System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an entry sheet submitted by a user; means for storing the entry sheet in a database; means for generating a face-to-face interview scenario; means for notifying a user of the date and time and method of the face-to-face interview; means for starting a video interview of the user; means for transmitting an answer video of the user to a server in real time during the video interview; means for analyzing the answer video and making a preliminary evaluation; means for making a detailed evaluation after the video interview; means for storing the evaluation in the database; and means for generating feedback based on the evaluation result and notifying the user of the feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The traditional recruitment process has problems with the interview process, which requires a lot of labor and time. Furthermore, because applicants cannot be fully understood before the initial screening stage, the efficiency of the recruitment process can decrease. Furthermore, it is difficult to provide appropriate feedback to applicants, which prevents them from improving their abilities. The goal of this project is to solve these problems, streamline the recruitment process, and improve the understanding of applicants. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a system including the following means.

[0006] The system includes a means for receiving an application form submitted by a user, a means for saving the application form in a database, a means for generating an interview question scenario, a means for notifying the user of the date, time, and method of the interview, a means for the user to start a video interview, a means for transmitting the user's video answers to a server in real time during the video interview, a means for analyzing the video answers and making a preliminary evaluation, a means for making a detailed evaluation after the video interview is completed, a means for saving the evaluation in a database, and a means for generating feedback based on the evaluation results and notifying the user. This system makes it possible to improve the efficiency of interviews, gain a detailed understanding of applicants, and provide appropriate feedback, thereby reducing labor costs and time while providing a highly efficient hiring process.

[0007] An "entry sheet" is a document that a job seeker submits when applying for a job, listing their career history, skills, reasons for applying, etc.

[0008] A "database" is a system for systematically organizing and storing information, which enables efficient retrieval and management of information.

[0009] An "interview question scenario" refers to the order and content of pre-set questions that guide the conversation during an interview, and serves as the basis for evaluating the suitability of applicants.

[0010] "Natural language processing" is a technology that allows computers to understand, interpret, and generate natural human language, and is an area in which machine learning and AI technologies are applied.

[0011] A "video interview" is an interview conducted over the internet in real time or via recorded video.

[0012] "Speech recognition" is a technology in which a computer system analyzes human speech and converts that speech into text or data.

[0013] "Image processing technology" refers to a series of technologies for analyzing, processing, and converting digital image data, and is used for facial expression analysis and object recognition.

[0014] "Evaluation" is the act of judging the value or performance of an object, action, or person based on specific criteria and drawing a score or conclusion.

[0015] "Feedback" is information or opinions based on the results of an action or process that can be used to guide subsequent actions or improvements.

[0016] "Generative AI" is a type of artificial intelligence and a general term for algorithms and devices that have the ability to generate new data and information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening that takes place after submitting an application form. The purpose of this system is to deepen understanding of applicants while reducing labor costs.

[0039] Receiving application forms and saving data

[0040] The user fills out an application form and presses the submit button via a web form or a dedicated application. The terminal converts this data into JSON or XML format and sends it as a POST request to the server using the HTTPS protocol. The server receives this data, validates it, and stores it in a database. During this process, a confirmation email is automatically sent to the user.

[0041] Setting up and conducting a video interview

[0042] The server generates an interview question scenario based on the contents of the application form received from the user. The scenario uses natural language processing (NLP) technology to include questions based on the applicant's experience and skills. The server then sends the user an email containing the interview date and time and login information. At the specified date and time, the user uses their device to access a web portal or dedicated application to begin the video interview.

[0043] During the interview, the device transmits the user's video responses in real time to a server, which uses voice recognition and video processing technology to extract text and facial expression data from the responses and conducts a preliminary evaluation, including the appropriateness of the responses, speech fluency, and facial expression consistency.

[0044] Video interview assessment and recording

[0045] Once the video interview is over, the server analyzes all responses again and performs a more detailed evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and prepared for submission to the next panel of judges.

[0046] Feedback and next steps for applicants

[0047] The server automatically generates feedback based on the analysis results, including details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then emailed to the user, informing them of the next steps and schedule.

[0048] Specific examples

[0049] For example, User A applying for a new position might go through the process as follows:

[0050] 1. User A fills out an application form and sends it from their device. The server receives and saves the application form data.

[0051] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies User A of the interview date and time and login information.

[0052] 3. User A starts the video interview using the device at the specified date and time and answers the questions. The device sends the answer video to the server in real time.

[0053] 4. The server evaluates User A's answers initially, and then performs a detailed evaluation after the interview. The evaluation results are saved in the database.

[0054] 5. The server generates feedback and notifies User A with details of next steps.

[0055] This system reduces labor costs and time, making the recruitment process more efficient and effective.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The user submits the application form. The user enters the required information using a web form or a dedicated application and presses the submit button.

[0059] Step 2:

[0060] The terminal sends the application form data to the server. The terminal converts the user's input data into JSON or XML format and sends it to the server as a POST request using the HTTPS protocol.

[0061] Step 3:

[0062] The server receives the application form data, validates the received data, and checks for accuracy and completeness.

[0063] Step 4:

[0064] The server saves the application form data in the database. Data that passes validation is stored in the database.

[0065] Step 5:

[0066] The server will send the user an email acknowledging receipt of the application form. To ensure receipt confirmation, a notification email will be sent automatically to the user.

[0067] Step 6:

[0068] The server generates an interview question scenario, analyzes the contents of the application form, and uses natural language processing technology to create a list of questions suited to the applicant.

[0069] Step 7:

[0070] The server sends a notification to the user, including the date, time, and procedure for the interview. The generated scenario is sent to the user via email, along with the interview date, time, login information, and instructions.

[0071] Step 8:

[0072] The user starts the video interview at the specified date and time. The user uses a device to access the specified web portal or application and starts the interview.

[0073] Step 9:

[0074] The device transmits the user's answer video in real time to the server. During the video interview, the device records the user's video with a camera and transmits it as streaming data to the server.

[0075] Step 10:

[0076] The server analyzes the video responses and performs a preliminary evaluation. AI is used to perform real-time voice recognition and video processing, extracting the text and facial expression data from the responses, and then a preliminary evaluation is performed.

[0077] Step 11:

[0078] After the video interview is completed, the server reanalyzes all responses and conducts a detailed evaluation. In addition to a basic evaluation, the server also evaluates the depth of the content, logic, emotional expression, and other factors.

[0079] Step 12:

[0080] The server saves the detailed evaluation results in a database. The evaluation results are stored in the database as structured data, making them easily accessible to the next judge.

[0081] Step 13:

[0082] The server generates feedback based on the analysis results. Based on the detailed evaluation results, feedback is automatically generated that includes the applicant's strengths, weaknesses, and recommendations for next steps.

[0083] Step 14:

[0084] The server notifies the user of the feedback letter and details of the next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[0085] This series of processing flows reduces the burden on applicants and interviewers while realizing an efficient and effective recruitment process.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] In the traditional recruitment process, managing a large number of application forms, arranging interviews, and evaluating the interview results required a great deal of time and effort. Furthermore, it was prone to artificial bias in the evaluations and difficult to provide efficient feedback. This resulted in an inefficiency in the entire recruitment process, delaying the selection of the best candidates.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes means for receiving an application form submitted by a user, means for converting the application form into a data format and transmitting it to the server using a secure protocol, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's video answers to the server in real time during the video interview, means for analyzing the video answers and making a preliminary evaluation, means for making a detailed evaluation after the video interview is completed, means for saving the evaluation in a database, and means for generating feedback based on the evaluation results and notifying the user. This streamlines the entire hiring process, reduces labor costs and time, and enables fair and rapid personnel evaluation.

[0091] "User" refers to an applicant who uses this system to submit an application form and participate in a video interview.

[0092] An "entry form" refers to a document that contains personal information, work history, etc. that a user fills out and submits in order to apply for a job.

[0093] "Data format" refers to the digital format, such as JSON or XML, into which the application form is converted.

[0094] "Secure Protocol" refers to a protocol, such as HTTPS, used to ensure the secure transmission of data.

[0095] "Server" refers to a computer system that receives, stores, analyzes, and generates feedback on application forms.

[0096] A "database" refers to an information system that systematically stores and manages data such as application forms and evaluation results.

[0097] An "interview question scenario" refers to a list of interview questions generated based on an applicant's application form.

[0098] "Notification means" refers to the procedures and techniques for notifying users of information such as the date, time, and method of the interview.

[0099] A "video interview" refers to an online interview that a user participates in using a web portal or dedicated application.

[0100] "Answer video" refers to video data that records a user answering questions during a video interview.

[0101] "Analysis means" refers to the speech recognition and / or video processing technology used to evaluate the recorded response videos.

[0102] The "feedback generation means" refers to a method for automatically generating feedback to be provided to the user based on the analysis results.

[0103] This invention relates to a system that uses a generative AI model to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form. The system aims to streamline the recruitment process and reduce labor costs.

[0104] Receiving application forms and saving data

[0105] When a user fills out an application form and presses the submit button via a web form or a dedicated application, the device converts the collected data into JSON or XML format and sends it to the server using the HTTPS protocol. The server receives the data, validates it, and stores it in a database. During this process, the server automatically sends the user a confirmation email.

[0106] Setting up and conducting a video interview

[0107] Based on the contents of the application form received from the user, the server uses natural language processing (NLP) technology to generate an interview question scenario based on the applicant's experience and skills. The server then sends the user an email containing the interview date and time and login information. At the specified date and time, the user uses their device to access a web portal or dedicated application and begin the video interview. The device then transmits the user's video responses in real time to the server, which uses voice recognition and video processing technology to extract the text and facial expression data from the responses and conducts a preliminary evaluation.

[0108] Video interview assessment and recording

[0109] Once the video interview is over, the server analyzes all responses again and performs a more detailed evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and prepared for submission to the next panel of judges.

[0110] Feedback and next steps for applicants

[0111] The server automatically generates feedback based on the analysis results, including details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then emailed to the user, informing them of the next steps and schedule.

[0112] Specific examples

[0113] For example, User A applying for a new position might go through the process as follows:

[0114] 1. User A fills out an application form and sends it from their device. The server receives and saves the application form data.

[0115] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies User A of the interview date and time and login information.

[0116] 3. User A starts the video interview using the device at the specified date and time and answers the questions. The device sends the answer video to the server in real time.

[0117] 4. The server evaluates User A's answers initially, and then performs a detailed evaluation after the interview. The evaluation results are saved in the database.

[0118] 5. The server generates feedback and notifies User A with details of next steps.

[0119] This system reduces labor costs and time, making the recruitment process more efficient and effective.

[0120] Prompt Sentence Examples

[0121] "The applicant has submitted their application. Please provide details about the prospective process and technical requirements."

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1: Receive your application form

[0124] Input: Contents of the application form filled out by the user

[0125] Specific operation: The user enters the details of the application form on the web form or dedicated application and presses the submit button. This causes the data entered by the user to be temporarily saved on the device.

[0126] Output: Application form data collected by the device

[0127] Step 2: Convert data format and send

[0128] Input: Application form data

[0129] Specific operation: The terminal converts the application form data into JSON or XML format. The converted data is sent to the server as a POST request using the HTTPS protocol. AJAX and fetch API are used for conversion and transmission.

[0130] Output: Data converted to JSON or XML format is sent to the server

[0131] Step 3: Receiving and storing data

[0132] Input: Application form data sent to the server in JSON or XML format

[0133] Specific behavior: The server receives the request and validates the format and content of the data. If the validation is successful, it is saved in the database. During this process, the server automatically sends a receipt confirmation email to the user.

[0134] Output: Validated application form data is saved in the database.

[0135] Step 4: Generate interview question scenarios

[0136] Input: Saved application form data

[0137] Specific operation: The server uses natural language processing (NLP) technology to analyze the contents of the application form. Based on the analysis results, a generative AI model (e.g., GPT-3 (registered trademark)) is used to generate an interview question scenario based on the applicant's experience and skills.

[0138] Output: Generated interview question scenario

[0139] Step 5: Notification of interview date and time and login information

[0140] Input: Generated interview question scenario

[0141] What happens: The server sends an email to the user containing the interview date and time and login information. The email is sent using an SMTP server.

[0142] Output: Email to user containing interview date and time and login information

[0143] Step 6: Start the video interview

[0144] Input: Interview date and time and login information notified by email

[0145] Specific operation: At the specified date and time, the user accesses the web portal or dedicated application using their device to start the video interview. When the user presses the start interview button, video streaming begins.

[0146] Output: Start of video interview

[0147] Step 7: Submit your answer video

[0148] Input: Interview answer video

[0149] Specific operation: The device uses WebRTC or other video streaming technology to send the answer video to the server in real time. The server receives the video data and prepares it for analysis.

[0150] Output: Answer video data sent to the server

[0151] Step 8: Conduct an initial assessment

[0152] Input: Submitted answer video data

[0153] Specific operation: The server uses speech recognition (e.g., Google® Cloud Speech-to-Text) and video analysis (e.g., OpenCV) to extract text and facial expression data from the answer video. Based on the extracted data, a preliminary evaluation is performed.

[0154] Output: preliminary evaluation results

[0155] Step 9: Conduct a detailed assessment

[0156] Input: Initial evaluation results and answer video data

[0157] How it works: After the video interview is completed, the server uses the stored video data and the initial evaluation results to conduct a detailed analysis. This is done using AI models and other analytical tools to evaluate the depth, logic, and emotional expression of the answers.

[0158] Output: Detailed evaluation results

[0159] Step 10: Save the evaluation results

[0160] Input: Detailed evaluation results

[0161] What happens: The server saves the detailed evaluation results in the database, and also sends a notification to the next judge to submit the evaluation results.

[0162] Output: Detailed evaluation results stored in a database

[0163] Step 11: Generate and communicate feedback

[0164] Input: Detailed evaluation results

[0165] What it does: The server uses the AI ​​model to generate a feedback letter from the analysis results, detailing the applicant's strengths, weaknesses, and next steps. The server then sends the feedback letter to the user via the SMTP server.

[0166] Output: Feedback letter sent to the user

[0167] (Application example 1)

[0168] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0169] Traditional recruitment processes are expensive, and it's difficult to efficiently screen applicants with limited resources. It's also difficult to ensure fairness and consistency in evaluations. Furthermore, the process for assessing security staff suitability is complicated, and detailed evaluations must be provided quickly.

[0170] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0171] In this invention, the server includes: means for receiving an application form submitted by a user; means for saving the application form in a database; means for generating an interview question scenario; means for notifying the user of the date, time, and method of the interview; means for the user to start a video interview; means for transmitting the user's video answers to the server in real time during the video interview; means for analyzing the video answers and conducting a preliminary evaluation; means for conducting a detailed evaluation after the video interview is completed; means for saving the evaluation in a database; means for generating feedback based on the evaluation results and notifying the user; means for extracting text and facial expression data from answers in real time during the video interview using voice recognition and video processing technology; means for evaluating the applicant's aptitude in real time based on the extracted text and facial expression data; and means for automatically notifying the user of details of next steps based on feedback after the interview is completed. This reduces labor costs and time, and enables the applicant evaluation process to proceed efficiently and effectively. It also ensures fairness and consistency in evaluations, and enables accurate understanding of the applicant's aptitude through prompt feedback.

[0172] "User" refers to an individual or corporation that accesses the system, submits an application form, and takes a video interview.

[0173] An "application form" is a paper or digital form that an applicant fills out and submits, and includes information such as name, experience, and skills.

[0174] A "database" is a system for managing and storing data such as application forms and evaluation results.

[0175] An "interview question scenario" is a set of questions that are generated based on the contents of the applicant's application form and are used during the interview.

[0176] A "video interview" is a live or recorded interactive interview conducted by a user using a camera and microphone.

[0177] "Server" is a central processing unit for receiving, storing, analyzing, evaluating data, and generating feedback.

[0178] "Speech recognition" is a technology that extracts what a user says as text data.

[0179] "Video processing technology" is a technology that analyzes and extracts data such as facial expressions and gestures from video.

[0180] "Real-time analytics" is the process of instantly analyzing data collected during a video interview.

[0181] An "initial assessment" is a basic assessment conducted during the video interview, including the appropriateness of answers and fluency of speech.

[0182] A "detailed evaluation" is a more in-depth analysis that takes place after the video interview is completed, and is a process of making a comprehensive evaluation based on the logic of the content, emotional expression, etc.

[0183] "Feedback" refers to comments to applicants and details of next steps generated based on the evaluation results.

[0184] This invention uses a system that automates a series of processes, from receiving application forms to providing feedback. This system is realized by combining multiple technologies, including a server, user terminals, and generative AI models.

[0185] First, the user fills out an application form and submits it through a dedicated web form or application. The application form data is converted from the device into JSON or XML format and sent to the server using the HTTPS protocol. The server receives this data, validates it, and stores it in a database. A receipt confirmation email is also automatically sent to the user.

[0186] Next, the server generates a question scenario for the video interview based on the contents of the application form received from the user. This scenario generation uses natural language processing (NLP) technology. Based on the generated question scenario, the server sends the user an email containing the interview date and time and login information. The user accesses the interview portal via their device at the specified date and time to begin the video interview.

[0187] As the video interview progresses, the device transmits the user's responses in real time to a server. The server then uses voice recognition and video processing technology to extract the applicant's responses and facial expression data, and conducts a preliminary evaluation. Specifically, it analyzes the appropriateness of the responses, the fluency of the speech, and the consistency of the facial expressions.

[0188] After the video interview is completed, the server analyzes all responses again and performs a detailed evaluation. This analysis uses a generative AI model to perform a comprehensive evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and made available for the next step.

[0189] Finally, the server automatically generates feedback based on the analysis, detailing the applicant's strengths, weaknesses, and next steps, and then emails the feedback to the user.

[0190] Specific examples

[0191] For example, when a user applies for a security guard position, the following process occurs:

[0192] 1. The user fills out the application form and submits it from the terminal.

[0193] 2. The server receives the application form data, validates it, and saves it in the database.

[0194] 3. The server generates a question scenario and notifies the user of the interview date, time, and method.

[0195] 4. The user starts the video interview at the specified date and time, and the answer video is sent to the server in real time.

[0196] 5. The server analyzes the answer video using voice recognition and video processing technology and performs a preliminary evaluation.

[0197] 6. After the video interview is completed, the server conducts a detailed evaluation and stores the results in a database.

[0198] 7. Finally, the server generates feedback, informing the user of the details of next steps.

[0199] Prompt Sentence Examples

[0200] "Please tell us specifically about your security experience. For example, what kind of problems did you solve?"

[0201] This system reduces labor costs and time, and allows the applicant evaluation process to proceed efficiently and effectively. It also ensures fairness and consistency in evaluation, and provides prompt feedback to accurately grasp the suitability of applicants.

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1:

[0204] Receipt of application form

[0205] The user fills out an application form and submits it from their device. The entered application data is converted to JSON or XML format on the device and sent to the server using the HTTPS protocol. The server receives this data and validates its format and content. Data that passes validation is stored in a database and a receipt confirmation email is automatically sent to the user.

[0206] Input: Application form data (name, experience, skills)

[0207] Output: Save to database, confirmation email

[0208] Step 2:

[0209] Interview question scenario generation

[0210] The server generates an interview question scenario based on the contents of the application form stored in the database. Natural language processing (NLP) technology is used to generate specific questions based on the experience and skills described in the application form. Based on the generated question scenario, an email containing the interview date and time and login information is sent to the user.

[0211] Input: Contents of application form

[0212] Output: An email containing the interview question scenario, interview date and time, and login information

[0213] Step 3:

[0214] Start of video interview

[0215] At the appointed time, the user accesses a web portal or dedicated application on their device to begin the video interview. The interview portal displays pre-generated questions, which the user answers.

[0216] Input: Interview date and time, login information, device

[0217] Output: Start of video interview, recording of answers

[0218] Step 4:

[0219] Real-time transmission of answer videos

[0220] The device transmits the video responses captured during the video interview in real time to a server, using compression technology to ensure high-quality video and audio, and is securely transferred using the HTTPS protocol.

[0221] Input: Answer video (video and audio)

[0222] Output: Video data sent to the server in real time

[0223] Step 5:

[0224] Initial evaluation

[0225] The server analyzes the received video data, extracts the text of the answers using speech recognition technology, and then analyzes the facial expression data using video processing technology to perform a preliminary evaluation based on criteria such as the appropriateness of the answers, the fluency of the speech, and the consistency of the facial expressions.

[0226] Input: Answer video data

[0227] Output: Preliminary evaluation results

[0228] Step 6:

[0229] Detailed evaluation

[0230] After the video interview is completed, the server analyzes the response data in detail again, using a generative AI model to comprehensively evaluate the responses based on criteria such as depth, logic, and emotional expression. The evaluation results are then stored in a database.

[0231] Input: Answer text and facial expression data

[0232] Output: Detailed evaluation results

[0233] Step 7:

[0234] Feedback generation and notification

[0235] The server automatically generates feedback for the applicant based on the detailed evaluation results. The feedback includes details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then sent to the user via email.

[0236] Input: Detailed evaluation results

[0237] Output: Feedback letter, notification of next steps

[0238] This system enables users to be evaluated effectively and efficiently, and to smoothly proceed with the hiring process. By using the prompt sentence "Tell us specifically about your security experience. For example, tell us what kind of trouble you solved," as a model, the system generates specific questions, making it possible to accurately evaluate the suitability of applicants.

[0239] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0240] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form, and further combines it with an emotion engine that recognizes the user's emotions. This system improves interview efficiency and provides a means to deepen understanding of applicants.

[0241] Receiving application forms and saving data

[0242] The user fills out an application form and presses the submit button via a web form or a dedicated application. The device converts the user's input data into JSON or XML format and sends it to the server as a POST request using the secure communication protocol HTTPS. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[0243] Setting up and conducting a video interview

[0244] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions that are appropriate for the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures. At the specified date and time, the user uses their device to access a web portal or dedicated application to begin the video interview.

[0245] During the video interview, the device transmits the user's video responses in real time to a server. The responses are sent as live streaming data and analyzed by the server using voice recognition and video processing technology, resulting in a preliminary evaluation. Furthermore, an emotion engine analyzes the user's emotions based on facial expressions, tone of voice, and body movements in the video responses. This allows the user's emotional data to be collected and used for evaluation along with the text data of the responses.

[0246] Video interview assessment and recording

[0247] Once the video interview is over, the server re-analyzes all answers and conducts a more detailed evaluation. This evaluation considers the depth of the answers, their logic, and the accuracy of the emotional expression. The detailed evaluation also incorporates emotional data obtained by the emotion engine. The evaluation results are stored in a database for easy access by the next judge.

[0248] Feedback and next steps for applicants

[0249] The server automatically generates feedback based on the analysis results. The feedback includes the applicant's strengths, weaknesses, and recommendations for next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[0250] Specific examples

[0251] For example, User A applying for a new position might go through the following process:

[0252] 1. User A fills out an application form and sends it from their device. The server receives the application form data and saves it after validation.

[0253] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies the interview date and time and login information.

[0254] 3. At the specified date and time, User A starts the video interview using the device and answers the questions. The device sends the answer video to the server in real time.

[0255] 4. The server initially evaluates User A's answers, and the emotion engine also analyzes User A's emotions. After the interview is over, a detailed evaluation is conducted and the results are stored in the database.

[0256] 5. The server generates feedback and notifies User A with details of next steps.

[0257] This system reduces labor costs and time, and makes it possible to conduct the recruitment process efficiently and effectively.The emotion engine also performs detailed evaluations that take into account the emotional aspects of applicants, resulting in more accurate selection.

[0258] The processing flow will be explained below.

[0259] Step 1:

[0260] The user submits the application form. The user enters the required information using a web form or a dedicated application and presses the submit button.

[0261] Step 2:

[0262] The terminal sends the application form data to the server. The terminal converts the user's input data into JSON or XML format and sends it to the server as a POST request using the HTTPS protocol.

[0263] Step 3:

[0264] The server receives the application form data, validates the received data, and checks for accuracy and completeness.

[0265] Step 4:

[0266] The server saves the application form data in the database. Data that passes validation is stored in the database.

[0267] Step 5:

[0268] The server will send the user an email acknowledging receipt of the application form. To ensure receipt confirmation, a notification email will be sent automatically to the user.

[0269] Step 6:

[0270] The server generates an interview question scenario, analyzes the contents of the application form, and uses natural language processing technology to create a list of questions suited to the applicant.

[0271] Step 7:

[0272] The server sends an email to the user informing them of the interview date, time, and procedure. An email containing the interview date, time, login information, and procedure is sent to the user along with the generated scenario.

[0273] Step 8:

[0274] The user starts the video interview at the specified date and time. The user uses a device to access the specified web portal or application and starts the interview.

[0275] Step 9:

[0276] The device transmits the user's answer video in real time to the server. During the video interview, the device records the user's video with a camera and transmits it as streaming data to the server.

[0277] Step 10:

[0278] The server analyzes the video responses and performs a preliminary evaluation. It uses voice recognition and video processing technology to extract text data and facial expression data from the responses.

[0279] Step 11:

[0280] The server uses an emotion engine to analyze the emotions in the answer video, collecting emotion data based on the user's facial expressions, tone of voice, and body movements.

[0281] Step 12:

[0282] After the interview, the server reanalyzes all responses and conducts a detailed evaluation. In addition to the initial evaluation results, the evaluation criteria also include depth of content, logic, and emotional expression.

[0283] Step 13:

[0284] The server saves the detailed evaluation results in a database. The evaluation results are stored in the database as structured data, making them easily accessible to the next judge.

[0285] Step 14:

[0286] The server uses the analysis and sentiment data to generate feedback, including the applicant's strengths, weaknesses, and recommended next steps.

[0287] Step 15:

[0288] The server notifies the user of the feedback letter and details of the next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[0289] This series of processing flows reduces the burden on applicants and interviewers while enabling an efficient and effective recruitment process, and also enables detailed analysis using an emotion engine.

[0290] Example 2

[0291] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0292] In the traditional hiring process, designing and running interviews required a great deal of effort and time, placing a heavy burden on hiring managers. It was also difficult to take into account the applicant's emotions and facial expressions, making it difficult to accurately assess the applicant's true abilities and aptitude. Furthermore, the lack of consistent evaluation criteria posed challenges in ensuring the fairness and quality of interview results.

[0293] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an application form submitted by a user, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's answer video to the server in real time during the video interview, means for analyzing the answer video and making a preliminary evaluation, means for analyzing the user's emotions using an emotion engine, means for making a detailed evaluation after the video interview ends, means for saving the evaluation in a database, and means for generating feedback based on the evaluation results and notifying the user. This improves the efficiency and accuracy of the hiring process and enables more accurate evaluations that take applicants' emotions into account.

[0294] "User" refers to an applicant who uses this system to submit an application form and take a video interview.

[0295] An "application form" refers to an electronic form that a user fills in and submits their information (such as name, address, and work history).

[0296] "Database" refers to the data storage area within the system for saving data such as application forms and evaluation results.

[0297] An "interview question scenario" refers to a list of interview questions that is generated based on the user's application form.

[0298] "Notification" refers to emails or messages sent to users informing them of the date, time and manner of their interview.

[0299] A "video interview" refers to an interview in which the user records their answers using a camera and microphone.

[0300] "Server" refers to a central computing device that executes various functions of the system.

[0301] "Answer video" refers to video data containing answers recorded by a user during a video interview.

[0302] "Analysis" refers to the process for analyzing and evaluating response videos and other data.

[0303] "Basic evaluation" refers to the basic evaluation given to the answer video.

[0304] "Emotion engine" refers to a software engine for analyzing a user's emotions.

[0305] "Detailed evaluation" refers to an advanced evaluation based on the depth of the responses and emotional data in addition to the basic evaluation.

[0306] "Feedback" refers to advice and information about next steps provided to the user based on the evaluation results.

[0307] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form, and further combines it with an emotion engine that recognizes the user's emotions. This system improves interview efficiency and provides a means to deepen understanding of applicants.

[0308] Specifically, the user fills out an application form and presses the submit button via a web form or dedicated application. The device converts the user's input data into JSON or XML format and sends it to the server as a POST request using HTTPS, a secure communication protocol. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[0309] Next, the server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions appropriate to the applicant's experience and skills. The server sends the user a notification email containing the interview date and time, login information, and procedures. At the specified date and time, the user uses their device to access a web portal or dedicated application and begin the video interview. During the video interview, the device transmits the user's video answers in real time to the server. The video answers transmitted as live streaming data are analyzed by the server using voice recognition and video processing technology, and a preliminary evaluation is performed. Furthermore, an emotion engine analyzes the user's emotions based on facial expressions, tone of voice, and body movements in the video answers. This allows the user's emotional data to be collected and used for evaluation along with the text data of the answers.

[0310] Once the video interview is over, the server re-analyzes all answers and conducts a more detailed evaluation. This evaluation considers the depth of the answers, their logic, and the accuracy of the emotional expression. The detailed evaluation also incorporates emotional data obtained by the emotion engine. The evaluation results are stored in a database for easy access by the next judge.

[0311] Finally, the server automatically generates feedback based on the analysis results. The feedback includes the applicant's strengths and weaknesses, as well as recommendations for next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule. For example, the process for User A applying for a new position would proceed as follows: User A fills out an application form and submits it from their device. The server receives the application form data and stores it after validation. The server generates an interview question scenario based on User A's experience and skills and notifies them of the interview date and time and login information. At the specified date and time, User A starts a video interview using their device and answers the questions. The device sends the video of their answers to the server in real time. The server performs a preliminary evaluation of User A's answers, and the emotion engine also analyzes User A's emotions. After the interview is completed, a detailed evaluation is conducted and the results are stored in a database. The server generates feedback and notifies User A along with details of next steps.

[0312] The hardware and software used include Google Cloud AI for machine learning model operation on the server side, and Microsoft® Azure® Emotion API for the emotion engine. On the device side, a React.js-based application is used to build the web portal, and WebRTC is used for live streaming technology for video interviews.

[0313] An example of a prompt to be input to the generative AI model is: "Generate interview questions for applicants for a new position. Create a scenario that includes questions based on the applicant's experience and the skills to be verified in the interview. In doing so, also generate data to analyze the applicant's sentiment and provide feedback."

[0314] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0315] Step 1:

[0316] The user fills out the application form.

[0317] Input: A user enters information required into a web form or dedicated application.

[0318] Specific behavior: The user fills in information such as name, address, work history, and skills in the input fields and presses the submit button.

[0319] Step 2:

[0320] The terminal converts the input data and sends it to the server.

[0321] Input: Information entered by the user.

[0322] Data processing: Converts data entered by the terminal into JSON or XML format.

[0323] Output: The converted data is sent to the server via HTTPS.

[0324] Specific operation: As soon as the terminal receives the data, it sends a POST request to the server using a secure communication protocol (HTTPS).

[0325] Step 3:

[0326] The server validates and saves the data.

[0327] Input: Data sent from the terminal in JSON or XML format.

[0328] Data processing: Validate data based on the data schema and check for accuracy and completeness.

[0329] Output: Data that passes validation is saved to the database.

[0330] Specific operation: The server receives the data, checks whether each field is in the required format and content, and if validation is successful, saves it to the database.

[0331] Step 4:

[0332] The server sends a confirmation email.

[0333] Input: Saved entry data.

[0334] Data processing: Generate a confirmation email by filling in the receipt confirmation email template.

[0335] Output: A confirmation email is sent to the user.

[0336] Specific operation: The server sends a message to the user via the mail server saying "The application form has been received."

[0337] Step 5:

[0338] The server generates an interview question scenario.

[0339] Input: Contents of application form data.

[0340] Data processing: Use natural language processing (NLP) techniques to generate appropriate interview questions.

[0341] Output: Interview question scenarios based on the user's experience and skills.

[0342] Specific operation: Entry data is input into the NLP generation AI model, and a question scenario tailored to the job seeker is generated.

[0343] Step 6:

[0344] The server sends an email notification of the interview.

[0345] Input: Generated interview question scenarios.

[0346] Data processing: Generate a notification email containing the interview date and time, login information, and procedures.

[0347] Output: A notification email is sent to the user.

[0348] Specific operation: The server sends an email to the user via the mail server containing the specified date and time and instructions.

[0349] Step 7:

[0350] The user starts the video interview at the specified date and time.

[0351] Input: Notified interview information.

[0352] Specific operation: The user uses the device to access the web portal or dedicated application at the specified date and time to start the video interview.

[0353] Step 8:

[0354] The device sends the answer video to the server.

[0355] Input: Answer video recorded by the user using a camera and microphone.

[0356] Data processing: The device live streams video data in real time.

[0357] Output: The live streaming data sent to the server.

[0358] Specific operation: Using WebRTC technology, the user's answer video is sent to the server in real time.

[0359] Step 9:

[0360] The server analyzes the answer video and performs a preliminary evaluation.

[0361] Input: Answer video data sent from the device.

[0362] Data processing: Answers are converted into text using voice recognition technology, and facial expressions and movements are analyzed using video processing technology.

[0363] Output: Preliminary evaluation data.

[0364] Specific operation: The server converts the answers into text using a voice recognition engine, and analyzes facial expressions and movements using a video processing engine.

[0365] Step 10:

[0366] The server analyzes emotions using an emotion engine.

[0367] Input: Elementary assessment data and answer video data.

[0368] Data processing: Emotions are analyzed based on facial expressions, tone of voice, body movements, etc.

[0369] Output: Emotion data.

[0370] Specific operation: The server uses an emotion engine (such as Microsoft Azure's Emotion API) to analyze and extract emotion data.

[0371] Step 11:

[0372] The server will perform a detailed evaluation.

[0373] Input: Rudimentary rating and emotion data.

[0374] Data processing: A detailed evaluation is conducted taking into consideration the depth of the answers, logic, and accuracy of emotional expression.

[0375] Output: Detailed evaluation data is generated.

[0376] Specific operation: The server will score and comment based on each evaluation item and determine the final evaluation.

[0377] Step 12:

[0378] The server stores the evaluation results in a database.

[0379] Input: Detailed assessment data.

[0380] Data processing: Format the evaluation data to fit the database format.

[0381] Output: The evaluation data is stored in a database.

[0382] Specific operation: The server writes the evaluation data to a database so that the next judge can access it.

[0383] Step 13:

[0384] The server generates feedback and notifies the user.

[0385] Input: Evaluation result data.

[0386] Data processing: Generate feedback letters based on the evaluation results.

[0387] Output: A feedback letter is sent to the user via email.

[0388] What happens: The server fills in an email template and notifies the user with feedback and details about next steps.

[0389] This process allows the system to efficiently and effectively evaluate applicants, and allows for detailed evaluations that also take emotional aspects into account.

[0390] (Application example 2)

[0391] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0392] Conventional interview systems have the drawback of requiring a lot of time and cost for the interview process, and are also difficult to fully grasp the emotions of applicants. Furthermore, it is difficult to provide feedback and support in real time, leaving room for improvement in applicant satisfaction. Therefore, there is a need for an efficient interview system that utilizes emotion recognition.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an application form submitted by a user, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's answer video to the server in real time during the video interview, means for analyzing the answer video and making a preliminary evaluation, means for making a detailed evaluation after the video interview is completed, means for saving the evaluation in a database, means for generating feedback based on the evaluation results and notifying the user, emotion recognition means for analyzing facial expressions and tone of voice to analyze the user's emotions and reflect them in the feedback, and means for acquiring the user's emotion analysis results in real time and providing appropriate feedback based on the analysis results. This enables efficient interview processes and detailed evaluations that take the applicant's emotions into consideration.

[0394] An "entry form" is an information sheet that an applicant fills out and submits, and includes application information such as name, career history, and skills.

[0395] A "database" is a digital information management system that organizes and stores information for quick and efficient access.

[0396] An "interview question scenario" is a scenario that configures the order and content of questions to be asked to an applicant, and is generated based on the contents of the applicant's application form.

[0397] A "video interview" is an online interview conducted over the internet that allows for real-time interaction with applicants.

[0398] A "server" is a computer system that provides services and resources to clients over a network.

[0399] "Real-time" refers to processing and data communication occurring immediately without delay.

[0400] "Emotion recognition means" is a technology that analyzes an applicant's facial expressions and tone of voice to identify their emotional state.

[0401] "Feedback" refers to evaluations and advice provided based on the applicant's interview results and sentiment analysis.

[0402] "Natural language processing" is a general term for computer technologies for processing, understanding, and generating human language.

[0403] "Speech recognition" is a technology that analyzes voice data and converts it into linguistic text.

[0404] "Image processing technology" refers to computer technology for analyzing and processing video and still images, including facial recognition and motion analysis.

[0405] "Initial assessment" refers to basic screening conducted at the early stages of an interview.

[0406] "Detailed evaluation" refers to an in-depth analytical evaluation based on the applicant's responses and emotional data.

[0407] "Login information" refers to the authentication information required when a user accesses a system, including ID and password.

[0408] A "real-time feedback tool" is a system that provides immediate advice and instructions based on the applicant's emotional state and the progress of the interview.

[0409] System program generation

[0410] The system can receive applicants' application forms and conduct video interviews based on their content. It also uses emotion recognition technology to analyze the applicant's emotional state and reflect that in its evaluation and feedback.

[0411] 1. Receiving application forms and saving data

[0412] The user fills out an application form and presses the submit button via a web form or dedicated application. The user's device converts the input data into JSON or XML format and sends it as a POST request to the server using HTTPS, a secure communication protocol. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[0413] 2. Generation and notification of interview question scenarios

[0414] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions that are appropriate for the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures.

[0415] 3. Conducting video interviews

[0416] At the designated date and time, the user will begin the video interview using their device. The video responses are sent in real time to a server, where they are analyzed using voice recognition and video processing technology for a preliminary evaluation.

[0417] 4. Emotion recognition

[0418] The server performs emotion recognition based on the applicant's facial expressions, tone of voice, and body movements in the video of the applicant's answer. Based on the analysis results, the user's emotional data is included in the evaluation.

[0419] 5. Generate detailed evaluations and feedback

[0420] After the video interview, the server reanalyzes the applicant's responses and emotional data to conduct a detailed evaluation. The results of this evaluation are stored in a database, and feedback is automatically generated and notified to the user to help them move on to the next step.

[0421] Hardware and Software Use

[0422] Hardware: Camera and microphone in the smart glasses, the user's computer or smartphone.

[0423] Software: Natural language processing models (NLPModel), speech recognition software (e.g., Google Speech-to-Text), image processing technology (OpenCV), emotion engines (EmotionEngine), database management systems (e.g., MySQL®).

[0424] Specific examples

[0425] For example, consider the process of User A, who has applied for a new position, submitting an application form and then undergoing a video interview. Based on the contents of the application form, a generation AI generates questions such as, "Please tell us more about the projects you have worked on in the past." When User A answers, the server analyzes User A's emotions, such as confidence or nervousness, in real time through facial expression recognition and tone of voice analysis, and provides appropriate feedback. Specifically, real-time advice such as, "The customer is interested. Please tell us more." is provided.

[0426] Prompt Sentence Examples

[0427] "Generate customer service scenarios that ask customers questions about past purchases and spark interest."

[0428] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0429] Step 1: Receiving the application form and saving the data

[0430] The user submits an application form. The device converts the input data into JSON or XML format and sends it to the server using a secure communication protocol (HTTPS). The server validates the received data to ensure accuracy and completeness. After verification, the application form data is saved in a database and a receipt confirmation email is automatically sent to the user.

[0431] Input: Application form data (JSON or XML format)

[0432] Data processing: Data validation

[0433] Output: Application form stored in the database, receipt confirmation email

[0434] Step 2: Generate and notify interview question scenarios

[0435] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes appropriate questions based on the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures.

[0436] Input: Application form data

[0437] Data processing: Generate interview question scenarios (using NLP technology)

[0438] Output: Interview question scenario, notification email

[0439] Step 3: Conduct a video interview

[0440] At the specified date and time, the user begins the video interview using their device. The device sends the video responses in real time to the server. The server then uses voice recognition and video processing technology to analyze the video and perform a preliminary evaluation of the applicant's responses.

[0441] Input: User answer video

[0442] Data processing: Analysis using voice recognition and video processing technology

[0443] Output: preliminary evaluation data

[0444] Step 4: Emotion Recognition

[0445] During the video interview, the server analyzes the applicant's facial expressions, tone of voice, and body movements. It uses an emotion recognition engine to identify the applicant's emotions and generate emotional data. The generated emotional data is then used to evaluate the applicant's answers.

[0446] Input: User's answer video (facial expressions, tone of voice, body movements)

[0447] Data processing: Emotion recognition using an emotion engine

[0448] Output: Emotion data

[0449] Step 5: Generate detailed evaluation and feedback

[0450] After the video interview is completed, the server reanalyzes the answer video and emotional data to conduct a detailed evaluation. This evaluation includes the depth of the answer, logic, and accuracy of emotional expression. The evaluation results are stored in a database, and feedback is automatically generated and notified to the user to help them move on to the next step.

[0451] Input: Answer video, emotion data

[0452] Data processing: detailed evaluation reanalysis and feedback generation

[0453] Output: Evaluation results, feedback, notification email

[0454] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0455] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0456] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0457] [Second embodiment]

[0458] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0459] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0460] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0461] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0462] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0463] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0464] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0465] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0466] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0467] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0468] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0469] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0470] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening that takes place after submitting an application form. The purpose of this system is to deepen understanding of applicants while reducing labor costs.

[0471] Receiving application forms and saving data

[0472] The user fills out an application form and presses the submit button via a web form or a dedicated application. The terminal converts this data into JSON or XML format and sends it as a POST request to the server using the HTTPS protocol. The server receives this data, validates it, and stores it in a database. During this process, a confirmation email is automatically sent to the user.

[0473] Setting up and conducting a video interview

[0474] The server generates an interview question scenario based on the contents of the application form received from the user. The scenario uses natural language processing (NLP) technology to include questions based on the applicant's experience and skills. The server then sends the user an email containing the interview date and time and login information. At the specified date and time, the user uses their device to access a web portal or dedicated application to begin the video interview.

[0475] During the interview, the device transmits the user's video responses in real time to a server, which uses voice recognition and video processing technology to extract text and facial expression data from the responses and conducts a preliminary evaluation, including the appropriateness of the responses, speech fluency, and facial expression consistency.

[0476] Video interview assessment and recording

[0477] Once the video interview is over, the server analyzes all responses again and performs a more detailed evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and prepared for submission to the next panel of judges.

[0478] Feedback and next steps for applicants

[0479] The server automatically generates feedback based on the analysis results, including details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then emailed to the user, informing them of the next steps and schedule.

[0480] Specific examples

[0481] For example, User A applying for a new position might go through the process as follows:

[0482] 1. User A fills out an application form and sends it from their device. The server receives and saves the application form data.

[0483] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies User A of the interview date and time and login information.

[0484] 3. User A starts the video interview using the device at the specified date and time and answers the questions. The device sends the answer video to the server in real time.

[0485] 4. The server evaluates User A's answers initially, and then performs a detailed evaluation after the interview. The evaluation results are saved in the database.

[0486] 5. The server generates feedback and notifies User A with details of next steps.

[0487] This system reduces labor costs and time, making the recruitment process more efficient and effective.

[0488] The processing flow will be explained below.

[0489] Step 1:

[0490] The user submits the application form. The user enters the required information using a web form or a dedicated application and presses the submit button.

[0491] Step 2:

[0492] The terminal sends the application form data to the server. The terminal converts the user's input data into JSON or XML format and sends it to the server as a POST request using the HTTPS protocol.

[0493] Step 3:

[0494] The server receives the application form data, validates the received data, and checks for accuracy and completeness.

[0495] Step 4:

[0496] The server saves the application form data in the database. Data that passes validation is stored in the database.

[0497] Step 5:

[0498] The server will send the user an email acknowledging receipt of the application form. To ensure receipt confirmation, a notification email will be sent automatically to the user.

[0499] Step 6:

[0500] The server generates an interview question scenario, analyzes the contents of the application form, and uses natural language processing technology to create a list of questions suited to the applicant.

[0501] Step 7:

[0502] The server sends a notification to the user, including the date, time, and procedure for the interview. The generated scenario is sent to the user via email, along with the interview date, time, login information, and instructions.

[0503] Step 8:

[0504] The user starts the video interview at the specified date and time. The user uses a device to access the specified web portal or application and starts the interview.

[0505] Step 9:

[0506] The device transmits the user's answer video in real time to the server. During the video interview, the device records the user's video with a camera and transmits it as streaming data to the server.

[0507] Step 10:

[0508] The server analyzes the video responses and performs a preliminary evaluation. AI is used to perform real-time voice recognition and video processing, extracting the text and facial expression data from the responses, and then a preliminary evaluation is performed.

[0509] Step 11:

[0510] After the video interview is completed, the server reanalyzes all responses and conducts a detailed evaluation. In addition to a basic evaluation, the server also evaluates the depth of the content, logic, emotional expression, and other factors.

[0511] Step 12:

[0512] The server saves the detailed evaluation results in a database. The evaluation results are stored in the database as structured data, making them easily accessible to the next judge.

[0513] Step 13:

[0514] The server generates feedback based on the analysis results. Based on the detailed evaluation results, feedback is automatically generated that includes the applicant's strengths, weaknesses, and recommendations for next steps.

[0515] Step 14:

[0516] The server notifies the user of the feedback letter and details of the next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[0517] This series of processing flows reduces the burden on applicants and interviewers while realizing an efficient and effective recruitment process.

[0518] Example 1

[0519] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0520] In the traditional recruitment process, managing a large number of application forms, arranging interviews, and evaluating the interview results required a great deal of time and effort. Furthermore, it was prone to artificial bias in the evaluations and difficult to provide efficient feedback. This resulted in an inefficiency in the entire recruitment process, delaying the selection of the best candidates.

[0521] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0522] In this invention, the server includes means for receiving an application form submitted by a user, means for converting the application form into a data format and transmitting it to the server using a secure protocol, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's video answers to the server in real time during the video interview, means for analyzing the video answers and making a preliminary evaluation, means for making a detailed evaluation after the video interview is completed, means for saving the evaluation in a database, and means for generating feedback based on the evaluation results and notifying the user. This streamlines the entire hiring process, reduces labor costs and time, and enables fair and rapid personnel evaluation.

[0523] "User" refers to an applicant who uses this system to submit an application form and participate in a video interview.

[0524] An "entry form" refers to a document that contains personal information, work history, etc. that a user fills out and submits in order to apply for a job.

[0525] "Data format" refers to the digital format, such as JSON or XML, into which the application form is converted.

[0526] "Secure Protocol" refers to a protocol, such as HTTPS, used to ensure the secure transmission of data.

[0527] "Server" refers to a computer system that receives, stores, analyzes, and generates feedback on application forms.

[0528] A "database" refers to an information system that systematically stores and manages data such as application forms and evaluation results.

[0529] An "interview question scenario" refers to a list of interview questions generated based on an applicant's application form.

[0530] "Notification means" refers to the procedures and techniques for notifying users of information such as the date, time, and method of the interview.

[0531] A "video interview" refers to an online interview that a user participates in using a web portal or dedicated application.

[0532] "Answer video" refers to video data that records a user answering questions during a video interview.

[0533] "Analysis means" refers to the speech recognition and / or video processing technology used to evaluate the recorded response videos.

[0534] The "feedback generation means" refers to a method for automatically generating feedback to be provided to the user based on the analysis results.

[0535] This invention relates to a system that uses a generative AI model to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form. The system aims to streamline the recruitment process and reduce labor costs.

[0536] Receiving application forms and saving data

[0537] When a user fills out an application form and presses the submit button via a web form or a dedicated application, the device converts the collected data into JSON or XML format and sends it to the server using the HTTPS protocol. The server receives the data, validates it, and stores it in a database. During this process, the server automatically sends the user a confirmation email.

[0538] Setting up and conducting a video interview

[0539] Based on the contents of the application form received from the user, the server uses natural language processing (NLP) technology to generate an interview question scenario based on the applicant's experience and skills. The server then sends the user an email containing the interview date and time and login information. At the specified date and time, the user uses their device to access a web portal or dedicated application and begin the video interview. The device then transmits the user's video responses in real time to the server, which uses voice recognition and video processing technology to extract the text and facial expression data from the responses and conducts a preliminary evaluation.

[0540] Video interview assessment and recording

[0541] Once the video interview is over, the server analyzes all responses again and performs a more detailed evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and prepared for submission to the next panel of judges.

[0542] Feedback and next steps for applicants

[0543] The server automatically generates feedback based on the analysis results, including details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then emailed to the user, informing them of the next steps and schedule.

[0544] Specific examples

[0545] For example, User A applying for a new position might go through the process as follows:

[0546] 1. User A fills out an application form and sends it from their device. The server receives and saves the application form data.

[0547] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies User A of the interview date and time and login information.

[0548] 3. User A starts the video interview using the device at the specified date and time and answers the questions. The device sends the answer video to the server in real time.

[0549] 4. The server evaluates User A's answers initially, and then performs a detailed evaluation after the interview. The evaluation results are saved in the database.

[0550] 5. The server generates feedback and notifies User A with details of next steps.

[0551] This system reduces labor costs and time, making the recruitment process more efficient and effective.

[0552] Prompt Sentence Examples

[0553] "The applicant has submitted their application. Please provide details about the prospective process and technical requirements."

[0554] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0555] Step 1: Receive your application form

[0556] Input: Contents of the application form filled out by the user

[0557] Specific operation: The user enters the details of the application form on the web form or dedicated application and presses the submit button. This causes the data entered by the user to be temporarily saved on the device.

[0558] Output: Application form data collected by the device

[0559] Step 2: Convert data format and send

[0560] Input: Application form data

[0561] Specific operation: The terminal converts the application form data into JSON or XML format. The converted data is sent to the server as a POST request using the HTTPS protocol. AJAX and fetch API are used for conversion and transmission.

[0562] Output: Data converted to JSON or XML format is sent to the server

[0563] Step 3: Receiving and storing data

[0564] Input: Application form data sent to the server in JSON or XML format

[0565] Specific behavior: The server receives the request and validates the format and content of the data. If the validation is successful, it is saved in the database. During this process, the server automatically sends a receipt confirmation email to the user.

[0566] Output: Validated application form data is saved in the database.

[0567] Step 4: Generate interview question scenarios

[0568] Input: Saved application form data

[0569] How it works: The server uses natural language processing (NLP) technology to analyze the contents of the application form. Based on the analysis results, a generative AI model (e.g., GPT-3) is used to generate interview question scenarios based on the applicant's experience and skills.

[0570] Output: Generated interview question scenario

[0571] Step 5: Notification of interview date and time and login information

[0572] Input: Generated interview question scenario

[0573] What happens: The server sends an email to the user containing the interview date and time and login information. The email is sent using an SMTP server.

[0574] Output: Email to user containing interview date and time and login information

[0575] Step 6: Start the video interview

[0576] Input: Interview date and time and login information notified by email

[0577] Specific operation: At the specified date and time, the user accesses the web portal or dedicated application using their device to start the video interview. When the user presses the start interview button, video streaming begins.

[0578] Output: Start of video interview

[0579] Step 7: Submit your answer video

[0580] Input: Interview answer video

[0581] Specific operation: The device uses WebRTC or other video streaming technology to send the answer video to the server in real time. The server receives the video data and prepares it for analysis.

[0582] Output: Answer video data sent to the server

[0583] Step 8: Conduct an initial assessment

[0584] Input: Submitted answer video data

[0585] Specific operation: The server uses speech recognition (e.g., Google Cloud Speech-to-Text) and video analysis (e.g., OpenCV) to extract text and facial expression data from the answer video. Based on the extracted data, a preliminary evaluation is performed.

[0586] Output: preliminary evaluation results

[0587] Step 9: Conduct a detailed assessment

[0588] Input: Initial evaluation results and answer video data

[0589] How it works: After the video interview is completed, the server uses the stored video data and the initial evaluation results to conduct a detailed analysis. This is done using AI models and other analytical tools to evaluate the depth, logic, and emotional expression of the answers.

[0590] Output: Detailed evaluation results

[0591] Step 10: Save the evaluation results

[0592] Input: Detailed evaluation results

[0593] What happens: The server saves the detailed evaluation results in the database, and also sends a notification to the next judge to submit the evaluation results.

[0594] Output: Detailed evaluation results stored in a database

[0595] Step 11: Generate and communicate feedback

[0596] Input: Detailed evaluation results

[0597] What it does: The server uses the AI ​​model to generate a feedback letter from the analysis results, detailing the applicant's strengths, weaknesses, and next steps. The server then sends the feedback letter to the user via the SMTP server.

[0598] Output: Feedback letter sent to the user

[0599] (Application example 1)

[0600] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0601] Traditional recruitment processes are expensive, and it's difficult to efficiently screen applicants with limited resources. It's also difficult to ensure fairness and consistency in evaluations. Furthermore, the process for assessing security staff suitability is complicated, and detailed evaluations must be provided quickly.

[0602] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0603] In this invention, the server includes: means for receiving an application form submitted by a user; means for saving the application form in a database; means for generating an interview question scenario; means for notifying the user of the date, time, and method of the interview; means for the user to start a video interview; means for transmitting the user's video answers to the server in real time during the video interview; means for analyzing the video answers and conducting a preliminary evaluation; means for conducting a detailed evaluation after the video interview is completed; means for saving the evaluation in a database; means for generating feedback based on the evaluation results and notifying the user; means for extracting text and facial expression data from answers in real time during the video interview using voice recognition and video processing technology; means for evaluating the applicant's aptitude in real time based on the extracted text and facial expression data; and means for automatically notifying the user of details of next steps based on feedback after the interview is completed. This reduces labor costs and time, and enables the applicant evaluation process to proceed efficiently and effectively. It also ensures fairness and consistency in evaluations, and enables accurate understanding of the applicant's aptitude through prompt feedback.

[0604] "User" refers to an individual or corporation that accesses the system, submits an application form, and takes a video interview.

[0605] An "application form" is a paper or digital form that an applicant fills out and submits, and includes information such as name, experience, and skills.

[0606] A "database" is a system for managing and storing data such as application forms and evaluation results.

[0607] An "interview question scenario" is a set of questions that are generated based on the contents of the applicant's application form and are used during the interview.

[0608] A "video interview" is a live or recorded interactive interview conducted by a user using a camera and microphone.

[0609] "Server" is a central processing unit for receiving, storing, analyzing, evaluating data, and generating feedback.

[0610] "Speech recognition" is a technology that extracts what a user says as text data.

[0611] "Video processing technology" is a technology that analyzes and extracts data such as facial expressions and gestures from video.

[0612] "Real-time analytics" is the process of instantly analyzing data collected during a video interview.

[0613] An "initial assessment" is a basic assessment conducted during the video interview, including the appropriateness of answers and fluency of speech.

[0614] A "detailed evaluation" is a more in-depth analysis that takes place after the video interview is completed, and is a process of making a comprehensive evaluation based on the logic of the content, emotional expression, etc.

[0615] "Feedback" refers to comments to applicants and details of next steps generated based on the evaluation results.

[0616] This invention uses a system that automates a series of processes, from receiving application forms to providing feedback. This system is realized by combining multiple technologies, including a server, user terminals, and generative AI models.

[0617] First, the user fills out an application form and submits it through a dedicated web form or application. The application form data is converted from the device into JSON or XML format and sent to the server using the HTTPS protocol. The server receives this data, validates it, and stores it in a database. A receipt confirmation email is also automatically sent to the user.

[0618] Next, the server generates a question scenario for the video interview based on the contents of the application form received from the user. This scenario generation uses natural language processing (NLP) technology. Based on the generated question scenario, the server sends the user an email containing the interview date and time and login information. The user accesses the interview portal via their device at the specified date and time to begin the video interview.

[0619] As the video interview progresses, the device transmits the user's responses in real time to a server. The server then uses voice recognition and video processing technology to extract the applicant's responses and facial expression data, and conducts a preliminary evaluation. Specifically, it analyzes the appropriateness of the responses, the fluency of the speech, and the consistency of the facial expressions.

[0620] After the video interview is completed, the server analyzes all responses again and performs a detailed evaluation. This analysis uses a generative AI model to perform a comprehensive evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and made available for the next step.

[0621] Finally, the server automatically generates feedback based on the analysis, detailing the applicant's strengths, weaknesses, and next steps, and then emails the feedback to the user.

[0622] Specific examples

[0623] For example, when a user applies for a security guard position, the following process occurs:

[0624] 1. The user fills out the application form and submits it from the terminal.

[0625] 2. The server receives the application form data, validates it, and saves it in the database.

[0626] 3. The server generates a question scenario and notifies the user of the interview date, time, and method.

[0627] 4. The user starts the video interview at the specified date and time, and the answer video is sent to the server in real time.

[0628] 5. The server analyzes the answer video using voice recognition and video processing technology and performs a preliminary evaluation.

[0629] 6. After the video interview is completed, the server conducts a detailed evaluation and stores the results in a database.

[0630] 7. Finally, the server generates feedback, informing the user of the details of next steps.

[0631] Prompt Sentence Examples

[0632] "Please tell us specifically about your security experience. For example, what kind of problems did you solve?"

[0633] This system reduces labor costs and time, and allows the applicant evaluation process to proceed efficiently and effectively. It also ensures fairness and consistency in evaluation, and provides prompt feedback to accurately grasp the suitability of applicants.

[0634] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0635] Step 1:

[0636] Receipt of application form

[0637] The user fills out an application form and submits it from their device. The entered application data is converted to JSON or XML format on the device and sent to the server using the HTTPS protocol. The server receives this data and validates its format and content. Data that passes validation is stored in a database and a receipt confirmation email is automatically sent to the user.

[0638] Input: Application form data (name, experience, skills)

[0639] Output: Save to database, confirmation email

[0640] Step 2:

[0641] Interview question scenario generation

[0642] The server generates an interview question scenario based on the contents of the application form stored in the database. Natural language processing (NLP) technology is used to generate specific questions based on the experience and skills described in the application form. Based on the generated question scenario, an email containing the interview date and time and login information is sent to the user.

[0643] Input: Contents of application form

[0644] Output: An email containing the interview question scenario, interview date and time, and login information

[0645] Step 3:

[0646] Start of video interview

[0647] At the appointed time, the user accesses a web portal or dedicated application on their device to begin the video interview. The interview portal displays pre-generated questions, which the user answers.

[0648] Input: Interview date and time, login information, device

[0649] Output: Start of video interview, recording of answers

[0650] Step 4:

[0651] Real-time transmission of answer videos

[0652] The device transmits the video responses captured during the video interview in real time to a server, using compression technology to ensure high-quality video and audio, and is securely transferred using the HTTPS protocol.

[0653] Input: Answer video (video and audio)

[0654] Output: Video data sent to the server in real time

[0655] Step 5:

[0656] Initial evaluation

[0657] The server analyzes the received video data, extracts the text of the answers using speech recognition technology, and then analyzes the facial expression data using video processing technology to perform a preliminary evaluation based on criteria such as the appropriateness of the answers, the fluency of the speech, and the consistency of the facial expressions.

[0658] Input: Answer video data

[0659] Output: Preliminary evaluation results

[0660] Step 6:

[0661] Detailed evaluation

[0662] After the video interview is completed, the server analyzes the response data in detail again, using a generative AI model to comprehensively evaluate the responses based on criteria such as depth, logic, and emotional expression. The evaluation results are then stored in a database.

[0663] Input: Answer text and facial expression data

[0664] Output: Detailed evaluation results

[0665] Step 7:

[0666] Feedback generation and notification

[0667] The server automatically generates feedback for the applicant based on the detailed evaluation results. The feedback includes details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then sent to the user via email.

[0668] Input: Detailed evaluation results

[0669] Output: Feedback letter, notification of next steps

[0670] This system enables users to be evaluated effectively and efficiently, and to smoothly proceed with the hiring process. By using the prompt sentence "Tell us specifically about your security experience. For example, tell us what kind of trouble you solved," as a model, the system generates specific questions, making it possible to accurately evaluate the suitability of applicants.

[0671] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0672] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form, and further combines it with an emotion engine that recognizes the user's emotions. This system improves interview efficiency and provides a means to deepen understanding of applicants.

[0673] Receiving application forms and saving data

[0674] The user fills out an application form and presses the submit button via a web form or a dedicated application. The device converts the user's input data into JSON or XML format and sends it to the server as a POST request using the secure communication protocol HTTPS. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[0675] Setting up and conducting a video interview

[0676] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions that are appropriate for the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures. At the specified date and time, the user uses their device to access a web portal or dedicated application to begin the video interview.

[0677] During the video interview, the device transmits the user's video responses in real time to a server. The responses are sent as live streaming data and analyzed by the server using voice recognition and video processing technology, resulting in a preliminary evaluation. Furthermore, an emotion engine analyzes the user's emotions based on facial expressions, tone of voice, and body movements in the video responses. This allows the user's emotional data to be collected and used for evaluation along with the text data of the responses.

[0678] Video interview assessment and recording

[0679] Once the video interview is over, the server re-analyzes all answers and conducts a more detailed evaluation. This evaluation considers the depth of the answers, their logic, and the accuracy of the emotional expression. The detailed evaluation also incorporates emotional data obtained by the emotion engine. The evaluation results are stored in a database for easy access by the next judge.

[0680] Feedback and next steps for applicants

[0681] The server automatically generates feedback based on the analysis results. The feedback includes the applicant's strengths, weaknesses, and recommendations for next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[0682] Specific examples

[0683] For example, User A applying for a new position might go through the following process:

[0684] 1. User A fills out an application form and sends it from their device. The server receives the application form data and saves it after validation.

[0685] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies the interview date and time and login information.

[0686] 3. At the specified date and time, User A starts the video interview using the device and answers the questions. The device sends the answer video to the server in real time.

[0687] 4. The server initially evaluates User A's answers, and the emotion engine also analyzes User A's emotions. After the interview is over, a detailed evaluation is conducted and the results are stored in the database.

[0688] 5. The server generates feedback and notifies User A with details of next steps.

[0689] This system reduces labor costs and time, and makes it possible to conduct the recruitment process efficiently and effectively.The emotion engine also performs detailed evaluations that take into account the emotional aspects of applicants, resulting in more accurate selection.

[0690] The processing flow will be explained below.

[0691] Step 1:

[0692] The user submits the application form. The user enters the required information using a web form or a dedicated application and presses the submit button.

[0693] Step 2:

[0694] The terminal sends the application form data to the server. The terminal converts the user's input data into JSON or XML format and sends it to the server as a POST request using the HTTPS protocol.

[0695] Step 3:

[0696] The server receives the application form data, validates the received data, and checks for accuracy and completeness.

[0697] Step 4:

[0698] The server saves the application form data in the database. Data that passes validation is stored in the database.

[0699] Step 5:

[0700] The server will send the user an email acknowledging receipt of the application form. To ensure receipt confirmation, a notification email will be sent automatically to the user.

[0701] Step 6:

[0702] The server generates an interview question scenario, analyzes the contents of the application form, and uses natural language processing technology to create a list of questions suited to the applicant.

[0703] Step 7:

[0704] The server sends an email to the user informing them of the interview date, time, and procedure. An email containing the interview date, time, login information, and procedure is sent to the user along with the generated scenario.

[0705] Step 8:

[0706] The user starts the video interview at the specified date and time. The user uses a device to access the specified web portal or application and starts the interview.

[0707] Step 9:

[0708] The device transmits the user's answer video in real time to the server. During the video interview, the device records the user's video with a camera and transmits it as streaming data to the server.

[0709] Step 10:

[0710] The server analyzes the video responses and performs a preliminary evaluation. It uses voice recognition and video processing technology to extract text data and facial expression data from the responses.

[0711] Step 11:

[0712] The server uses an emotion engine to analyze the emotions in the answer video, collecting emotion data based on the user's facial expressions, tone of voice, and body movements.

[0713] Step 12:

[0714] After the interview, the server reanalyzes all responses and conducts a detailed evaluation. In addition to the initial evaluation results, the evaluation criteria also include depth of content, logic, and emotional expression.

[0715] Step 13:

[0716] The server saves the detailed evaluation results in a database. The evaluation results are stored in the database as structured data, making them easily accessible to the next judge.

[0717] Step 14:

[0718] The server uses the analysis and sentiment data to generate feedback, including the applicant's strengths, weaknesses, and recommended next steps.

[0719] Step 15:

[0720] The server notifies the user of the feedback letter and details of the next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[0721] This series of processing flows reduces the burden on applicants and interviewers while enabling an efficient and effective recruitment process, and also enables detailed analysis using an emotion engine.

[0722] Example 2

[0723] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0724] In the traditional hiring process, designing and running interviews required a great deal of effort and time, placing a heavy burden on hiring managers. It was also difficult to take into account the applicant's emotions and facial expressions, making it difficult to accurately assess the applicant's true abilities and aptitude. Furthermore, the lack of consistent evaluation criteria posed challenges in ensuring the fairness and quality of interview results.

[0725] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an application form submitted by a user, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's answer video to the server in real time during the video interview, means for analyzing the answer video and making a preliminary evaluation, means for analyzing the user's emotions using an emotion engine, means for making a detailed evaluation after the video interview ends, means for saving the evaluation in a database, and means for generating feedback based on the evaluation results and notifying the user. This improves the efficiency and accuracy of the hiring process and enables more accurate evaluations that take applicants' emotions into account.

[0726] "User" refers to an applicant who uses this system to submit an application form and take a video interview.

[0727] An "application form" refers to an electronic form that a user fills in and submits their information (such as name, address, and work history).

[0728] "Database" refers to the data storage area within the system for saving data such as application forms and evaluation results.

[0729] An "interview question scenario" refers to a list of interview questions that is generated based on the user's application form.

[0730] "Notification" refers to emails or messages sent to users informing them of the date, time and manner of their interview.

[0731] A "video interview" refers to an interview in which the user records their answers using a camera and microphone.

[0732] "Server" refers to a central computing device that executes various functions of the system.

[0733] "Answer video" refers to video data containing answers recorded by a user during a video interview.

[0734] "Analysis" refers to the process for analyzing and evaluating response videos and other data.

[0735] "Basic evaluation" refers to the basic evaluation given to the answer video.

[0736] "Emotion engine" refers to a software engine for analyzing a user's emotions.

[0737] "Detailed evaluation" refers to an advanced evaluation based on the depth of the responses and emotional data in addition to the basic evaluation.

[0738] "Feedback" refers to advice and information about next steps provided to the user based on the evaluation results.

[0739] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form, and further combines it with an emotion engine that recognizes the user's emotions. This system improves interview efficiency and provides a means to deepen understanding of applicants.

[0740] Specifically, the user fills out an application form and presses the submit button via a web form or dedicated application. The device converts the user's input data into JSON or XML format and sends it to the server as a POST request using HTTPS, a secure communication protocol. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[0741] Next, the server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions appropriate to the applicant's experience and skills. The server sends the user a notification email containing the interview date and time, login information, and procedures. At the specified date and time, the user uses their device to access a web portal or dedicated application and begin the video interview. During the video interview, the device transmits the user's video answers in real time to the server. The video answers transmitted as live streaming data are analyzed by the server using voice recognition and video processing technology, and a preliminary evaluation is performed. Furthermore, an emotion engine analyzes the user's emotions based on facial expressions, tone of voice, and body movements in the video answers. This allows the user's emotional data to be collected and used for evaluation along with the text data of the answers.

[0742] Once the video interview is over, the server re-analyzes all answers and conducts a more detailed evaluation. This evaluation considers the depth of the answers, their logic, and the accuracy of the emotional expression. The detailed evaluation also incorporates emotional data obtained by the emotion engine. The evaluation results are stored in a database for easy access by the next judge.

[0743] Finally, the server automatically generates feedback based on the analysis results. The feedback includes the applicant's strengths and weaknesses, as well as recommendations for next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule. For example, the process for User A applying for a new position would proceed as follows: User A fills out an application form and submits it from their device. The server receives the application form data and stores it after validation. The server generates an interview question scenario based on User A's experience and skills and notifies them of the interview date and time and login information. At the specified date and time, User A starts a video interview using their device and answers the questions. The device sends the video of their answers to the server in real time. The server performs a preliminary evaluation of User A's answers, and the emotion engine also analyzes User A's emotions. After the interview is completed, a detailed evaluation is conducted and the results are stored in a database. The server generates feedback and notifies User A along with details of next steps.

[0744] The hardware and software used include Google Cloud AI for machine learning model operation on the server side and Microsoft Azure's Emotion API for the emotion engine, while the device side uses a React.js-based application to build the web portal and WebRTC for live streaming technology for video interviews.

[0745] An example of a prompt to be input to the generative AI model is: "Generate interview questions for applicants for a new position. Create a scenario that includes questions based on the applicant's experience and the skills to be verified in the interview. In doing so, also generate data to analyze the applicant's sentiment and provide feedback."

[0746] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0747] Step 1:

[0748] The user fills out the application form.

[0749] Input: A user enters information required into a web form or dedicated application.

[0750] Specific behavior: The user fills in information such as name, address, work history, and skills in the input fields and presses the submit button.

[0751] Step 2:

[0752] The terminal converts the input data and sends it to the server.

[0753] Input: Information entered by the user.

[0754] Data processing: Converts data entered by the terminal into JSON or XML format.

[0755] Output: The converted data is sent to the server via HTTPS.

[0756] Specific operation: As soon as the terminal receives the data, it sends a POST request to the server using a secure communication protocol (HTTPS).

[0757] Step 3:

[0758] The server validates and saves the data.

[0759] Input: Data sent from the terminal in JSON or XML format.

[0760] Data processing: Validate data based on the data schema and check for accuracy and completeness.

[0761] Output: Data that passes validation is saved to the database.

[0762] Specific operation: The server receives the data, checks whether each field is in the required format and content, and if validation is successful, saves it to the database.

[0763] Step 4:

[0764] The server sends a confirmation email.

[0765] Input: Saved entry data.

[0766] Data processing: Generate a confirmation email by filling in the receipt confirmation email template.

[0767] Output: A confirmation email is sent to the user.

[0768] Specific operation: The server sends a message to the user via the mail server saying "The application form has been received."

[0769] Step 5:

[0770] The server generates an interview question scenario.

[0771] Input: Contents of application form data.

[0772] Data processing: Use natural language processing (NLP) techniques to generate appropriate interview questions.

[0773] Output: Interview question scenarios based on the user's experience and skills.

[0774] Specific operation: Entry data is input into the NLP generation AI model, and a question scenario tailored to the job seeker is generated.

[0775] Step 6:

[0776] The server sends an email notification of the interview.

[0777] Input: Generated interview question scenarios.

[0778] Data processing: Generate a notification email containing the interview date and time, login information, and procedures.

[0779] Output: A notification email is sent to the user.

[0780] Specific operation: The server sends an email to the user via the mail server containing the specified date and time and instructions.

[0781] Step 7:

[0782] The user starts the video interview at the specified date and time.

[0783] Input: Notified interview information.

[0784] Specific operation: The user uses the device to access the web portal or dedicated application at the specified date and time to start the video interview.

[0785] Step 8:

[0786] The device sends the answer video to the server.

[0787] Input: Answer video recorded by the user using a camera and microphone.

[0788] Data processing: The device live streams video data in real time.

[0789] Output: The live streaming data sent to the server.

[0790] Specific operation: Using WebRTC technology, the user's answer video is sent to the server in real time.

[0791] Step 9:

[0792] The server analyzes the answer video and performs a preliminary evaluation.

[0793] Input: Answer video data sent from the device.

[0794] Data processing: Answers are converted into text using voice recognition technology, and facial expressions and movements are analyzed using video processing technology.

[0795] Output: Preliminary evaluation data.

[0796] Specific operation: The server converts the answers into text using a voice recognition engine, and analyzes facial expressions and movements using a video processing engine.

[0797] Step 10:

[0798] The server analyzes emotions using an emotion engine.

[0799] Input: Elementary assessment data and answer video data.

[0800] Data processing: Emotions are analyzed based on facial expressions, tone of voice, body movements, etc.

[0801] Output: Emotion data.

[0802] Specific operation: The server uses an emotion engine (such as Microsoft Azure's Emotion API) to analyze and extract emotion data.

[0803] Step 11:

[0804] The server will perform a detailed evaluation.

[0805] Input: Rudimentary rating and emotion data.

[0806] Data processing: A detailed evaluation is conducted taking into consideration the depth of the answers, logic, and accuracy of emotional expression.

[0807] Output: Detailed evaluation data is generated.

[0808] Specific operation: The server will score and comment based on each evaluation item and determine the final evaluation.

[0809] Step 12:

[0810] The server stores the evaluation results in a database.

[0811] Input: Detailed assessment data.

[0812] Data processing: Format the evaluation data to fit the database format.

[0813] Output: The evaluation data is stored in a database.

[0814] Specific operation: The server writes the evaluation data to a database so that the next judge can access it.

[0815] Step 13:

[0816] The server generates feedback and notifies the user.

[0817] Input: Evaluation result data.

[0818] Data processing: Generate feedback letters based on the evaluation results.

[0819] Output: A feedback letter is sent to the user via email.

[0820] What happens: The server fills in an email template and notifies the user with feedback and details about next steps.

[0821] This process allows the system to efficiently and effectively evaluate applicants, and allows for detailed evaluations that also take emotional aspects into account.

[0822] (Application example 2)

[0823] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0824] Conventional interview systems have the drawback of requiring a lot of time and cost for the interview process, and are also difficult to fully grasp the emotions of applicants. Furthermore, it is difficult to provide feedback and support in real time, leaving room for improvement in applicant satisfaction. Therefore, there is a need for an efficient interview system that utilizes emotion recognition.

[0825] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an application form submitted by a user, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's answer video to the server in real time during the video interview, means for analyzing the answer video and making a preliminary evaluation, means for making a detailed evaluation after the video interview is completed, means for saving the evaluation in a database, means for generating feedback based on the evaluation results and notifying the user, emotion recognition means for analyzing facial expressions and tone of voice to analyze the user's emotions and reflect them in the feedback, and means for acquiring the user's emotion analysis results in real time and providing appropriate feedback based on the analysis results. This enables efficient interview processes and detailed evaluations that take the applicant's emotions into consideration.

[0826] An "entry form" is an information sheet that an applicant fills out and submits, and includes application information such as name, career history, and skills.

[0827] A "database" is a digital information management system that organizes and stores information for quick and efficient access.

[0828] An "interview question scenario" is a scenario that configures the order and content of questions to be asked to an applicant, and is generated based on the contents of the applicant's application form.

[0829] A "video interview" is an online interview conducted over the internet that allows for real-time interaction with applicants.

[0830] A "server" is a computer system that provides services and resources to clients over a network.

[0831] "Real-time" refers to processing and data communication occurring immediately without delay.

[0832] "Emotion recognition means" is a technology that analyzes an applicant's facial expressions and tone of voice to identify their emotional state.

[0833] "Feedback" refers to evaluations and advice provided based on the applicant's interview results and sentiment analysis.

[0834] "Natural language processing" is a general term for computer technologies for processing, understanding, and generating human language.

[0835] "Speech recognition" is a technology that analyzes voice data and converts it into linguistic text.

[0836] "Image processing technology" refers to computer technology for analyzing and processing video and still images, including facial recognition and motion analysis.

[0837] "Initial assessment" refers to basic screening conducted at the early stages of an interview.

[0838] "Detailed evaluation" refers to an in-depth analytical evaluation based on the applicant's responses and emotional data.

[0839] "Login information" refers to the authentication information required when a user accesses a system, including ID and password.

[0840] A "real-time feedback tool" is a system that provides immediate advice and instructions based on the applicant's emotional state and the progress of the interview.

[0841] System program generation

[0842] The system can receive applicants' application forms and conduct video interviews based on their content. It also uses emotion recognition technology to analyze the applicant's emotional state and reflect that in its evaluation and feedback.

[0843] 1. Receiving application forms and saving data

[0844] The user fills out an application form and presses the submit button via a web form or dedicated application. The user's device converts the input data into JSON or XML format and sends it as a POST request to the server using HTTPS, a secure communication protocol. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[0845] 2. Generation and notification of interview question scenarios

[0846] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions that are appropriate for the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures.

[0847] 3. Conducting video interviews

[0848] At the designated date and time, the user will begin the video interview using their device. The video responses are sent in real time to a server, where they are analyzed using voice recognition and video processing technology for a preliminary evaluation.

[0849] 4. Emotion recognition

[0850] The server performs emotion recognition based on the applicant's facial expressions, tone of voice, and body movements in the video of the applicant's answer. Based on the analysis results, the user's emotional data is included in the evaluation.

[0851] 5. Generate detailed evaluations and feedback

[0852] After the video interview, the server reanalyzes the applicant's responses and emotional data to conduct a detailed evaluation. The results of this evaluation are stored in a database, and feedback is automatically generated and notified to the user to help them move on to the next step.

[0853] Hardware and Software Use

[0854] Hardware: Camera and microphone in the smart glasses, the user's computer or smartphone.

[0855] Software: Natural language processing models (NLPModel), speech recognition software (e.g., Google Speech-to-Text), image processing technology (OpenCV), emotion engines (EmotionEngine), database management systems (e.g., MySQL).

[0856] Specific examples

[0857] For example, consider the process of User A, who has applied for a new position, submitting an application form and then undergoing a video interview. Based on the contents of the application form, a generation AI generates questions such as, "Please tell us more about the projects you have worked on in the past." When User A answers, the server analyzes User A's emotions, such as confidence or nervousness, in real time through facial expression recognition and tone of voice analysis, and provides appropriate feedback. Specifically, real-time advice such as, "The customer is interested. Please tell us more." is provided.

[0858] Prompt Sentence Examples

[0859] "Generate customer service scenarios that ask customers questions about past purchases and spark interest."

[0860] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0861] Step 1: Receiving the application form and saving the data

[0862] The user submits an application form. The device converts the input data into JSON or XML format and sends it to the server using a secure communication protocol (HTTPS). The server validates the received data to ensure accuracy and completeness. After verification, the application form data is saved in a database and a receipt confirmation email is automatically sent to the user.

[0863] Input: Application form data (JSON or XML format)

[0864] Data processing: Data validation

[0865] Output: Application form stored in the database, receipt confirmation email

[0866] Step 2: Generate and notify interview question scenarios

[0867] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes appropriate questions based on the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures.

[0868] Input: Application form data

[0869] Data processing: Generate interview question scenarios (using NLP technology)

[0870] Output: Interview question scenario, notification email

[0871] Step 3: Conduct a video interview

[0872] At the specified date and time, the user begins the video interview using their device. The device sends the video responses in real time to the server. The server then uses voice recognition and video processing technology to analyze the video and perform a preliminary evaluation of the applicant's responses.

[0873] Input: User answer video

[0874] Data processing: Analysis using voice recognition and video processing technology

[0875] Output: preliminary evaluation data

[0876] Step 4: Emotion Recognition

[0877] During the video interview, the server analyzes the applicant's facial expressions, tone of voice, and body movements. It uses an emotion recognition engine to identify the applicant's emotions and generate emotional data. The generated emotional data is then used to evaluate the applicant's answers.

[0878] Input: User's answer video (facial expressions, tone of voice, body movements)

[0879] Data processing: Emotion recognition using an emotion engine

[0880] Output: Emotion data

[0881] Step 5: Generate detailed evaluation and feedback

[0882] After the video interview is completed, the server reanalyzes the answer video and emotional data to conduct a detailed evaluation. This evaluation includes the depth of the answer, logic, and accuracy of emotional expression. The evaluation results are stored in a database, and feedback is automatically generated and notified to the user to help them move on to the next step.

[0883] Input: Answer video, emotion data

[0884] Data processing: detailed evaluation reanalysis and feedback generation

[0885] Output: Evaluation results, feedback, notification email

[0886] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0887] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0888] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0889] [Third embodiment]

[0890] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0891] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0892] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0893] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0894] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0895] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0896] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0897] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0898] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0899] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0900] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0901] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0902] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening that takes place after submitting an application form. The purpose of this system is to deepen understanding of applicants while reducing labor costs.

[0903] Receiving application forms and saving data

[0904] The user fills out an application form and presses the submit button via a web form or a dedicated application. The terminal converts this data into JSON or XML format and sends it as a POST request to the server using the HTTPS protocol. The server receives this data, validates it, and stores it in a database. During this process, a confirmation email is automatically sent to the user.

[0905] Setting up and conducting a video interview

[0906] The server generates an interview question scenario based on the contents of the application form received from the user. The scenario uses natural language processing (NLP) technology to include questions based on the applicant's experience and skills. The server then sends the user an email containing the interview date and time and login information. At the specified date and time, the user uses their device to access a web portal or dedicated application to begin the video interview.

[0907] During the interview, the device transmits the user's video responses in real time to a server, which uses voice recognition and video processing technology to extract text and facial expression data from the responses and conducts a preliminary evaluation, including the appropriateness of the responses, speech fluency, and facial expression consistency.

[0908] Video interview assessment and recording

[0909] Once the video interview is over, the server analyzes all responses again and performs a more detailed evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and prepared for submission to the next panel of judges.

[0910] Feedback and next steps for applicants

[0911] The server automatically generates feedback based on the analysis results, including details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then emailed to the user, informing them of the next steps and schedule.

[0912] Specific examples

[0913] For example, User A applying for a new position might go through the process as follows:

[0914] 1. User A fills out an application form and sends it from their device. The server receives and saves the application form data.

[0915] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies User A of the interview date and time and login information.

[0916] 3. User A starts the video interview using the device at the specified date and time and answers the questions. The device sends the answer video to the server in real time.

[0917] 4. The server evaluates User A's answers initially, and then performs a detailed evaluation after the interview. The evaluation results are saved in the database.

[0918] 5. The server generates feedback and notifies User A with details of next steps.

[0919] This system reduces labor costs and time, making the recruitment process more efficient and effective.

[0920] The processing flow will be explained below.

[0921] Step 1:

[0922] The user submits the application form. The user enters the required information using a web form or a dedicated application and presses the submit button.

[0923] Step 2:

[0924] The terminal sends the application form data to the server. The terminal converts the user's input data into JSON or XML format and sends it to the server as a POST request using the HTTPS protocol.

[0925] Step 3:

[0926] The server receives the application form data, validates the received data, and checks for accuracy and completeness.

[0927] Step 4:

[0928] The server saves the application form data in the database. Data that passes validation is stored in the database.

[0929] Step 5:

[0930] The server will send the user an email acknowledging receipt of the application form. To ensure receipt confirmation, a notification email will be sent automatically to the user.

[0931] Step 6:

[0932] The server generates an interview question scenario, analyzes the contents of the application form, and uses natural language processing technology to create a list of questions suited to the applicant.

[0933] Step 7:

[0934] The server sends a notification to the user, including the date, time, and procedure for the interview. The generated scenario is sent to the user via email, along with the interview date, time, login information, and instructions.

[0935] Step 8:

[0936] The user starts the video interview at the specified date and time. The user uses a device to access the specified web portal or application and starts the interview.

[0937] Step 9:

[0938] The device transmits the user's answer video in real time to the server. During the video interview, the device records the user's video with a camera and transmits it as streaming data to the server.

[0939] Step 10:

[0940] The server analyzes the video responses and performs a preliminary evaluation. AI is used to perform real-time voice recognition and video processing, extracting the text and facial expression data from the responses, and then a preliminary evaluation is performed.

[0941] Step 11:

[0942] After the video interview is completed, the server reanalyzes all responses and conducts a detailed evaluation. In addition to a basic evaluation, the server also evaluates the depth of the content, logic, emotional expression, and other factors.

[0943] Step 12:

[0944] The server saves the detailed evaluation results in a database. The evaluation results are stored in the database as structured data, making them easily accessible to the next judge.

[0945] Step 13:

[0946] The server generates feedback based on the analysis results. Based on the detailed evaluation results, feedback is automatically generated that includes the applicant's strengths, weaknesses, and recommendations for next steps.

[0947] Step 14:

[0948] The server notifies the user of the feedback letter and details of the next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[0949] This series of processing flows reduces the burden on applicants and interviewers while realizing an efficient and effective recruitment process.

[0950] Example 1

[0951] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0952] In the traditional recruitment process, managing a large number of application forms, arranging interviews, and evaluating the interview results required a great deal of time and effort. Furthermore, it was prone to artificial bias in the evaluations and difficult to provide efficient feedback. This resulted in an inefficiency in the entire recruitment process, delaying the selection of the best candidates.

[0953] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0954] In this invention, the server includes means for receiving an application form submitted by a user, means for converting the application form into a data format and transmitting it to the server using a secure protocol, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's video answers to the server in real time during the video interview, means for analyzing the video answers and making a preliminary evaluation, means for making a detailed evaluation after the video interview is completed, means for saving the evaluation in a database, and means for generating feedback based on the evaluation results and notifying the user. This streamlines the entire hiring process, reduces labor costs and time, and enables fair and rapid personnel evaluation.

[0955] "User" refers to an applicant who uses this system to submit an application form and participate in a video interview.

[0956] An "entry form" refers to a document that contains personal information, work history, etc. that a user fills out and submits in order to apply for a job.

[0957] "Data format" refers to the digital format, such as JSON or XML, into which the application form is converted.

[0958] "Secure Protocol" refers to a protocol, such as HTTPS, used to ensure the secure transmission of data.

[0959] "Server" refers to a computer system that receives, stores, analyzes, and generates feedback on application forms.

[0960] A "database" refers to an information system that systematically stores and manages data such as application forms and evaluation results.

[0961] An "interview question scenario" refers to a list of interview questions generated based on an applicant's application form.

[0962] "Notification means" refers to the procedures and techniques for notifying users of information such as the date, time, and method of the interview.

[0963] A "video interview" refers to an online interview that a user participates in using a web portal or dedicated application.

[0964] "Answer video" refers to video data that records a user answering questions during a video interview.

[0965] "Analysis means" refers to the speech recognition and / or video processing technology used to evaluate the recorded response videos.

[0966] The "feedback generation means" refers to a method for automatically generating feedback to be provided to the user based on the analysis results.

[0967] This invention relates to a system that uses a generative AI model to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form. The system aims to streamline the recruitment process and reduce labor costs.

[0968] Receiving application forms and saving data

[0969] When a user fills out an application form and presses the submit button via a web form or a dedicated application, the device converts the collected data into JSON or XML format and sends it to the server using the HTTPS protocol. The server receives the data, validates it, and stores it in a database. During this process, the server automatically sends the user a confirmation email.

[0970] Setting up and conducting a video interview

[0971] Based on the contents of the application form received from the user, the server uses natural language processing (NLP) technology to generate an interview question scenario based on the applicant's experience and skills. The server then sends the user an email containing the interview date and time and login information. At the specified date and time, the user uses their device to access a web portal or dedicated application and begin the video interview. The device then transmits the user's video responses in real time to the server, which uses voice recognition and video processing technology to extract the text and facial expression data from the responses and conducts a preliminary evaluation.

[0972] Video interview assessment and recording

[0973] Once the video interview is over, the server analyzes all responses again and performs a more detailed evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and prepared for submission to the next panel of judges.

[0974] Feedback and next steps for applicants

[0975] The server automatically generates feedback based on the analysis results, including details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then emailed to the user, informing them of the next steps and schedule.

[0976] Specific examples

[0977] For example, User A applying for a new position might go through the process as follows:

[0978] 1. User A fills out an application form and sends it from their device. The server receives and saves the application form data.

[0979] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies User A of the interview date and time and login information.

[0980] 3. User A starts the video interview using the device at the specified date and time and answers the questions. The device sends the answer video to the server in real time.

[0981] 4. The server evaluates User A's answers initially, and then performs a detailed evaluation after the interview. The evaluation results are saved in the database.

[0982] 5. The server generates feedback and notifies User A with details of next steps.

[0983] This system reduces labor costs and time, making the recruitment process more efficient and effective.

[0984] Prompt Sentence Examples

[0985] "The applicant has submitted their application. Please provide details about the prospective process and technical requirements."

[0986] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0987] Step 1: Receive your application form

[0988] Input: Contents of the application form filled out by the user

[0989] Specific operation: The user enters the details of the application form on the web form or dedicated application and presses the submit button. This causes the data entered by the user to be temporarily saved on the device.

[0990] Output: Application form data collected by the device

[0991] Step 2: Convert data format and send

[0992] Input: Application form data

[0993] Specific operation: The terminal converts the application form data into JSON or XML format. The converted data is sent to the server as a POST request using the HTTPS protocol. AJAX and fetch API are used for conversion and transmission.

[0994] Output: Data converted to JSON or XML format is sent to the server

[0995] Step 3: Receiving and storing data

[0996] Input: Application form data sent to the server in JSON or XML format

[0997] Specific behavior: The server receives the request and validates the format and content of the data. If the validation is successful, it is saved in the database. During this process, the server automatically sends a receipt confirmation email to the user.

[0998] Output: Validated application form data is saved in the database.

[0999] Step 4: Generate interview question scenarios

[1000] Input: Saved application form data

[1001] How it works: The server uses natural language processing (NLP) technology to analyze the contents of the application form. Based on the analysis results, a generative AI model (e.g., GPT-3) is used to generate interview question scenarios based on the applicant's experience and skills.

[1002] Output: Generated interview question scenario

[1003] Step 5: Notification of interview date and time and login information

[1004] Input: Generated interview question scenario

[1005] What happens: The server sends an email to the user containing the interview date and time and login information. The email is sent using an SMTP server.

[1006] Output: Email to user containing interview date and time and login information

[1007] Step 6: Start the video interview

[1008] Input: Interview date and time and login information notified by email

[1009] Specific operation: At the specified date and time, the user accesses the web portal or dedicated application using their device to start the video interview. When the user presses the start interview button, video streaming begins.

[1010] Output: Start of video interview

[1011] Step 7: Submit your answer video

[1012] Input: Interview answer video

[1013] Specific operation: The device uses WebRTC or other video streaming technology to send the answer video to the server in real time. The server receives the video data and prepares it for analysis.

[1014] Output: Answer video data sent to the server

[1015] Step 8: Conduct an initial assessment

[1016] Input: Submitted answer video data

[1017] Specific operation: The server uses speech recognition (e.g., Google Cloud Speech-to-Text) and video analysis (e.g., OpenCV) to extract text and facial expression data from the answer video. Based on the extracted data, a preliminary evaluation is performed.

[1018] Output: preliminary evaluation results

[1019] Step 9: Conduct a detailed assessment

[1020] Input: Initial evaluation results and answer video data

[1021] How it works: After the video interview is completed, the server uses the stored video data and the initial evaluation results to conduct a detailed analysis. This is done using AI models and other analytical tools to evaluate the depth, logic, and emotional expression of the answers.

[1022] Output: Detailed evaluation results

[1023] Step 10: Save the evaluation results

[1024] Input: Detailed evaluation results

[1025] What happens: The server saves the detailed evaluation results in the database, and also sends a notification to the next judge to submit the evaluation results.

[1026] Output: Detailed evaluation results stored in a database

[1027] Step 11: Generate and communicate feedback

[1028] Input: Detailed evaluation results

[1029] What it does: The server uses the AI ​​model to generate a feedback letter from the analysis results, detailing the applicant's strengths, weaknesses, and next steps. The server then sends the feedback letter to the user via the SMTP server.

[1030] Output: Feedback letter sent to the user

[1031] (Application example 1)

[1032] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1033] Traditional recruitment processes are expensive, and it's difficult to efficiently screen applicants with limited resources. It's also difficult to ensure fairness and consistency in evaluations. Furthermore, the process for assessing security staff suitability is complicated, and detailed evaluations must be provided quickly.

[1034] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1035] In this invention, the server includes: means for receiving an application form submitted by a user; means for saving the application form in a database; means for generating an interview question scenario; means for notifying the user of the date, time, and method of the interview; means for the user to start a video interview; means for transmitting the user's video answers to the server in real time during the video interview; means for analyzing the video answers and conducting a preliminary evaluation; means for conducting a detailed evaluation after the video interview is completed; means for saving the evaluation in a database; means for generating feedback based on the evaluation results and notifying the user; means for extracting text and facial expression data from answers in real time during the video interview using voice recognition and video processing technology; means for evaluating the applicant's aptitude in real time based on the extracted text and facial expression data; and means for automatically notifying the user of details of next steps based on feedback after the interview is completed. This reduces labor costs and time, and enables the applicant evaluation process to proceed efficiently and effectively. It also ensures fairness and consistency in evaluations, and enables accurate understanding of the applicant's aptitude through prompt feedback.

[1036] "User" refers to an individual or corporation that accesses the system, submits an application form, and takes a video interview.

[1037] An "application form" is a paper or digital form that an applicant fills out and submits, and includes information such as name, experience, and skills.

[1038] A "database" is a system for managing and storing data such as application forms and evaluation results.

[1039] An "interview question scenario" is a set of questions that are generated based on the contents of the applicant's application form and are used during the interview.

[1040] A "video interview" is a live or recorded interactive interview conducted by a user using a camera and microphone.

[1041] "Server" is a central processing unit for receiving, storing, analyzing, evaluating data, and generating feedback.

[1042] "Speech recognition" is a technology that extracts what a user says as text data.

[1043] "Video processing technology" is a technology that analyzes and extracts data such as facial expressions and gestures from video.

[1044] "Real-time analytics" is the process of instantly analyzing data collected during a video interview.

[1045] An "initial assessment" is a basic assessment conducted during the video interview, including the appropriateness of answers and fluency of speech.

[1046] A "detailed evaluation" is a more in-depth analysis that takes place after the video interview is completed, and is a process of making a comprehensive evaluation based on the logic of the content, emotional expression, etc.

[1047] "Feedback" refers to comments to applicants and details of next steps generated based on the evaluation results.

[1048] This invention uses a system that automates a series of processes, from receiving application forms to providing feedback. This system is realized by combining multiple technologies, including a server, user terminals, and generative AI models.

[1049] First, the user fills out an application form and submits it through a dedicated web form or application. The application form data is converted from the device into JSON or XML format and sent to the server using the HTTPS protocol. The server receives this data, validates it, and stores it in a database. A receipt confirmation email is also automatically sent to the user.

[1050] Next, the server generates a question scenario for the video interview based on the contents of the application form received from the user. This scenario generation uses natural language processing (NLP) technology. Based on the generated question scenario, the server sends the user an email containing the interview date and time and login information. The user accesses the interview portal via their device at the specified date and time to begin the video interview.

[1051] As the video interview progresses, the device transmits the user's responses in real time to a server. The server then uses voice recognition and video processing technology to extract the applicant's responses and facial expression data, and conducts a preliminary evaluation. Specifically, it analyzes the appropriateness of the responses, the fluency of the speech, and the consistency of the facial expressions.

[1052] After the video interview is completed, the server analyzes all responses again and performs a detailed evaluation. This analysis uses a generative AI model to perform a comprehensive evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and made available for the next step.

[1053] Finally, the server automatically generates feedback based on the analysis, detailing the applicant's strengths, weaknesses, and next steps, and then emails the feedback to the user.

[1054] Specific examples

[1055] For example, when a user applies for a security guard position, the following process occurs:

[1056] 1. The user fills out the application form and submits it from the terminal.

[1057] 2. The server receives the application form data, validates it, and saves it in the database.

[1058] 3. The server generates a question scenario and notifies the user of the interview date, time, and method.

[1059] 4. The user starts the video interview at the specified date and time, and the answer video is sent to the server in real time.

[1060] 5. The server analyzes the answer video using voice recognition and video processing technology and performs a preliminary evaluation.

[1061] 6. After the video interview is completed, the server conducts a detailed evaluation and stores the results in a database.

[1062] 7. Finally, the server generates feedback, informing the user of the details of next steps.

[1063] Prompt Sentence Examples

[1064] "Please tell us specifically about your security experience. For example, what kind of problems did you solve?"

[1065] This system reduces labor costs and time, and allows the applicant evaluation process to proceed efficiently and effectively. It also ensures fairness and consistency in evaluation, and provides prompt feedback to accurately grasp the suitability of applicants.

[1066] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1067] Step 1:

[1068] Receipt of application form

[1069] The user fills out an application form and submits it from their device. The entered application data is converted to JSON or XML format on the device and sent to the server using the HTTPS protocol. The server receives this data and validates its format and content. Data that passes validation is stored in a database and a receipt confirmation email is automatically sent to the user.

[1070] Input: Application form data (name, experience, skills)

[1071] Output: Save to database, confirmation email

[1072] Step 2:

[1073] Interview question scenario generation

[1074] The server generates an interview question scenario based on the contents of the application form stored in the database. Natural language processing (NLP) technology is used to generate specific questions based on the experience and skills described in the application form. Based on the generated question scenario, an email containing the interview date and time and login information is sent to the user.

[1075] Input: Contents of application form

[1076] Output: An email containing the interview question scenario, interview date and time, and login information

[1077] Step 3:

[1078] Start of video interview

[1079] At the appointed time, the user accesses a web portal or dedicated application on their device to begin the video interview. The interview portal displays pre-generated questions, which the user answers.

[1080] Input: Interview date and time, login information, device

[1081] Output: Start of video interview, recording of answers

[1082] Step 4:

[1083] Real-time transmission of answer videos

[1084] The device transmits the video responses captured during the video interview in real time to a server, using compression technology to ensure high-quality video and audio, and is securely transferred using the HTTPS protocol.

[1085] Input: Answer video (video and audio)

[1086] Output: Video data sent to the server in real time

[1087] Step 5:

[1088] Initial evaluation

[1089] The server analyzes the received video data, extracts the text of the answers using speech recognition technology, and then analyzes the facial expression data using video processing technology to perform a preliminary evaluation based on criteria such as the appropriateness of the answers, the fluency of the speech, and the consistency of the facial expressions.

[1090] Input: Answer video data

[1091] Output: Preliminary evaluation results

[1092] Step 6:

[1093] Detailed evaluation

[1094] After the video interview is completed, the server analyzes the response data in detail again, using a generative AI model to comprehensively evaluate the responses based on criteria such as depth, logic, and emotional expression. The evaluation results are then stored in a database.

[1095] Input: Answer text and facial expression data

[1096] Output: Detailed evaluation results

[1097] Step 7:

[1098] Feedback generation and notification

[1099] The server automatically generates feedback for the applicant based on the detailed evaluation results. The feedback includes details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then sent to the user via email.

[1100] Input: Detailed evaluation results

[1101] Output: Feedback letter, notification of next steps

[1102] This system enables users to be evaluated effectively and efficiently, and to smoothly proceed with the hiring process. By using the prompt sentence "Tell us specifically about your security experience. For example, tell us what kind of trouble you solved," as a model, the system generates specific questions, making it possible to accurately evaluate the suitability of applicants.

[1103] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1104] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form, and further combines it with an emotion engine that recognizes the user's emotions. This system improves interview efficiency and provides a means to deepen understanding of applicants.

[1105] Receiving application forms and saving data

[1106] The user fills out an application form and presses the submit button via a web form or a dedicated application. The device converts the user's input data into JSON or XML format and sends it to the server as a POST request using the secure communication protocol HTTPS. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[1107] Setting up and conducting a video interview

[1108] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions that are appropriate for the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures. At the specified date and time, the user uses their device to access a web portal or dedicated application to begin the video interview.

[1109] During the video interview, the device transmits the user's video responses in real time to a server. The responses are sent as live streaming data and analyzed by the server using voice recognition and video processing technology, resulting in a preliminary evaluation. Furthermore, an emotion engine analyzes the user's emotions based on facial expressions, tone of voice, and body movements in the video responses. This allows the user's emotional data to be collected and used for evaluation along with the text data of the responses.

[1110] Video interview assessment and recording

[1111] Once the video interview is over, the server re-analyzes all answers and conducts a more detailed evaluation. This evaluation considers the depth of the answers, their logic, and the accuracy of the emotional expression. The detailed evaluation also incorporates emotional data obtained by the emotion engine. The evaluation results are stored in a database for easy access by the next judge.

[1112] Feedback and next steps for applicants

[1113] The server automatically generates feedback based on the analysis results. The feedback includes the applicant's strengths, weaknesses, and recommendations for next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[1114] Specific examples

[1115] For example, User A applying for a new position might go through the following process:

[1116] 1. User A fills out an application form and sends it from their device. The server receives the application form data and saves it after validation.

[1117] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies the interview date and time and login information.

[1118] 3. At the specified date and time, User A starts the video interview using the device and answers the questions. The device sends the answer video to the server in real time.

[1119] 4. The server initially evaluates User A's answers, and the emotion engine also analyzes User A's emotions. After the interview is over, a detailed evaluation is conducted and the results are stored in the database.

[1120] 5. The server generates feedback and notifies User A with details of next steps.

[1121] This system reduces labor costs and time, and makes it possible to conduct the recruitment process efficiently and effectively.The emotion engine also performs detailed evaluations that take into account the emotional aspects of applicants, resulting in more accurate selection.

[1122] The processing flow will be explained below.

[1123] Step 1:

[1124] The user submits the application form. The user enters the required information using a web form or a dedicated application and presses the submit button.

[1125] Step 2:

[1126] The terminal sends the application form data to the server. The terminal converts the user's input data into JSON or XML format and sends it to the server as a POST request using the HTTPS protocol.

[1127] Step 3:

[1128] The server receives the application form data, validates the received data, and checks for accuracy and completeness.

[1129] Step 4:

[1130] The server saves the application form data in the database. Data that passes validation is stored in the database.

[1131] Step 5:

[1132] The server will send the user an email acknowledging receipt of the application form. To ensure receipt confirmation, a notification email will be sent automatically to the user.

[1133] Step 6:

[1134] The server generates an interview question scenario, analyzes the contents of the application form, and uses natural language processing technology to create a list of questions suited to the applicant.

[1135] Step 7:

[1136] The server sends an email to the user informing them of the interview date, time, and procedure. An email containing the interview date, time, login information, and procedure is sent to the user along with the generated scenario.

[1137] Step 8:

[1138] The user starts the video interview at the specified date and time. The user uses a device to access the specified web portal or application and starts the interview.

[1139] Step 9:

[1140] The device transmits the user's answer video in real time to the server. During the video interview, the device records the user's video with a camera and transmits it as streaming data to the server.

[1141] Step 10:

[1142] The server analyzes the video responses and performs a preliminary evaluation. It uses voice recognition and video processing technology to extract text data and facial expression data from the responses.

[1143] Step 11:

[1144] The server uses an emotion engine to analyze the emotions in the answer video, collecting emotion data based on the user's facial expressions, tone of voice, and body movements.

[1145] Step 12:

[1146] After the interview, the server reanalyzes all responses and conducts a detailed evaluation. In addition to the initial evaluation results, the evaluation criteria also include depth of content, logic, and emotional expression.

[1147] Step 13:

[1148] The server saves the detailed evaluation results in a database. The evaluation results are stored in the database as structured data, making them easily accessible to the next judge.

[1149] Step 14:

[1150] The server uses the analysis and sentiment data to generate feedback, including the applicant's strengths, weaknesses, and recommended next steps.

[1151] Step 15:

[1152] The server notifies the user of the feedback letter and details of the next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[1153] This series of processing flows reduces the burden on applicants and interviewers while enabling an efficient and effective recruitment process, and also enables detailed analysis using an emotion engine.

[1154] Example 2

[1155] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1156] In the traditional hiring process, designing and running interviews required a great deal of effort and time, placing a heavy burden on hiring managers. It was also difficult to take into account the applicant's emotions and facial expressions, making it difficult to accurately assess the applicant's true abilities and aptitude. Furthermore, the lack of consistent evaluation criteria posed challenges in ensuring the fairness and quality of interview results.

[1157] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an application form submitted by a user, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's answer video to the server in real time during the video interview, means for analyzing the answer video and making a preliminary evaluation, means for analyzing the user's emotions using an emotion engine, means for making a detailed evaluation after the video interview ends, means for saving the evaluation in a database, and means for generating feedback based on the evaluation results and notifying the user. This improves the efficiency and accuracy of the hiring process and enables more accurate evaluations that take applicants' emotions into account.

[1158] "User" refers to an applicant who uses this system to submit an application form and take a video interview.

[1159] An "application form" refers to an electronic form that a user fills in and submits their information (such as name, address, and work history).

[1160] "Database" refers to the data storage area within the system for saving data such as application forms and evaluation results.

[1161] An "interview question scenario" refers to a list of interview questions that is generated based on the user's application form.

[1162] "Notification" refers to emails or messages sent to users informing them of the date, time and manner of their interview.

[1163] A "video interview" refers to an interview in which the user records their answers using a camera and microphone.

[1164] "Server" refers to a central computing device that executes various functions of the system.

[1165] "Answer video" refers to video data containing answers recorded by a user during a video interview.

[1166] "Analysis" refers to the process for analyzing and evaluating response videos and other data.

[1167] "Basic evaluation" refers to the basic evaluation given to the answer video.

[1168] "Emotion engine" refers to a software engine for analyzing a user's emotions.

[1169] "Detailed evaluation" refers to an advanced evaluation based on the depth of the responses and emotional data in addition to the basic evaluation.

[1170] "Feedback" refers to advice and information about next steps provided to the user based on the evaluation results.

[1171] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form, and further combines it with an emotion engine that recognizes the user's emotions. This system improves interview efficiency and provides a means to deepen understanding of applicants.

[1172] Specifically, the user fills out an application form and presses the submit button via a web form or dedicated application. The device converts the user's input data into JSON or XML format and sends it to the server as a POST request using HTTPS, a secure communication protocol. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[1173] Next, the server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions appropriate to the applicant's experience and skills. The server sends the user a notification email containing the interview date and time, login information, and procedures. At the specified date and time, the user uses their device to access a web portal or dedicated application and begin the video interview. During the video interview, the device transmits the user's video answers in real time to the server. The video answers transmitted as live streaming data are analyzed by the server using voice recognition and video processing technology, and a preliminary evaluation is performed. Furthermore, an emotion engine analyzes the user's emotions based on facial expressions, tone of voice, and body movements in the video answers. This allows the user's emotional data to be collected and used for evaluation along with the text data of the answers.

[1174] Once the video interview is over, the server re-analyzes all answers and conducts a more detailed evaluation. This evaluation considers the depth of the answers, their logic, and the accuracy of the emotional expression. The detailed evaluation also incorporates emotional data obtained by the emotion engine. The evaluation results are stored in a database for easy access by the next judge.

[1175] Finally, the server automatically generates feedback based on the analysis results. The feedback includes the applicant's strengths and weaknesses, as well as recommendations for next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule. For example, the process for User A applying for a new position would proceed as follows: User A fills out an application form and submits it from their device. The server receives the application form data and stores it after validation. The server generates an interview question scenario based on User A's experience and skills and notifies them of the interview date and time and login information. At the specified date and time, User A starts a video interview using their device and answers the questions. The device sends the video of their answers to the server in real time. The server performs a preliminary evaluation of User A's answers, and the emotion engine also analyzes User A's emotions. After the interview is completed, a detailed evaluation is conducted and the results are stored in a database. The server generates feedback and notifies User A along with details of next steps.

[1176] The hardware and software used include Google Cloud AI for machine learning model operation on the server side and Microsoft Azure's Emotion API for the emotion engine, while the device side uses a React.js-based application to build the web portal and WebRTC for live streaming technology for video interviews.

[1177] An example of a prompt to be input to the generative AI model is: "Generate interview questions for applicants for a new position. Create a scenario that includes questions based on the applicant's experience and the skills to be verified in the interview. In doing so, also generate data to analyze the applicant's sentiment and provide feedback."

[1178] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1179] Step 1:

[1180] The user fills out the application form.

[1181] Input: A user enters information required into a web form or dedicated application.

[1182] Specific behavior: The user fills in information such as name, address, work history, and skills in the input fields and presses the submit button.

[1183] Step 2:

[1184] The terminal converts the input data and sends it to the server.

[1185] Input: Information entered by the user.

[1186] Data processing: Converts data entered by the terminal into JSON or XML format.

[1187] Output: The converted data is sent to the server via HTTPS.

[1188] Specific operation: As soon as the terminal receives the data, it sends a POST request to the server using a secure communication protocol (HTTPS).

[1189] Step 3:

[1190] The server validates and saves the data.

[1191] Input: Data sent from the terminal in JSON or XML format.

[1192] Data processing: Validate data based on the data schema and check for accuracy and completeness.

[1193] Output: Data that passes validation is saved to the database.

[1194] Specific operation: The server receives the data, checks whether each field is in the required format and content, and if validation is successful, saves it to the database.

[1195] Step 4:

[1196] The server sends a confirmation email.

[1197] Input: Saved entry data.

[1198] Data processing: Generate a confirmation email by filling in the receipt confirmation email template.

[1199] Output: A confirmation email is sent to the user.

[1200] Specific operation: The server sends a message to the user via the mail server saying "The application form has been received."

[1201] Step 5:

[1202] The server generates an interview question scenario.

[1203] Input: Contents of application form data.

[1204] Data processing: Use natural language processing (NLP) techniques to generate appropriate interview questions.

[1205] Output: Interview question scenarios based on the user's experience and skills.

[1206] Specific operation: Entry data is input into the NLP generation AI model, and a question scenario tailored to the job seeker is generated.

[1207] Step 6:

[1208] The server sends an email notification of the interview.

[1209] Input: Generated interview question scenarios.

[1210] Data processing: Generate a notification email containing the interview date and time, login information, and procedures.

[1211] Output: A notification email is sent to the user.

[1212] Specific operation: The server sends an email to the user via the mail server containing the specified date and time and instructions.

[1213] Step 7:

[1214] The user starts the video interview at the specified date and time.

[1215] Input: Notified interview information.

[1216] Specific operation: The user uses the device to access the web portal or dedicated application at the specified date and time to start the video interview.

[1217] Step 8:

[1218] The device sends the answer video to the server.

[1219] Input: Answer video recorded by the user using a camera and microphone.

[1220] Data processing: The device live streams video data in real time.

[1221] Output: The live streaming data sent to the server.

[1222] Specific operation: Using WebRTC technology, the user's answer video is sent to the server in real time.

[1223] Step 9:

[1224] The server analyzes the answer video and performs a preliminary evaluation.

[1225] Input: Answer video data sent from the device.

[1226] Data processing: Answers are converted into text using voice recognition technology, and facial expressions and movements are analyzed using video processing technology.

[1227] Output: Preliminary evaluation data.

[1228] Specific operation: The server converts the answers into text using a voice recognition engine, and analyzes facial expressions and movements using a video processing engine.

[1229] Step 10:

[1230] The server analyzes emotions using an emotion engine.

[1231] Input: Elementary assessment data and answer video data.

[1232] Data processing: Emotions are analyzed based on facial expressions, tone of voice, body movements, etc.

[1233] Output: Emotion data.

[1234] Specific operation: The server uses an emotion engine (such as Microsoft Azure's Emotion API) to analyze and extract emotion data.

[1235] Step 11:

[1236] The server will perform a detailed evaluation.

[1237] Input: Rudimentary rating and emotion data.

[1238] Data processing: A detailed evaluation is conducted taking into consideration the depth of the answers, logic, and accuracy of emotional expression.

[1239] Output: Detailed evaluation data is generated.

[1240] Specific operation: The server will score and comment based on each evaluation item and determine the final evaluation.

[1241] Step 12:

[1242] The server stores the evaluation results in a database.

[1243] Input: Detailed assessment data.

[1244] Data processing: Format the evaluation data to fit the database format.

[1245] Output: The evaluation data is stored in a database.

[1246] Specific operation: The server writes the evaluation data to a database so that the next judge can access it.

[1247] Step 13:

[1248] The server generates feedback and notifies the user.

[1249] Input: Evaluation result data.

[1250] Data processing: Generate feedback letters based on the evaluation results.

[1251] Output: A feedback letter is sent to the user via email.

[1252] What happens: The server fills in an email template and notifies the user with feedback and details about next steps.

[1253] This process allows the system to efficiently and effectively evaluate applicants, and allows for detailed evaluations that also take emotional aspects into account.

[1254] (Application example 2)

[1255] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1256] Conventional interview systems have the drawback of requiring a lot of time and cost for the interview process, and are also difficult to fully grasp the emotions of applicants. Furthermore, it is difficult to provide feedback and support in real time, leaving room for improvement in applicant satisfaction. Therefore, there is a need for an efficient interview system that utilizes emotion recognition.

[1257] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an application form submitted by a user, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's answer video to the server in real time during the video interview, means for analyzing the answer video and making a preliminary evaluation, means for making a detailed evaluation after the video interview is completed, means for saving the evaluation in a database, means for generating feedback based on the evaluation results and notifying the user, emotion recognition means for analyzing facial expressions and tone of voice to analyze the user's emotions and reflect them in the feedback, and means for acquiring the user's emotion analysis results in real time and providing appropriate feedback based on the analysis results. This enables efficient interview processes and detailed evaluations that take the applicant's emotions into consideration.

[1258] An "entry form" is an information sheet that an applicant fills out and submits, and includes application information such as name, career history, and skills.

[1259] A "database" is a digital information management system that organizes and stores information for quick and efficient access.

[1260] An "interview question scenario" is a scenario that configures the order and content of questions to be asked to an applicant, and is generated based on the contents of the applicant's application form.

[1261] A "video interview" is an online interview conducted over the internet that allows for real-time interaction with applicants.

[1262] A "server" is a computer system that provides services and resources to clients over a network.

[1263] "Real-time" refers to processing and data communication occurring immediately without delay.

[1264] "Emotion recognition means" is a technology that analyzes an applicant's facial expressions and tone of voice to identify their emotional state.

[1265] "Feedback" refers to evaluations and advice provided based on the applicant's interview results and sentiment analysis.

[1266] "Natural language processing" is a general term for computer technologies for processing, understanding, and generating human language.

[1267] "Speech recognition" is a technology that analyzes voice data and converts it into linguistic text.

[1268] "Image processing technology" refers to computer technology for analyzing and processing video and still images, including facial recognition and motion analysis.

[1269] "Initial assessment" refers to basic screening conducted at the early stages of an interview.

[1270] "Detailed evaluation" refers to an in-depth analytical evaluation based on the applicant's responses and emotional data.

[1271] "Login information" refers to the authentication information required when a user accesses a system, including ID and password.

[1272] A "real-time feedback tool" is a system that provides immediate advice and instructions based on the applicant's emotional state and the progress of the interview.

[1273] System program generation

[1274] The system can receive applicants' application forms and conduct video interviews based on their content. It also uses emotion recognition technology to analyze the applicant's emotional state and reflect that in its evaluation and feedback.

[1275] 1. Receiving application forms and saving data

[1276] The user fills out an application form and presses the submit button via a web form or dedicated application. The user's device converts the input data into JSON or XML format and sends it as a POST request to the server using HTTPS, a secure communication protocol. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[1277] 2. Generation and notification of interview question scenarios

[1278] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions that are appropriate for the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures.

[1279] 3. Conducting video interviews

[1280] At the designated date and time, the user will begin the video interview using their device. The video responses are sent in real time to a server, where they are analyzed using voice recognition and video processing technology for a preliminary evaluation.

[1281] 4. Emotion recognition

[1282] The server performs emotion recognition based on the applicant's facial expressions, tone of voice, and body movements in the video of the applicant's answer. Based on the analysis results, the user's emotional data is included in the evaluation.

[1283] 5. Generate detailed evaluations and feedback

[1284] After the video interview, the server reanalyzes the applicant's responses and emotional data to conduct a detailed evaluation. The results of this evaluation are stored in a database, and feedback is automatically generated and notified to the user to help them move on to the next step.

[1285] Hardware and Software Use

[1286] Hardware: Camera and microphone in the smart glasses, the user's computer or smartphone.

[1287] Software: Natural language processing models (NLPModel), speech recognition software (e.g., Google Speech-to-Text), image processing technology (OpenCV), emotion engines (EmotionEngine), database management systems (e.g., MySQL).

[1288] Specific examples

[1289] For example, consider the process of User A, who has applied for a new position, submitting an application form and then undergoing a video interview. Based on the contents of the application form, a generation AI generates questions such as, "Please tell us more about the projects you have worked on in the past." When User A answers, the server analyzes User A's emotions, such as confidence or nervousness, in real time through facial expression recognition and tone of voice analysis, and provides appropriate feedback. Specifically, real-time advice such as, "The customer is interested. Please tell us more." is provided.

[1290] Prompt Sentence Examples

[1291] "Generate customer service scenarios that ask customers questions about past purchases and spark interest."

[1292] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1293] Step 1: Receiving the application form and saving the data

[1294] The user submits an application form. The device converts the input data into JSON or XML format and sends it to the server using a secure communication protocol (HTTPS). The server validates the received data to ensure accuracy and completeness. After verification, the application form data is saved in a database and a receipt confirmation email is automatically sent to the user.

[1295] Input: Application form data (JSON or XML format)

[1296] Data processing: Data validation

[1297] Output: Application form stored in the database, receipt confirmation email

[1298] Step 2: Generate and notify interview question scenarios

[1299] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes appropriate questions based on the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures.

[1300] Input: Application form data

[1301] Data processing: Generate interview question scenarios (using NLP technology)

[1302] Output: Interview question scenario, notification email

[1303] Step 3: Conduct a video interview

[1304] At the specified date and time, the user begins the video interview using their device. The device sends the video responses in real time to the server. The server then uses voice recognition and video processing technology to analyze the video and perform a preliminary evaluation of the applicant's responses.

[1305] Input: User answer video

[1306] Data processing: Analysis using voice recognition and video processing technology

[1307] Output: preliminary evaluation data

[1308] Step 4: Emotion Recognition

[1309] During the video interview, the server analyzes the applicant's facial expressions, tone of voice, and body movements. It uses an emotion recognition engine to identify the applicant's emotions and generate emotional data. The generated emotional data is then used to evaluate the applicant's answers.

[1310] Input: User's answer video (facial expressions, tone of voice, body movements)

[1311] Data processing: Emotion recognition using an emotion engine

[1312] Output: Emotion data

[1313] Step 5: Generate detailed evaluation and feedback

[1314] After the video interview is completed, the server reanalyzes the answer video and emotional data to conduct a detailed evaluation. This evaluation includes the depth of the answer, logic, and accuracy of emotional expression. The evaluation results are stored in a database, and feedback is automatically generated and notified to the user to help them move on to the next step.

[1315] Input: Answer video, emotion data

[1316] Data processing: detailed evaluation reanalysis and feedback generation

[1317] Output: Evaluation results, feedback, notification email

[1318] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1319] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1320] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1321] [Fourth embodiment]

[1322] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1323] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1324] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1325] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1326] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1327] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1328] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1329] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1330] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1331] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1332] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1333] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1334] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1335] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening that takes place after submitting an application form. The purpose of this system is to deepen understanding of applicants while reducing labor costs.

[1336] Receiving application forms and saving data

[1337] The user fills out an application form and presses the submit button via a web form or a dedicated application. The terminal converts this data into JSON or XML format and sends it as a POST request to the server using the HTTPS protocol. The server receives this data, validates it, and stores it in a database. During this process, a confirmation email is automatically sent to the user.

[1338] Setting up and conducting a video interview

[1339] The server generates an interview question scenario based on the contents of the application form received from the user. The scenario uses natural language processing (NLP) technology to include questions based on the applicant's experience and skills. The server then sends the user an email containing the interview date and time and login information. At the specified date and time, the user uses their device to access a web portal or dedicated application to begin the video interview.

[1340] During the interview, the device transmits the user's video responses in real time to a server, which uses voice recognition and video processing technology to extract text and facial expression data from the responses and conducts a preliminary evaluation, including the appropriateness of the responses, speech fluency, and facial expression consistency.

[1341] Video interview assessment and recording

[1342] Once the video interview is over, the server analyzes all responses again and performs a more detailed evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and prepared for submission to the next panel of judges.

[1343] Feedback and next steps for applicants

[1344] The server automatically generates feedback based on the analysis results, including details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then emailed to the user, informing them of the next steps and schedule.

[1345] Specific examples

[1346] For example, User A applying for a new position might go through the process as follows:

[1347] 1. User A fills out an application form and sends it from their device. The server receives and saves the application form data.

[1348] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies User A of the interview date and time and login information.

[1349] 3. User A starts the video interview using the device at the specified date and time and answers the questions. The device sends the answer video to the server in real time.

[1350] 4. The server evaluates User A's answers initially, and then performs a detailed evaluation after the interview. The evaluation results are saved in the database.

[1351] 5. The server generates feedback and notifies User A with details of next steps.

[1352] This system reduces labor costs and time, making the recruitment process more efficient and effective.

[1353] The processing flow will be explained below.

[1354] Step 1:

[1355] The user submits the application form. The user enters the required information using a web form or a dedicated application and presses the submit button.

[1356] Step 2:

[1357] The terminal sends the application form data to the server. The terminal converts the user's input data into JSON or XML format and sends it to the server as a POST request using the HTTPS protocol.

[1358] Step 3:

[1359] The server receives the application form data, validates the received data, and checks for accuracy and completeness.

[1360] Step 4:

[1361] The server saves the application form data in the database. Data that passes validation is stored in the database.

[1362] Step 5:

[1363] The server will send the user an email acknowledging receipt of the application form. To ensure receipt confirmation, a notification email will be sent automatically to the user.

[1364] Step 6:

[1365] The server generates an interview question scenario, analyzes the contents of the application form, and uses natural language processing technology to create a list of questions suited to the applicant.

[1366] Step 7:

[1367] The server sends a notification to the user, including the date, time, and procedure for the interview. The generated scenario is sent to the user via email, along with the interview date, time, login information, and instructions.

[1368] Step 8:

[1369] The user starts the video interview at the specified date and time. The user uses a device to access the specified web portal or application and starts the interview.

[1370] Step 9:

[1371] The device transmits the user's answer video in real time to the server. During the video interview, the device records the user's video with a camera and transmits it as streaming data to the server.

[1372] Step 10:

[1373] The server analyzes the video responses and performs a preliminary evaluation. AI is used to perform real-time voice recognition and video processing, extracting the text and facial expression data from the responses, and then a preliminary evaluation is performed.

[1374] Step 11:

[1375] After the video interview is completed, the server reanalyzes all responses and conducts a detailed evaluation. In addition to a basic evaluation, the server also evaluates the depth of the content, logic, emotional expression, and other factors.

[1376] Step 12:

[1377] The server saves the detailed evaluation results in a database. The evaluation results are stored in the database as structured data, making them easily accessible to the next judge.

[1378] Step 13:

[1379] The server generates feedback based on the analysis results. Based on the detailed evaluation results, feedback is automatically generated that includes the applicant's strengths, weaknesses, and recommendations for next steps.

[1380] Step 14:

[1381] The server notifies the user of the feedback letter and details of the next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[1382] This series of processing flows reduces the burden on applicants and interviewers while realizing an efficient and effective recruitment process.

[1383] Example 1

[1384] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1385] In the traditional recruitment process, managing a large number of application forms, arranging interviews, and evaluating the interview results required a great deal of time and effort. Furthermore, it was prone to artificial bias in the evaluations and difficult to provide efficient feedback. This resulted in an inefficiency in the entire recruitment process, delaying the selection of the best candidates.

[1386] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1387] In this invention, the server includes means for receiving an application form submitted by a user, means for converting the application form into a data format and transmitting it to the server using a secure protocol, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's video answers to the server in real time during the video interview, means for analyzing the video answers and making a preliminary evaluation, means for making a detailed evaluation after the video interview is completed, means for saving the evaluation in a database, and means for generating feedback based on the evaluation results and notifying the user. This streamlines the entire hiring process, reduces labor costs and time, and enables fair and rapid personnel evaluation.

[1388] "User" refers to an applicant who uses this system to submit an application form and participate in a video interview.

[1389] An "entry form" refers to a document that contains personal information, work history, etc. that a user fills out and submits in order to apply for a job.

[1390] "Data format" refers to the digital format, such as JSON or XML, into which the application form is converted.

[1391] "Secure Protocol" refers to a protocol, such as HTTPS, used to ensure the secure transmission of data.

[1392] "Server" refers to a computer system that receives, stores, analyzes, and generates feedback on application forms.

[1393] A "database" refers to an information system that systematically stores and manages data such as application forms and evaluation results.

[1394] An "interview question scenario" refers to a list of interview questions generated based on an applicant's application form.

[1395] "Notification means" refers to the procedures and techniques for notifying users of information such as the date, time, and method of the interview.

[1396] A "video interview" refers to an online interview that a user participates in using a web portal or dedicated application.

[1397] "Answer video" refers to video data that records a user answering questions during a video interview.

[1398] "Analysis means" refers to the speech recognition and / or video processing technology used to evaluate the recorded response videos.

[1399] The "feedback generation means" refers to a method for automatically generating feedback to be provided to the user based on the analysis results.

[1400] This invention relates to a system that uses a generative AI model to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form. The system aims to streamline the recruitment process and reduce labor costs.

[1401] Receiving application forms and saving data

[1402] When a user fills out an application form and presses the submit button via a web form or a dedicated application, the device converts the collected data into JSON or XML format and sends it to the server using the HTTPS protocol. The server receives the data, validates it, and stores it in a database. During this process, the server automatically sends the user a confirmation email.

[1403] Setting up and conducting a video interview

[1404] Based on the contents of the application form received from the user, the server uses natural language processing (NLP) technology to generate an interview question scenario based on the applicant's experience and skills. The server then sends the user an email containing the interview date and time and login information. At the specified date and time, the user uses their device to access a web portal or dedicated application and begin the video interview. The device then transmits the user's video responses in real time to the server, which uses voice recognition and video processing technology to extract the text and facial expression data from the responses and conducts a preliminary evaluation.

[1405] Video interview assessment and recording

[1406] Once the video interview is over, the server analyzes all responses again and performs a more detailed evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and prepared for submission to the next panel of judges.

[1407] Feedback and next steps for applicants

[1408] The server automatically generates feedback based on the analysis results, including details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then emailed to the user, informing them of the next steps and schedule.

[1409] Specific examples

[1410] For example, User A applying for a new position might go through the process as follows:

[1411] 1. User A fills out an application form and sends it from their device. The server receives and saves the application form data.

[1412] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies User A of the interview date and time and login information.

[1413] 3. User A starts the video interview using the device at the specified date and time and answers the questions. The device sends the answer video to the server in real time.

[1414] 4. The server evaluates User A's answers initially, and then performs a detailed evaluation after the interview. The evaluation results are saved in the database.

[1415] 5. The server generates feedback and notifies User A with details of next steps.

[1416] This system reduces labor costs and time, making the recruitment process more efficient and effective.

[1417] Prompt Sentence Examples

[1418] "The applicant has submitted their application. Please provide details about the prospective process and technical requirements."

[1419] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1420] Step 1: Receive your application form

[1421] Input: Contents of the application form filled out by the user

[1422] Specific operation: The user enters the details of the application form on the web form or dedicated application and presses the submit button. This causes the data entered by the user to be temporarily saved on the device.

[1423] Output: Application form data collected by the device

[1424] Step 2: Convert data format and send

[1425] Input: Application form data

[1426] Specific operation: The terminal converts the application form data into JSON or XML format. The converted data is sent to the server as a POST request using the HTTPS protocol. AJAX and fetch API are used for conversion and transmission.

[1427] Output: Data converted to JSON or XML format is sent to the server

[1428] Step 3: Receiving and storing data

[1429] Input: Application form data sent to the server in JSON or XML format

[1430] Specific behavior: The server receives the request and validates the format and content of the data. If the validation is successful, it is saved in the database. During this process, the server automatically sends a receipt confirmation email to the user.

[1431] Output: Validated application form data is saved in the database.

[1432] Step 4: Generate interview question scenarios

[1433] Input: Saved application form data

[1434] How it works: The server uses natural language processing (NLP) technology to analyze the contents of the application form. Based on the analysis results, a generative AI model (e.g., GPT-3) is used to generate interview question scenarios based on the applicant's experience and skills.

[1435] Output: Generated interview question scenario

[1436] Step 5: Notification of interview date and time and login information

[1437] Input: Generated interview question scenario

[1438] What happens: The server sends an email to the user containing the interview date and time and login information. The email is sent using an SMTP server.

[1439] Output: Email to user containing interview date and time and login information

[1440] Step 6: Start the video interview

[1441] Input: Interview date and time and login information notified by email

[1442] Specific operation: At the specified date and time, the user accesses the web portal or dedicated application using their device to start the video interview. When the user presses the start interview button, video streaming begins.

[1443] Output: Start of video interview

[1444] Step 7: Submit your answer video

[1445] Input: Interview answer video

[1446] Specific operation: The device uses WebRTC or other video streaming technology to send the answer video to the server in real time. The server receives the video data and prepares it for analysis.

[1447] Output: Answer video data sent to the server

[1448] Step 8: Conduct an initial assessment

[1449] Input: Submitted answer video data

[1450] Specific operation: The server uses speech recognition (e.g., Google Cloud Speech-to-Text) and video analysis (e.g., OpenCV) to extract text and facial expression data from the answer video. Based on the extracted data, a preliminary evaluation is performed.

[1451] Output: preliminary evaluation results

[1452] Step 9: Conduct a detailed assessment

[1453] Input: Initial evaluation results and answer video data

[1454] How it works: After the video interview is completed, the server uses the stored video data and the initial evaluation results to conduct a detailed analysis. This is done using AI models and other analytical tools to evaluate the depth, logic, and emotional expression of the answers.

[1455] Output: Detailed evaluation results

[1456] Step 10: Save the evaluation results

[1457] Input: Detailed evaluation results

[1458] What happens: The server saves the detailed evaluation results in the database, and also sends a notification to the next judge to submit the evaluation results.

[1459] Output: Detailed evaluation results stored in a database

[1460] Step 11: Generate and communicate feedback

[1461] Input: Detailed evaluation results

[1462] What it does: The server uses the AI ​​model to generate a feedback letter from the analysis results, detailing the applicant's strengths, weaknesses, and next steps. The server then sends the feedback letter to the user via the SMTP server.

[1463] Output: Feedback letter sent to the user

[1464] (Application example 1)

[1465] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1466] Traditional recruitment processes are expensive, and it's difficult to efficiently screen applicants with limited resources. It's also difficult to ensure fairness and consistency in evaluations. Furthermore, the process for assessing security staff suitability is complicated, and detailed evaluations must be provided quickly.

[1467] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1468] In this invention, the server includes: means for receiving an application form submitted by a user; means for saving the application form in a database; means for generating an interview question scenario; means for notifying the user of the date, time, and method of the interview; means for the user to start a video interview; means for transmitting the user's video answers to the server in real time during the video interview; means for analyzing the video answers and conducting a preliminary evaluation; means for conducting a detailed evaluation after the video interview is completed; means for saving the evaluation in a database; means for generating feedback based on the evaluation results and notifying the user; means for extracting text and facial expression data from answers in real time during the video interview using voice recognition and video processing technology; means for evaluating the applicant's aptitude in real time based on the extracted text and facial expression data; and means for automatically notifying the user of details of next steps based on feedback after the interview is completed. This reduces labor costs and time, and enables the applicant evaluation process to proceed efficiently and effectively. It also ensures fairness and consistency in evaluations, and enables accurate understanding of the applicant's aptitude through prompt feedback.

[1469] "User" refers to an individual or corporation that accesses the system, submits an application form, and takes a video interview.

[1470] An "application form" is a paper or digital form that an applicant fills out and submits, and includes information such as name, experience, and skills.

[1471] A "database" is a system for managing and storing data such as application forms and evaluation results.

[1472] An "interview question scenario" is a set of questions that are generated based on the contents of the applicant's application form and are used during the interview.

[1473] A "video interview" is a live or recorded interactive interview conducted by a user using a camera and microphone.

[1474] "Server" is a central processing unit for receiving, storing, analyzing, evaluating data, and generating feedback.

[1475] "Speech recognition" is a technology that extracts what a user says as text data.

[1476] "Video processing technology" is a technology that analyzes and extracts data such as facial expressions and gestures from video.

[1477] "Real-time analytics" is the process of instantly analyzing data collected during a video interview.

[1478] An "initial assessment" is a basic assessment conducted during the video interview, including the appropriateness of answers and fluency of speech.

[1479] A "detailed evaluation" is a more in-depth analysis that takes place after the video interview is completed, and is a process of making a comprehensive evaluation based on the logic of the content, emotional expression, etc.

[1480] "Feedback" refers to comments to applicants and details of next steps generated based on the evaluation results.

[1481] This invention uses a system that automates a series of processes, from receiving application forms to providing feedback. This system is realized by combining multiple technologies, including a server, user terminals, and generative AI models.

[1482] First, the user fills out an application form and submits it through a dedicated web form or application. The application form data is converted from the device into JSON or XML format and sent to the server using the HTTPS protocol. The server receives this data, validates it, and stores it in a database. A receipt confirmation email is also automatically sent to the user.

[1483] Next, the server generates a question scenario for the video interview based on the contents of the application form received from the user. This scenario generation uses natural language processing (NLP) technology. Based on the generated question scenario, the server sends the user an email containing the interview date and time and login information. The user accesses the interview portal via their device at the specified date and time to begin the video interview.

[1484] As the video interview progresses, the device transmits the user's responses in real time to a server. The server then uses voice recognition and video processing technology to extract the applicant's responses and facial expression data, and conducts a preliminary evaluation. Specifically, it analyzes the appropriateness of the responses, the fluency of the speech, and the consistency of the facial expressions.

[1485] After the video interview is completed, the server analyzes all responses again and performs a detailed evaluation. This analysis uses a generative AI model to perform a comprehensive evaluation based on criteria such as depth of response, logic, and emotional expression. The evaluation results are stored in a database and made available for the next step.

[1486] Finally, the server automatically generates feedback based on the analysis, detailing the applicant's strengths, weaknesses, and next steps, and then emails the feedback to the user.

[1487] Specific examples

[1488] For example, when a user applies for a security guard position, the following process occurs:

[1489] 1. The user fills out the application form and submits it from the terminal.

[1490] 2. The server receives the application form data, validates it, and saves it in the database.

[1491] 3. The server generates a question scenario and notifies the user of the interview date, time, and method.

[1492] 4. The user starts the video interview at the specified date and time, and the answer video is sent to the server in real time.

[1493] 5. The server analyzes the answer video using voice recognition and video processing technology and performs a preliminary evaluation.

[1494] 6. After the video interview is completed, the server conducts a detailed evaluation and stores the results in a database.

[1495] 7. Finally, the server generates feedback, informing the user of the details of next steps.

[1496] Prompt Sentence Examples

[1497] "Please tell us specifically about your security experience. For example, what kind of problems did you solve?"

[1498] This system reduces labor costs and time, and allows the applicant evaluation process to proceed efficiently and effectively. It also ensures fairness and consistency in evaluation, and provides prompt feedback to accurately grasp the suitability of applicants.

[1499] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1500] Step 1:

[1501] Receipt of application form

[1502] The user fills out an application form and submits it from their device. The entered application data is converted to JSON or XML format on the device and sent to the server using the HTTPS protocol. The server receives this data and validates its format and content. Data that passes validation is stored in a database and a receipt confirmation email is automatically sent to the user.

[1503] Input: Application form data (name, experience, skills)

[1504] Output: Save to database, confirmation email

[1505] Step 2:

[1506] Interview question scenario generation

[1507] The server generates an interview question scenario based on the contents of the application form stored in the database. Natural language processing (NLP) technology is used to generate specific questions based on the experience and skills described in the application form. Based on the generated question scenario, an email containing the interview date and time and login information is sent to the user.

[1508] Input: Contents of application form

[1509] Output: An email containing the interview question scenario, interview date and time, and login information

[1510] Step 3:

[1511] Start of video interview

[1512] At the appointed time, the user accesses a web portal or dedicated application on their device to begin the video interview. The interview portal displays pre-generated questions, which the user answers.

[1513] Input: Interview date and time, login information, device

[1514] Output: Start of video interview, recording of answers

[1515] Step 4:

[1516] Real-time transmission of answer videos

[1517] The device transmits the video responses captured during the video interview in real time to a server, using compression technology to ensure high-quality video and audio, and is securely transferred using the HTTPS protocol.

[1518] Input: Answer video (video and audio)

[1519] Output: Video data sent to the server in real time

[1520] Step 5:

[1521] Initial evaluation

[1522] The server analyzes the received video data, extracts the text of the answers using speech recognition technology, and then analyzes the facial expression data using video processing technology to perform a preliminary evaluation based on criteria such as the appropriateness of the answers, the fluency of the speech, and the consistency of the facial expressions.

[1523] Input: Answer video data

[1524] Output: Preliminary evaluation results

[1525] Step 6:

[1526] Detailed evaluation

[1527] After the video interview is completed, the server analyzes the response data in detail again, using a generative AI model to comprehensively evaluate the responses based on criteria such as depth, logic, and emotional expression. The evaluation results are then stored in a database.

[1528] Input: Answer text and facial expression data

[1529] Output: Detailed evaluation results

[1530] Step 7:

[1531] Feedback generation and notification

[1532] The server automatically generates feedback for the applicant based on the detailed evaluation results. The feedback includes details of the applicant's strengths, weaknesses, and next steps. The generated feedback letter is then sent to the user via email.

[1533] Input: Detailed evaluation results

[1534] Output: Feedback letter, notification of next steps

[1535] This system enables users to be evaluated effectively and efficiently, and to smoothly proceed with the hiring process. By using the prompt sentence "Tell us specifically about your security experience. For example, tell us what kind of trouble you solved," as a model, the system generates specific questions, making it possible to accurately evaluate the suitability of applicants.

[1536] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1537] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form, and further combines it with an emotion engine that recognizes the user's emotions. This system improves interview efficiency and provides a means to deepen understanding of applicants.

[1538] Receiving application forms and saving data

[1539] The user fills out an application form and presses the submit button via a web form or a dedicated application. The device converts the user's input data into JSON or XML format and sends it to the server as a POST request using the secure communication protocol HTTPS. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[1540] Setting up and conducting a video interview

[1541] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions that are appropriate for the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures. At the specified date and time, the user uses their device to access a web portal or dedicated application to begin the video interview.

[1542] During the video interview, the device transmits the user's video responses in real time to a server. The responses are sent as live streaming data and analyzed by the server using voice recognition and video processing technology, resulting in a preliminary evaluation. Furthermore, an emotion engine analyzes the user's emotions based on facial expressions, tone of voice, and body movements in the video responses. This allows the user's emotional data to be collected and used for evaluation along with the text data of the responses.

[1543] Video interview assessment and recording

[1544] Once the video interview is over, the server re-analyzes all answers and conducts a more detailed evaluation. This evaluation considers the depth of the answers, their logic, and the accuracy of the emotional expression. The detailed evaluation also incorporates emotional data obtained by the emotion engine. The evaluation results are stored in a database for easy access by the next judge.

[1545] Feedback and next steps for applicants

[1546] The server automatically generates feedback based on the analysis results. The feedback includes the applicant's strengths, weaknesses, and recommendations for next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[1547] Specific examples

[1548] For example, User A applying for a new position might go through the following process:

[1549] 1. User A fills out an application form and sends it from their device. The server receives the application form data and saves it after validation.

[1550] 2. The server generates an interview question scenario based on User A's experience and skills, and notifies the interview date and time and login information.

[1551] 3. At the specified date and time, User A starts the video interview using the device and answers the questions. The device sends the answer video to the server in real time.

[1552] 4. The server initially evaluates User A's answers, and the emotion engine also analyzes User A's emotions. After the interview is over, a detailed evaluation is conducted and the results are stored in the database.

[1553] 5. The server generates feedback and notifies User A with details of next steps.

[1554] This system reduces labor costs and time, and makes it possible to conduct the recruitment process efficiently and effectively.The emotion engine also performs detailed evaluations that take into account the emotional aspects of applicants, resulting in more accurate selection.

[1555] The processing flow will be explained below.

[1556] Step 1:

[1557] The user submits the application form. The user enters the required information using a web form or a dedicated application and presses the submit button.

[1558] Step 2:

[1559] The terminal sends the application form data to the server. The terminal converts the user's input data into JSON or XML format and sends it to the server as a POST request using the HTTPS protocol.

[1560] Step 3:

[1561] The server receives the application form data, validates the received data, and checks for accuracy and completeness.

[1562] Step 4:

[1563] The server saves the application form data in the database. Data that passes validation is stored in the database.

[1564] Step 5:

[1565] The server will send the user an email acknowledging receipt of the application form. To ensure receipt confirmation, a notification email will be sent automatically to the user.

[1566] Step 6:

[1567] The server generates an interview question scenario, analyzes the contents of the application form, and uses natural language processing technology to create a list of questions suited to the applicant.

[1568] Step 7:

[1569] The server sends an email to the user informing them of the interview date, time, and procedure. An email containing the interview date, time, login information, and procedure is sent to the user along with the generated scenario.

[1570] Step 8:

[1571] The user starts the video interview at the specified date and time. The user uses a device to access the specified web portal or application and starts the interview.

[1572] Step 9:

[1573] The device transmits the user's answer video in real time to the server. During the video interview, the device records the user's video with a camera and transmits it as streaming data to the server.

[1574] Step 10:

[1575] The server analyzes the video responses and performs a preliminary evaluation. It uses voice recognition and video processing technology to extract text data and facial expression data from the responses.

[1576] Step 11:

[1577] The server uses an emotion engine to analyze the emotions in the answer video, collecting emotion data based on the user's facial expressions, tone of voice, and body movements.

[1578] Step 12:

[1579] After the interview, the server reanalyzes all responses and conducts a detailed evaluation. In addition to the initial evaluation results, the evaluation criteria also include depth of content, logic, and emotional expression.

[1580] Step 13:

[1581] The server saves the detailed evaluation results in a database. The evaluation results are stored in the database as structured data, making them easily accessible to the next judge.

[1582] Step 14:

[1583] The server uses the analysis and sentiment data to generate feedback, including the applicant's strengths, weaknesses, and recommended next steps.

[1584] Step 15:

[1585] The server notifies the user of the feedback letter and details of the next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule.

[1586] This series of processing flows reduces the burden on applicants and interviewers while enabling an efficient and effective recruitment process, and also enables detailed analysis using an emotion engine.

[1587] Example 2

[1588] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1589] In the traditional hiring process, designing and running interviews required a great deal of effort and time, placing a heavy burden on hiring managers. It was also difficult to take into account the applicant's emotions and facial expressions, making it difficult to accurately assess the applicant's true abilities and aptitude. Furthermore, the lack of consistent evaluation criteria posed challenges in ensuring the fairness and quality of interview results.

[1590] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving an application form submitted by a user, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's answer video to the server in real time during the video interview, means for analyzing the answer video and making a preliminary evaluation, means for analyzing the user's emotions using an emotion engine, means for making a detailed evaluation after the video interview ends, means for saving the evaluation in a database, and means for generating feedback based on the evaluation results and notifying the user. This improves the efficiency and accuracy of the hiring process and enables more accurate evaluations that take applicants' emotions into account.

[1591] "User" refers to an applicant who uses this system to submit an application form and take a video interview.

[1592] An "application form" refers to an electronic form that a user fills in and submits their information (such as name, address, and work history).

[1593] "Database" refers to the data storage area within the system for saving data such as application forms and evaluation results.

[1594] An "interview question scenario" refers to a list of interview questions that is generated based on the user's application form.

[1595] "Notification" refers to emails or messages sent to users informing them of the date, time and manner of their interview.

[1596] A "video interview" refers to an interview in which the user records their answers using a camera and microphone.

[1597] "Server" refers to a central computing device that executes various functions of the system.

[1598] "Answer video" refers to video data containing answers recorded by a user during a video interview.

[1599] "Analysis" refers to the process for analyzing and evaluating response videos and other data.

[1600] "Basic evaluation" refers to the basic evaluation given to the answer video.

[1601] "Emotion engine" refers to a software engine for analyzing a user's emotions.

[1602] "Detailed evaluation" refers to an advanced evaluation based on the depth of the responses and emotional data in addition to the basic evaluation.

[1603] "Feedback" refers to advice and information about next steps provided to the user based on the evaluation results.

[1604] This invention relates to a system that uses generative AI to conduct a preliminary screening in the form of a video interview before the first screening after submitting an application form, and further combines it with an emotion engine that recognizes the user's emotions. This system improves interview efficiency and provides a means to deepen understanding of applicants.

[1605] Specifically, the user fills out an application form and presses the submit button via a web form or dedicated application. The device converts the user's input data into JSON or XML format and sends it to the server as a POST request using HTTPS, a secure communication protocol. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[1606] Next, the server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions appropriate to the applicant's experience and skills. The server sends the user a notification email containing the interview date and time, login information, and procedures. At the specified date and time, the user uses their device to access a web portal or dedicated application and begin the video interview. During the video interview, the device transmits the user's video answers in real time to the server. The video answers transmitted as live streaming data are analyzed by the server using voice recognition and video processing technology, and a preliminary evaluation is performed. Furthermore, an emotion engine analyzes the user's emotions based on facial expressions, tone of voice, and body movements in the video answers. This allows the user's emotional data to be collected and used for evaluation along with the text data of the answers.

[1607] Once the video interview is over, the server re-analyzes all answers and conducts a more detailed evaluation. This evaluation considers the depth of the answers, their logic, and the accuracy of the emotional expression. The detailed evaluation also incorporates emotional data obtained by the emotion engine. The evaluation results are stored in a database for easy access by the next judge.

[1608] Finally, the server automatically generates feedback based on the analysis results. The feedback includes the applicant's strengths and weaknesses, as well as recommendations for next steps. The generated feedback letter is sent to the user via email, informing them of the next steps and schedule. For example, the process for User A applying for a new position would proceed as follows: User A fills out an application form and submits it from their device. The server receives the application form data and stores it after validation. The server generates an interview question scenario based on User A's experience and skills and notifies them of the interview date and time and login information. At the specified date and time, User A starts a video interview using their device and answers the questions. The device sends the video of their answers to the server in real time. The server performs a preliminary evaluation of User A's answers, and the emotion engine also analyzes User A's emotions. After the interview is completed, a detailed evaluation is conducted and the results are stored in a database. The server generates feedback and notifies User A along with details of next steps.

[1609] The hardware and software used include Google Cloud AI for machine learning model operation on the server side and Microsoft Azure's Emotion API for the emotion engine, while the device side uses a React.js-based application to build the web portal and WebRTC for live streaming technology for video interviews.

[1610] An example of a prompt to be input to the generative AI model is: "Generate interview questions for applicants for a new position. Create a scenario that includes questions based on the applicant's experience and the skills to be verified in the interview. In doing so, also generate data to analyze the applicant's sentiment and provide feedback."

[1611] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1612] Step 1:

[1613] The user fills out the application form.

[1614] Input: A user enters information required into a web form or dedicated application.

[1615] Specific behavior: The user fills in information such as name, address, work history, and skills in the input fields and presses the submit button.

[1616] Step 2:

[1617] The terminal converts the input data and sends it to the server.

[1618] Input: Information entered by the user.

[1619] Data processing: Converts data entered by the terminal into JSON or XML format.

[1620] Output: The converted data is sent to the server via HTTPS.

[1621] Specific operation: As soon as the terminal receives the data, it sends a POST request to the server using a secure communication protocol (HTTPS).

[1622] Step 3:

[1623] The server validates and saves the data.

[1624] Input: Data sent from the terminal in JSON or XML format.

[1625] Data processing: Validate data based on the data schema and check for accuracy and completeness.

[1626] Output: Data that passes validation is saved to the database.

[1627] Specific operation: The server receives the data, checks whether each field is in the required format and content, and if validation is successful, saves it to the database.

[1628] Step 4:

[1629] The server sends a confirmation email.

[1630] Input: Saved entry data.

[1631] Data processing: Generate a confirmation email by filling in the receipt confirmation email template.

[1632] Output: A confirmation email is sent to the user.

[1633] Specific operation: The server sends a message to the user via the mail server saying "The application form has been received."

[1634] Step 5:

[1635] The server generates an interview question scenario.

[1636] Input: Contents of application form data.

[1637] Data processing: Use natural language processing (NLP) techniques to generate appropriate interview questions.

[1638] Output: Interview question scenarios based on the user's experience and skills.

[1639] Specific operation: Entry data is input into the NLP generation AI model, and a question scenario tailored to the job seeker is generated.

[1640] Step 6:

[1641] The server sends an email notification of the interview.

[1642] Input: Generated interview question scenarios.

[1643] Data processing: Generate a notification email containing the interview date and time, login information, and procedures.

[1644] Output: A notification email is sent to the user.

[1645] Specific operation: The server sends an email to the user via the mail server containing the specified date and time and instructions.

[1646] Step 7:

[1647] The user starts the video interview at the specified date and time.

[1648] Input: Notified interview information.

[1649] Specific operation: The user uses the device to access the web portal or dedicated application at the specified date and time to start the video interview.

[1650] Step 8:

[1651] The device sends the answer video to the server.

[1652] Input: Answer video recorded by the user using a camera and microphone.

[1653] Data processing: The device live streams video data in real time.

[1654] Output: The live streaming data sent to the server.

[1655] Specific operation: Using WebRTC technology, the user's answer video is sent to the server in real time.

[1656] Step 9:

[1657] The server analyzes the answer video and performs a preliminary evaluation.

[1658] Input: Answer video data sent from the device.

[1659] Data processing: Answers are converted into text using voice recognition technology, and facial expressions and movements are analyzed using video processing technology.

[1660] Output: Preliminary evaluation data.

[1661] Specific operation: The server converts the answers into text using a voice recognition engine, and analyzes facial expressions and movements using a video processing engine.

[1662] Step 10:

[1663] The server analyzes emotions using an emotion engine.

[1664] Input: Elementary assessment data and answer video data.

[1665] Data processing: Emotions are analyzed based on facial expressions, tone of voice, body movements, etc.

[1666] Output: Emotion data.

[1667] Specific operation: The server uses an emotion engine (such as Microsoft Azure's Emotion API) to analyze and extract emotion data.

[1668] Step 11:

[1669] The server will perform a detailed evaluation.

[1670] Input: Rudimentary rating and emotion data.

[1671] Data processing: A detailed evaluation is conducted taking into consideration the depth of the answers, logic, and accuracy of emotional expression.

[1672] Output: Detailed evaluation data is generated.

[1673] Specific operation: The server will score and comment based on each evaluation item and determine the final evaluation.

[1674] Step 12:

[1675] The server stores the evaluation results in a database.

[1676] Input: Detailed assessment data.

[1677] Data processing: Format the evaluation data to fit the database format.

[1678] Output: The evaluation data is stored in a database.

[1679] Specific operation: The server writes the evaluation data to a database so that the next judge can access it.

[1680] Step 13:

[1681] The server generates feedback and notifies the user.

[1682] Input: Evaluation result data.

[1683] Data processing: Generate feedback letters based on the evaluation results.

[1684] Output: A feedback letter is sent to the user via email.

[1685] What happens: The server fills in an email template and notifies the user with feedback and details about next steps.

[1686] This process allows the system to efficiently and effectively evaluate applicants, and allows for detailed evaluations that also take emotional aspects into account.

[1687] (Application example 2)

[1688] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1689] Conventional interview systems have the drawback of requiring a lot of time and cost for the interview process, and are also difficult to fully grasp the emotions of applicants. Furthermore, it is difficult to provide feedback and support in real time, leaving room for improvement in applicant satisfaction. Therefore, there is a need for an efficient interview system that utilizes emotion recognition.

[1690] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving an application form submitted by a user, means for saving the application form in a database, means for generating an interview question scenario, means for notifying the user of the date, time, and method of the interview, means for the user to start a video interview, means for transmitting the user's answer video to the server in real time during the video interview, means for analyzing the answer video and making a preliminary evaluation, means for making a detailed evaluation after the video interview is completed, means for saving the evaluation in a database, means for generating feedback based on the evaluation results and notifying the user, emotion recognition means for analyzing facial expressions and tone of voice to analyze the user's emotions and reflect them in the feedback, and means for acquiring the user's emotion analysis results in real time and providing appropriate feedback based on the analysis results. This enables efficient interview processes and detailed evaluations that take the applicant's emotions into consideration.

[1691] An "entry form" is an information sheet that an applicant fills out and submits, and includes application information such as name, career history, and skills.

[1692] A "database" is a digital information management system that organizes and stores information for quick and efficient access.

[1693] An "interview question scenario" is a scenario that configures the order and content of questions to be asked to an applicant, and is generated based on the contents of the applicant's application form.

[1694] A "video interview" is an online interview conducted over the internet that allows for real-time interaction with applicants.

[1695] A "server" is a computer system that provides services and resources to clients over a network.

[1696] "Real-time" refers to processing and data communication occurring immediately without delay.

[1697] "Emotion recognition means" is a technology that analyzes an applicant's facial expressions and tone of voice to identify their emotional state.

[1698] "Feedback" refers to evaluations and advice provided based on the applicant's interview results and sentiment analysis.

[1699] "Natural language processing" is a general term for computer technologies for processing, understanding, and generating human language.

[1700] "Speech recognition" is a technology that analyzes voice data and converts it into linguistic text.

[1701] "Image processing technology" refers to computer technology for analyzing and processing video and still images, including facial recognition and motion analysis.

[1702] "Initial assessment" refers to basic screening conducted at the early stages of an interview.

[1703] "Detailed evaluation" refers to an in-depth analytical evaluation based on the applicant's responses and emotional data.

[1704] "Login information" refers to the authentication information required when a user accesses a system, including ID and password.

[1705] A "real-time feedback tool" is a system that provides immediate advice and instructions based on the applicant's emotional state and the progress of the interview.

[1706] System program generation

[1707] The system can receive applicants' application forms and conduct video interviews based on their content. It also uses emotion recognition technology to analyze the applicant's emotional state and reflect that in its evaluation and feedback.

[1708] 1. Receiving application forms and saving data

[1709] The user fills out an application form and presses the submit button via a web form or dedicated application. The user's device converts the input data into JSON or XML format and sends it as a POST request to the server using HTTPS, a secure communication protocol. The server validates the received data, checking for accuracy and completeness, and then stores it in a database. After the data is saved, a confirmation email is automatically sent to the user.

[1710] 2. Generation and notification of interview question scenarios

[1711] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes questions that are appropriate for the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures.

[1712] 3. Conducting video interviews

[1713] At the designated date and time, the user will begin the video interview using their device. The video responses are sent in real time to a server, where they are analyzed using voice recognition and video processing technology for a preliminary evaluation.

[1714] 4. Emotion recognition

[1715] The server performs emotion recognition based on the applicant's facial expressions, tone of voice, and body movements in the video of the applicant's answer. Based on the analysis results, the user's emotional data is included in the evaluation.

[1716] 5. Generate detailed evaluations and feedback

[1717] After the video interview, the server reanalyzes the applicant's responses and emotional data to conduct a detailed evaluation. The results of this evaluation are stored in a database, and feedback is automatically generated and notified to the user to help them move on to the next step.

[1718] Hardware and Software Use

[1719] Hardware: Camera and microphone in the smart glasses, the user's computer or smartphone.

[1720] Software: Natural language processing models (NLPModel), speech recognition software (e.g., Google Speech-to-Text), image processing technology (OpenCV), emotion engines (EmotionEngine), database management systems (e.g., MySQL).

[1721] Specific examples

[1722] For example, consider the process of User A, who has applied for a new position, submitting an application form and then undergoing a video interview. Based on the contents of the application form, a generation AI generates questions such as, "Please tell us more about the projects you have worked on in the past." When User A answers, the server analyzes User A's emotions, such as confidence or nervousness, in real time through facial expression recognition and tone of voice analysis, and provides appropriate feedback. Specifically, real-time advice such as, "The customer is interested. Please tell us more." is provided.

[1723] Prompt Sentence Examples

[1724] "Generate customer service scenarios that ask customers questions about past purchases and spark interest."

[1725] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1726] Step 1: Receiving the application form and saving the data

[1727] The user submits an application form. The device converts the input data into JSON or XML format and sends it to the server using a secure communication protocol (HTTPS). The server validates the received data to ensure accuracy and completeness. After verification, the application form data is saved in a database and a receipt confirmation email is automatically sent to the user.

[1728] Input: Application form data (JSON or XML format)

[1729] Data processing: Data validation

[1730] Output: Application form stored in the database, receipt confirmation email

[1731] Step 2: Generate and notify interview question scenarios

[1732] The server uses natural language processing (NLP) technology to generate an interview question scenario based on the contents of the application form. The generated scenario includes appropriate questions based on the applicant's experience and skills. The server then sends the user a notification email containing the interview date and time, login information, and procedures.

[1733] Input: Application form data

[1734] Data processing: Generate interview question scenarios (using NLP technology)

[1735] Output: Interview question scenario, notification email

[1736] Step 3: Conduct a video interview

[1737] At the specified date and time, the user begins the video interview using their device. The device sends the video responses in real time to the server. The server then uses voice recognition and video processing technology to analyze the video and perform a preliminary evaluation of the applicant's responses.

[1738] Input: User answer video

[1739] Data processing: Analysis using voice recognition and video processing technology

[1740] Output: preliminary evaluation data

[1741] Step 4: Emotion Recognition

[1742] During the video interview, the server analyzes the applicant's facial expressions, tone of voice, and body movements. It uses an emotion recognition engine to identify the applicant's emotions and generate emotional data. The generated emotional data is then used to evaluate the applicant's answers.

[1743] Input: User's answer video (facial expressions, tone of voice, body movements)

[1744] Data processing: Emotion recognition using an emotion engine

[1745] Output: Emotion data

[1746] Step 5: Generate detailed evaluation and feedback

[1747] After the video interview is completed, the server reanalyzes the answer video and emotional data to conduct a detailed evaluation. This evaluation includes the depth of the answer, logic, and accuracy of emotional expression. The evaluation results are stored in a database, and feedback is automatically generated and notified to the user to help them move on to the next step.

[1748] Input: Answer video, emotion data

[1749] Data processing: detailed evaluation reanalysis and feedback generation

[1750] Output: Evaluation results, feedback, notification email

[1751] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1752] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1753] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1754] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1755] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1756] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1757] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1758] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1759] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1760] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1761] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1762] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1763] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1764] 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.

[1765] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1766] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1767] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1768] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1769] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1770] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1771] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1772] The following is further disclosed regarding the above embodiment.

[1773] (Claim 1)

[1774] A means for receiving an entry form submitted by a user;

[1775] A means for storing the entry sheet in a database;

[1776] A means for generating an interview question scenario;

[1777] means for notifying the user of the date, time and manner of the interview;

[1778] a means for a user to initiate a video interview;

[1779] A means for transmitting the user's answer video to a server in real time during the video interview;

[1780] A means for analyzing the answer video and making a preliminary evaluation;

[1781] A means of conducting a detailed evaluation after the video interview is completed, and

[1782] means for storing said evaluations in a database;

[1783] a means for generating feedback based on the evaluation result and notifying the user of the feedback;

[1784] A system including:

[1785] (Claim 2)

[1786] 2. The system according to claim 1, wherein the means for generating an interview question scenario is configured to generate appropriate questions from the contents of the application form using natural language processing.

[1787] (Claim 3)

[1788] 2. The system according to claim 1, wherein the means for analyzing the answer video is configured to extract text and facial expression data from the answer using voice recognition and video processing techniques, and to perform evaluation based on the extracted text and facial expression data.

[1789] "Example 1"

[1790] (Claim 1)

[1791] A means for receiving an entry form submitted by a user;

[1792] A means for converting the entry sheet into a data format and transmitting it to a server using a secure protocol;

[1793] A means for storing the entry sheet in a database;

[1794] A means for generating an interview question scenario;

[1795] means for notifying the user of the date, time and manner of the interview;

[1796] a means for a user to initiate a video interview;

[1797] A means for transmitting the user's answer video to a server in real time during the video interview;

[1798] A means for analyzing the answer video and making a preliminary evaluation;

[1799] A means of conducting a detailed evaluation after the video interview is completed, and

[1800] means for storing said evaluations in a database;

[1801] a means for generating feedback based on the evaluation result and notifying the user of the feedback;

[1802] A system including:

[1803] (Claim 2)

[1804] 2. The system according to claim 1, wherein the means for generating an interview question scenario is configured to generate appropriate questions from the contents of the application form using natural language processing.

[1805] (Claim 3)

[1806] 2. The system according to claim 1, wherein the means for analyzing the answer video is configured to extract text and facial expression data from the answer using voice recognition and video processing techniques, and to perform evaluation based on the extracted text and facial expression data.

[1807] "Application Example 1"

[1808] (Claim 1)

[1809] A means for receiving an entry form submitted by a user;

[1810] A means for storing the entry sheet in a database;

[1811] A means for generating an interview ques...

Claims

1. A means for receiving an entry form submitted by a user; A means for storing the entry sheet in a database; A means for generating an interview question scenario; means for notifying the user of the date, time and manner of the interview; a means for a user to initiate a video interview; A means for transmitting the user's answer video to a server in real time during the video interview; A means for analyzing the answer video and making a preliminary evaluation; A means of conducting a detailed evaluation after the video interview is completed, and means for storing said evaluations in a database; a means for generating feedback based on the evaluation result and notifying the user of the feedback; A system including:

2. 2. The system according to claim 1, wherein the means for generating an interview question scenario is configured to generate appropriate questions from the contents of the application form using natural language processing.

3. 2. The system according to claim 1, wherein the means for analyzing the answer video is configured to extract text and facial expression data from the answer using voice recognition and video processing techniques, and to perform evaluation based on the extracted text and facial expression data.

Images