system

Abstract

The system according to this embodiment aims to reduce the cost of the interview process and to interview many candidates simultaneously. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, a feedback unit, and a navigation unit. The reception unit inputs required questions. The generation unit conducts a job interview based on the questions input by the reception unit. The feedback unit records and scores the answers collected by the generation unit and provides feedback to the interviewer. The navigation unit determines whether to proceed to the next step based on the information provided by the feedback unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the cost is high in the interview process and it is difficult to interview many candidates at the same time.

[0005] The system according to the embodiment aims to reduce the cost of the interview process and interview many candidates at the same time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a generation unit, a feedback unit, and a navigation unit. The reception unit inputs required questions. The generation unit conducts a job interview based on the questions entered by the reception unit. The feedback unit records and scores the answers collected by the generation unit and provides feedback to the interviewer. The navigation unit determines whether to proceed to the next step based on the information provided by the feedback unit. [Effects of the Invention]

[0007] The system according to this embodiment reduces the cost of the interview process and allows for interviewing many candidates simultaneously. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The voice-interactive AI assistant system according to an embodiment of the present invention is a system that conducts initial interviews. This system enables cost reduction and allows for interviews with multiple candidates simultaneously, thus reaching candidates who might have been rejected during the initial screening process. For example, a company inputs essential questions (e.g., "motivation for applying," "desired annual salary," "achievement rate of past figures," "desired start date," etc.) and instructs the AI ​​to conduct a 30-minute job interview. Next, the candidate and the AI ​​assistant enter an online meeting tool, and the AI ​​assistant conducts the interview. During the interview, the AI ​​assistant collects the candidate's responses through natural conversation, and records and scores them. After the interview, the AI ​​assistant posts a summary of the information to a team chat tool and a talent management database, reviews the recording, and decides whether to proceed to the next step. This mechanism allows companies to efficiently process a large number of applications and to proceed with the selection process without missing promising candidates, especially in job categories where skills are difficult to visualize. Furthermore, because the AI ​​assistant conducts interviews with multiple candidates simultaneously, the efficiency of the interview process is significantly improved. For example, an AI assistant might ask a sales candidate, "Please tell us what motivates you to work for our company," and the candidate responds. The AI ​​assistant records the response, scores it, and provides feedback to the interviewer. This allows the interviewer to efficiently evaluate the candidate. Furthermore, the AI ​​assistant provides information based on the candidate's response to determine whether they should proceed to the next step. For example, it can evaluate whether the candidate's motivation and desired salary align with the company's requirements and decide whether they should proceed to the next interview. In this way, using a voice-activated AI assistant allows companies to reduce costs and efficiently process a large volume of applications. For candidates, the natural interaction with the AI ​​reduces stress and allows them to perform better. Thus, a voice-activated AI assistant system allows companies to reduce costs and efficiently process a large volume of applications.

[0029] The voice-interactive AI assistant system according to this embodiment comprises a reception unit, a generation unit, a feedback unit, and a navigation unit. The reception unit inputs required questions. Required questions include, for example, basic information and job-related questions, but are not limited to such examples. The reception unit provides, for example, an interface for companies to input required questions. The generation unit conducts job interviews based on the questions input by the reception unit. Job interviews are conducted, for example, based on the type of interview and the content of the questions, but are not limited to such examples. The generation unit conducts job interviews, for example, using an online meeting tool. The generation unit engages in dialogue with candidates using a generation AI. The generation AI generates natural dialogue using, for example, a text generation AI (e.g., LLM). The feedback unit records and scores the responses collected by the generation unit. The recordings are saved, for example, in video format, and the scoring is performed, for example, based on evaluation items and scoring methods, but is not limited to such examples. The feedback unit records and scores the collected responses, for example. The feedback unit posts a summary of the information to a team chat tool and a talent management database. The information summary may include, for example, criteria for summarization and the information to be included. The feedback unit may, for example, create a summary of the collected responses and post it to a team chat tool and a talent management database. The navigation unit will determine whether to proceed to the next step based on the information provided by the feedback unit. The next step may include, for example, the next interview or hiring decision. The navigation unit may, for example, evaluate whether the candidate's motivation and desired salary meet the company's requirements and determine whether to proceed to the next interview. This allows the voice-interactive AI assistant system according to the embodiment to efficiently perform tasks from inputting required questions to conducting job interviews, recording and scoring responses, and determining the next step.

[0030] The reception desk inputs required questions. These required questions include, but are not limited to, basic information and job-related questions. The reception desk provides an interface for companies to input these required questions. Specifically, it allows companies to easily input questions through a web-based dashboard or mobile application used by their recruiters. This interface employs a user-friendly design, allowing for intuitive addition, deletion, and editing of questions. Furthermore, the reception desk provides question templates and samples to help companies create questions efficiently. For example, it provides question sets optimized for each job role and example questions based on past successes, enabling companies to quickly create effective questions. The reception desk also includes a function to set the importance and priority of questions, allowing companies to focus on collecting answers to questions that are particularly important to them. This allows the reception desk to efficiently collect the information companies need and improve the quality of job interviews. In addition, the reception desk provides a function to automatically save the entered questions for later reuse. This allows companies to easily recall past question sets and modify or update them as needed.

[0031] The generation unit conducts job interviews based on questions entered by the reception unit. Job interviews are conducted based on, for example, the type of interview and the content of the questions, but are not limited to these examples. The generation unit conducts job interviews using, for example, online meeting tools. The generation unit uses generative AI to interact with candidates. The generative AI generates natural dialogue using, for example, text generation AI (e.g., LLM). Specifically, the generative AI uses a pre-trained large-scale language model to generate appropriate follow-up questions for the candidate's answers, ensuring a smooth conversation. The generative AI analyzes the candidate's answers in real time and automatically generates questions to elicit relevant information. For example, if a candidate talks about a specific project, the generative AI will ask questions to delve further into the project's details and results. The generative AI also analyzes the tone and emotion of the candidate's answers, providing appropriate feedback and empathy to achieve a more natural and human-like dialogue. Furthermore, the generation unit has the ability to monitor the progress of the interview and adjust the flow as needed. For example, if the interview is progressing faster than planned, it can insert additional questions to adjust the time. This allows the generation unit to conduct job interviews efficiently and effectively, and to accurately evaluate the suitability of candidates.

[0032] The feedback department records and scores the responses collected by the generation department. The recordings are saved in video format, for example, and the scoring is based on evaluation criteria and scoring methods, for example, but is not limited to such examples. The feedback department records and scores the collected responses, for example. The feedback department posts summaries of the information to the team chat tool and the talent management database. The summaries of the information include, for example, the criteria for summarization and the information included, for example. The feedback department creates summaries of the collected responses and posts them to the team chat tool and the talent management database. Specifically, the feedback department uses AI to automatically analyze the candidate's responses and assign scores to each evaluation criterion. For example, scoring is based on evaluation criteria such as communication skills, problem-solving skills, and expertise. The AI ​​uses natural language processing technology to analyze the candidate's responses and quantify their suitability for each evaluation criterion. Furthermore, based on the scoring results, the feedback department creates a feedback report that clearly shows the candidate's strengths and weaknesses. This report includes specific areas for improvement and advice for the next steps. The feedback department also provides an interface that allows company recruiters to easily view recorded interview videos. This enables recruiters to review candidates' responses in detail and evaluate them in comparison to scoring results. Furthermore, the feedback department analyzes the collected data to improve the quality of interviews and evaluation criteria. This allows the feedback department to continuously improve the entire job interview process and achieve more accurate and fair evaluations.

[0033] The Navigation Department determines whether to proceed to the next step based on the information provided by the Feedback Department. This next step may include, but is not limited to, the next interview or a final hiring decision. For example, the Navigation Department evaluates whether a candidate's motivation and desired salary align with the company's requirements to determine whether they should proceed to the next interview. Specifically, the Navigation Department comprehensively assesses the candidate's suitability based on the scoring results and feedback reports provided by the Feedback Department. Using AI, it analyzes the candidate's score and feedback content and determines whether they should proceed to the next step in accordance with the company's hiring criteria. For example, if a candidate's score meets a certain standard, it automatically schedules the next interview. The Navigation Department also evaluates whether a candidate's motivation and desired salary align with the company's requirements and takes appropriate action. For example, if a candidate's desired salary is within the company's budget, it instructs them to proceed to the next interview; if it is outside the budget, it provides appropriate feedback to the candidate. Furthermore, the Navigation Department provides a concrete action plan for proceeding to the next step. For example, it has functions to automatically schedule the next interview, prepare necessary documents, and notify interviewers. This allows the navigation unit to efficiently manage the candidate selection process and smoothly move candidates to the next step. Furthermore, the navigation unit can monitor the progress of the entire selection process in real time and make adjustments as needed. As a result, the navigation unit can improve the transparency and efficiency of the selection process and lead to optimal results for both the company and the candidates.

[0034] The generation unit can conduct job interviews using online conferencing tools. This makes remote job interviews possible by using online conferencing tools. Some or all of the above-described processes in the generation unit may be performed using generation AI, or they may not be performed using generation AI. For example, when conducting job interviews using online conferencing tools, the generation unit can use generation AI to interact with candidates.

[0035] The feedback unit can record and score the collected responses. For example, the feedback unit can record the collected responses in video format. The feedback unit can also record the collected responses in audio format. The feedback unit can also save the collected responses in text format. The feedback unit can score the collected responses based on evaluation criteria. The feedback unit can also score the collected responses based on scoring criteria. The feedback unit can also score the collected responses using AI. This allows for detailed feedback to be provided to the interviewer by recording and scoring the responses. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can score the collected responses using AI and provide the results to the interviewer.

[0036] The feedback department can post summaries of information to the team chat tool and the talent management database. For example, the feedback department can create a summary of the collected responses and post it to the team chat tool. The feedback department can also create a summary of the collected responses and post it to the talent management database. The feedback department can also create a summary of the collected responses and send it via email. This allows for efficient sharing of interview results by posting summaries of information. Some or all of the above processes in the feedback department may be performed using AI or not. For example, the feedback department can create a summary of the collected responses using AI and post the results to the team chat tool and the talent management database.

[0037] The navigation unit can evaluate whether a candidate's motivation and desired salary meet the company's requirements and determine whether they should proceed to the next interview. For example, the navigation unit can evaluate a candidate's motivation. The navigation unit can also evaluate a candidate's desired salary. The navigation unit can also comprehensively evaluate a candidate's motivation and desired salary. For example, the navigation unit can evaluate whether a candidate's motivation meets the company's requirements. The navigation unit can also evaluate whether a candidate's desired salary meets the company's requirements. The navigation unit can also comprehensively evaluate whether a candidate's motivation and desired salary meet the company's requirements. This allows for an efficient determination of whether a candidate should proceed to the next step by evaluating their motivation and desired salary. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to evaluate a candidate's motivation and desired salary and determine whether they should proceed to the next step based on the results.

[0038] The reception department can analyze past interview data and automatically generate an optimal set of questions. For example, the reception department can analyze the answer patterns of successful candidates from past interview data and generate similar questions. For example, the reception department can extract questions suitable for a specific job from past interview data and generate a set of questions. For example, the reception department can optimize the order of questions from past interview data to increase the success rate of interviews. In this way, an optimal set of questions can be automatically generated by analyzing past interview data. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department can analyze past interview data using AI and automatically generate an optimal set of questions based on the results.

[0039] The reception desk can customize questions based on the company's current needs and trends when questions are entered. For example, the reception desk can add relevant questions based on the company's latest projects and goals. For example, the reception desk can add questions testing up-to-date knowledge based on industry trends and technological advancements. For example, the reception desk can add questions to assess suitability based on the company's culture and values. This allows for more appropriate questions to be asked by customizing them based on the company's needs and trends. Some or all of the above processing in the reception desk may or may not be performed using AI. For example, the reception desk can use AI to analyze the company's current needs and trends and customize questions based on the results.

[0040] The reception desk can automatically analyze a candidate's resume and work history when questions are entered and suggest relevant questions. For example, the reception desk can generate relevant questions based on the candidate's past experience from their work history. The reception desk can also generate questions based on specific skills and qualifications from the candidate's resume. The reception desk can also generate questions based on past projects and achievements from the candidate's work history. In this way, relevant questions can be suggested by analyzing the candidate's resume and work history. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can analyze a candidate's resume and work history using AI and suggest relevant questions based on the results.

[0041] The reception desk can optimize questions by referencing industry best practices when questions are entered. For example, the reception desk can generate effective questions based on industry best practices. The reception desk can also generate relevant questions based on the latest industry trends and technologies. The reception desk can also generate appropriate questions based on industry success stories. This allows for question optimization by referencing industry best practices. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can use AI to reference industry best practices and optimize questions based on the results.

[0042] The generation unit can automatically generate additional follow-up questions during an interview based on the candidate's answers. For example, the generation unit can generate follow-up questions that request further explanation based on the candidate's answers. The generation unit can also generate follow-up questions about relevant skills and experience based on the candidate's answers. The generation unit can also generate follow-up questions about specific examples and achievements based on the candidate's answers. This allows for obtaining more detailed information by generating follow-up questions in response to the candidate's answers. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the candidate's answers into a generation AI and generate follow-up questions based on the results.

[0043] The generation unit can analyze a candidate's nonverbal responses during an interview and provide appropriate feedback. For example, the generation unit can analyze a candidate's facial expressions and tone of voice and provide feedback to help them relax. For example, the generation unit can analyze a candidate's posture and gestures and provide feedback to help them gain confidence. For example, the generation unit can analyze a candidate's gaze and eye movements and provide feedback to help them concentrate. In this way, appropriate feedback can be provided by analyzing the candidate's nonverbal responses. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the candidate's nonverbal responses into a generation AI and provide feedback based on the results.

[0044] The generation unit can generate relevant questions during an interview by referring to the candidate's past interview history. For example, the generation unit can generate unanswered questions from the candidate's past interview history. The generation unit can also generate questions about specific skills or experience from the candidate's past interview history. For example, the generation unit can generate questions based on feedback from the previous interview from the candidate's past interview history. This allows for the generation of relevant questions by referring to the candidate's past interview history. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input the candidate's past interview history into a generation AI and generate relevant questions based on the results.

[0045] The generation unit can evaluate a candidate's adaptability during an interview using industry-specific scenarios. For example, the generation unit can present an industry-specific problem-solving scenario and evaluate the candidate's response. It can also present an industry-specific project management scenario and evaluate the candidate's leadership skills. It can also present an industry-specific customer service scenario and evaluate the candidate's communication skills. In this way, the candidate's adaptability can be evaluated by using industry-specific scenarios. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input industry-specific scenarios into a generation AI and evaluate the candidate's adaptability based on the results.

[0046] The feedback unit can comprehensively evaluate the quality of a candidate's response during the feedback process and perform detailed scoring. For example, the feedback unit can evaluate and score the content, expression, and logic of the candidate's response. The feedback unit can also evaluate and score the specificity, achievements, and experience of the candidate's response. The feedback unit can also evaluate and score the consistency, reliability, and sincerity of the candidate's response. This allows for detailed scoring by comprehensively evaluating the quality of the candidate's response. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can evaluate a candidate's response using AI and perform detailed scoring based on the results.

[0047] The feedback unit can compare a candidate's responses with those of other candidates and provide a relative evaluation during the feedback process. For example, the feedback unit can compare a candidate's responses with those of other candidates and provide a relative score. The feedback unit can also compare the quality of a candidate's responses with those of other candidates and provide a relative evaluation. The feedback unit can also compare the specificity and achievements of a candidate's responses with those of other candidates and provide a relative evaluation. This makes it possible to provide a relative evaluation by comparing a candidate's responses with those of other candidates. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to compare a candidate's responses with those of other candidates and provide a relative evaluation based on the results.

[0048] The feedback unit can evaluate candidates by considering their past performance and skill sets when providing feedback. For example, the feedback unit can evaluate a candidate's past performance and provide feedback. The feedback unit can also evaluate a candidate's skill set and provide feedback. The feedback unit can also evaluate a candidate's past projects and achievements and provide feedback. This allows for a more accurate evaluation by considering the candidate's past performance and skill sets. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to evaluate a candidate's past performance and skill sets and provide feedback based on the results.

[0049] The feedback unit can score candidates' responses by referring to industry standard evaluation criteria during the feedback process. For example, the feedback unit can score candidates' responses based on industry standard evaluation criteria. The feedback unit can also score candidates' responses based on industry best practices. The feedback unit can also score candidates' responses based on industry success stories. This improves the accuracy of scoring by referring to industry standard evaluation criteria. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can refer to industry standard evaluation criteria using AI and score candidates' responses based on the results.

[0050] The navigation unit can analyze the candidate's response data in real time during navigation and suggest the optimal next step. For example, the navigation unit can analyze the candidate's response data in real time and suggest whether or not to proceed to the next interview. For example, the navigation unit can analyze the candidate's response data in real time and suggest additional follow-up questions. For example, the navigation unit can analyze the candidate's response data in real time and suggest appropriate training or workshops as the next step. In this way, by analyzing the candidate's response data in real time, the optimal next step can be suggested. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to analyze the candidate's response data in real time and suggest the optimal next step based on the results.

[0051] The navigation unit can suggest a customized career path based on the candidate's skill set and experience during navigation. For example, the navigation unit can suggest the optimal career path based on the candidate's skill set. The navigation unit can also suggest an appropriate career path based on the candidate's experience. For example, the navigation unit can comprehensively evaluate the candidate's skill set and experience and suggest a customized career path. This allows for the provision of a more appropriate career path by suggesting a customized career path based on the candidate's skill set and experience. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to evaluate the candidate's skill set and experience and suggest a customized career path based on the results.

[0052] The navigation unit can suggest the next step during navigation, taking into account the candidate's geographical constraints and preferred work location. For example, the navigation unit can suggest the next step based on the candidate's preferred work location. The navigation unit can also suggest an appropriate next step, taking into account the candidate's geographical constraints. For example, the navigation unit can comprehensively evaluate the candidate's preferred work location and geographical constraints to suggest the optimal next step. This allows for the suggestion of a more appropriate next step by considering the candidate's geographical constraints and preferred work location. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to evaluate the candidate's geographical constraints and preferred work location and suggest the next step based on the results.

[0053] The navigation unit can optimize the next step by referring to the candidate's past interview history and feedback during navigation. For example, the navigation unit can refer to the candidate's past interview history and optimize the next step. The navigation unit can also refer to the candidate's past feedback and optimize the next step. For example, the navigation unit can comprehensively evaluate the candidate's past interview history and feedback and suggest the optimal next step. This allows for the optimization of the next step by referring to the candidate's past interview history and feedback. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to evaluate the candidate's past interview history and feedback and optimize the next step based on the results.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The reception desk can analyze a candidate's social media profile and generate relevant questions. For example, it can generate questions based on a candidate's past work experience and skills from their online resume. It can also generate questions based on a candidate's interests and passions from their social media posts. Furthermore, it can generate questions based on a candidate's technical skills and creative abilities from their GitHub and Behance projects. This allows for the generation of more personalized questions by analyzing a candidate's social media profile.

[0056] The feedback system can analyze candidates' responses and evaluate their consistency and reliability. For example, it can assess whether a candidate's responses are consistent and assign high scores to consistent responses. It can also assess whether a candidate's responses are based on reliable information and assign high scores to reliable responses. Furthermore, it can assess whether a candidate's responses are specific and assign high scores to specific responses. This allows for more accurate scoring by evaluating the consistency and reliability of candidates' responses.

[0057] The navigation unit can analyze candidate response data and suggest appropriate training and education as the next step. For example, if a candidate's response data indicates a lack of specific skills, it can suggest training to address those skills. Similarly, if a candidate's response data indicates a lack of knowledge in a particular field, it can suggest training in that area. Furthermore, if a candidate's response data indicates a lack of experience in a specific job, it can suggest practical training related to that job. In this way, by analyzing candidate response data, the system can suggest appropriate training and education as the next step.

[0058] The generation unit can analyze the candidate's responses in real time during the interview and adjust the interview's progress according to the quality of the responses. For example, if a candidate's response is detailed and specific, the generation unit can ask follow-up questions to delve deeper. If a candidate's response is vague, the generation unit can ask additional follow-up questions. Furthermore, if a candidate's response is insufficient, the generation unit can request further explanation. This allows for obtaining more detailed information by adjusting the interview's progress according to the quality of the candidate's responses.

[0059] The navigation unit can analyze candidate response data and suggest appropriate career paths as the next steps. For example, it can suggest career paths based on specific skill sets from candidate response data. It can also suggest career paths based on specific experience from candidate response data. Furthermore, it can suggest career paths based on aptitude for specific tasks from candidate response data. In this way, by analyzing candidate response data, it can suggest appropriate career paths as the next steps.

[0060] The generation unit can analyze a candidate's nonverbal responses during an interview and provide appropriate feedback. For example, it can analyze a candidate's facial expressions and tone of voice and provide feedback to help them relax. It can also analyze a candidate's posture and gestures and provide feedback to help them gain confidence. Furthermore, it can analyze a candidate's gaze and eye movements and provide feedback to improve their concentration. In this way, by analyzing a candidate's nonverbal responses, it can provide appropriate feedback.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The reception desk enters the required questions. These required questions include, for example, basic information and questions related to the job. The reception desk provides an interface for companies to enter these required questions. Step 2: The generation unit conducts job interviews based on questions entered by the reception unit. The generation unit conducts job interviews using, for example, an online meeting tool and interacts with candidates using a generation AI. The generation AI generates natural-sounding dialogues using a text generation AI (e.g., LLM). Step 3: The feedback team records and scores the responses collected by the generation team. The recordings are saved in video format, and scoring is performed based on evaluation criteria and scoring methods. The feedback team creates a summary of the collected responses and posts it to the team chat tool and the talent management database. Step 4: The Navigation Department determines whether to proceed to the next step based on the information provided by the Feedback Department. The next step may include the next interview or hiring decision. The Navigation Department evaluates whether the candidate's motivation and desired salary meet the company's requirements and determines whether they should proceed to the next interview.

[0063] (Example of form 2) The voice-interactive AI assistant system according to an embodiment of the present invention is a system that conducts initial interviews. This system enables cost reduction and allows for interviews with multiple candidates simultaneously, thus reaching candidates who might have been rejected during the initial screening process. For example, a company inputs essential questions (e.g., "motivation for applying," "desired annual salary," "achievement rate of past figures," "desired start date," etc.) and instructs the AI ​​to conduct a 30-minute job interview. Next, the candidate and the AI ​​assistant enter an online meeting tool, and the AI ​​assistant conducts the interview. During the interview, the AI ​​assistant collects the candidate's responses through natural conversation, and records and scores them. After the interview, the AI ​​assistant posts a summary of the information to a team chat tool and a talent management database, reviews the recording, and decides whether to proceed to the next step. This mechanism allows companies to efficiently process a large number of applications and to proceed with the selection process without missing promising candidates, especially in job categories where skills are difficult to visualize. Furthermore, because the AI ​​assistant conducts interviews with multiple candidates simultaneously, the efficiency of the interview process is significantly improved. For example, an AI assistant might ask a sales candidate, "Please tell us what motivates you to work for our company," and the candidate responds. The AI ​​assistant records the response, scores it, and provides feedback to the interviewer. This allows the interviewer to efficiently evaluate the candidate. Furthermore, the AI ​​assistant provides information based on the candidate's response to determine whether they should proceed to the next step. For example, it can evaluate whether the candidate's motivation and desired salary align with the company's requirements and decide whether they should proceed to the next interview. In this way, using a voice-activated AI assistant allows companies to reduce costs and efficiently process a large volume of applications. For candidates, the natural interaction with the AI ​​reduces stress and allows them to perform better. Thus, a voice-activated AI assistant system allows companies to reduce costs and efficiently process a large volume of applications.

[0064] The voice-interactive AI assistant system according to this embodiment comprises a reception unit, a generation unit, a feedback unit, and a navigation unit. The reception unit inputs required questions. Required questions include, for example, basic information and job-related questions, but are not limited to such examples. The reception unit provides, for example, an interface for companies to input required questions. The generation unit conducts job interviews based on the questions input by the reception unit. Job interviews are conducted, for example, based on the type of interview and the content of the questions, but are not limited to such examples. The generation unit conducts job interviews, for example, using an online meeting tool. The generation unit engages in dialogue with candidates using a generation AI. The generation AI generates natural dialogue using, for example, a text generation AI (e.g., LLM). The feedback unit records and scores the responses collected by the generation unit. The recordings are saved, for example, in video format, and the scoring is performed, for example, based on evaluation items and scoring methods, but is not limited to such examples. The feedback unit records and scores the collected responses, for example. The feedback unit posts a summary of the information to a team chat tool and a talent management database. The information summary may include, for example, criteria for summarization and the information to be included. The feedback unit may, for example, create a summary of the collected responses and post it to a team chat tool and a talent management database. The navigation unit will determine whether to proceed to the next step based on the information provided by the feedback unit. The next step may include, for example, the next interview or hiring decision. The navigation unit may, for example, evaluate whether the candidate's motivation and desired salary meet the company's requirements and determine whether to proceed to the next interview. This allows the voice-interactive AI assistant system according to the embodiment to efficiently perform tasks from inputting required questions to conducting job interviews, recording and scoring responses, and determining the next step.

[0065] The reception desk inputs required questions. These required questions include, but are not limited to, basic information and job-related questions. The reception desk provides an interface for companies to input these required questions. Specifically, it allows companies to easily input questions through a web-based dashboard or mobile application used by their recruiters. This interface employs a user-friendly design, allowing for intuitive addition, deletion, and editing of questions. Furthermore, the reception desk provides question templates and samples to help companies create questions efficiently. For example, it provides question sets optimized for each job role and example questions based on past successes, enabling companies to quickly create effective questions. The reception desk also includes a function to set the importance and priority of questions, allowing companies to focus on collecting answers to questions that are particularly important to them. This allows the reception desk to efficiently collect the information companies need and improve the quality of job interviews. In addition, the reception desk provides a function to automatically save the entered questions for later reuse. This allows companies to easily recall past question sets and modify or update them as needed.

[0066] The generation unit conducts job interviews based on questions entered by the reception unit. Job interviews are conducted based on, for example, the type of interview and the content of the questions, but are not limited to these examples. The generation unit conducts job interviews using, for example, online meeting tools. The generation unit uses generative AI to interact with candidates. The generative AI generates natural dialogue using, for example, text generation AI (e.g., LLM). Specifically, the generative AI uses a pre-trained large-scale language model to generate appropriate follow-up questions for the candidate's answers, ensuring a smooth conversation. The generative AI analyzes the candidate's answers in real time and automatically generates questions to elicit relevant information. For example, if a candidate talks about a specific project, the generative AI will ask questions to delve further into the project's details and results. The generative AI also analyzes the tone and emotion of the candidate's answers, providing appropriate feedback and empathy to achieve a more natural and human-like dialogue. Furthermore, the generation unit has the ability to monitor the progress of the interview and adjust the flow as needed. For example, if the interview is progressing faster than planned, it can insert additional questions to adjust the time. This allows the generation unit to conduct job interviews efficiently and effectively, and to accurately evaluate the suitability of candidates.

[0067] The feedback department records and scores the responses collected by the generation department. The recordings are saved in video format, for example, and the scoring is based on evaluation criteria and scoring methods, for example, but is not limited to such examples. The feedback department records and scores the collected responses, for example. The feedback department posts summaries of the information to the team chat tool and the talent management database. The summaries of the information include, for example, the criteria for summarization and the information included, for example. The feedback department creates summaries of the collected responses and posts them to the team chat tool and the talent management database. Specifically, the feedback department uses AI to automatically analyze the candidate's responses and assign scores to each evaluation criterion. For example, scoring is based on evaluation criteria such as communication skills, problem-solving skills, and expertise. The AI ​​uses natural language processing technology to analyze the candidate's responses and quantify their suitability for each evaluation criterion. Furthermore, based on the scoring results, the feedback department creates a feedback report that clearly shows the candidate's strengths and weaknesses. This report includes specific areas for improvement and advice for the next steps. The feedback department also provides an interface that allows company recruiters to easily view recorded interview videos. This enables recruiters to review candidates' responses in detail and evaluate them in comparison to scoring results. Furthermore, the feedback department analyzes the collected data to improve the quality of interviews and evaluation criteria. This allows the feedback department to continuously improve the entire job interview process and achieve more accurate and fair evaluations.

[0068] The Navigation Department determines whether to proceed to the next step based on the information provided by the Feedback Department. This next step may include, but is not limited to, the next interview or a final hiring decision. For example, the Navigation Department evaluates whether a candidate's motivation and desired salary align with the company's requirements to determine whether they should proceed to the next interview. Specifically, the Navigation Department comprehensively assesses the candidate's suitability based on the scoring results and feedback reports provided by the Feedback Department. Using AI, it analyzes the candidate's score and feedback content and determines whether they should proceed to the next step in accordance with the company's hiring criteria. For example, if a candidate's score meets a certain standard, it automatically schedules the next interview. The Navigation Department also evaluates whether a candidate's motivation and desired salary align with the company's requirements and takes appropriate action. For example, if a candidate's desired salary is within the company's budget, it instructs them to proceed to the next interview; if it is outside the budget, it provides appropriate feedback to the candidate. Furthermore, the Navigation Department provides a concrete action plan for proceeding to the next step. For example, it has functions to automatically schedule the next interview, prepare necessary documents, and notify interviewers. This allows the navigation unit to efficiently manage the candidate selection process and smoothly move candidates to the next step. Furthermore, the navigation unit can monitor the progress of the entire selection process in real time and make adjustments as needed. As a result, the navigation unit can improve the transparency and efficiency of the selection process and lead to optimal results for both the company and the candidates.

[0069] The generation unit can conduct job interviews using online conferencing tools. This makes remote job interviews possible by using online conferencing tools. Some or all of the above-described processes in the generation unit may be performed using generation AI, or they may not be performed using generation AI. For example, when conducting job interviews using online conferencing tools, the generation unit can use generation AI to interact with candidates.

[0070] The feedback unit can record and score the collected responses. For example, the feedback unit can record the collected responses in video format. The feedback unit can also record the collected responses in audio format. The feedback unit can also save the collected responses in text format. The feedback unit can score the collected responses based on evaluation criteria. The feedback unit can also score the collected responses based on scoring criteria. The feedback unit can also score the collected responses using AI. This allows for detailed feedback to be provided to the interviewer by recording and scoring the responses. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can score the collected responses using AI and provide the results to the interviewer.

[0071] The feedback department can post summaries of information to the team chat tool and the talent management database. For example, the feedback department can create a summary of the collected responses and post it to the team chat tool. The feedback department can also create a summary of the collected responses and post it to the talent management database. The feedback department can also create a summary of the collected responses and send it via email. This allows for efficient sharing of interview results by posting summaries of information. Some or all of the above processes in the feedback department may be performed using AI or not. For example, the feedback department can create a summary of the collected responses using AI and post the results to the team chat tool and the talent management database.

[0072] The navigation unit can evaluate whether a candidate's motivation and desired salary meet the company's requirements and determine whether they should proceed to the next interview. For example, the navigation unit can evaluate a candidate's motivation. The navigation unit can also evaluate a candidate's desired salary. The navigation unit can also comprehensively evaluate a candidate's motivation and desired salary. For example, the navigation unit can evaluate whether a candidate's motivation meets the company's requirements. The navigation unit can also evaluate whether a candidate's desired salary meets the company's requirements. The navigation unit can also comprehensively evaluate whether a candidate's motivation and desired salary meet the company's requirements. This allows for an efficient determination of whether a candidate should proceed to the next step by evaluating their motivation and desired salary. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to evaluate a candidate's motivation and desired salary and determine whether they should proceed to the next step based on the results.

[0073] The reception desk can estimate the user's emotions and adjust the content and order of questions based on the estimated emotions. For example, if the user is nervous, the reception desk may start with simple questions to help them relax. If the user is relaxed, the reception desk may ask more detailed questions earlier. If the user is anxious, the reception desk may prioritize important questions. By adjusting the content and order of questions according to the user's emotions, a more appropriate interview can be conducted. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can estimate the user's emotions using AI and adjust the content and order of questions based on the result.

[0074] The reception department can analyze past interview data and automatically generate an optimal set of questions. For example, the reception department can analyze the answer patterns of successful candidates from past interview data and generate similar questions. For example, the reception department can extract questions suitable for a specific job from past interview data and generate a set of questions. For example, the reception department can optimize the order of questions from past interview data to increase the success rate of interviews. In this way, an optimal set of questions can be automatically generated by analyzing past interview data. Some or all of the above processes in the reception department may be performed using AI or not. For example, the reception department can analyze past interview data using AI and automatically generate an optimal set of questions based on the results.

[0075] The reception desk can customize questions based on the company's current needs and trends when questions are entered. For example, the reception desk can add relevant questions based on the company's latest projects and goals. For example, the reception desk can add questions testing up-to-date knowledge based on industry trends and technological advancements. For example, the reception desk can add questions to assess suitability based on the company's culture and values. This allows for more appropriate questions to be asked by customizing them based on the company's needs and trends. Some or all of the above processing in the reception desk may or may not be performed using AI. For example, the reception desk can use AI to analyze the company's current needs and trends and customize questions based on the results.

[0076] The reception desk can estimate the user's emotions and adjust the difficulty of questions based on the estimated emotions. For example, if the user is nervous, the reception desk can start with easy questions and gradually increase the difficulty. If the user is relaxed, the reception desk can ask more difficult questions earlier. If the user is anxious, the reception desk can prioritize important questions. By adjusting the difficulty of questions according to the user's emotions, a more appropriate interview can be conducted. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can estimate the user's emotions using AI and adjust the difficulty of questions based on the result.

[0077] The reception desk can automatically analyze a candidate's resume and work history when questions are entered and suggest relevant questions. For example, the reception desk can generate relevant questions based on the candidate's past experience from their work history. The reception desk can also generate questions based on specific skills and qualifications from the candidate's resume. The reception desk can also generate questions based on past projects and achievements from the candidate's work history. In this way, relevant questions can be suggested by analyzing the candidate's resume and work history. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can analyze a candidate's resume and work history using AI and suggest relevant questions based on the results.

[0078] The reception desk can optimize questions by referencing industry best practices when questions are entered. For example, the reception desk can generate effective questions based on industry best practices. The reception desk can also generate relevant questions based on the latest industry trends and technologies. The reception desk can also generate appropriate questions based on industry success stories. This allows for question optimization by referencing industry best practices. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can use AI to reference industry best practices and optimize questions based on the results.

[0079] The generation unit can estimate the user's emotions and adjust the interview pace based on the estimated emotions. For example, if the user is nervous, the generation unit can conduct the interview at a slow pace. For example, if the user is relaxed, the generation unit can conduct the interview at a normal pace. For example, if the user is anxious, the generation unit can conduct the interview quickly. By adjusting the interview pace according to the user's emotions, a more appropriate interview becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using a generative AI or not. For example, the generation unit can estimate the user's emotions using a generative AI and adjust the interview pace based on the result.

[0080] The generation unit can automatically generate additional follow-up questions during an interview based on the candidate's answers. For example, the generation unit can generate follow-up questions that request further explanation based on the candidate's answers. The generation unit can also generate follow-up questions about relevant skills and experience based on the candidate's answers. The generation unit can also generate follow-up questions about specific examples and achievements based on the candidate's answers. This allows for obtaining more detailed information by generating follow-up questions in response to the candidate's answers. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the candidate's answers into a generation AI and generate follow-up questions based on the results.

[0081] The generation unit can analyze a candidate's nonverbal responses during an interview and provide appropriate feedback. For example, the generation unit can analyze a candidate's facial expressions and tone of voice and provide feedback to help them relax. For example, the generation unit can analyze a candidate's posture and gestures and provide feedback to help them gain confidence. For example, the generation unit can analyze a candidate's gaze and eye movements and provide feedback to help them concentrate. In this way, appropriate feedback can be provided by analyzing the candidate's nonverbal responses. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the candidate's nonverbal responses into a generation AI and provide feedback based on the results.

[0082] The generation unit can estimate the user's emotions and adjust the tone and style of the interview based on the estimated emotions. For example, if the user is nervous, the generation unit will conduct the interview in a gentle tone. For example, if the user is relaxed, the generation unit can conduct the interview in a friendly tone. For example, if the user is anxious, the generation unit can conduct the interview in a quick and concise tone. By adjusting the tone and style of the interview according to the user's emotions, a more appropriate interview becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using a generative AI or not. For example, the generation unit can estimate the user's emotions using a generative AI and adjust the tone and style of the interview based on the result.

[0083] The generation unit can generate relevant questions during an interview by referring to the candidate's past interview history. For example, the generation unit can generate unanswered questions from the candidate's past interview history. The generation unit can also generate questions about specific skills or experience from the candidate's past interview history. For example, the generation unit can generate questions based on feedback from the previous interview from the candidate's past interview history. This allows for the generation of relevant questions by referring to the candidate's past interview history. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input the candidate's past interview history into a generation AI and generate relevant questions based on the results.

[0084] The generation unit can evaluate a candidate's adaptability during an interview using industry-specific scenarios. For example, the generation unit can present an industry-specific problem-solving scenario and evaluate the candidate's response. It can also present an industry-specific project management scenario and evaluate the candidate's leadership skills. It can also present an industry-specific customer service scenario and evaluate the candidate's communication skills. In this way, the candidate's adaptability can be evaluated by using industry-specific scenarios. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input industry-specific scenarios into a generation AI and evaluate the candidate's adaptability based on the results.

[0085] The feedback unit can estimate the user's emotions and adjust the content and expression of the feedback based on the estimated emotions. For example, if the user is nervous, the feedback unit will prioritize providing positive feedback. For example, if the user is relaxed, the feedback unit may also provide detailed feedback. For example, if the user is anxious, the feedback unit may also provide concise and to-the-point feedback. This allows for more appropriate feedback by adjusting the content and expression of the feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can estimate the user's emotions using AI and adjust the content and expression of the feedback based on the result.

[0086] The feedback unit can comprehensively evaluate the quality of a candidate's response during the feedback process and perform detailed scoring. For example, the feedback unit can evaluate and score the content, expression, and logic of the candidate's response. The feedback unit can also evaluate and score the specificity, achievements, and experience of the candidate's response. The feedback unit can also evaluate and score the consistency, reliability, and sincerity of the candidate's response. This allows for detailed scoring by comprehensively evaluating the quality of the candidate's response. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can evaluate a candidate's response using AI and perform detailed scoring based on the results.

[0087] The feedback unit can compare a candidate's responses with those of other candidates and provide a relative evaluation during the feedback process. For example, the feedback unit can compare a candidate's responses with those of other candidates and provide a relative score. The feedback unit can also compare the quality of a candidate's responses with those of other candidates and provide a relative evaluation. The feedback unit can also compare the specificity and achievements of a candidate's responses with those of other candidates and provide a relative evaluation. This makes it possible to provide a relative evaluation by comparing a candidate's responses with those of other candidates. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to compare a candidate's responses with those of other candidates and provide a relative evaluation based on the results.

[0088] The feedback unit can estimate the user's emotions and adjust the timing of feedback based on the estimated emotions. For example, if the user is nervous, the feedback unit may provide feedback earlier. For example, if the user is relaxed, the feedback unit may provide feedback at the normal timing. For example, if the user is anxious, the feedback unit may provide feedback quickly. By adjusting the timing of feedback according to the user's emotions, more appropriate feedback becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the feedback unit may be performed using AI or not using AI. For example, the feedback unit can estimate the user's emotions using AI and adjust the timing of feedback based on the result.

[0089] The feedback unit can evaluate candidates by considering their past performance and skill sets when providing feedback. For example, the feedback unit can evaluate a candidate's past performance and provide feedback. The feedback unit can also evaluate a candidate's skill set and provide feedback. The feedback unit can also evaluate a candidate's past projects and achievements and provide feedback. This allows for a more accurate evaluation by considering the candidate's past performance and skill sets. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can use AI to evaluate a candidate's past performance and skill sets and provide feedback based on the results.

[0090] The feedback unit can score candidates' responses by referring to industry standard evaluation criteria during the feedback process. For example, the feedback unit can score candidates' responses based on industry standard evaluation criteria. The feedback unit can also score candidates' responses based on industry best practices. The feedback unit can also score candidates' responses based on industry success stories. This improves the accuracy of scoring by referring to industry standard evaluation criteria. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can refer to industry standard evaluation criteria using AI and score candidates' responses based on the results.

[0091] The navigation unit can estimate the user's emotions and adjust the next step suggestions based on the estimated emotions. For example, if the user is tense, the navigation unit can suggest the next step to help them relax. If the user is relaxed, the navigation unit can also suggest the normal next step. If the user is anxious, the navigation unit can also suggest the next step quickly. By adjusting the next step suggestions according to the user's emotions, more appropriate suggestions become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can estimate the user's emotions using AI and adjust the next step suggestions based on the result.

[0092] The navigation unit can analyze the candidate's response data in real time during navigation and suggest the optimal next step. For example, the navigation unit can analyze the candidate's response data in real time and suggest whether or not to proceed to the next interview. For example, the navigation unit can analyze the candidate's response data in real time and suggest additional follow-up questions. For example, the navigation unit can analyze the candidate's response data in real time and suggest appropriate training or workshops as the next step. In this way, by analyzing the candidate's response data in real time, the optimal next step can be suggested. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to analyze the candidate's response data in real time and suggest the optimal next step based on the results.

[0093] The navigation unit can suggest a customized career path based on the candidate's skill set and experience during navigation. For example, the navigation unit can suggest the optimal career path based on the candidate's skill set. The navigation unit can also suggest an appropriate career path based on the candidate's experience. For example, the navigation unit can comprehensively evaluate the candidate's skill set and experience and suggest a customized career path. This allows for the provision of a more appropriate career path by suggesting a customized career path based on the candidate's skill set and experience. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to evaluate the candidate's skill set and experience and suggest a customized career path based on the results.

[0094] The navigation unit can estimate the user's emotions and determine the priority of the next steps based on the estimated emotions. For example, if the user is tense, the navigation unit may prioritize steps to help them relax. If the user is relaxed, the navigation unit may also prioritize normal steps. If the user is anxious, the navigation unit may also prioritize steps to help them proceed quickly. This allows for more appropriate progress by determining the priority of the next steps according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can estimate the user's emotions using AI and determine the priority of the next steps based on the result.

[0095] The navigation unit can suggest the next step during navigation, taking into account the candidate's geographical constraints and preferred work location. For example, the navigation unit can suggest the next step based on the candidate's preferred work location. The navigation unit can also suggest an appropriate next step, taking into account the candidate's geographical constraints. For example, the navigation unit can comprehensively evaluate the candidate's preferred work location and geographical constraints to suggest the optimal next step. This allows for the suggestion of a more appropriate next step by considering the candidate's geographical constraints and preferred work location. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to evaluate the candidate's geographical constraints and preferred work location and suggest the next step based on the results.

[0096] The navigation unit can optimize the next step by referring to the candidate's past interview history and feedback during navigation. For example, the navigation unit can refer to the candidate's past interview history and optimize the next step. The navigation unit can also refer to the candidate's past feedback and optimize the next step. For example, the navigation unit can comprehensively evaluate the candidate's past interview history and feedback and suggest the optimal next step. This allows for the optimization of the next step by referring to the candidate's past interview history and feedback. Some or all of the above processing in the navigation unit may be performed using AI or not. For example, the navigation unit can use AI to evaluate the candidate's past interview history and feedback and optimize the next step based on the results.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The reception desk can analyze a candidate's social media profile and generate relevant questions. For example, it can generate questions based on a candidate's past work experience and skills from their online resume. It can also generate questions based on a candidate's interests and passions from their social media posts. Furthermore, it can generate questions based on a candidate's technical skills and creative abilities from their GitHub and Behance projects. This allows for the generation of more personalized questions by analyzing a candidate's social media profile.

[0099] The generation unit can estimate the candidate's emotions in real time based on their responses and adjust the interview accordingly. For example, if the candidate is nervous, the generation unit can slow down the pace of the interview to help them relax. If the candidate is confident, the generation unit can ask more detailed questions. Furthermore, if the candidate is anxious, the generation unit can prioritize asking important questions. This allows for a more effective interview by adjusting the interview pace according to the candidate's emotions.

[0100] The feedback system can analyze candidates' responses and evaluate their consistency and reliability. For example, it can assess whether a candidate's responses are consistent and assign high scores to consistent responses. It can also assess whether a candidate's responses are based on reliable information and assign high scores to reliable responses. Furthermore, it can assess whether a candidate's responses are specific and assign high scores to specific responses. This allows for more accurate scoring by evaluating the consistency and reliability of candidates' responses.

[0101] The navigation unit can analyze candidate response data and suggest appropriate training and education as the next step. For example, if a candidate's response data indicates a lack of specific skills, it can suggest training to address those skills. Similarly, if a candidate's response data indicates a lack of knowledge in a particular field, it can suggest training in that area. Furthermore, if a candidate's response data indicates a lack of experience in a specific job, it can suggest practical training related to that job. In this way, by analyzing candidate response data, the system can suggest appropriate training and education as the next step.

[0102] The reception desk can estimate the candidate's emotions and adjust the timing of the interview based on that estimation. For example, if the candidate is nervous, they can be given time to relax before the interview begins. If the candidate is relaxed, the interview can begin immediately. Furthermore, if the candidate is anxious, important questions can be asked earlier. By adjusting the timing of the interview according to the candidate's emotions, a more effective interview can be conducted.

[0103] The generation unit can analyze the candidate's responses in real time during the interview and adjust the interview's progress according to the quality of the responses. For example, if a candidate's response is detailed and specific, the generation unit can ask follow-up questions to delve deeper. If a candidate's response is vague, the generation unit can ask additional follow-up questions. Furthermore, if a candidate's response is insufficient, the generation unit can request further explanation. This allows for obtaining more detailed information by adjusting the interview's progress according to the quality of the candidate's responses.

[0104] The feedback system can estimate the candidate's emotions and adjust the content of the feedback based on those estimates. For example, if the candidate is nervous, it can prioritize providing positive feedback. If the candidate is relaxed, it can provide detailed feedback. Furthermore, if the candidate is anxious, it can provide concise and to-the-point feedback. By adjusting the content of the feedback according to the candidate's emotions, it becomes possible to provide more appropriate feedback.

[0105] The navigation unit can analyze candidate response data and suggest appropriate career paths as the next steps. For example, it can suggest career paths based on specific skill sets from candidate response data. It can also suggest career paths based on specific experience from candidate response data. Furthermore, it can suggest career paths based on aptitude for specific tasks from candidate response data. In this way, by analyzing candidate response data, it can suggest appropriate career paths as the next steps.

[0106] The reception desk can estimate the candidate's emotions and adjust the interview questions based on that estimation. For example, if the candidate is nervous, they can start with simple questions to help them relax. If the candidate is relaxed, they can ask more detailed questions sooner. Furthermore, if the candidate is anxious, they can prioritize important questions. By adjusting the interview questions according to the candidate's emotions, a more effective interview can be conducted.

[0107] The generation unit can analyze a candidate's nonverbal responses during an interview and provide appropriate feedback. For example, it can analyze a candidate's facial expressions and tone of voice and provide feedback to help them relax. It can also analyze a candidate's posture and gestures and provide feedback to help them gain confidence. Furthermore, it can analyze a candidate's gaze and eye movements and provide feedback to improve their concentration. In this way, by analyzing a candidate's nonverbal responses, it can provide appropriate feedback.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The reception desk enters the required questions. These required questions include, for example, basic information and questions related to the job. The reception desk provides an interface for companies to enter these required questions. Step 2: The generation unit conducts job interviews based on questions entered by the reception unit. The generation unit conducts job interviews using, for example, an online meeting tool and interacts with candidates using a generation AI. The generation AI generates natural-sounding dialogues using a text generation AI (e.g., LLM). Step 3: The feedback team records and scores the responses collected by the generation team. The recordings are saved in video format, and scoring is performed based on evaluation criteria and scoring methods. The feedback team creates a summary of the collected responses and posts it to the team chat tool and the talent management database. Step 4: The Navigation Department determines whether to proceed to the next step based on the information provided by the Feedback Department. The next step may include the next interview or hiring decision. The Navigation Department evaluates whether the candidate's motivation and desired salary meet the company's requirements and determines whether they should proceed to the next interview.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0111] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0112] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0113] Each of the multiple elements described above, including the reception unit, generation unit, feedback unit, and navigation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and provides an interface for companies to input required questions. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and conducts job interviews using an online conferencing tool. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and records and scores the collected responses. The navigation unit is implemented by the control unit 46A of the smart device 14 and determines whether to proceed to the next step based on the information provided by the feedback unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0120] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0121] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0122] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0123] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0124] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0125] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0127] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the reception unit, generation unit, feedback unit, and navigation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface for companies to input required questions. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and conducts job interviews using an online conferencing tool. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and records and scores the collected responses. The navigation unit is implemented, for example, by the control unit 46A of the smart glasses 214 and determines whether to proceed to the next step based on the information provided by the feedback unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the reception unit, generation unit, feedback unit, and navigation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface for companies to input required questions. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and conducts job interviews using an online conferencing tool. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and records and scores the collected responses. The navigation unit is implemented by the control unit 46A of the headset terminal 314 and determines whether to proceed to the next step based on the information provided by the feedback unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0154] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the reception unit, generation unit, feedback unit, and navigation unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and provides an interface for companies to input required questions. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and conducts job interviews using an online conferencing tool. The feedback unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and records and scores the collected answers. The navigation unit is implemented by, for example, the control unit 46A of the robot 414 and determines whether to proceed to the next step based on the information provided by the feedback unit. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0163] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0165] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0166] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0167] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0171] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0172] 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.

[0173] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0176] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0178] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0179] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0180] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0181] (Note 1) The reception desk where you enter the required questions, A generation unit conducts a job interview based on questions entered by the reception unit, A feedback unit records and scores the responses collected by the generation unit and provides feedback to the interviewer, The system includes a navigation unit that determines whether to proceed to the next step based on the information provided by the feedback unit. A system characterized by the following features. (Note 2) The generating unit is Conduct job interviews using online meeting tools. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned feedback unit is The collected responses are recorded and scored. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned feedback unit is Post a summary of the information to the team chat tool and the talent management database. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned navigation unit is The company evaluates whether the candidate's motivation and desired salary meet its requirements and decides whether they should proceed to the next interview. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is The system estimates the user's emotions and adjusts the content and order of questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is Analyze past interview data and automatically generate the optimal set of questions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When entering questions, customize them based on the company's current needs and trends. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is The system estimates the user's emotions and adjusts the difficulty of the questions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When you enter questions, the system automatically analyzes the candidate's resume and work history and suggests relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When entering your questions, refer to industry best practices to optimize them. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is The system estimates the user's emotions and adjusts the interview pace based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is During the interview, additional follow-up questions are automatically generated based on the candidate's answers. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is During the interview, we analyze the candidate's nonverbal responses and provide appropriate feedback. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is The system estimates the user's emotions and adjusts the tone and style of the interview based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is During the interview, we refer to the candidate's past interview history to generate relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is During the interview, we will use industry-specific scenarios to assess the candidate's adaptability. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned feedback unit is It estimates the user's emotions and adjusts the content and expression of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned feedback unit is During the feedback process, the quality of the candidate's responses is evaluated from multiple perspectives and a detailed scoring system is implemented. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned feedback unit is During the feedback process, we compare the candidate's responses to those of other candidates and provide a relative evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned feedback unit is It estimates the user's emotions and adjusts the timing of feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned feedback unit is When providing feedback, the evaluation should take into account the candidate's past performance and skill set. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned feedback unit is During the feedback process, scoring is performed by referring to industry standard evaluation criteria. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned navigation unit is It estimates the user's emotions and adjusts the next step suggestions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned navigation unit is During navigation, the system analyzes candidate response data in real time and suggests the optimal next steps. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned navigation unit is During the navigation process, we suggest customized career paths based on the candidate's skill set and experience. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned navigation unit is It estimates the user's emotions and determines the priority of the next steps based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned navigation unit is During navigation, we suggest the next steps while taking into account the candidate's geographical constraints and preferred work location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned navigation unit is During navigation, we optimize the next steps by referring to the candidate's past interview history and feedback. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The reception desk where you enter the required questions, A generation unit conducts a job interview based on questions entered by the reception unit, A feedback unit records and scores the responses collected by the generation unit and provides feedback to the interviewer, The system includes a navigation unit that determines whether to proceed to the next step based on the information provided by the feedback unit. A system characterized by the following features.

2. The generating unit is Conduct job interviews using online meeting tools. The system according to feature 1.

3. The aforementioned feedback unit is The collected responses are recorded and scored. The system according to feature 1.

4. The aforementioned feedback unit is Post a summary of the information to the team chat tool and the talent management database. The system according to feature 1.

5. The aforementioned navigation unit is The company evaluates whether the candidate's motivation and desired salary meet its requirements and decides whether they should proceed to the next interview. The system according to feature 1.

6. The aforementioned reception unit is The system estimates the user's emotions and adjusts the content and order of questions based on those estimated emotions. The system according to feature 1.

7. The aforementioned reception unit is Analyze past interview data and automatically generate the optimal set of questions. The system according to feature 1.

8. The aforementioned reception unit is When entering questions, customize them based on the company's current needs and trends. The system according to feature 1.

Images