successful or unsuccessful. This step grants the user permission to proceed to the next step.

[0915] Step 2:

[0916] Upon successful authentication, the device displays an interface prompting the user to begin a mock interview. Once the user starts the interview, the device activates its camera and microphone. It captures audio and video in real time and sends it to the server. The input is audio and video data, and the output is an encoded multimedia stream.

[0917] Step 3:

[0918] The server inputs the received audio data into the speech recognition engine and converts it into text data. Here, the waveform data extracted from the audio is converted into features, and the spoken content is output as a string. The input is audio data, and the output is text data.

[0919] Step 4:

[0920] The server analyzes the converted text data using natural language processing techniques. During this process, it analyzes the grammatical structure and vocabulary of the text, and evaluates the logic and consistency of the utterances. Furthermore, it sends the text data to a generative AI model for further analysis by the AI. The input is text data, and the output is the evaluation result of the utterance content.

[0921] Step 5:

[0922] The server inputs video data into a video analysis engine to evaluate the user's facial expressions, gaze, and posture. It extracts frames from the video and applies face recognition and posture estimation algorithms. The input is video data, and the output is non-verbal information.

[0923] Step 6:

[0924] The server uses emotion recognition capabilities to infer the user's emotional state from audio and video. Specifically, it analyzes the tone of voice and changes in facial expressions in the video to identify what emotions the user is experiencing. The input is audio and video data, and the output is the emotion recognition result.

[0925] Step 7:

[0926] The server comprehensively evaluates and scores the user's mock interview performance based on accumulated data. This involves integrating the results of voice analysis, video analysis, and emotion recognition to generate a numerical score. Inputs include text evaluation, nonverbal information, and emotion data, while output is the score.

[0927] Step 8:

[0928] The server generates feedback based on the user's emotional state and mock interview score, and sends it to the terminal in real time. For example, if the user appears anxious, advice such as "Try to relax and answer the questions" will be displayed. The input is the score and emotional data, and the output is the feedback message.

[0929] (Application Example 2)

[0930] 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".

[0931] In modern job hunting, there is a need to provide mock interview opportunities that closely resemble actual interviews, thereby supporting the improvement of individual interview performance. In particular, providing a system that can be easily used in a home environment and that offers diverse feedback is a key challenge.

[0932] 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.

[0933] In this invention, the server includes means for receiving and authenticating user authentication information, means for receiving user audio and video data in real time, means for analyzing the received audio data and converting it into text data, and means for using an application installed on a home support robot to advance a simulated scenario. This enables the provision of real-time and personalized feedback during simulated interviews in a home environment, thereby improving interview skills in job hunting.

[0934] "User authentication information" refers to the information necessary to identify a user and the data used to grant legitimate access to the system.

[0935] "Audio and video data" refers to digital data used to record and analyze user speech and actions in real time.

[0936] "Converting to text data" refers to the process of converting audio data into text using speech recognition technology.

[0937] "Non-verbal communication information" refers to information expressed through means other than words, such as a user's facial expressions, gaze, and posture.

[0938] "Calculating a score" means evaluating the analyzed user responses and expressing them as a quantitative score.

[0939] "Providing information in real time" means transmitting information without delay by providing immediate feedback during the user's activity.

[0940] "Industry and job suggestions" is a process that provides users with suitable industry and job options based on their results.

[0941] A "home support robot" is a robot designed to assist users in their daily lives within the home and provide various forms of support.

[0942] "Proceeding through a simulated scenario" refers to the process of providing users with a hypothetical scenario that closely resembles a real-world situation and engaging in interaction with it.

[0943] The system for realizing this invention is first implemented in which a user uses a home-use support robot at home to conduct a mock interview. When a user requests a mock interview, the robot begins to acquire the user's voice and video in real time using a high-resolution camera and microphone. The user's authentication information is registered in the system in advance, and access is granted through the login process.

[0944] The server uses the Google Cloud Speech-to-Text API to convert user speech into text data. It also analyzes video data using the OpenCV library to evaluate the user's facial expressions, gaze, and posture, and obtains nonverbal communication information based on the results. Furthermore, it uses NLTK for natural language processing to analyze the content of the user's speech. Throughout this process, the server performs evaluations in real time based on the analyzed data and calculates a score.

[0945] Based on the resulting evaluation, users are provided with appropriate feedback in real time. Sentiment analysis is performed using the Affectiva SDK, and the user's emotional state is reflected in the feedback. For example, if the user is feeling tense, supportive comments such as "Relax and continue" will be provided.

[0946] The system saves the results of the user's mock interviews and later suggests suitable industries and job roles. This allows the user to find direction for further improving their skills in their job search.

[0947] For example, if a user aspiring to a sales position displays many smiles, the system might provide feedback such as, "You have an aptitude for building customer relationships within a sales role."

[0948] Example prompt: "If a user aspiring to a sales position smiles frequently, what kind of feedback would be appropriate?"

[0949] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0950] Step 1:

[0951] The user logs into the home assistance robot.

[0952] Input: User authentication information.

[0953] Process: The robot sends authentication information to the server to verify the user's identity.

[0954] Output: Authentication complete, and the user can now access the system.

[0955] Step 2:

[0956] The mock interview begins, and the robot activates its camera and microphone.

[0957] Input: User's instruction to start a mock interview.

[0958] Processing: The device activates the camera and microphone and begins acquiring audio and video data.

[0959] Output: Audio and video data are transmitted to the server in real time.

[0960] Step 3:

[0961] The server converts the audio data into text data.

[0962] Input: User voice data received in real time.

[0963] Processing: The server uses the Google Cloud Speech-to-Text API to convert the audio data into text.

[0964] Output: Text data is generated and sent to the next processing step.

[0965] Step 4:

[0966] The server analyzes the video data and extracts nonverbal communication information.

[0967] Input: User video data received in real time.

[0968] Processing: The server uses OpenCV to analyze the video data and evaluate facial expressions, gaze, and posture.

[0969] Output: Nonverbal communication information is extracted.

[0970] Step 5:

[0971] The server evaluates the user's response based on the analysis results.

[0972] Input: Text data and nonverbal communication information.

[0973] Processing: The server uses natural language processing and evaluation algorithms to quantify the user's responses.

[0974] Output: Scores and ratings for the user's responses are generated.

[0975] Step 6:

[0976] The server provides real-time feedback.

[0977] Input: User scores, ratings, and sentiment information.

[0978] Processing: The server analyzes emotions using the Affectiva SDK and customizes the feedback content.

[0979] Output: Real-time feedback is provided to the user.

[0980] Step 7:

[0981] The server stores the user's interview results and makes industry and job-related suggestions.

[0982] Input: User scores and rating data.

[0983] Processing: The server stores the collected data, analyzes trends, and suggests suitable career paths to the user.

[0984] Output: Industry and job suggestions are generated and presented to the user.

[0985] 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.

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] 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.

[0992] 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.

[0993] 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."

[0994] 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.

[0995] 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.

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] 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.

[1003] 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.

[1004] 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.

[1005] 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 to be incorporated by reference.

[1006] The following is further disclosed regarding the embodiments described above.

[1007] (Claim 1)

[1008] A means of receiving user authentication information and performing authentication,

[1009] A means for receiving user audio and video data in real time,

[1010] A means for analyzing received audio data and converting it into text data,

[1011] A means of analyzing received video data and obtaining nonverbal communication information,

[1012] A means for evaluating user responses and calculating scores based on analysis results,

[1013] A means of providing feedback based on evaluation results in real time,

[1014] A means of saving user results and making industry and career suggestions,

[1015] A system that includes this.

[1016] (Claim 2)

[1017] The system according to claim 1, which uses natural language processing technology for analyzing audio data.

[1018] (Claim 3)

[1019] The system according to claim 1, which evaluates the user's facial expressions, gaze, and posture by analyzing video data.

[1020] "Example 1"

[1021] (Claim 1)

[1022] A means of receiving user authentication information and performing authentication,

[1023] A means for receiving user audio and video data in real time,

[1024] A means for analyzing received audio data and converting it into text data,

[1025] A means of analyzing received video data and obtaining nonverbal communication information,

[1026] A means for evaluating user responses and calculating scores based on analysis results,

[1027] A means of providing feedback based on evaluation results in real time,

[1028] A means of suggesting suitable job areas and career paths based on user analysis results,

[1029] A means of generating prompts using a generative AI model and providing personalized advice to the user,

[1030] A means of displaying evaluation and feedback results to the user and providing information for improvement,

[1031] A system that includes this.

[1032] (Claim 2)

[1033] The system according to claim 1, which uses natural language processing technology to analyze voice data and evaluates the user's response based on its logic and relevance of content.

[1034] (Claim 3)

[1035] The system according to claim 1, which evaluates the user's facial expressions, gaze, and posture by analyzing video data and extracts nonverbal communication information.

[1036] "Application Example 1"

[1037] (Claim 1)

[1038] A means of receiving user authentication information and performing authentication,

[1039] A means for receiving user audio and video data in real time,

[1040] A means for analyzing received audio data and converting it into text data,

[1041] A means of analyzing received video data and obtaining nonverbal communication information,

[1042] A means for evaluating user responses and calculating scores based on analysis results,

[1043] A means of providing feedback based on evaluation results in real time,

[1044] A means of saving user results and making industry and career suggestions,

[1045] A means of supporting career development by conducting mock interviews with users using robots,

[1046] A system that includes this.

[1047] (Claim 2)

[1048] The system according to claim 1, which uses natural language processing technology for analyzing audio data.

[1049] (Claim 3)

[1050] The system according to claim 1, which evaluates the user's facial expressions, gaze, and posture by analyzing video data.

[1051] "Example 2 of combining an emotion engine"

[1052] (Claim 1)

[1053] A means of authenticating a user to access information resources,

[1054] A means for receiving user audio and video information in real time,

[1055] A means for analyzing received audio information and converting it into text information,

[1056] A means of analyzing received video information and obtaining non-verbal information,

[1057] A means for evaluating user responses and calculating numerical values ​​based on analysis results,

[1058] A means of providing real-time feedback that takes the analysis results into consideration,

[1059] A means of accumulating user analysis results and making industry and occupational suggestions,

[1060] A means of inferring a user's emotional state using emotion recognition technology,

[1061] Means for providing the generated personalized feedback,

[1062] A system that includes this.

[1063] (Claim 2)

[1064] The system according to claim 1, which uses natural language processing technology for analyzing speech information.

[1065] (Claim 3)

[1066] The system according to claim 1, which evaluates the user's facial expressions, gaze, and posture by analyzing video information, and also uses emotion recognition technology.

[1067] "Application example 2 when combining with an emotional engine"

[1068] (Claim 1)

[1069] A means of receiving user authentication information and performing authentication,

[1070] A means for receiving user audio and video data in real time,

[1071] A means for analyzing received audio data and converting it into text data,

[1072] A means of analyzing received video data and obtaining nonverbal communication information,

[1073] A means for evaluating user responses and calculating scores based on analysis results,

[1074] A means of providing feedback based on evaluation results in real time,

[1075] A means of saving user results and making industry and job-related suggestions,

[1076] A means of conducting a simulated scenario using an application installed on a home assistance robot,

[1077] A system that includes this.

[1078] (Claim 2)

[1079] The system according to claim 1, which uses natural language processing technology for analyzing audio data.

[1080] (Claim 3)

[1081] The system according to claim 1, which evaluates the user's facial expressions, gaze, and posture by analyzing video data. [Explanation of symbols]

[1082] 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. A means of receiving user authentication information and performing authentication, A means for receiving user audio and video data in real time, A means for analyzing received audio data and converting it into text data, A means of analyzing received video data and obtaining nonverbal communication information, A means for evaluating user responses and calculating scores based on analysis results, A means of providing feedback based on evaluation results in real time, A means of saving user results and making industry and career suggestions, A system that includes this.

2. The system according to claim 1, which uses natural language processing technology for analyzing audio data.

3. The system according to claim 1, which evaluates the user's facial expressions, gaze, and posture by analyzing video data.

Images