system

Abstract

We provide the system. [Solution] A device capable of communicating with a candidate's actions, and means for analyzing recorded audio data and converting it into text data, A means of identifying the emotional state of a candidate by analyzing recorded video data, A means for analyzing the aforementioned text data to evaluate multiple abilities of the candidate, A means of evaluating a candidate's adaptability in different cultures, A means for generating an evaluation report that integrates the aforementioned multiple competency assessments and adaptability assessments, A means for providing the aforementioned evaluation report to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional interview process, it is difficult to accurately evaluate the soft skills and cultural adaptability of candidates in a short time, and it often depends on the interviewer's subjectivity. Furthermore, it is difficult to evaluate a large number of candidates based on consistent criteria, and there is a lack of fair and objective criteria for selecting appropriate talents.

Means for Solving the Problems

[0005] This invention analyzes audio and video data recorded during candidate interviews in real time and converts it into text data using a natural language processing model to evaluate multiple abilities of candidates, such as communication skills, leadership, teamwork, and problem-solving skills. Furthermore, it proposes a system that automatically generates and provides a comprehensive evaluation report to the user by identifying the candidate's emotional state from video data using a facial recognition model, analyzing and integrating their cultural adaptation. This system enables more accurate and objective hiring decisions.

[0006] A "candidate" refers to a person who undergoes evaluation during the hiring process.

[0007] "Device" refers to equipment or systems designed to perform some kind of processing or task.

[0008] "Audio data" refers to recordings of sounds, including human speech.

[0009] "Text data" refers to information in written form that is represented electronically.

[0010] "Analysis" refers to the process of analyzing data to extract specific information and deepen understanding.

[0011] "Emotional state" refers to the state of emotions expressed internally or externally in a person.

[0012] "Multiple abilities" refers to the multiple skills or characteristics that a particular subject possesses.

[0013] "Evaluation" refers to the act of judging value or performance based on specific criteria.

[0014] "Different cultures" refers to cultural backgrounds that differ from the usual cultural environment.

[0015] "Adaptability" refers to an individual's ability to effectively cope with new environments and conditions.

[0016] "Report" refers to a document that summarizes analysis results or survey results.

[0017] "User" refers to a person who uses a system or service.

Brief Explanation of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. <� [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14]This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0019] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0020] First, let's explain the terminology used in the following explanation.

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

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

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

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0033] 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.

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

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention provides a system for evaluating a candidate's soft skills and cultural adaptability in real time during the interview process. The system analyzes the candidate's actions, statements, and emotional state, and generates a comprehensive evaluation report based on these. The following describes a specific implementation of this system.

[0040] First, during the interview, the terminal records the candidate's video and audio in real time and sends the data to the server. The server receives this data and converts the audio data into text using speech recognition technology. The converted text data is then processed using natural language processing (NLP) technology to evaluate the candidate's various abilities, such as communication skills, problem-solving ability, teamwork, and leadership.

[0041] Furthermore, the server analyzes the candidate's facial expressions using video data and identifies their emotional state in real time using emotion recognition technology. This allows for an understanding of the candidate's emotions.

[0042] Furthermore, the server integrates this data to measure the results of multiple competency assessments and the candidate's adaptability in different cultures. It analyzes cross-cultural understanding and behavioral patterns to calculate cultural adaptability.

[0043] Finally, the server generates a comprehensive evaluation report of each candidate based on these analysis results. This report includes each candidate's soft skills score and cultural adaptation index. The terminal provides this evaluation report to the interviewer, who can then use it to quickly and accurately assess the candidate's suitability.

[0044] As a concrete example, in interviews for candidates capable of demonstrating leadership in international projects, this system can analyze the candidate's words and emotional state when they discuss their experience collaborating with team members from different cultures, thereby highly evaluating their leadership abilities and cultural adaptability. As a result, interviewers can objectively assess the candidate's suitability and receive support in selecting the most suitable candidate.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The device records the candidate's audio and video data in real time at the start of the interview and sends it to the server. Video is collected by the camera and audio by the microphone.

[0048] Step 2:

[0049] The server processes the received audio data through a speech recognition engine, converting it into text data based on natural language. This text data is used for subsequent natural language processing, therefore, a highly accurate conversion is required.

[0050] Step 3:

[0051] The server analyzes text data using a natural language processing (NLP) model to extract specific keywords and themes. This allows it to calculate scores that evaluate candidates' communication skills and problem-solving abilities.

[0052] Step 4:

[0053] The server analyzes how faces appear in the video data and uses facial recognition technology to identify emotional states. This allows it to determine what emotions the candidate is showing during the interview.

[0054] Step 5:

[0055] The server evaluates the candidate's cultural adaptability by comprehensively considering their statements and facial expressions. Statements indicating cross-cultural experience or understanding of other cultures are indexed accordingly. This index serves as an indicator of the candidate's ability to cope with diversity.

[0056] Step 6:

[0057] The server integrates all analytical data and generates a comprehensive evaluation report that includes the candidate's skills and cultural adaptability. The report clearly displays the scoring and visually represents each ability.

[0058] Step 7:

[0059] The server sends the generated evaluation report to the terminal and presents it to the interviewer, who is the user. Based on this report, the interviewer evaluates and judges the candidate's suitability and compatibility with the organization.

[0060] (Example 1)

[0061] 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."

[0062] In today's business environment, quickly and accurately assessing the suitability of candidates from diverse cultural backgrounds is crucial for ensuring international competitiveness. However, traditional interview processes often struggle to objectively evaluate candidates' soft skills and cross-cultural adaptability, tending to rely on the evaluator's subjectivity. This creates a risk of making incorrect decisions when selecting suitable personnel. This invention aims to solve this problem by providing a structured and fair evaluation of candidates' skills and adaptability.

[0063] 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.

[0064] In this invention, the server is capable of communicating with a device that collects the candidate's behavior and includes means for analyzing acquired audio information and converting it into text information, means for analyzing acquired image information and identifying the candidate's emotional state, means for analyzing the text information and evaluating the candidate's multiple abilities, algorithm means for enhancing ability evaluation based on the analysis of the behavior and statements, and means for utilizing a model for measuring cross-cultural adaptability. This makes it possible to accurately evaluate each candidate's abilities and cultural adaptability and immediately provide the evaluation results to the interviewer.

[0065] A "candidate" is a person who is evaluated during the interview and selection process.

[0066] "Behavior" refers to dynamic responses and actions, including gestures, verbal expressions, and facial expressions, that are demonstrated by the candidate.

[0067] "Audio information" refers to sound data obtained from the words and vocalizations spoken by the candidates.

[0068] "Textual information" refers to data in text format obtained by analyzing audio information.

[0069] "Image information" refers to visual data that records the candidate's facial expressions and movements.

[0070] "Emotional state" refers to the identification of a candidate's psychological and emotional state based on the results of facial expression and voice analysis.

[0071] "Competency assessment" is a process of objectively analyzing and measuring a candidate's multiple skills, such as communication skills, problem-solving abilities, and teamwork skills.

[0072] "Cross-cultural adaptability" is a measure of a candidate's ability to adapt flexibly and act effectively within different cultural backgrounds.

[0073] An "evaluation report" is a document that summarizes the results of an analysis of a candidate's various abilities and cross-cultural adaptability, and serves as reference material for the hiring decision.

[0074] "Users" refers to interviewers and recruiters who make decisions about whether or not to hire candidates based on evaluation reports.

[0075] An "algorithmic method" is a set of computational procedures for analyzing and processing data, and a series of computational processes for evaluating the characteristics and abilities of candidates.

[0076] A "model" is a mathematical or AI-based system used to perform specific evaluations or predictions based on data.

[0077] The system in this invention aims to evaluate soft skills and cultural adaptability in real time during the candidate interview process. Specifically, it consists of three main components: a terminal, a server, and a user.

[0078] First, the terminal uses a high-resolution camera and a high-sensitivity microphone during the interview. For example, it uses a camera and audio input device built into a typical laptop, or an externally connected webcam and dedicated microphone, to record the candidate's video and audio in real time and organize the data into a technically appropriate format. The organized data is then transmitted to a server via the internet.

[0079] The server converts received audio data into text information using AI-based speech recognition software (e.g., a speech recognition API for speech analysis). This text information is then subjected to grammatical analysis, keyword extraction, and sentiment analysis using natural language processing techniques to evaluate multiple candidate abilities, such as communication skills and problem-solving abilities. Additionally, video data is analyzed using facial expression recognition technology (e.g., a face recognition API) to identify the candidate's emotional state.

[0080] In addition, the server integrates the aforementioned audio and video data and uses an AI model designed to measure cross-cultural adaptability. This model calculates cultural adaptability by analyzing the candidate's cross-cultural understanding and behavioral patterns.

[0081] Finally, the server generates a comprehensive evaluation report based on these analysis results. This report includes soft skills evaluation scores and a cultural adaptation index.

[0082] The generated evaluation report is provided to the interviewer (user) via the terminal, allowing the interviewer to quickly and accurately assess the candidate's suitability based on it.

[0083] As a concrete example, for a candidate for a position requiring project leadership in a cross-cultural environment, this system analyzes their experience collaborating with cross-cultural teams and evaluates their leadership abilities and cultural adaptability. Based on these results, interviewers can objectively evaluate candidates and select individuals suitable for a diverse work environment.

[0084] An example of a prompt might be a question like, "Based on your experience, please share an example of a time when you demonstrated leadership in a project with a cross-cultural team."

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The device uses a high-resolution camera and high-sensitivity microphone to record the candidate's video and audio during the interview. This input data comprehensively captures the candidate's actions and statements, is converted into a secure file format, and then transmitted to a server via the internet. Specifically, recording begins, for example, when the video stream capture start button is pressed.

[0088] Step 2:

[0089] The server converts the transmitted audio data into text data using an AI-based speech recognition tool. This process extracts linguistic elements from the acoustic signal and generates output in string format. This allows the candidate's utterances to be stored in a database, enabling natural language processing. Specifically, as soon as the audio data is received, the speech recognition algorithm automatically activates, and text is generated within seconds.

[0090] Step 3:

[0091] The server uses natural language processing (NLP) techniques to analyze the converted text data and evaluate the candidate's abilities. This involves identifying the text's grammatical structure, keywords, and sentiment (emotional tone) to calculate the candidate's communication and problem-solving skills. For example, this analysis identifies frequently used positive or negative expressions. These results are used in scoring and form part of the candidate's overall ability assessment.

[0092] Step 4:

[0093] The server inputs video data into an facial recognition algorithm to analyze the candidate's emotional state. Here, various facial expressions of the candidate are recognized and classified into specific emotions, such as smiles or surprise. The output emotional data serves as an indicator of the candidate's emotions during the interview. This process involves frame-by-frame analysis, and the emotional state is updated in real time.

[0094] Step 5:

[0095] The server integrates the analyzed audio and video data and uses an AI model designed to assess cross-cultural adaptability. This model analyzes the candidate's understanding of different cultures and behavioral patterns to calculate their cultural adaptability. Specifically, the model estimates the degree of leadership and collaborative ability in different cultures and compiles the results into evaluation indicators. These results are reflected in the report as the candidate's cross-cultural adaptability index.

[0096] Step 6:

[0097] Based on these analysis results, the server generates a comprehensive evaluation report for each candidate. This report includes soft skills scores and a cultural adaptation index, and is provided to the interviewer (the user). The generation process integrates the evaluation results for each ability, producing a clear and easy-to-understand visualized output. The evaluation report is provided to the interviewer in digital format, helping them to quickly and accurately assess the candidate's overall suitability.

[0098] (Application Example 1)

[0099] 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."

[0100] In selecting candidates, a comprehensive assessment of soft skills, cultural adaptability, and awareness and response skills regarding safety measures is required. However, traditional interview and evaluation systems have struggled to accurately analyze these aspects in real time and generate detailed evaluation results. As a result, the process of selecting suitable personnel within companies has been inefficient, and there has been a risk of overlooking the potential of potential employees.

[0101] 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.

[0102] In this invention, the server is capable of communicating with a device that records the actions of candidates, and includes means for analyzing recorded audio data and converting it into text data, means for analyzing recorded video data and identifying the candidate's emotional state, means for analyzing the text data and evaluating multiple abilities of the candidate, means for evaluating the candidate's adaptability in different cultures, means for evaluating the candidate's awareness and response skills regarding safety measures, means for generating an evaluation report that integrates the evaluations of the multiple abilities, adaptability, and safety measures, and means for providing the evaluation report to the user. This makes it possible to efficiently and accurately grasp the wide range of abilities, adaptability, and safety-related abilities required in the candidate selection and evaluation process.

[0103] "Device" refers to hardware or software used to record data and communicate with other systems.

[0104] A "server" refers to a central computer that receives, analyzes, and processes data.

[0105] "Audio data" refers to digital audio information that records what a candidate has said.

[0106] "Text data" refers to digital information obtained by converting audio data into written text.

[0107] "Video data" refers to digital visual information that records the candidate's actions and facial expressions.

[0108] "Emotional state" refers to information identified as indicating a candidate's emotions or psychological state.

[0109] "Multiple abilities" refers to a variety of skills that a candidate possesses, such as communication skills and problem-solving abilities.

[0110] "Cultural adaptability" refers to a candidate's ability to adapt to different cultural environments.

[0111] "Awareness and response skills regarding safety measures" refers to a candidate's ability to understand and respond appropriately to safety issues.

[0112] An "evaluation report" refers to a report generated based on analysis results that comprehensively shows a candidate's abilities and adaptability.

[0113] "User" refers to an individual or organization that receives evaluation reports and selects candidates.

[0114] To implement this invention, a server and a terminal are required. The terminal records the actions and statements of candidates in real time during interviews. The data recorded in this process includes audio and video data. The audio data is sent to the server and converted into text data using speech recognition technology. Specifically, this conversion is performed using a speech recognition service such as Google® Cloud Speech-to-Text.

[0115] The server performs analysis on the converted text data using natural language processing (NLP) techniques. NLP utilizes language processing models such as spaCy and BERT to evaluate candidates' communication skills and problem-solving abilities. During this process, awareness of safety measures and response skills are also assessed based on the candidates' statements.

[0116] The server also processes the candidate's video data and identifies their emotional state based on an emotion recognition model. This process is carried out using services such as Microsoft® Azure® Face API. This allows for the identification of changes in the candidate's emotions and psychological state in real time.

[0117] By integrating this data, the server generates a comprehensive evaluation report that includes assessments of the candidate's multiple competencies, cultural adaptability, and safety measures. This evaluation report is provided to the user via a terminal, allowing the user to quickly and accurately assess the candidate's suitability.

[0118] As a concrete example, when selecting a leader for an international project, the server uses this system to analyze the content and emotional state of candidates when they talk about their experience collaborating with team members from different cultures. This allows for an objective assessment of the candidates' leadership abilities and cultural adaptability, making it possible to determine their suitability for the role.

[0119] An example of a prompt for the generating AI model is: "Please evaluate this candidate's security awareness. Below is a record of the candidate's statements. Question 1: What are your thoughts on recent changes to security protocols?"

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The terminal records the candidate's audio and video data in real time during the interview. This input data is used to capture the candidate's statements and actions in detail during the interview. The recorded data is then sent to a server.

[0123] Step 2:

[0124] The server converts the audio data received from the terminal into text data using speech recognition technology. Specifically, it uses Google Cloud Speech-to-Text to convert the audio signal into language data. This conversion outputs the specific content spoken by the candidate as text information.

[0125] Step 3:

[0126] The server analyzes text data using natural language processing (NLP) techniques. This process utilizes language models such as spaCy and BERT to extract important keywords and phrases from the text data. This generates output data for evaluating candidates' communication skills, problem-solving abilities, and awareness of safety measures.

[0127] Step 4:

[0128] Simultaneously, the server processes the video data and uses an emotion recognition model to identify the candidate's emotional state. Leveraging the Microsoft Azure Face API, it analyzes facial expressions from the video to extract the candidate's psychological state and emotional changes.

[0129] Step 5:

[0130] The server integrates the analyzed sentiment data and natural language processing results to generate a comprehensive evaluation report that includes the candidate's multiple abilities, cross-cultural adaptability, and safety awareness. This ensures that all evaluation results are output as a single, comprehensive report, making it easily accessible to the user.

[0131] Step 6:

[0132] Users receive this integrated evaluation report on their device. Based on the report, users can objectively assess candidates' leadership abilities, cultural adaptability, and safety management skills, and proceed with the selection process.

[0133] 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.

[0134] This invention is a system that aims to improve the quality of the interview process by analyzing the emotions of not only the candidate but also the interviewer (the user) in real time during the interview. This system grasps the emotional state of both the candidate and the interviewer and utilizes that data for interview evaluation. Specific embodiments are shown below.

[0135] First, the device records video and audio data of the candidate during the interview, while simultaneously recording the interviewer's presence via the camera and microphone. This data is transmitted to the server in real time.

[0136] The server converts the candidate's voice data into text data using speech recognition technology and evaluates the candidate's abilities (communication, leadership, teamwork, etc.) using a natural language processing model. Simultaneously, it analyzes video data and applies facial recognition technology to identify the candidate's emotional state.

[0137] Furthermore, the server utilizes an emotion engine to recognize the user's emotions. This emotion engine analyzes emotional data from the interviewer's tone of voice, body movements, and facial expressions. This makes it possible to understand how the interviewer's emotions are changing in real time.

[0138] Based on this data, the server can not only generate candidate evaluation reports, but also incorporate user sentiment data analyzed by the sentiment engine into the reports. As a result, it provides insights into how interviewers evaluate candidates based on their emotions.

[0139] For example, the system can consider how the interviewer reacted to a particular question and indicate that this could influence the evaluation in that area. The device then provides the interviewer with a final evaluation report, which they can use to make a comprehensive assessment of the candidate's suitability.

[0140] This system reduces subjective evaluation biases by interviewers, resulting in a more objective and fair hiring process. The introduction of an emotion engine allows for a deeper understanding of the interaction between candidates and interviewers, thereby improving the quality of interviews.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The device begins recording video and audio data of both the candidate and the interviewer (user) in real time as soon as the interview starts. This collects data on the actions and statements of both parties.

[0144] Step 2:

[0145] The server converts the received candidate's voice data into text data using speech recognition technology. This text data is then input into a natural language processing (NLP) model for analysis to evaluate the candidate's communication skills and problem-solving abilities.

[0146] Step 3:

[0147] The server analyzes the candidate's video data and uses facial recognition technology to identify their emotional state. It interprets the meaning behind the candidate's facial changes and understands their internal emotional dynamics.

[0148] Step 4:

[0149] The server analyzes the user's video and audio data based on an emotion engine. The emotion engine evaluates the user's emotions in real time based on their voice tone and facial expressions. This evaluation is used to understand the interviewer's psychological state during question-and-answer sessions.

[0150] Step 5:

[0151] The server integrates candidate competence assessments and emotional states, as well as user emotional assessments, to generate a comprehensive evaluation report. This report includes an emotional state timeline and scoring.

[0152] Step 6:

[0153] The server sends the final evaluation report to the terminal and displays it to the interviewer, who is the user. Based on this report, the interviewer can gain emotionally-driven insights and conduct a fairer, more balanced evaluation.

[0154] (Example 2)

[0155] 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".

[0156] Traditional interview processes were prone to bias due to the evaluator's subjectivity, making it difficult to objectively assess the candidate's abilities and suitability. Furthermore, it was difficult to adequately capture emotional changes during the interview, which could result in reduced evaluation accuracy. This made it challenging to achieve a fair and objective recruitment process.

[0157] 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.

[0158] In this invention, the server includes means for acquiring and communicating the voices of candidates and interviewers, means for analyzing the acquired voice information and converting it into text information, and means for analyzing recorded video information to identify the emotional state of the person being evaluated. This makes it possible to visualize the emotions of both parties during the interview and improve the objectivity and fairness of the evaluation.

[0159] A "candidate" is an individual who is subject to evaluation and selection, and whose abilities and suitability are assessed during an interview.

[0160] An "interviewer" is the person responsible for evaluating candidates and managing the interview process.

[0161] "Audio information" refers to the voices and audio data of candidates and interviewers, and is the data that will be analyzed.

[0162] "Textual information" refers to data in text format obtained by analyzing audio information.

[0163] "Visual information" refers to the visual data of candidates and interviewers recorded by cameras, etc., and is the data to be analyzed.

[0164] "Persons being evaluated" refers to individuals whose abilities are assessed based on data obtained from video and audio information.

[0165] "Emotional state" is an indicator that shows the psychological or emotional state of a candidate or interviewer.

[0166] An "evaluation report" is a document that summarizes the candidate's abilities, suitability, the interviewer's emotional state, and other factors, and records the evaluation results.

[0167] A "generative language model" is a computational model used in natural language processing to analyze speech and text and understand human language.

[0168] A "facial expression recognition algorithm" is a technology that analyzes a person's facial expressions from video information and identifies their emotional state.

[0169] This invention is a system that analyzes the emotions of candidates and interviewers in real time to improve the quality of the evaluation process. This system is implemented using the following hardware and software.

[0170] The terminal is equipped with a high-resolution camera and a high-sensitivity microphone, simultaneously recording audio and video information of both the candidate and the interviewer. This data is transmitted in real time to a server via a communication line.

[0171] The server converts received speech information into text information using a generative language model. A common cloud-based service providing speech recognition technology can be used as the generative language model. The text information is further analyzed using natural language processing techniques to evaluate the candidate's abilities.

[0172] The video information is analyzed by software equipped with a facial recognition algorithm to identify the candidate's emotional state. This algorithm detects the facial feature points of the person being evaluated and infers emotions from their movements.

[0173] Furthermore, the interviewer's voice tone and body movements are analyzed, and their emotional state is evaluated in real time. This evaluation uses an emotion analysis engine and is an advanced technology for understanding human emotions.

[0174] These analysis results are integrated by the server, and an evaluation report, including emotional states, is generated. Finally, the terminal provides this evaluation report to the interviewer, who can then use it to assess the candidate's overall suitability.

[0175] Specific usage examples and prompt messages

[0176] For example, an interviewer might ask a candidate, "Please tell me specifically how you demonstrated leadership in a team." In this scenario, the device records the interviewer's reactions and emotional changes, and the server uses this information to inform the evaluation report.

[0177] An example of a prompt message is, "Based on the evaluation report from this interview system, please quantify the candidate's communication skills and propose evaluation criteria." This allows for objective and fair evaluation.

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The terminal uses a camera and microphone installed in the interview room to simultaneously acquire video and audio information from both the candidate and the interviewer (the user). The input is video and audio, and the output is a signal transmitted to the server in real time. The video information is recorded in detail by a high-resolution camera, capturing the candidate's facial expressions and movements. The audio information is accurately captured by a high-sensitivity microphone, capturing both parties' statements.

[0181] Step 2:

[0182] The server utilizes an AI model to generate received audio information and converts it into text using speech recognition technology. The input is audio data sent from the terminal, and the output is text data. This conversion transcribes the content of the interview into text, generating text data. This then enables further natural language processing.

[0183] Step 3:

[0184] The server uses the converted text data to perform natural language processing and evaluate multiple abilities of the candidates, such as communication skills and leadership. The input is text data converted from speech, and the output is the evaluation results. By utilizing a generative AI model, the content and nuances of the text are analyzed, and the characteristics of the candidates are quantified.

[0185] Step 4:

[0186] The server analyzes video information and identifies emotional states through facial recognition algorithms. The input is video data transmitted from the terminal, and the output is the candidate's emotion label. By analyzing facial feature points and changes in expression, emotions such as excitement, tension, and joy are identified.

[0187] Step 5:

[0188] The server uses an emotion analysis engine that analyzes the interviewer's voice tone, facial expressions, and body movements to identify their emotional state. The input is the interviewer's voice and video data, and the output is data on the interviewer's emotional changes. This allows for real-time monitoring of the interviewer's emotional responses.

[0189] Step 6:

[0190] The server integrates sentiment data from both candidates and interviewers to generate a comprehensive evaluation report. The input consists of various evaluation data from both candidates and interviewers, and the output is a detailed evaluation report. The report includes an overview of the entire interview process and a summary of the evaluation, highlighting specific evaluation points.

[0191] Step 7:

[0192] The terminal provides the generated evaluation report to the interviewer, who is the user. The input is the evaluation report output from the server, and the output is the information provided to the user. Based on this report, the user can assess the candidate's overall suitability.

[0193] (Application Example 2)

[0194] 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".

[0195] In the interview process, it is difficult to objectively evaluate the emotions of both the interviewer and the candidate, and the process is often influenced by subjective judgments. This invention aims to provide a method for conducting this process more objectively and fairly. Furthermore, it aims to improve the quality of interviews by taking into account the interviewer's own emotions.

[0196] 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.

[0197] In this invention, the server is capable of communicating with an information terminal that records the actions of candidates and users, and includes means for analyzing recorded audio information and converting it into text information, means for analyzing recorded video information and identifying the emotional states of candidates and users, and means for analyzing the text information and evaluating the behavioral characteristics of candidates. This enables the visualization of emotions in the interview process and more accurate evaluation.

[0198] An "information terminal" is an electronic device used for collecting, processing, and communicating data, and in this context, it refers to a device that has the function of recording the actions of candidates and users.

[0199] "Voice information" refers to data that includes the statements and voice characteristics of candidates and users, and is subject to analysis after being recorded.

[0200] "Text information" refers to data obtained by converting analyzed audio information into text or linguistic format, and is used to evaluate the behavioral characteristics of candidates.

[0201] "Visual information" refers to visual data that records the posture, facial expressions, or movements of candidates and users, and is used to identify their emotional state.

[0202] "Emotional state" refers to information that reflects the psychological and physiological state exhibited by candidates and users, and is analyzed through facial expressions and body language.

[0203] "Behavioral characteristics" refer to data that describes the characteristics of a candidate's behavior and reactions under specific circumstances, and are used to assess their abilities during interviews.

[0204] "Evaluation materials" are report documents generated by integrating various analytical data, and are provided to users to help them determine the suitability of candidates.

[0205] The system for implementing this invention consists mainly of an information terminal, a server, and an analysis engine. The information terminal is equipped with a camera and microphone to record the actions of the candidate and user during the interview, thereby acquiring audio and video information. The acquired data is transmitted to the server in real time.

[0206] The server is equipped with software that converts speech information into text information using speech recognition technology. Specifically, it utilizes natural language processing technology to analyze the candidate's statements and extract behavioral characteristics. In addition, the server analyzes video information using facial recognition techniques to identify the emotional state of the candidate and the user. This reveals emotional changes during the interview.

[0207] Based on the collected data, the server generates evaluation materials. These materials integrate and include assessments of the candidate's behavioral characteristics, cross-cultural adaptability, and the user's emotional state. This material is provided to the user and used to assist in assessing the candidate's suitability.

[0208] As a concrete example, suppose a user asks a candidate during an interview, "Please tell me about a success story from your past experience." In this case, the candidate's response, recorded by an information terminal, and the user's reaction are analyzed as part of the evaluation materials and evaluated as a numerical indicator on the server.

[0209] An example of a prompt to input into the generating AI model is, "Analyze the emotions of the candidate and interviewer during the interview in real time and reflect this in the evaluation report after the interview." This prompt will initiate the appropriate data analysis.

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The device records video and audio of the candidate and interviewer during the interview. Input is data acquired by the camera and microphone, and output is the raw data. This data is transmitted to the server in real time and serves as foundational data for analysis.

[0213] Step 2:

[0214] The server uses speech recognition technology to convert the acquired audio data into text data. The input is audio information transmitted in real time, and the output is text information extracted through natural language processing. This process makes it possible to understand the content of the candidate's statements.

[0215] Step 3:

[0216] The server analyzes video data using facial recognition techniques. The input is video information of the candidate and the interviewer, and the output is the identification of their emotional state based on this information. The server analyzes emotional changes from changes in facial expressions and updates the information in real time.

[0217] Step 4:

[0218] The server uses the analyzed text data to evaluate the candidate's behavioral characteristics. The input is text information converted from speech, and the output is an evaluation index for behavioral characteristics. Natural language processing models are used to reflect the content and tone of speech in the evaluation.

[0219] Step 5:

[0220] Users review evaluation reports and make decisions based on interview results. Input is integrated evaluation data provided by the server, and output is the user's decision on whether to hire or reject a candidate. Users can conduct a comprehensive aptitude assessment based on a wide range of information, including sentiment analysis.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] This invention provides a system for evaluating a candidate's soft skills and cultural adaptability in real time during the interview process. The system analyzes the candidate's actions, statements, and emotional state, and generates a comprehensive evaluation report based on these. The following describes a specific implementation of this system.

[0238] First, during the interview, the terminal records the candidate's video and audio in real time and sends the data to the server. The server receives this data and converts the audio data into text using speech recognition technology. The converted text data is then processed using natural language processing (NLP) technology to evaluate the candidate's various abilities, such as communication skills, problem-solving ability, teamwork, and leadership.

[0239] Furthermore, the server analyzes the candidate's facial expressions using video data and identifies their emotional state in real time using emotion recognition technology. This allows for an understanding of the candidate's emotions.

[0240] Furthermore, the server integrates this data to measure the results of multiple competency assessments and the candidate's adaptability in different cultures. It analyzes cross-cultural understanding and behavioral patterns to calculate cultural adaptability.

[0241] Finally, the server generates a comprehensive evaluation report of each candidate based on these analysis results. This report includes each candidate's soft skills score and cultural adaptation index. The terminal provides this evaluation report to the interviewer, who can then use it to quickly and accurately assess the candidate's suitability.

[0242] As a concrete example, in interviews for candidates capable of demonstrating leadership in international projects, this system can analyze the candidate's words and emotional state when they discuss their experience collaborating with team members from different cultures, thereby highly evaluating their leadership abilities and cultural adaptability. As a result, interviewers can objectively assess the candidate's suitability and receive support in selecting the most suitable candidate.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The device records the candidate's audio and video data in real time at the start of the interview and sends it to the server. Video is collected by the camera and audio by the microphone.

[0246] Step 2:

[0247] The server processes the received audio data through a speech recognition engine, converting it into text data based on natural language. This text data is used for subsequent natural language processing, therefore, a highly accurate conversion is required.

[0248] Step 3:

[0249] The server analyzes text data using a natural language processing (NLP) model to extract specific keywords and themes. This allows it to calculate scores that evaluate candidates' communication skills and problem-solving abilities.

[0250] Step 4:

[0251] The server analyzes how faces appear in the video data and uses facial recognition technology to identify emotional states. This allows it to determine what emotions the candidate is showing during the interview.

[0252] Step 5:

[0253] The server evaluates the candidate's cultural adaptability by comprehensively considering their statements and facial expressions. Statements indicating cross-cultural experience or understanding of other cultures are indexed accordingly. This index serves as an indicator of the candidate's ability to cope with diversity.

[0254] Step 6:

[0255] The server integrates all analytical data and generates a comprehensive evaluation report that includes the candidate's skills and cultural adaptability. The report clearly displays the scoring and visually represents each ability.

[0256] Step 7:

[0257] The server sends the generated evaluation report to the terminal and presents it to the interviewer, who is the user. Based on this report, the interviewer evaluates and judges the candidate's suitability and compatibility with the organization.

[0258] (Example 1)

[0259] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0260] In today's business environment, quickly and accurately assessing the suitability of candidates from diverse cultural backgrounds is crucial for ensuring international competitiveness. However, traditional interview processes often struggle to objectively evaluate candidates' soft skills and cross-cultural adaptability, tending to rely on the evaluator's subjectivity. This creates a risk of making incorrect decisions when selecting suitable personnel. This invention aims to solve this problem by providing a structured and fair evaluation of candidates' skills and adaptability.

[0261] 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.

[0262] In this invention, the server is capable of communicating with a device that collects the candidate's behavior and includes means for analyzing acquired audio information and converting it into text information, means for analyzing acquired image information and identifying the candidate's emotional state, means for analyzing the text information and evaluating the candidate's multiple abilities, algorithm means for enhancing ability evaluation based on the analysis of the behavior and statements, and means for utilizing a model for measuring cross-cultural adaptability. This makes it possible to accurately evaluate each candidate's abilities and cultural adaptability and immediately provide the evaluation results to the interviewer.

[0263] A "candidate" is a person who is evaluated during the interview and selection process.

[0264] "Behavior" refers to dynamic responses and actions, including gestures, verbal expressions, and facial expressions, that are demonstrated by the candidate.

[0265] "Audio information" refers to sound data obtained from the words and vocalizations spoken by the candidates.

[0266] "Textual information" refers to data in text format obtained by analyzing audio information.

[0267] "Image information" refers to visual data that records the candidate's facial expressions and movements.

[0268] "Emotional state" refers to the identification of a candidate's psychological and emotional state based on the results of facial expression and voice analysis.

[0269] "Competency assessment" is a process of objectively analyzing and measuring a candidate's multiple skills, such as communication skills, problem-solving abilities, and teamwork skills.

[0270] "Cross-cultural adaptability" is a measure of a candidate's ability to adapt flexibly and act effectively within different cultural backgrounds.

[0271] An "evaluation report" is a document that summarizes the results of an analysis of a candidate's various abilities and cross-cultural adaptability, and serves as reference material for the hiring decision.

[0272] "Users" refers to interviewers and recruiters who make decisions about whether or not to hire candidates based on evaluation reports.

[0273] An "algorithmic method" is a set of computational procedures for analyzing and processing data, and a series of computational processes for evaluating the characteristics and abilities of candidates.

[0274] A "model" is a mathematical or AI-based system used to perform specific evaluations or predictions based on data.

[0275] The system in this invention aims to evaluate soft skills and cultural adaptability in real time during the candidate interview process. Specifically, it consists of three main components: a terminal, a server, and a user.

[0276] First, the terminal uses a high-resolution camera and a high-sensitivity microphone during the interview. For example, it uses a camera and audio input device built into a typical laptop, or an externally connected webcam and dedicated microphone, to record the candidate's video and audio in real time and organize the data into a technically appropriate format. The organized data is then transmitted to a server via the internet.

[0277] The server converts received audio data into text information using AI-based speech recognition software (e.g., a speech recognition API for speech analysis). This text information is then subjected to grammatical analysis, keyword extraction, and sentiment analysis using natural language processing techniques to evaluate multiple candidate abilities, such as communication skills and problem-solving abilities. Additionally, video data is analyzed using facial expression recognition technology (e.g., a face recognition API) to identify the candidate's emotional state.

[0278] In addition, the server integrates the aforementioned audio and video data and uses an AI model designed to measure cross-cultural adaptability. This model calculates cultural adaptability by analyzing the candidate's cross-cultural understanding and behavioral patterns.

[0279] Finally, the server generates a comprehensive evaluation report based on these analysis results. This report includes soft skills evaluation scores and a cultural adaptation index.

[0280] The generated evaluation report is provided to the interviewer (user) via the terminal, allowing the interviewer to quickly and accurately assess the candidate's suitability based on it.

[0281] As a specific example, for candidates for positions that require project leadership in a cross-cultural environment, this system analyzes their cooperation experience in cross-cultural teams and evaluates their leadership ability and cultural adaptability. Based on these results, interviewers can objectively evaluate candidates and select talents suitable for a diverse workplace environment.

[0282] As an example of a prompt sentence, questions such as "Please tell me about an example where you demonstrated leadership in a project with a cross-cultural team based on your experience" can be considered.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The terminal uses a high-resolution camera and a high-sensitivity microphone during the interview to record the video and audio of the candidate. This input data comprehensively captures the candidate's actions and statements, and after being converted into a secure file format, it is transmitted to the server through the Internet. As a specific operation, for example, recording starts by pressing the capture start button of the video stream.

[0286] Step 2:

[0287] The server converts the transmitted audio data into text data using an AI-based speech recognition tool. In this process, language elements are extracted from the acoustic signal to generate an output in string format. This accumulates the candidate's statement content in the database and enables natural language processing. Specifically, when the audio data is received, the speech recognition algorithm automatically operates and text is generated within a few seconds.

[0288] Step 3:

[0289] The server uses natural language processing (NLP) techniques to analyze the converted text data and evaluate the candidate's abilities. This involves identifying the text's grammatical structure, keywords, and sentiment (emotional tone) to calculate the candidate's communication and problem-solving skills. For example, this analysis identifies frequently used positive or negative expressions. These results are used in scoring and form part of the candidate's overall ability assessment.

[0290] Step 4:

[0291] The server inputs video data into an facial recognition algorithm to analyze the candidate's emotional state. Here, various facial expressions of the candidate are recognized and classified into specific emotions, such as smiles or surprise. The output emotional data serves as an indicator of the candidate's emotions during the interview. This process involves frame-by-frame analysis, and the emotional state is updated in real time.

[0292] Step 5:

[0293] The server integrates the analyzed audio and video data and uses an AI model designed to assess cross-cultural adaptability. This model analyzes the candidate's understanding of different cultures and behavioral patterns to calculate their cultural adaptability. Specifically, the model estimates the degree of leadership and collaborative ability in different cultures and compiles the results into evaluation indicators. These results are reflected in the report as the candidate's cross-cultural adaptability index.

[0294] Step 6:

[0295] Based on these analysis results, the server generates a comprehensive evaluation report for each candidate. This report includes soft skills scores and a cultural adaptation index, and is provided to the interviewer (the user). The generation process integrates the evaluation results for each ability, producing a clear and easy-to-understand visualized output. The evaluation report is provided to the interviewer in digital format, helping them to quickly and accurately assess the candidate's overall suitability.

[0296] (Application Example 1)

[0297] 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."

[0298] In selecting candidates, a comprehensive assessment of soft skills, cultural adaptability, and awareness and response skills regarding safety measures is required. However, traditional interview and evaluation systems have struggled to accurately analyze these aspects in real time and generate detailed evaluation results. As a result, the process of selecting suitable personnel within companies has been inefficient, and there has been a risk of overlooking the potential of potential employees.

[0299] 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.

[0300] In this invention, the server is capable of communicating with a device that records the actions of candidates, and includes means for analyzing recorded audio data and converting it into text data, means for analyzing recorded video data and identifying the candidate's emotional state, means for analyzing the text data and evaluating multiple abilities of the candidate, means for evaluating the candidate's adaptability in different cultures, means for evaluating the candidate's awareness and response skills regarding safety measures, means for generating an evaluation report that integrates the evaluations of the multiple abilities, adaptability, and safety measures, and means for providing the evaluation report to the user. This makes it possible to efficiently and accurately grasp the wide range of abilities, adaptability, and safety-related abilities required in the candidate selection and evaluation process.

[0301] "Device" refers to hardware or software used to record data and communicate with other systems.

[0302] A "server" refers to a central computer that receives, analyzes, and processes data.

[0303] "Voice data" refers to digital acoustic information that records the content spoken by a candidate.

[0304] "Text data" refers to digital information obtained by converting voice data into character information.

[0305] "Video data" refers to digital visual information that records the actions and expressions of a candidate.

[0306] "Emotional state" refers to information identified as indicating the emotions and psychological state of a candidate.

[0307] "Multiple abilities" refers to various abilities of a candidate, such as communication skills and problem-solving abilities.

[0308] "Adaptability in culture" refers to the ability of a candidate to adapt to different cultural environments.

[0309] "Awareness and response skills regarding safety measures" refers to the ability of a candidate to have awareness about safety and respond appropriately.

[0310] "Evaluation report" refers to a report that comprehensively shows the abilities and adaptability of a candidate, generated based on the analysis results.

[0311] "User" refers to an individual or group that receives an evaluation report and selects a candidate.

[0312] To implement this invention, first, a server and a terminal are required. When conducting an interview with a candidate, the terminal records their actions and statements in real time. The data recorded in this process includes voice data and video data. The voice data is sent to the server and converted into text data using speech recognition technology. Specifically, this conversion is performed using a speech recognition service such as Google Cloud Speech-to-Text.

[0313] The server performs analysis on the converted text data using natural language processing (NLP) techniques. NLP utilizes language processing models such as spaCy and BERT to evaluate candidates' communication skills and problem-solving abilities. During this process, awareness of safety measures and response skills are also assessed based on the candidates' statements.

[0314] The server also processes the candidate's video data and identifies their emotional state based on an emotion recognition model. This process is carried out using a service such as the Microsoft Azure Face API, which allows for the identification of changes in the candidate's emotions and psychological state in real time.

[0315] By integrating this data, the server generates a comprehensive evaluation report that includes assessments of the candidate's multiple competencies, cultural adaptability, and safety measures. This evaluation report is provided to the user via a terminal, allowing the user to quickly and accurately assess the candidate's suitability.

[0316] As a concrete example, when selecting a leader for an international project, the server uses this system to analyze the content and emotional state of candidates when they talk about their experience collaborating with team members from different cultures. This allows for an objective assessment of the candidates' leadership abilities and cultural adaptability, making it possible to determine their suitability for the role.

[0317] An example of a prompt for the generating AI model is: "Please evaluate this candidate's security awareness. Below is a record of the candidate's statements. Question 1: What are your thoughts on recent changes to security protocols?"

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The terminal records the candidate's audio and video data in real time during the interview. This input data is used to capture the candidate's statements and actions in detail during the interview. The recorded data is then sent to a server.

[0321] Step 2:

[0322] The server converts the audio data received from the terminal into text data using speech recognition technology. Specifically, it uses Google Cloud Speech-to-Text to convert the audio signal into language data. This conversion outputs the specific content spoken by the candidate as text information.

[0323] Step 3:

[0324] The server analyzes text data using natural language processing (NLP) techniques. This process utilizes language models such as spaCy and BERT to extract important keywords and phrases from the text data. This generates output data for evaluating candidates' communication skills, problem-solving abilities, and awareness of safety measures.

[0325] Step 4:

[0326] Simultaneously, the server processes the video data and uses an emotion recognition model to identify the candidate's emotional state. Leveraging the Microsoft Azure Face API, it analyzes facial expressions from the video to extract the candidate's psychological state and emotional changes.

[0327] Step 5:

[0328] The server integrates the analyzed sentiment data and natural language processing results to generate a comprehensive evaluation report that includes the candidate's multiple abilities, cross-cultural adaptability, and safety awareness. This ensures that all evaluation results are output as a single, comprehensive report, making it easily accessible to the user.

[0329] Step 6:

[0330] Users receive this integrated evaluation report on their device. Based on the report, users can objectively assess candidates' leadership abilities, cultural adaptability, and safety management skills, and proceed with the selection process.

[0331] 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.

[0332] This invention is a system that aims to improve the quality of the interview process by analyzing the emotions of not only the candidate but also the interviewer (the user) in real time during the interview. This system grasps the emotional state of both the candidate and the interviewer and utilizes that data for interview evaluation. Specific embodiments are shown below.

[0333] First, the device records video and audio data of the candidate during the interview, while simultaneously recording the interviewer's presence via the camera and microphone. This data is transmitted to the server in real time.

[0334] The server converts the candidate's voice data into text data using speech recognition technology and evaluates the candidate's abilities (communication, leadership, teamwork, etc.) using a natural language processing model. Simultaneously, it analyzes video data and applies facial recognition technology to identify the candidate's emotional state.

[0335] Furthermore, the server utilizes an emotion engine to recognize the user's emotions. This emotion engine analyzes emotional data from the interviewer's tone of voice, body movements, and facial expressions. This makes it possible to understand how the interviewer's emotions are changing in real time.

[0336] Based on this data, the server can not only generate candidate evaluation reports, but also incorporate user sentiment data analyzed by the sentiment engine into the reports. As a result, it provides insights into how interviewers evaluate candidates based on their emotions.

[0337] For example, the system can consider how the interviewer reacted to a particular question and indicate that this could influence the evaluation in that area. The device then provides the interviewer with a final evaluation report, which they can use to make a comprehensive assessment of the candidate's suitability.

[0338] This system reduces subjective evaluation biases by interviewers, resulting in a more objective and fair hiring process. The introduction of an emotion engine allows for a deeper understanding of the interaction between candidates and interviewers, thereby improving the quality of interviews.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The device begins recording video and audio data of both the candidate and the interviewer (user) in real time as soon as the interview starts. This collects data on the actions and statements of both parties.

[0342] Step 2:

[0343] The server converts the received candidate's voice data into text data using speech recognition technology. This text data is then input into a natural language processing (NLP) model for analysis to evaluate the candidate's communication skills and problem-solving abilities.

[0344] Step 3:

[0345] The server analyzes the candidate's video data and uses facial recognition technology to identify their emotional state. It interprets the meaning behind the candidate's facial changes and understands their internal emotional dynamics.

[0346] Step 4:

[0347] The server analyzes the user's video and audio data based on an emotion engine. The emotion engine evaluates the user's emotions in real time based on their voice tone and facial expressions. This evaluation is used to understand the interviewer's psychological state during question-and-answer sessions.

[0348] Step 5:

[0349] The server integrates candidate competence assessments and emotional states, as well as user emotional assessments, to generate a comprehensive evaluation report. This report includes an emotional state timeline and scoring.

[0350] Step 6:

[0351] The server sends the final evaluation report to the terminal and displays it to the interviewer, who is the user. Based on this report, the interviewer can gain emotionally-driven insights and conduct a fairer, more balanced evaluation.

[0352] (Example 2)

[0353] 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".

[0354] Traditional interview processes were prone to bias due to the evaluator's subjectivity, making it difficult to objectively assess the candidate's abilities and suitability. Furthermore, it was difficult to adequately capture emotional changes during the interview, which could result in reduced evaluation accuracy. This made it challenging to achieve a fair and objective recruitment process.

[0355] 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.

[0356] In this invention, the server includes means for acquiring and communicating the voices of candidates and interviewers, means for analyzing the acquired voice information and converting it into text information, and means for analyzing recorded video information to identify the emotional state of the person being evaluated. This makes it possible to visualize the emotions of both parties during the interview and improve the objectivity and fairness of the evaluation.

[0357] A "candidate" is an individual who is subject to evaluation and selection, and whose abilities and suitability are assessed during an interview.

[0358] An "interviewer" is the person responsible for evaluating candidates and managing the interview process.

[0359] "Audio information" refers to the voices and audio data of candidates and interviewers, and is the data that will be analyzed.

[0360] "Textual information" refers to data in text format obtained by analyzing audio information.

[0361] "Visual information" refers to the visual data of candidates and interviewers recorded by cameras, etc., and is the data to be analyzed.

[0362] "Persons being evaluated" refers to individuals whose abilities are assessed based on data obtained from video and audio information.

[0363] "Emotional state" is an indicator that shows the psychological or emotional state of a candidate or interviewer.

[0364] An "evaluation report" is a document that summarizes the candidate's abilities, suitability, the interviewer's emotional state, and other factors, and records the evaluation results.

[0365] A "generative language model" is a computational model used in natural language processing to analyze speech and text and understand human language.

[0366] A "facial expression recognition algorithm" is a technology that analyzes a person's facial expressions from video information and identifies their emotional state.

[0367] This invention is a system that analyzes the emotions of candidates and interviewers in real time to improve the quality of the evaluation process. This system is implemented using the following hardware and software.

[0368] The terminal is equipped with a high-resolution camera and a high-sensitivity microphone, simultaneously recording audio and video information of both the candidate and the interviewer. This data is transmitted in real time to a server via a communication line.

[0369] The server converts received speech information into text information using a generative language model. A common cloud-based service providing speech recognition technology can be used as the generative language model. The text information is further analyzed using natural language processing techniques to evaluate the candidate's abilities.

[0370] The video information is analyzed by software equipped with a facial recognition algorithm to identify the candidate's emotional state. This algorithm detects the facial feature points of the person being evaluated and infers emotions from their movements.

[0371] Furthermore, the interviewer's voice tone and body movements are analyzed, and their emotional state is evaluated in real time. This evaluation uses an emotion analysis engine and is an advanced technology for understanding human emotions.

[0372] These analysis results are integrated by the server, and an evaluation report, including emotional states, is generated. Finally, the terminal provides this evaluation report to the interviewer, who can then use it to assess the candidate's overall suitability.

[0373] Specific usage examples and prompt messages

[0374] For example, an interviewer might ask a candidate, "Please tell me specifically how you demonstrated leadership in a team." In this scenario, the device records the interviewer's reactions and emotional changes, and the server uses this information to inform the evaluation report.

[0375] An example of a prompt message is, "Based on the evaluation report from this interview system, please quantify the candidate's communication skills and propose evaluation criteria." This allows for objective and fair evaluation.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The terminal uses a camera and microphone installed in the interview room to simultaneously acquire video and audio information from both the candidate and the interviewer (the user). The input is video and audio, and the output is a signal transmitted to the server in real time. The video information is recorded in detail by a high-resolution camera, capturing the candidate's facial expressions and movements. The audio information is accurately captured by a high-sensitivity microphone, capturing both parties' statements.

[0379] Step 2:

[0380] The server utilizes an AI model to generate received audio information and converts it into text using speech recognition technology. The input is audio data sent from the terminal, and the output is text data. This conversion transcribes the content of the interview into text, generating text data. This then enables further natural language processing.

[0381] Step 3:

[0382] The server uses the converted text data to perform natural language processing and evaluate multiple abilities of the candidates, such as communication skills and leadership. The input is text data converted from speech, and the output is the evaluation results. By utilizing a generative AI model, the content and nuances of the text are analyzed, and the characteristics of the candidates are quantified.

[0383] Step 4:

[0384] The server analyzes video information and identifies emotional states through facial recognition algorithms. The input is video data transmitted from the terminal, and the output is the candidate's emotion label. By analyzing facial feature points and changes in expression, emotions such as excitement, tension, and joy are identified.

[0385] Step 5:

[0386] The server uses an emotion analysis engine that analyzes the interviewer's voice tone, facial expressions, and body movements to identify their emotional state. The input is the interviewer's voice and video data, and the output is data on the interviewer's emotional changes. This allows for real-time monitoring of the interviewer's emotional responses.

[0387] Step 6:

[0388] The server integrates sentiment data from both candidates and interviewers to generate a comprehensive evaluation report. The input consists of various evaluation data from both candidates and interviewers, and the output is a detailed evaluation report. The report includes an overview of the entire interview process and a summary of the evaluation, highlighting specific evaluation points.

[0389] Step 7:

[0390] The terminal provides the generated evaluation report to the interviewer, who is the user. The input is the evaluation report output from the server, and the output is the information provided to the user. Based on this report, the user can assess the candidate's overall suitability.

[0391] (Application Example 2)

[0392] 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".

[0393] In the interview process, it is difficult to objectively evaluate the emotions of both the interviewer and the candidate, and the process is often influenced by subjective judgments. This invention aims to provide a method for conducting this process more objectively and fairly. Furthermore, it aims to improve the quality of interviews by taking into account the interviewer's own emotions.

[0394] 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.

[0395] In this invention, the server is capable of communicating with an information terminal that records the actions of candidates and users, and includes means for analyzing recorded audio information and converting it into text information, means for analyzing recorded video information and identifying the emotional states of candidates and users, and means for analyzing the text information and evaluating the behavioral characteristics of candidates. This enables the visualization of emotions in the interview process and more accurate evaluation.

[0396] An "information terminal" is an electronic device used for collecting, processing, and communicating data, and in this context, it refers to a device that has the function of recording the actions of candidates and users.

[0397] "Voice information" refers to data that includes the statements and voice characteristics of candidates and users, and is subject to analysis after being recorded.

[0398] "Text information" refers to data obtained by converting analyzed audio information into text or linguistic format, and is used to evaluate the behavioral characteristics of candidates.

[0399] "Visual information" refers to visual data that records the posture, facial expressions, or movements of candidates and users, and is used to identify their emotional state.

[0400] "Emotional state" refers to information that reflects the psychological and physiological state exhibited by candidates and users, and is analyzed through facial expressions and body language.

[0401] "Behavioral characteristics" refer to data that describes the characteristics of a candidate's behavior and reactions under specific circumstances, and are used to assess their abilities during interviews.

[0402] "Evaluation materials" are report documents generated by integrating various analytical data, and are provided to users to help them determine the suitability of candidates.

[0403] The system for implementing this invention consists mainly of an information terminal, a server, and an analysis engine. The information terminal is equipped with a camera and microphone to record the actions of the candidate and user during the interview, thereby acquiring audio and video information. The acquired data is transmitted to the server in real time.

[0404] The server is equipped with software that converts speech information into text information using speech recognition technology. Specifically, it utilizes natural language processing technology to analyze the candidate's statements and extract behavioral characteristics. In addition, the server analyzes video information using facial recognition techniques to identify the emotional state of the candidate and the user. This reveals emotional changes during the interview.

[0405] Based on the collected data, the server generates evaluation materials. These materials integrate and include assessments of the candidate's behavioral characteristics, cross-cultural adaptability, and the user's emotional state. This material is provided to the user and used to assist in assessing the candidate's suitability.

[0406] As a concrete example, suppose a user asks a candidate during an interview, "Please tell me about a success story from your past experience." In this case, the candidate's response, recorded by an information terminal, and the user's reaction are analyzed as part of the evaluation materials and evaluated as a numerical indicator on the server.

[0407] An example of a prompt to input into the generating AI model is, "Analyze the emotions of the candidate and interviewer during the interview in real time and reflect this in the evaluation report after the interview." This prompt will initiate the appropriate data analysis.

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The device records video and audio of the candidate and interviewer during the interview. Input is data acquired by the camera and microphone, and output is the raw data. This data is transmitted to the server in real time and serves as foundational data for analysis.

[0411] Step 2:

[0412] The server uses speech recognition technology to convert the acquired audio data into text data. The input is audio information transmitted in real time, and the output is text information extracted through natural language processing. This process makes it possible to understand the content of the candidate's statements.

[0413] Step 3:

[0414] The server analyzes video data using facial recognition techniques. The input is video information of the candidate and the interviewer, and the output is the identification of their emotional state based on this information. The server analyzes emotional changes from changes in facial expressions and updates the information in real time.

[0415] Step 4:

[0416] The server uses the analyzed text data to evaluate the candidate's behavioral characteristics. The input is text information converted from speech, and the output is an evaluation index for behavioral characteristics. Natural language processing models are used to reflect the content and tone of speech in the evaluation.

[0417] Step 5:

[0418] Users review evaluation reports and make decisions based on interview results. Input is integrated evaluation data provided by the server, and output is the user's decision on whether to hire or reject a candidate. Users can conduct a comprehensive aptitude assessment based on a wide range of information, including sentiment analysis.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] [Third Embodiment]

[0423] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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".

[0435] This invention provides a system for evaluating a candidate's soft skills and cultural adaptability in real time during the interview process. The system analyzes the candidate's actions, statements, and emotional state, and generates a comprehensive evaluation report based on these. The following describes a specific implementation of this system.

[0436] First, during the interview, the terminal records the candidate's video and audio in real time and sends the data to the server. The server receives this data and converts the audio data into text using speech recognition technology. The converted text data is then processed using natural language processing (NLP) technology to evaluate the candidate's various abilities, such as communication skills, problem-solving ability, teamwork, and leadership.

[0437] Furthermore, the server analyzes the candidate's facial expressions using video data and identifies their emotional state in real time using emotion recognition technology. This allows for an understanding of the candidate's emotions.

[0438] Furthermore, the server integrates this data to measure the results of multiple competency assessments and the candidate's adaptability in different cultures. It analyzes cross-cultural understanding and behavioral patterns to calculate cultural adaptability.

[0439] Finally, the server generates a comprehensive evaluation report of each candidate based on these analysis results. This report includes each candidate's soft skills score and cultural adaptation index. The terminal provides this evaluation report to the interviewer, who can then use it to quickly and accurately assess the candidate's suitability.

[0440] As a concrete example, in interviews for candidates capable of demonstrating leadership in international projects, this system can analyze the candidate's words and emotional state when they discuss their experience collaborating with team members from different cultures, thereby highly evaluating their leadership abilities and cultural adaptability. As a result, interviewers can objectively assess the candidate's suitability and receive support in selecting the most suitable candidate.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The device records the candidate's audio and video data in real time at the start of the interview and sends it to the server. Video is collected by the camera and audio by the microphone.

[0444] Step 2:

[0445] The server processes the received audio data through a speech recognition engine, converting it into text data based on natural language. This text data is used for subsequent natural language processing, therefore, a highly accurate conversion is required.

[0446] Step 3:

[0447] The server analyzes text data using a natural language processing (NLP) model to extract specific keywords and themes. This allows it to calculate scores that evaluate candidates' communication skills and problem-solving abilities.

[0448] Step 4:

[0449] The server analyzes how faces appear in the video data and uses facial recognition technology to identify emotional states. This allows it to determine what emotions the candidate is showing during the interview.

[0450] Step 5:

[0451] The server evaluates the candidate's cultural adaptability by comprehensively considering their statements and facial expressions. Statements indicating cross-cultural experience or understanding of other cultures are indexed accordingly. This index serves as an indicator of the candidate's ability to cope with diversity.

[0452] Step 6:

[0453] The server integrates all analytical data and generates a comprehensive evaluation report that includes the candidate's skills and cultural adaptability. The report clearly displays the scoring and visually represents each ability.

[0454] Step 7:

[0455] The server sends the generated evaluation report to the terminal and presents it to the interviewer, who is the user. Based on this report, the interviewer evaluates and judges the candidate's suitability and compatibility with the organization.

[0456] (Example 1)

[0457] 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."

[0458] In today's business environment, quickly and accurately assessing the suitability of candidates from diverse cultural backgrounds is crucial for ensuring international competitiveness. However, traditional interview processes often struggle to objectively evaluate candidates' soft skills and cross-cultural adaptability, tending to rely on the evaluator's subjectivity. This creates a risk of making incorrect decisions when selecting suitable personnel. This invention aims to solve this problem by providing a structured and fair evaluation of candidates' skills and adaptability.

[0459] 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.

[0460] In this invention, the server is capable of communicating with a device that collects the candidate's behavior and includes means for analyzing acquired audio information and converting it into text information, means for analyzing acquired image information and identifying the candidate's emotional state, means for analyzing the text information and evaluating the candidate's multiple abilities, algorithm means for enhancing ability evaluation based on the analysis of the behavior and statements, and means for utilizing a model for measuring cross-cultural adaptability. This makes it possible to accurately evaluate each candidate's abilities and cultural adaptability and immediately provide the evaluation results to the interviewer.

[0461] A "candidate" is a person who is evaluated during the interview and selection process.

[0462] "Behavior" refers to dynamic responses and actions, including gestures, verbal expressions, and facial expressions, that are demonstrated by the candidate.

[0463] "Audio information" refers to sound data obtained from the words and vocalizations spoken by the candidates.

[0464] "Textual information" refers to data in text format obtained by analyzing audio information.

[0465] "Image information" refers to visual data that records the candidate's facial expressions and movements.

[0466] "Emotional state" refers to the identification of a candidate's psychological and emotional state based on the results of facial expression and voice analysis.

[0467] "Competency assessment" is a process of objectively analyzing and measuring a candidate's multiple skills, such as communication skills, problem-solving abilities, and teamwork skills.

[0468] "Cross-cultural adaptability" is a measure of a candidate's ability to adapt flexibly and act effectively within different cultural backgrounds.

[0469] An "evaluation report" is a document that summarizes the results of an analysis of a candidate's various abilities and cross-cultural adaptability, and serves as reference material for the hiring decision.

[0470] "Users" refers to interviewers and recruiters who make decisions about whether or not to hire candidates based on evaluation reports.

[0471] An "algorithmic method" is a set of computational procedures for analyzing and processing data, and a series of computational processes for evaluating the characteristics and abilities of candidates.

[0472] A "model" is a mathematical or AI-based system used to perform specific evaluations or predictions based on data.

[0473] The system in this invention aims to evaluate soft skills and cultural adaptability in real time during the candidate interview process. Specifically, it consists of three main components: a terminal, a server, and a user.

[0474] First, the terminal uses a high-resolution camera and a high-sensitivity microphone during the interview. For example, it uses a camera and audio input device built into a typical laptop, or an externally connected webcam and dedicated microphone, to record the candidate's video and audio in real time and organize the data into a technically appropriate format. The organized data is then transmitted to a server via the internet.

[0475] The server converts received audio data into text information using AI-based speech recognition software (e.g., a speech recognition API for speech analysis). This text information is then subjected to grammatical analysis, keyword extraction, and sentiment analysis using natural language processing techniques to evaluate multiple candidate abilities, such as communication skills and problem-solving abilities. Additionally, video data is analyzed using facial expression recognition technology (e.g., a face recognition API) to identify the candidate's emotional state.

[0476] In addition, the server integrates the aforementioned audio and video data and uses an AI model designed to measure cross-cultural adaptability. This model calculates cultural adaptability by analyzing the candidate's cross-cultural understanding and behavioral patterns.

[0477] Finally, the server generates a comprehensive evaluation report based on these analysis results. This report includes soft skills evaluation scores and a cultural adaptation index.

[0478] The generated evaluation report is provided to the interviewer (user) via the terminal, allowing the interviewer to quickly and accurately assess the candidate's suitability based on it.

[0479] As a concrete example, for a candidate for a position requiring project leadership in a cross-cultural environment, this system analyzes their experience collaborating with cross-cultural teams and evaluates their leadership abilities and cultural adaptability. Based on these results, interviewers can objectively evaluate candidates and select individuals suitable for a diverse work environment.

[0480] An example of a prompt might be a question like, "Based on your experience, please share an example of a time when you demonstrated leadership in a project with a cross-cultural team."

[0481] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0482] Step 1:

[0483] The device uses a high-resolution camera and high-sensitivity microphone to record the candidate's video and audio during the interview. This input data comprehensively captures the candidate's actions and statements, is converted into a secure file format, and then transmitted to a server via the internet. Specifically, recording begins, for example, when the video stream capture start button is pressed.

[0484] Step 2:

[0485] The server converts the transmitted audio data into text data using an AI-based speech recognition tool. This process extracts linguistic elements from the acoustic signal and generates output in string format. This allows the candidate's utterances to be stored in a database, enabling natural language processing. Specifically, as soon as the audio data is received, the speech recognition algorithm automatically activates, and text is generated within seconds.

[0486] Step 3:

[0487] The server uses natural language processing (NLP) techniques to analyze the converted text data and evaluate the candidate's abilities. This involves identifying the text's grammatical structure, keywords, and sentiment (emotional tone) to calculate the candidate's communication and problem-solving skills. For example, this analysis identifies frequently used positive or negative expressions. These results are used in scoring and form part of the candidate's overall ability assessment.

[0488] Step 4:

[0489] The server inputs video data into an facial recognition algorithm to analyze the candidate's emotional state. Here, various facial expressions of the candidate are recognized and classified into specific emotions, such as smiles or surprise. The output emotional data serves as an indicator of the candidate's emotions during the interview. This process involves frame-by-frame analysis, and the emotional state is updated in real time.

[0490] Step 5:

[0491] The server integrates the analyzed audio and video data and uses an AI model designed to assess cross-cultural adaptability. This model analyzes the candidate's understanding of different cultures and behavioral patterns to calculate their cultural adaptability. Specifically, the model estimates the degree of leadership and collaborative ability in different cultures and compiles the results into evaluation indicators. These results are reflected in the report as the candidate's cross-cultural adaptability index.

[0492] Step 6:

[0493] Based on these analysis results, the server generates a comprehensive evaluation report for each candidate. This report includes soft skills scores and a cultural adaptation index, and is provided to the interviewer (the user). The generation process integrates the evaluation results for each ability, producing a clear and easy-to-understand visualized output. The evaluation report is provided to the interviewer in digital format, helping them to quickly and accurately assess the candidate's overall suitability.

[0494] (Application Example 1)

[0495] 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."

[0496] In selecting candidates, a comprehensive assessment of soft skills, cultural adaptability, and awareness and response skills regarding safety measures is required. However, traditional interview and evaluation systems have struggled to accurately analyze these aspects in real time and generate detailed evaluation results. As a result, the process of selecting suitable personnel within companies has been inefficient, and there has been a risk of overlooking the potential of potential employees.

[0497] 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.

[0498] In this invention, the server is capable of communicating with a device that records the actions of candidates, and includes means for analyzing recorded audio data and converting it into text data, means for analyzing recorded video data and identifying the candidate's emotional state, means for analyzing the text data and evaluating multiple abilities of the candidate, means for evaluating the candidate's adaptability in different cultures, means for evaluating the candidate's awareness and response skills regarding safety measures, means for generating an evaluation report that integrates the evaluations of the multiple abilities, adaptability, and safety measures, and means for providing the evaluation report to the user. This makes it possible to efficiently and accurately grasp the wide range of abilities, adaptability, and safety-related abilities required in the candidate selection and evaluation process.

[0499] "Device" refers to hardware or software used to record data and communicate with other systems.

[0500] A "server" refers to a central computer that receives, analyzes, and processes data.

[0501] "Audio data" refers to digital audio information that records what a candidate has said.

[0502] "Text data" refers to digital information obtained by converting audio data into written text.

[0503] "Video data" refers to digital visual information that records the candidate's actions and facial expressions.

[0504] "Emotional state" refers to information identified as indicating a candidate's emotions or psychological state.

[0505] "Multiple abilities" refers to a variety of skills that a candidate possesses, such as communication skills and problem-solving abilities.

[0506] "Cultural adaptability" refers to a candidate's ability to adapt to different cultural environments.

[0507] "Awareness and response skills regarding safety measures" refers to a candidate's ability to understand and respond appropriately to safety issues.

[0508] An "evaluation report" refers to a report generated based on analysis results that comprehensively shows a candidate's abilities and adaptability.

[0509] "User" refers to an individual or organization that receives evaluation reports and selects candidates.

[0510] To implement this invention, a server and a terminal are required. The terminal records the actions and statements of candidates in real time during interviews. The data recorded in this process includes audio and video data. The audio data is sent to the server and converted into text data using speech recognition technology. Specifically, this conversion is performed using a speech recognition service such as Google Cloud Speech-to-Text.

[0511] The server performs analysis on the converted text data using natural language processing (NLP) techniques. NLP utilizes language processing models such as spaCy and BERT to evaluate candidates' communication skills and problem-solving abilities. During this process, awareness of safety measures and response skills are also assessed based on the candidates' statements.

[0512] The server also processes the candidate's video data and identifies their emotional state based on an emotion recognition model. This process is carried out using a service such as the Microsoft Azure Face API, which allows for the identification of changes in the candidate's emotions and psychological state in real time.

[0513] By integrating this data, the server generates a comprehensive evaluation report that includes assessments of the candidate's multiple competencies, cultural adaptability, and safety measures. This evaluation report is provided to the user via a terminal, allowing the user to quickly and accurately assess the candidate's suitability.

[0514] As a concrete example, when selecting a leader for an international project, the server uses this system to analyze the content and emotional state of candidates when they talk about their experience collaborating with team members from different cultures. This allows for an objective assessment of the candidates' leadership abilities and cultural adaptability, making it possible to determine their suitability for the role.

[0515] An example of a prompt for the generating AI model is: "Please evaluate this candidate's security awareness. Below is a record of the candidate's statements. Question 1: What are your thoughts on recent changes to security protocols?"

[0516] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0517] Step 1:

[0518] The terminal records the candidate's audio and video data in real time during the interview. This input data is used to capture the candidate's statements and actions in detail during the interview. The recorded data is then sent to a server.

[0519] Step 2:

[0520] The server converts the audio data received from the terminal into text data using speech recognition technology. Specifically, it uses Google Cloud Speech-to-Text to convert the audio signal into language data. This conversion outputs the specific content spoken by the candidate as text information.

[0521] Step 3:

[0522] The server analyzes text data using natural language processing (NLP) techniques. This process utilizes language models such as spaCy and BERT to extract important keywords and phrases from the text data. This generates output data for evaluating candidates' communication skills, problem-solving abilities, and awareness of safety measures.

[0523] Step 4:

[0524] Simultaneously, the server processes the video data and uses an emotion recognition model to identify the candidate's emotional state. Leveraging the Microsoft Azure Face API, it analyzes facial expressions from the video to extract the candidate's psychological state and emotional changes.

[0525] Step 5:

[0526] The server integrates the analyzed sentiment data and natural language processing results to generate a comprehensive evaluation report that includes the candidate's multiple abilities, cross-cultural adaptability, and safety awareness. This ensures that all evaluation results are output as a single, comprehensive report, making it easily accessible to the user.

[0527] Step 6:

[0528] Users receive this integrated evaluation report on their device. Based on the report, users can objectively assess candidates' leadership abilities, cultural adaptability, and safety management skills, and proceed with the selection process.

[0529] 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.

[0530] This invention is a system that aims to improve the quality of the interview process by analyzing the emotions of not only the candidate but also the interviewer (the user) in real time during the interview. This system grasps the emotional state of both the candidate and the interviewer and utilizes that data for interview evaluation. Specific embodiments are shown below.

[0531] First, the device records video and audio data of the candidate during the interview, while simultaneously recording the interviewer's presence via the camera and microphone. This data is transmitted to the server in real time.

[0532] The server converts the candidate's voice data into text data using speech recognition technology and evaluates the candidate's abilities (communication, leadership, teamwork, etc.) using a natural language processing model. Simultaneously, it analyzes video data and applies facial recognition technology to identify the candidate's emotional state.

[0533] Furthermore, the server utilizes an emotion engine to recognize the user's emotions. This emotion engine analyzes emotional data from the interviewer's tone of voice, body movements, and facial expressions. This makes it possible to understand how the interviewer's emotions are changing in real time.

[0534] Based on this data, the server can not only generate candidate evaluation reports, but also incorporate user sentiment data analyzed by the sentiment engine into the reports. As a result, it provides insights into how interviewers evaluate candidates based on their emotions.

[0535] For example, the system can consider how the interviewer reacted to a particular question and indicate that this could influence the evaluation in that area. The device then provides the interviewer with a final evaluation report, which they can use to make a comprehensive assessment of the candidate's suitability.

[0536] This system reduces subjective evaluation biases by interviewers, resulting in a more objective and fair hiring process. The introduction of an emotion engine allows for a deeper understanding of the interaction between candidates and interviewers, thereby improving the quality of interviews.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The device begins recording video and audio data of both the candidate and the interviewer (user) in real time as soon as the interview starts. This collects data on the actions and statements of both parties.

[0540] Step 2:

[0541] The server converts the received candidate's voice data into text data using speech recognition technology. This text data is then input into a natural language processing (NLP) model for analysis to evaluate the candidate's communication skills and problem-solving abilities.

[0542] Step 3:

[0543] The server analyzes the candidate's video data and uses facial recognition technology to identify their emotional state. It interprets the meaning behind the candidate's facial changes and understands their internal emotional dynamics.

[0544] Step 4:

[0545] The server analyzes the user's video and audio data based on an emotion engine. The emotion engine evaluates the user's emotions in real time based on their voice tone and facial expressions. This evaluation is used to understand the interviewer's psychological state during question-and-answer sessions.

[0546] Step 5:

[0547] The server integrates candidate competence assessments and emotional states, as well as user emotional assessments, to generate a comprehensive evaluation report. This report includes an emotional state timeline and scoring.

[0548] Step 6:

[0549] The server sends the final evaluation report to the terminal and displays it to the interviewer, who is the user. Based on this report, the interviewer can gain emotionally-driven insights and conduct a fairer, more balanced evaluation.

[0550] (Example 2)

[0551] 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."

[0552] Traditional interview processes were prone to bias due to the evaluator's subjectivity, making it difficult to objectively assess the candidate's abilities and suitability. Furthermore, it was difficult to adequately capture emotional changes during the interview, which could result in reduced evaluation accuracy. This made it challenging to achieve a fair and objective recruitment process.

[0553] 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.

[0554] In this invention, the server includes means for acquiring and communicating the voices of candidates and interviewers, means for analyzing the acquired voice information and converting it into text information, and means for analyzing recorded video information to identify the emotional state of the person being evaluated. This makes it possible to visualize the emotions of both parties during the interview and improve the objectivity and fairness of the evaluation.

[0555] A "candidate" is an individual who is subject to evaluation and selection, and whose abilities and suitability are assessed during an interview.

[0556] An "interviewer" is the person responsible for evaluating candidates and managing the interview process.

[0557] "Audio information" refers to the voices and audio data of candidates and interviewers, and is the data that will be analyzed.

[0558] "Textual information" refers to data in text format obtained by analyzing audio information.

[0559] "Visual information" refers to the visual data of candidates and interviewers recorded by cameras, etc., and is the data to be analyzed.

[0560] "Persons being evaluated" refers to individuals whose abilities are assessed based on data obtained from video and audio information.

[0561] "Emotional state" is an indicator that shows the psychological or emotional state of a candidate or interviewer.

[0562] An "evaluation report" is a document that summarizes the candidate's abilities, suitability, the interviewer's emotional state, and other factors, and records the evaluation results.

[0563] A "generative language model" is a computational model used in natural language processing to analyze speech and text and understand human language.

[0564] A "facial expression recognition algorithm" is a technology that analyzes a person's facial expressions from video information and identifies their emotional state.

[0565] This invention is a system that analyzes the emotions of candidates and interviewers in real time to improve the quality of the evaluation process. This system is implemented using the following hardware and software.

[0566] The terminal is equipped with a high-resolution camera and a high-sensitivity microphone, simultaneously recording audio and video information of both the candidate and the interviewer. This data is transmitted in real time to a server via a communication line.

[0567] The server converts received speech information into text information using a generative language model. A common cloud-based service providing speech recognition technology can be used as the generative language model. The text information is further analyzed using natural language processing techniques to evaluate the candidate's abilities.

[0568] The video information is analyzed by software equipped with a facial recognition algorithm to identify the candidate's emotional state. This algorithm detects the facial feature points of the person being evaluated and infers emotions from their movements.

[0569] Furthermore, the interviewer's voice tone and body movements are analyzed, and their emotional state is evaluated in real time. This evaluation uses an emotion analysis engine and is an advanced technology for understanding human emotions.

[0570] These analysis results are integrated by the server, and an evaluation report, including emotional states, is generated. Finally, the terminal provides this evaluation report to the interviewer, who can then use it to assess the candidate's overall suitability.

[0571] Specific usage examples and prompt messages

[0572] For example, an interviewer might ask a candidate, "Please tell me specifically how you demonstrated leadership in a team." In this scenario, the device records the interviewer's reactions and emotional changes, and the server uses this information to inform the evaluation report.

[0573] An example of a prompt message is, "Based on the evaluation report from this interview system, please quantify the candidate's communication skills and propose evaluation criteria." This allows for objective and fair evaluation.

[0574] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0575] Step 1:

[0576] The terminal uses a camera and microphone installed in the interview room to simultaneously acquire video and audio information from both the candidate and the interviewer (the user). The input is video and audio, and the output is a signal transmitted to the server in real time. The video information is recorded in detail by a high-resolution camera, capturing the candidate's facial expressions and movements. The audio information is accurately captured by a high-sensitivity microphone, capturing both parties' statements.

[0577] Step 2:

[0578] The server utilizes an AI model to generate received audio information and converts it into text using speech recognition technology. The input is audio data sent from the terminal, and the output is text data. This conversion transcribes the content of the interview into text, generating text data. This then enables further natural language processing.

[0579] Step 3:

[0580] The server uses the converted text data to perform natural language processing and evaluate multiple abilities of the candidates, such as communication skills and leadership. The input is text data converted from speech, and the output is the evaluation results. By utilizing a generative AI model, the content and nuances of the text are analyzed, and the characteristics of the candidates are quantified.

[0581] Step 4:

[0582] The server analyzes video information and identifies emotional states through facial recognition algorithms. The input is video data transmitted from the terminal, and the output is the candidate's emotion label. By analyzing facial feature points and changes in expression, emotions such as excitement, tension, and joy are identified.

[0583] Step 5:

[0584] The server uses an emotion analysis engine that analyzes the interviewer's voice tone, facial expressions, and body movements to identify their emotional state. The input is the interviewer's voice and video data, and the output is data on the interviewer's emotional changes. This allows for real-time monitoring of the interviewer's emotional responses.

[0585] Step 6:

[0586] The server integrates sentiment data from both candidates and interviewers to generate a comprehensive evaluation report. The input consists of various evaluation data from both candidates and interviewers, and the output is a detailed evaluation report. The report includes an overview of the entire interview process and a summary of the evaluation, highlighting specific evaluation points.

[0587] Step 7:

[0588] The terminal provides the generated evaluation report to the interviewer, who is the user. The input is the evaluation report output from the server, and the output is the information provided to the user. Based on this report, the user can assess the candidate's overall suitability.

[0589] (Application Example 2)

[0590] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0591] In the interview process, it is difficult to objectively evaluate the emotions of both the interviewer and the candidate, and the process is often influenced by subjective judgments. This invention aims to provide a method for conducting this process more objectively and fairly. Furthermore, it aims to improve the quality of interviews by taking into account the interviewer's own emotions.

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

[0593] In this invention, the server is capable of communicating with an information terminal that records the actions of candidates and users, and includes means for analyzing recorded audio information and converting it into text information, means for analyzing recorded video information and identifying the emotional states of candidates and users, and means for analyzing the text information and evaluating the behavioral characteristics of candidates. This enables the visualization of emotions in the interview process and more accurate evaluation.

[0594] An "information terminal" is an electronic device used for collecting, processing, and communicating data, and in this context, it refers to a device that has the function of recording the actions of candidates and users.

[0595] "Voice information" refers to data that includes the statements and voice characteristics of candidates and users, and is subject to analysis after being recorded.

[0596] "Text information" refers to data obtained by converting analyzed audio information into text or linguistic format, and is used to evaluate the behavioral characteristics of candidates.

[0597] "Visual information" refers to visual data that records the posture, facial expressions, or movements of candidates and users, and is used to identify their emotional state.

[0598] "Emotional state" refers to information that reflects the psychological and physiological state exhibited by candidates and users, and is analyzed through facial expressions and body language.

[0599] "Behavioral characteristics" refer to data that describes the characteristics of a candidate's behavior and reactions under specific circumstances, and are used to assess their abilities during interviews.

[0600] "Evaluation materials" are report documents generated by integrating various analytical data, and are provided to users to help them determine the suitability of candidates.

[0601] The system for implementing this invention consists mainly of an information terminal, a server, and an analysis engine. The information terminal is equipped with a camera and microphone to record the actions of the candidate and user during the interview, thereby acquiring audio and video information. The acquired data is transmitted to the server in real time.

[0602] The server is equipped with software that converts speech information into text information using speech recognition technology. Specifically, it utilizes natural language processing technology to analyze the candidate's statements and extract behavioral characteristics. In addition, the server analyzes video information using facial recognition techniques to identify the emotional state of the candidate and the user. This reveals emotional changes during the interview.

[0603] Based on the collected data, the server generates evaluation materials. These materials integrate and include assessments of the candidate's behavioral characteristics, cross-cultural adaptability, and the user's emotional state. This material is provided to the user and used to assist in assessing the candidate's suitability.

[0604] As a concrete example, suppose a user asks a candidate during an interview, "Please tell me about a success story from your past experience." In this case, the candidate's response, recorded by an information terminal, and the user's reaction are analyzed as part of the evaluation materials and evaluated as a numerical indicator on the server.

[0605] An example of a prompt to input into the generating AI model is, "Analyze the emotions of the candidate and interviewer during the interview in real time and reflect this in the evaluation report after the interview." This prompt will initiate the appropriate data analysis.

[0606] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0607] Step 1:

[0608] The device records video and audio of the candidate and interviewer during the interview. Input is data acquired by the camera and microphone, and output is the raw data. This data is transmitted to the server in real time and serves as foundational data for analysis.

[0609] Step 2:

[0610] The server uses speech recognition technology to convert the acquired audio data into text data. The input is audio information transmitted in real time, and the output is text information extracted through natural language processing. This process makes it possible to understand the content of the candidate's statements.

[0611] Step 3:

[0612] The server analyzes video data using facial recognition techniques. The input is video information of the candidate and the interviewer, and the output is the identification of their emotional state based on this information. The server analyzes emotional changes from changes in facial expressions and updates the information in real time.

[0613] Step 4:

[0614] The server uses the analyzed text data to evaluate the candidate's behavioral characteristics. The input is text information converted from speech, and the output is an evaluation index for behavioral characteristics. Natural language processing models are used to reflect the content and tone of speech in the evaluation.

[0615] Step 5:

[0616] Users review evaluation reports and make decisions based on interview results. Input is integrated evaluation data provided by the server, and output is the user's decision on whether to hire or reject a candidate. Users can conduct a comprehensive aptitude assessment based on a wide range of information, including sentiment analysis.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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".

[0634] This invention provides a system for evaluating a candidate's soft skills and cultural adaptability in real time during the interview process. The system analyzes the candidate's actions, statements, and emotional state, and generates a comprehensive evaluation report based on these. The following describes a specific implementation of this system.

[0635] First, during the interview, the terminal records the candidate's video and audio in real time and sends the data to the server. The server receives this data and converts the audio data into text using speech recognition technology. The converted text data is then processed using natural language processing (NLP) technology to evaluate the candidate's various abilities, such as communication skills, problem-solving ability, teamwork, and leadership.

[0636] Furthermore, the server analyzes the candidate's facial expressions using video data and identifies their emotional state in real time using emotion recognition technology. This allows for an understanding of the candidate's emotions.

[0637] Furthermore, the server integrates this data to measure the results of multiple competency assessments and the candidate's adaptability in different cultures. It analyzes cross-cultural understanding and behavioral patterns to calculate cultural adaptability.

[0638] Finally, the server generates a comprehensive evaluation report of each candidate based on these analysis results. This report includes each candidate's soft skills score and cultural adaptation index. The terminal provides this evaluation report to the interviewer, who can then use it to quickly and accurately assess the candidate's suitability.

[0639] As a concrete example, in interviews for candidates capable of demonstrating leadership in international projects, this system can analyze the candidate's words and emotional state when they discuss their experience collaborating with team members from different cultures, thereby highly evaluating their leadership abilities and cultural adaptability. As a result, interviewers can objectively assess the candidate's suitability and receive support in selecting the most suitable candidate.

[0640] The following describes the processing flow.

[0641] Step 1:

[0642] The device records the candidate's audio and video data in real time at the start of the interview and sends it to the server. Video is collected by the camera and audio by the microphone.

[0643] Step 2:

[0644] The server processes the received audio data through a speech recognition engine, converting it into text data based on natural language. This text data is used for subsequent natural language processing, therefore, a highly accurate conversion is required.

[0645] Step 3:

[0646] The server analyzes text data using a natural language processing (NLP) model to extract specific keywords and themes. This allows it to calculate scores that evaluate candidates' communication skills and problem-solving abilities.

[0647] Step 4:

[0648] The server analyzes how faces appear in the video data and uses facial recognition technology to identify emotional states. This allows it to determine what emotions the candidate is showing during the interview.

[0649] Step 5:

[0650] The server evaluates the candidate's cultural adaptability by comprehensively considering their statements and facial expressions. Statements indicating cross-cultural experience or understanding of other cultures are indexed accordingly. This index serves as an indicator of the candidate's ability to cope with diversity.

[0651] Step 6:

[0652] The server integrates all analytical data and generates a comprehensive evaluation report that includes the candidate's skills and cultural adaptability. The report clearly displays the scoring and visually represents each ability.

[0653] Step 7:

[0654] The server sends the generated evaluation report to the terminal and presents it to the interviewer, who is the user. Based on this report, the interviewer evaluates and judges the candidate's suitability and compatibility with the organization.

[0655] (Example 1)

[0656] 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".

[0657] In today's business environment, quickly and accurately assessing the suitability of candidates from diverse cultural backgrounds is crucial for ensuring international competitiveness. However, traditional interview processes often struggle to objectively evaluate candidates' soft skills and cross-cultural adaptability, tending to rely on the evaluator's subjectivity. This creates a risk of making incorrect decisions when selecting suitable personnel. This invention aims to solve this problem by providing a structured and fair evaluation of candidates' skills and adaptability.

[0658] 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.

[0659] In this invention, the server is capable of communicating with a device that collects the candidate's behavior and includes means for analyzing acquired audio information and converting it into text information, means for analyzing acquired image information and identifying the candidate's emotional state, means for analyzing the text information and evaluating the candidate's multiple abilities, algorithm means for enhancing ability evaluation based on the analysis of the behavior and statements, and means for utilizing a model for measuring cross-cultural adaptability. This makes it possible to accurately evaluate each candidate's abilities and cultural adaptability and immediately provide the evaluation results to the interviewer.

[0660] A "candidate" is a person who is evaluated during the interview and selection process.

[0661] "Behavior" refers to dynamic responses and actions, including gestures, verbal expressions, and facial expressions, that are demonstrated by the candidate.

[0662] "Audio information" refers to sound data obtained from the words and vocalizations spoken by the candidates.

[0663] "Textual information" refers to data in text format obtained by analyzing audio information.

[0664] "Image information" refers to visual data that records the candidate's facial expressions and movements.

[0665] "Emotional state" refers to the identification of a candidate's psychological and emotional state based on the results of facial expression and voice analysis.

[0666] "Competency assessment" is a process of objectively analyzing and measuring a candidate's multiple skills, such as communication skills, problem-solving abilities, and teamwork skills.

[0667] "Cross-cultural adaptability" is a measure of a candidate's ability to adapt flexibly and act effectively within different cultural backgrounds.

[0668] An "evaluation report" is a document that summarizes the results of an analysis of a candidate's various abilities and cross-cultural adaptability, and serves as reference material for the hiring decision.

[0669] "Users" refers to interviewers and recruiters who make decisions about whether or not to hire candidates based on evaluation reports.

[0670] An "algorithmic method" is a set of computational procedures for analyzing and processing data, and a series of computational processes for evaluating the characteristics and abilities of candidates.

[0671] A "model" is a mathematical or AI-based system used to perform specific evaluations or predictions based on data.

[0672] The system in this invention aims to evaluate soft skills and cultural adaptability in real time during the candidate interview process. Specifically, it consists of three main components: a terminal, a server, and a user.

[0673] First, the terminal uses a high-resolution camera and a high-sensitivity microphone during the interview. For example, it uses a camera and audio input device built into a typical laptop, or an externally connected webcam and dedicated microphone, to record the candidate's video and audio in real time and organize the data into a technically appropriate format. The organized data is then transmitted to a server via the internet.

[0674] The server converts received audio data into text information using AI-based speech recognition software (e.g., a speech recognition API for speech analysis). This text information is then subjected to grammatical analysis, keyword extraction, and sentiment analysis using natural language processing techniques to evaluate multiple candidate abilities, such as communication skills and problem-solving abilities. Additionally, video data is analyzed using facial expression recognition technology (e.g., a face recognition API) to identify the candidate's emotional state.

[0675] In addition, the server integrates the aforementioned audio and video data and uses an AI model designed to measure cross-cultural adaptability. This model calculates cultural adaptability by analyzing the candidate's cross-cultural understanding and behavioral patterns.

[0676] Finally, the server generates a comprehensive evaluation report based on these analysis results. This report includes soft skills evaluation scores and a cultural adaptation index.

[0677] The generated evaluation report is provided to the interviewer (user) via the terminal, allowing the interviewer to quickly and accurately assess the candidate's suitability based on it.

[0678] As a concrete example, for a candidate for a position requiring project leadership in a cross-cultural environment, this system analyzes their experience collaborating with cross-cultural teams and evaluates their leadership abilities and cultural adaptability. Based on these results, interviewers can objectively evaluate candidates and select individuals suitable for a diverse work environment.

[0679] An example of a prompt might be a question like, "Based on your experience, please share an example of a time when you demonstrated leadership in a project with a cross-cultural team."

[0680] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0681] Step 1:

[0682] The device uses a high-resolution camera and high-sensitivity microphone to record the candidate's video and audio during the interview. This input data comprehensively captures the candidate's actions and statements, is converted into a secure file format, and then transmitted to a server via the internet. Specifically, recording begins, for example, when the video stream capture start button is pressed.

[0683] Step 2:

[0684] The server converts the transmitted audio data into text data using an AI-based speech recognition tool. This process extracts linguistic elements from the acoustic signal and generates output in string format. This allows the candidate's utterances to be stored in a database, enabling natural language processing. Specifically, as soon as the audio data is received, the speech recognition algorithm automatically activates, and text is generated within seconds.

[0685] Step 3:

[0686] The server uses natural language processing (NLP) techniques to analyze the converted text data and evaluate the candidate's abilities. This involves identifying the text's grammatical structure, keywords, and sentiment (emotional tone) to calculate the candidate's communication and problem-solving skills. For example, this analysis identifies frequently used positive or negative expressions. These results are used in scoring and form part of the candidate's overall ability assessment.

[0687] Step 4:

[0688] The server inputs video data into an facial recognition algorithm to analyze the candidate's emotional state. Here, various facial expressions of the candidate are recognized and classified into specific emotions, such as smiles or surprise. The output emotional data serves as an indicator of the candidate's emotions during the interview. This process involves frame-by-frame analysis, and the emotional state is updated in real time.

[0689] Step 5:

[0690] The server integrates the analyzed audio and video data and uses an AI model designed to assess cross-cultural adaptability. This model analyzes the candidate's understanding of different cultures and behavioral patterns to calculate their cultural adaptability. Specifically, the model estimates the degree of leadership and collaborative ability in different cultures and compiles the results into evaluation indicators. These results are reflected in the report as the candidate's cross-cultural adaptability index.

[0691] Step 6:

[0692] Based on these analysis results, the server generates a comprehensive evaluation report for each candidate. This report includes soft skills scores and a cultural adaptation index, and is provided to the interviewer (the user). The generation process integrates the evaluation results for each ability, producing a clear and easy-to-understand visualized output. The evaluation report is provided to the interviewer in digital format, helping them to quickly and accurately assess the candidate's overall suitability.

[0693] (Application Example 1)

[0694] 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".

[0695] In selecting candidates, a comprehensive assessment of soft skills, cultural adaptability, and awareness and response skills regarding safety measures is required. However, traditional interview and evaluation systems have struggled to accurately analyze these aspects in real time and generate detailed evaluation results. As a result, the process of selecting suitable personnel within companies has been inefficient, and there has been a risk of overlooking the potential of potential employees.

[0696] 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.

[0697] In this invention, the server is capable of communicating with a device that records the actions of candidates, and includes means for analyzing recorded audio data and converting it into text data, means for analyzing recorded video data and identifying the candidate's emotional state, means for analyzing the text data and evaluating multiple abilities of the candidate, means for evaluating the candidate's adaptability in different cultures, means for evaluating the candidate's awareness and response skills regarding safety measures, means for generating an evaluation report that integrates the evaluations of the multiple abilities, adaptability, and safety measures, and means for providing the evaluation report to the user. This makes it possible to efficiently and accurately grasp the wide range of abilities, adaptability, and safety-related abilities required in the candidate selection and evaluation process.

[0698] "Device" refers to hardware or software used to record data and communicate with other systems.

[0699] A "server" refers to a central computer that receives, analyzes, and processes data.

[0700] "Audio data" refers to digital audio information that records what a candidate has said.

[0701] "Text data" refers to digital information obtained by converting audio data into written text.

[0702] "Video data" refers to digital visual information that records the candidate's actions and facial expressions.

[0703] "Emotional state" refers to information identified as indicating a candidate's emotions or psychological state.

[0704] "Multiple abilities" refers to a variety of skills that a candidate possesses, such as communication skills and problem-solving abilities.

[0705] "Cultural adaptability" refers to a candidate's ability to adapt to different cultural environments.

[0706] "Awareness and response skills regarding safety measures" refers to a candidate's ability to understand and respond appropriately to safety issues.

[0707] An "evaluation report" refers to a report generated based on analysis results that comprehensively shows a candidate's abilities and adaptability.

[0708] "User" refers to an individual or organization that receives evaluation reports and selects candidates.

[0709] To implement this invention, a server and a terminal are required. The terminal records the actions and statements of candidates in real time during interviews. The data recorded in this process includes audio and video data. The audio data is sent to the server and converted into text data using speech recognition technology. Specifically, this conversion is performed using a speech recognition service such as Google Cloud Speech-to-Text.

[0710] The server performs analysis on the converted text data using natural language processing (NLP) techniques. NLP utilizes language processing models such as spaCy and BERT to evaluate candidates' communication skills and problem-solving abilities. During this process, awareness of safety measures and response skills are also assessed based on the candidates' statements.

[0711] The server also processes the candidate's video data and identifies their emotional state based on an emotion recognition model. This process is carried out using a service such as the Microsoft Azure Face API, which allows for the identification of changes in the candidate's emotions and psychological state in real time.

[0712] By integrating this data, the server generates a comprehensive evaluation report that includes assessments of the candidate's multiple competencies, cultural adaptability, and safety measures. This evaluation report is provided to the user via a terminal, allowing the user to quickly and accurately assess the candidate's suitability.

[0713] As a concrete example, when selecting a leader for an international project, the server uses this system to analyze the content and emotional state of candidates when they talk about their experience collaborating with team members from different cultures. This allows for an objective assessment of the candidates' leadership abilities and cultural adaptability, making it possible to determine their suitability for the role.

[0714] An example of a prompt for the generating AI model is: "Please evaluate this candidate's security awareness. Below is a record of the candidate's statements. Question 1: What are your thoughts on recent changes to security protocols?"

[0715] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0716] Step 1:

[0717] The terminal records the candidate's audio and video data in real time during the interview. This input data is used to capture the candidate's statements and actions in detail during the interview. The recorded data is then sent to a server.

[0718] Step 2:

[0719] The server converts the audio data received from the terminal into text data using speech recognition technology. Specifically, it uses Google Cloud Speech-to-Text to convert the audio signal into language data. This conversion outputs the specific content spoken by the candidate as text information.

[0720] Step 3:

[0721] The server analyzes text data using natural language processing (NLP) techniques. This process utilizes language models such as spaCy and BERT to extract important keywords and phrases from the text data. This generates output data for evaluating candidates' communication skills, problem-solving abilities, and awareness of safety measures.

[0722] Step 4:

[0723] Simultaneously, the server processes the video data and uses an emotion recognition model to identify the candidate's emotional state. Leveraging the Microsoft Azure Face API, it analyzes facial expressions from the video to extract the candidate's psychological state and emotional changes.

[0724] Step 5:

[0725] The server integrates the analyzed sentiment data and natural language processing results to generate a comprehensive evaluation report that includes the candidate's multiple abilities, cross-cultural adaptability, and safety awareness. This ensures that all evaluation results are output as a single, comprehensive report, making it easily accessible to the user.

[0726] Step 6:

[0727] Users receive this integrated evaluation report on their device. Based on the report, users can objectively assess candidates' leadership abilities, cultural adaptability, and safety management skills, and proceed with the selection process.

[0728] 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.

[0729] This invention is a system that aims to improve the quality of the interview process by analyzing the emotions of not only the candidate but also the interviewer (the user) in real time during the interview. This system grasps the emotional state of both the candidate and the interviewer and utilizes that data for interview evaluation. Specific embodiments are shown below.

[0730] First, the device records video and audio data of the candidate during the interview, while simultaneously recording the interviewer's presence via the camera and microphone. This data is transmitted to the server in real time.

[0731] The server converts the candidate's voice data into text data using speech recognition technology and evaluates the candidate's abilities (communication, leadership, teamwork, etc.) using a natural language processing model. Simultaneously, it analyzes video data and applies facial recognition technology to identify the candidate's emotional state.

[0732] Furthermore, the server utilizes an emotion engine to recognize the user's emotions. This emotion engine analyzes emotional data from the interviewer's tone of voice, body movements, and facial expressions. This makes it possible to understand how the interviewer's emotions are changing in real time.

[0733] Based on this data, the server can not only generate candidate evaluation reports, but also incorporate user sentiment data analyzed by the sentiment engine into the reports. As a result, it provides insights into how interviewers evaluate candidates based on their emotions.

[0734] For example, the system can consider how the interviewer reacted to a particular question and indicate that this could influence the evaluation in that area. The device then provides the interviewer with a final evaluation report, which they can use to make a comprehensive assessment of the candidate's suitability.

[0735] This system reduces subjective evaluation biases by interviewers, resulting in a more objective and fair hiring process. The introduction of an emotion engine allows for a deeper understanding of the interaction between candidates and interviewers, thereby improving the quality of interviews.

[0736] The following describes the processing flow.

[0737] Step 1:

[0738] The device begins recording video and audio data of both the candidate and the interviewer (user) in real time as soon as the interview starts. This collects data on the actions and statements of both parties.

[0739] Step 2:

[0740] The server converts the received candidate's voice data into text data using speech recognition technology. This text data is then input into a natural language processing (NLP) model for analysis to evaluate the candidate's communication skills and problem-solving abilities.

[0741] Step 3:

[0742] The server analyzes the candidate's video data and uses facial recognition technology to identify their emotional state. It interprets the meaning behind the candidate's facial changes and understands their internal emotional dynamics.

[0743] Step 4:

[0744] The server analyzes the user's video and audio data based on an emotion engine. The emotion engine evaluates the user's emotions in real time based on their voice tone and facial expressions. This evaluation is used to understand the interviewer's psychological state during question-and-answer sessions.

[0745] Step 5:

[0746] The server integrates candidate competence assessments and emotional states, as well as user emotional assessments, to generate a comprehensive evaluation report. This report includes an emotional state timeline and scoring.

[0747] Step 6:

[0748] The server sends the final evaluation report to the terminal and displays it to the interviewer, who is the user. Based on this report, the interviewer can gain emotionally-driven insights and conduct a fairer, more balanced evaluation.

[0749] (Example 2)

[0750] 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".

[0751] Traditional interview processes were prone to bias due to the evaluator's subjectivity, making it difficult to objectively assess the candidate's abilities and suitability. Furthermore, it was difficult to adequately capture emotional changes during the interview, which could result in reduced evaluation accuracy. This made it challenging to achieve a fair and objective recruitment process.

[0752] 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.

[0753] In this invention, the server includes means for acquiring and communicating the voices of candidates and interviewers, means for analyzing the acquired voice information and converting it into text information, and means for analyzing recorded video information to identify the emotional state of the person being evaluated. This makes it possible to visualize the emotions of both parties during the interview and improve the objectivity and fairness of the evaluation.

[0754] A "candidate" is an individual who is subject to evaluation and selection, and whose abilities and suitability are assessed during an interview.

[0755] An "interviewer" is the person responsible for evaluating candidates and managing the interview process.

[0756] "Audio information" refers to the voices and audio data of candidates and interviewers, and is the data that will be analyzed.

[0757] "Textual information" refers to data in text format obtained by analyzing audio information.

[0758] "Visual information" refers to the visual data of candidates and interviewers recorded by cameras, etc., and is the data to be analyzed.

[0759] "Persons being evaluated" refers to individuals whose abilities are assessed based on data obtained from video and audio information.

[0760] "Emotional state" is an indicator that shows the psychological or emotional state of a candidate or interviewer.

[0761] An "evaluation report" is a document that summarizes the candidate's abilities, suitability, the interviewer's emotional state, and other factors, and records the evaluation results.

[0762] A "generative language model" is a computational model used in natural language processing to analyze speech and text and understand human language.

[0763] A "facial expression recognition algorithm" is a technology that analyzes a person's facial expressions from video information and identifies their emotional state.

[0764] This invention is a system that analyzes the emotions of candidates and interviewers in real time to improve the quality of the evaluation process. This system is implemented using the following hardware and software.

[0765] The terminal is equipped with a high-resolution camera and a high-sensitivity microphone, simultaneously recording audio and video information of both the candidate and the interviewer. This data is transmitted in real time to a server via a communication line.

[0766] The server converts received speech information into text information using a generative language model. A common cloud-based service providing speech recognition technology can be used as the generative language model. The text information is further analyzed using natural language processing techniques to evaluate the candidate's abilities.

[0767] The video information is analyzed by software equipped with a facial recognition algorithm to identify the candidate's emotional state. This algorithm detects the facial feature points of the person being evaluated and infers emotions from their movements.

[0768] Furthermore, the interviewer's voice tone and body movements are analyzed, and their emotional state is evaluated in real time. This evaluation uses an emotion analysis engine and is an advanced technology for understanding human emotions.

[0769] These analysis results are integrated by the server, and an evaluation report, including emotional states, is generated. Finally, the terminal provides this evaluation report to the interviewer, who can then use it to assess the candidate's overall suitability.

[0770] Specific usage examples and prompt messages

[0771] For example, an interviewer might ask a candidate, "Please tell me specifically how you demonstrated leadership in a team." In this scenario, the device records the interviewer's reactions and emotional changes, and the server uses this information to inform the evaluation report.

[0772] An example of a prompt message is, "Based on the evaluation report from this interview system, please quantify the candidate's communication skills and propose evaluation criteria." This allows for objective and fair evaluation.

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

[0774] Step 1:

[0775] The terminal uses a camera and microphone installed in the interview room to simultaneously acquire video and audio information from both the candidate and the interviewer (the user). The input is video and audio, and the output is a signal transmitted to the server in real time. The video information is recorded in detail by a high-resolution camera, capturing the candidate's facial expressions and movements. The audio information is accurately captured by a high-sensitivity microphone, capturing both parties' statements.

[0776] Step 2:

[0777] The server utilizes an AI model to generate received audio information and converts it into text using speech recognition technology. The input is audio data sent from the terminal, and the output is text data. This conversion transcribes the content of the interview into text, generating text data. This then enables further natural language processing.

[0778] Step 3:

[0779] The server uses the converted text data to perform natural language processing and evaluate multiple abilities of the candidates, such as communication skills and leadership. The input is text data converted from speech, and the output is the evaluation results. By utilizing a generative AI model, the content and nuances of the text are analyzed, and the characteristics of the candidates are quantified.

[0780] Step 4:

[0781] The server analyzes video information and identifies emotional states through facial recognition algorithms. The input is video data transmitted from the terminal, and the output is the candidate's emotion label. By analyzing facial feature points and changes in expression, emotions such as excitement, tension, and joy are identified.

[0782] Step 5:

[0783] The server uses an emotion analysis engine that analyzes the interviewer's voice tone, facial expressions, and body movements to identify their emotional state. The input is the interviewer's voice and video data, and the output is data on the interviewer's emotional changes. This allows for real-time monitoring of the interviewer's emotional responses.

[0784] Step 6:

[0785] The server integrates sentiment data from both candidates and interviewers to generate a comprehensive evaluation report. The input consists of various evaluation data from both candidates and interviewers, and the output is a detailed evaluation report. The report includes an overview of the entire interview process and a summary of the evaluation, highlighting specific evaluation points.

[0786] Step 7:

[0787] The terminal provides the generated evaluation report to the interviewer, who is the user. The input is the evaluation report output from the server, and the output is the information provided to the user. Based on this report, the user can assess the candidate's overall suitability.

[0788] (Application Example 2)

[0789] 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".

[0790] In the interview process, it is difficult to objectively evaluate the emotions of both the interviewer and the candidate, and the process is often influenced by subjective judgments. This invention aims to provide a method for conducting this process more objectively and fairly. Furthermore, it aims to improve the quality of interviews by taking into account the interviewer's own emotions.

[0791] 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.

[0792] In this invention, the server is capable of communicating with an information terminal that records the actions of candidates and users, and includes means for analyzing recorded audio information and converting it into text information, means for analyzing recorded video information and identifying the emotional states of candidates and users, and means for analyzing the text information and evaluating the behavioral characteristics of candidates. This enables the visualization of emotions in the interview process and more accurate evaluation.

[0793] An "information terminal" is an electronic device used for collecting, processing, and communicating data, and in this context, it refers to a device that has the function of recording the actions of candidates and users.

[0794] "Voice information" refers to data that includes the statements and voice characteristics of candidates and users, and is subject to analysis after being recorded.

[0795] "Text information" refers to data obtained by converting analyzed audio information into text or linguistic format, and is used to evaluate the behavioral characteristics of candidates.

[0796] "Visual information" refers to visual data that records the posture, facial expressions, or movements of candidates and users, and is used to identify their emotional state.

[0797] "Emotional state" refers to information that reflects the psychological and physiological state exhibited by candidates and users, and is analyzed through facial expressions and body language.

[0798] "Behavioral characteristics" refer to data that describes the characteristics of a candidate's behavior and reactions under specific circumstances, and are used to assess their abilities during interviews.

[0799] "Evaluation materials" are report documents generated by integrating various analytical data, and are provided to users to help them determine the suitability of candidates.

[0800] The system for implementing this invention consists mainly of an information terminal, a server, and an analysis engine. The information terminal is equipped with a camera and microphone to record the actions of the candidate and user during the interview, thereby acquiring audio and video information. The acquired data is transmitted to the server in real time.

[0801] The server is equipped with software that converts speech information into text information using speech recognition technology. Specifically, it utilizes natural language processing technology to analyze the candidate's statements and extract behavioral characteristics. In addition, the server analyzes video information using facial recognition techniques to identify the emotional state of the candidate and the user. This reveals emotional changes during the interview.

[0802] Based on the collected data, the server generates evaluation materials. These materials integrate and include assessments of the candidate's behavioral characteristics, cross-cultural adaptability, and the user's emotional state. This material is provided to the user and used to assist in assessing the candidate's suitability.

[0803] As a concrete example, suppose a user asks a candidate during an interview, "Please tell me about a success story from your past experience." In this case, the candidate's response, recorded by an information terminal, and the user's reaction are analyzed as part of the evaluation materials and evaluated as a numerical indicator on the server.

[0804] An example of a prompt to input into the generating AI model is, "Analyze the emotions of the candidate and interviewer during the interview in real time and reflect this in the evaluation report after the interview." This prompt will initiate the appropriate data analysis.

[0805] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0806] Step 1:

[0807] The device records video and audio of the candidate and interviewer during the interview. Input is data acquired by the camera and microphone, and output is the raw data. This data is transmitted to the server in real time and serves as foundational data for analysis.

[0808] Step 2:

[0809] The server uses speech recognition technology to convert the acquired audio data into text data. The input is audio information transmitted in real time, and the output is text information extracted through natural language processing. This process makes it possible to understand the content of the candidate's statements.

[0810] Step 3:

[0811] The server analyzes video data using facial recognition techniques. The input is video information of the candidate and the interviewer, and the output is the identification of their emotional state based on this information. The server analyzes emotional changes from changes in facial expressions and updates the information in real time.

[0812] Step 4:

[0813] The server uses the analyzed text data to evaluate the candidate's behavioral characteristics. The input is text information converted from speech, and the output is an evaluation index for behavioral characteristics. Natural language processing models are used to reflect the content and tone of speech in the evaluation.

[0814] Step 5:

[0815] Users review evaluation reports and make decisions based on interview results. Input is integrated evaluation data provided by the server, and output is the user's decision on whether to hire or reject a candidate. Users can conduct a comprehensive aptitude assessment based on a wide range of information, including sentiment analysis.

[0816] 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.

[0817] 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.

[0818] 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 robot 414.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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."

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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 this memory.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] The following is further disclosed regarding the embodiments described above.

[0838] (Claim 1)

[0839] A device capable of communicating with a candidate's actions, and means for analyzing recorded audio data and converting it into text data,

[0840] A means of identifying the emotional state of a candidate by analyzing recorded video data,

[0841] A means for analyzing the aforementioned text data to evaluate multiple abilities of the candidate,

[0842] A means of evaluating a candidate's adaptability in different cultures,

[0843] A means for generating an evaluation report that integrates the aforementioned multiple competency assessments and adaptability assessments,

[0844] A means for providing the aforementioned evaluation report to the user,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, which uses a natural language processing model to process audio data and text data.

[0848] (Claim 3)

[0849] The system according to claim 1, which uses a facial recognition model to analyze the emotional state of a candidate from video data.

[0850] "Example 1"

[0851] (Claim 1)

[0852] It is capable of communicating with a device that collects the candidate's actions, and has means to analyze the acquired audio information and convert it into text information.

[0853] A means of analyzing acquired image information to identify the candidate's emotional state,

[0854] A means for analyzing the aforementioned textual information to evaluate multiple abilities of the candidate,

[0855] A means of evaluating a candidate's adaptability in different cultures,

[0856] A means for generating an evaluation report that integrates the aforementioned multiple competency evaluations and adaptability evaluations,

[0857] A means of providing the aforementioned evaluation report to the user,

[0858] An algorithmic means for improving ability evaluation based on the analysis of the aforementioned behaviors and statements,

[0859] Methods for using models to measure cross-cultural adaptability,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, which uses a natural language processing model to process audio information and text information.

[0863] (Claim 3)

[0864] The system according to claim 1, which uses an facial expression recognition model to analyze the emotional state of a candidate from image information.

[0865] "Application Example 1"

[0866] (Claim 1)

[0867] A device capable of communicating with a candidate's actions, and means for analyzing recorded audio data and converting it into text data,

[0868] A means of identifying the emotional state of a candidate by analyzing recorded video data,

[0869] A means for analyzing the aforementioned text data to evaluate multiple abilities of the candidate,

[0870] A means of evaluating a candidate's adaptability in different cultures,

[0871] A means of evaluating candidates' awareness and response skills regarding safety measures,

[0872] A means for generating an evaluation report that integrates the aforementioned multiple competency evaluations, adaptability evaluations, and safety measures evaluations,

[0873] A means of providing the aforementioned evaluation report to the user,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, which uses a language processing model to process audio data and text data.

[0877] (Claim 3)

[0878] The system according to claim 1, which uses a facial recognition model to analyze the emotional state of a candidate from video data.

[0879] "Example 2 of combining an emotion engine"

[0880] (Claim 1)

[0881] A device that acquires and communicates the voices of candidates and interviewers,

[0882] A means for analyzing acquired audio information and converting it into text information,

[0883] A means of analyzing recorded video information to identify the emotional state of the person being evaluated,

[0884] A means for analyzing the aforementioned textual information to evaluate multiple abilities of the person being evaluated,

[0885] A means of analyzing the interviewer's voice tone and body movements to identify the evaluator's emotions,

[0886] An evaluation report is generated that incorporates the emotional states of the person being evaluated and the evaluator.

[0887] A means of providing the aforementioned evaluation report to the evaluator,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, which utilizes a generative language model to process speech information and text information.

[0891] (Claim 3)

[0892] The system according to claim 1, which uses a facial expression recognition algorithm to analyze the emotional state of a person being evaluated from video information.

[0893] "Application example 2 when combining with an emotional engine"

[0894] (Claim 1)

[0895] It is capable of communicating with an information terminal that records the actions of candidates and users, and has means for analyzing recorded voice information and converting it into text information,

[0896] A means for analyzing recorded video information to identify the emotional state of candidates and users,

[0897] A means for analyzing the aforementioned text information to evaluate the behavioral characteristics of candidates,

[0898] A means of evaluating a candidate's adaptability in different cultures,

[0899] A means for generating evaluation data that integrates the aforementioned behavioral characteristics evaluation, adaptability evaluation, and the user's emotional state,

[0900] Means for providing the aforementioned evaluation materials to users,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, which processes speech information and text information using natural language processing technology.

[0904] (Claim 3)

[0905] The system according to claim 1, which uses facial recognition techniques to analyze the emotional states of candidates and users from video information. [Explanation of Symbols]

[0906] 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 device capable of communicating with a candidate's actions, and means for analyzing recorded audio data and converting it into text data, A means of identifying the emotional state of a candidate by analyzing recorded video data, A means for analyzing the aforementioned text data to evaluate multiple abilities of the candidate, A means of evaluating a candidate's adaptability in different cultures, A means for generating an evaluation report that integrates the aforementioned multiple competency assessments and adaptability assessments, A means for providing the aforementioned evaluation report to the user, A system that includes this.

2. The system according to claim 1, which uses a natural language processing model to process audio data and text data.

3. The system according to claim 1, which uses a facial expression recognition model to analyze the emotional state of a candidate from video data.

Images