system

Abstract

The system according to this embodiment aims to estimate the emotions of interviewers and support the hiring process. [Solution] The system according to the embodiment comprises an acquisition unit, an emotion estimation unit, a feedback collection unit, and an advice provision unit. The acquisition unit acquires emotion estimation information, which is information used to estimate the emotions of the interviewer. The emotion estimation unit estimates the emotions of the interviewer based on the emotion estimation information acquired by the acquisition unit. The feedback collection unit collects and shares the emotions estimated by the emotion estimation unit. The advice provision unit provides question suggestions and communication advice based on the emotions collected by the feedback collection 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 it is difficult to accurately grasp the feelings of an interviewer and reflect them in the employment process.

[0005] The system according to the embodiment aims to estimate the feelings of an interviewer and support the employment process.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, an emotion estimation unit, a feedback collection unit, and an advice provision unit. The acquisition unit acquires emotion estimation information, which is information used to estimate the emotions of the interviewer. The emotion estimation unit estimates the emotions of the interviewer based on the emotion estimation information acquired by the acquisition unit. The feedback collection unit collects and shares the emotions estimated by the emotion estimation unit. The advice provision unit provides question suggestions and communication advice based on the emotions collected by the feedback collection unit. [Effects of the Invention]

[0007] The system according to this embodiment can estimate the emotions of interviewers and support the hiring process. [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 a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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 linked 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 receiving 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 receiving 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 recruitment support robot according to an embodiment of the present invention is a system that estimates the emotions of interviewers and supports the recruitment process. This system estimates the emotions of interviewers and supports the recruitment process. For example, if an interviewer has a favorable impression of a candidate, it collects that impression as specific feedback and shares it with other interviewers and the recruitment team. This allows for a unified evaluation standard for candidates, even when multiple interviewers are involved or when different people make the final decision. In addition, based on the estimation of the interviewer's emotions, it also provides suggestions for questions appropriate to the progress of the interview and communication advice to ease the atmosphere of the interview. Furthermore, it estimates the candidate's suitability and compatibility with members of the department to be recruited based on the interviewer's emotions and the interaction with the candidate, and provides this information to the interviewer. For example, it acquires information to estimate the interviewer's emotions. This information is obtained from the interviewer's facial expressions, tone of voice, and choice of words. For example, if the interviewer is smiling while speaking, this information is acquired as information for emotion estimation. Next, the system estimates the interviewer's emotions based on the acquired information. The emotion estimation unit analyzes the acquired information and estimates what kind of emotions the interviewer is feeling. For example, if an interviewer is smiling while speaking, the emotion estimation unit estimates that the interviewer has positive emotions. The estimated emotions are collected and shared with other interviewers and the hiring team. The feedback collection unit collects the estimated emotions and shares them with other interviewers and the hiring team. This allows for a unified evaluation standard for candidates, even when multiple interviewers are involved or different people make the final decision. Based on the estimated interviewer's emotions, the system also provides suggestions for questions appropriate to the progress of the interview and communication advice to ease the interview atmosphere. The advice provision unit provides suggestions for questions appropriate to the progress of the interview and communication advice to ease the interview atmosphere based on the estimated emotions. For example, if an interviewer is nervous, the advice provision unit provides advice to help them relax. Furthermore, based on the interviewer's emotions and their interaction with the candidate, the system estimates the candidate's suitability and compatibility with members of the department they are being hired for, and provides this information to the interviewers.The aptitude assessment unit evaluates a candidate's suitability based on the interviewer's emotions and their interaction with the candidate, and estimates their compatibility with the members of the department where they are being hired. For example, if the interviewer has positive feelings towards the candidate, the aptitude assessment unit will evaluate the candidate as suitable for that department. This allows the recruitment support robot to estimate the interviewer's emotions and support the recruitment process.

[0029] The recruitment support robot according to this embodiment comprises an acquisition unit, an emotion estimation unit, a feedback collection unit, and an advice provision unit. The acquisition unit acquires emotion estimation information, which is information used to estimate the emotions of interviewers. Emotion estimation information includes, for example, the interviewer's facial expression data, voice data, and text data. The acquisition unit can, for example, capture the interviewer's facial expression with a camera and acquire facial expression data. The acquisition unit can also record the interviewer's voice tone with a microphone and acquire voice data. Furthermore, the acquisition unit can acquire the interviewer's choice of words as text data. For example, the acquisition unit converts the interviewer's statements into text data in real time and acquires it as emotion estimation information. The emotion estimation unit estimates the interviewer's emotions based on the emotion estimation information acquired by the acquisition unit. The emotion estimation unit can, for example, use a machine learning algorithm to analyze the acquired facial expression data and estimate the interviewer's emotions. The emotion estimation unit can also analyze voice data and estimate emotions from the interviewer's voice tone. Furthermore, the emotion estimation unit can analyze text data and estimate emotions from the interviewer's choice of words. For example, the emotion estimation unit uses machine learning algorithms to analyze the interviewer's statements and estimate their emotions. The feedback collection unit collects the emotions estimated by the emotion estimation unit and shares them with other interviewers and the recruitment team. For example, the feedback collection unit stores the estimated emotions in a database, making them accessible to other interviewers and the recruitment team. The feedback collection unit can also share the estimated emotions in real time. For example, the feedback collection unit notifies other interviewers and the recruitment team of the estimated emotions in real time. The advice provision unit provides question suggestions and communication advice based on the emotions collected by the feedback collection unit. For example, the advice provision unit suggests questions according to the progress of the interview. The advice provision unit can also provide communication advice to ease the atmosphere of the interview. For example, if the interviewer is nervous, the advice provision unit provides advice on how to relax.As a result, the recruitment support robot according to this embodiment can estimate the emotions of the interviewer and support the recruitment process.

[0030] The acquisition unit acquires emotion estimation information, which is information used to estimate the interviewer's emotions. This emotion estimation information includes, for example, the interviewer's facial expression data, voice data, and text data. For example, the acquisition unit can capture the interviewer's facial expression with a camera and acquire facial expression data. Specifically, it uses a high-resolution camera to capture subtle changes in the interviewer's facial expression and analyzes this in real time. The acquisition unit can also record the interviewer's voice tone with a microphone and acquire voice data. The voice data includes parameters such as pitch, intensity, speed, and rhythm, and by analyzing these, changes in emotion can be captured. Furthermore, the acquisition unit can acquire the interviewer's word choice as text data. For example, the acquisition unit converts the interviewer's statements into text data in real time and acquires it as emotion estimation information. This involves using speech recognition technology to transcribe the content of the statements into text and analyzing the word choice and context to capture the nuances of emotion. In this way, the acquisition unit collects multifaceted data and provides a foundation for estimating the interviewer's emotions with high accuracy.

[0031] The emotion estimation unit estimates the interviewer's emotions based on the emotion estimation information acquired by the acquisition unit. For example, the emotion estimation unit uses machine learning algorithms to analyze the acquired facial expression data and estimate the interviewer's emotions. Specifically, it utilizes deep learning-based image recognition technology to analyze subtle changes in facial expressions, thereby estimating emotions such as joy, anger, sadness, and surprise with high accuracy. The emotion estimation unit can also analyze audio data and estimate emotions from the interviewer's voice tone. Audio analysis includes the extraction of acoustic features and the subsequent emotion classification, which allows it to capture changes in emotion from voice tone and rhythm. Furthermore, the emotion estimation unit can analyze text data and estimate emotions from the interviewer's word choices. For example, it uses natural language processing technology to analyze the emotional nuances of the statements and classify them into positive, negative, neutral, etc. As a result, the emotion estimation unit can comprehensively analyze facial expression, audio, and text data to estimate the interviewer's emotions from multiple perspectives.

[0032] The Feedback Collection Unit collects the emotions estimated by the Emotion Estimation Unit and shares them with other interviewers and the recruitment team. For example, the Feedback Collection Unit stores the estimated emotions in a database, making them accessible to other interviewers and the recruitment team. Specifically, it uses a cloud-based database to securely store the estimated emotion data and sets access rights as needed, ensuring both data sharing and protection. The Feedback Collection Unit can also share estimated emotions in real time. For example, it can notify other interviewers and the recruitment team of the estimated emotions in real time. This includes visually displaying emotion data using a dedicated dashboard or notification system to support real-time decision-making. Furthermore, the Feedback Collection Unit can analyze changes and trends in interviewers' emotions by comparing them with past interview data, helping to improve the recruitment process. This allows the Feedback Collection Unit to efficiently collect and share emotion data, supporting decision-making across the entire recruitment team.

[0033] The Advice Department provides question suggestions and communication advice based on the emotions collected by the Feedback Collection Department. For example, the Advice Department suggests questions that are appropriate to the progress of the interview. Specifically, it selects appropriate questions based on the interviewer's emotional state and provides advice to ensure the interview flows smoothly. The Advice Department can also provide communication advice to ease the atmosphere of the interview. For example, if the interviewer is nervous, the Advice Department will offer advice to help them relax. This may include suggesting relaxation techniques such as deep breathing or light stretching. Furthermore, if the interviewer has positive emotions, the Advice Department can suggest communication strategies to maintain those emotions. For example, if the interviewer has favorable feelings towards the candidate, the Advice Department will suggest specific feedback and compliments to reinforce those feelings. In this way, the Advice Department can provide appropriate advice tailored to the interviewer's emotional state and improve the quality of the interview.

[0034] The aptitude evaluation department assesses a candidate's suitability based on the interviewer's emotions and the candidate's dialogue. For example, the department analyzes the interviewer's emotional data and the candidate's dialogue data to evaluate the candidate's suitability. For instance, if the interviewer has positive feelings towards the candidate, the department will evaluate the candidate as suitable for that department. Conversely, if the interviewer has negative feelings towards the candidate, the department may evaluate the candidate as unsuitable for that department. Furthermore, the department can combine the interviewer's emotional data and the candidate's dialogue data to comprehensively evaluate the candidate's suitability. For example, the department can score the candidate's suitability based on the interviewer's emotional data and the candidate's dialogue data, and then make an evaluation based on that score. This allows for an assessment of the candidate's suitability and an estimation of their compatibility with the members of the department they are being recruited for.

[0035] The feedback collection unit shares the emotions estimated by the emotion estimation unit with other interviewers and the hiring team. For example, the feedback collection unit can store the estimated emotions in a database, making them accessible to other interviewers and the hiring team. The feedback collection unit can also share the estimated emotions in real time. For instance, it can notify other interviewers and the hiring team of the estimated emotions in real time. This allows for a consistent evaluation standard for candidates, even when multiple interviewers are involved or when different people make the final decision.

[0036] The Advice Department provides suggested questions and communication advice tailored to the progress of the interview. For example, the Advice Department can suggest questions appropriate to the stage of the interview. It can also provide communication advice to ease the interview atmosphere. For instance, if the interviewer appears nervous, the Advice Department can offer advice to help them relax. This allows for the provision of suggested questions tailored to the stage of the interview and communication advice to ease the interview atmosphere.

[0037] The data acquisition unit analyzes the interviewer's past interview history and selects the optimal data acquisition method. For example, the data acquisition unit prioritizes selecting data acquisition methods for sentiment estimation that the interviewer has preferred to use in the past. The data acquisition unit can also select data acquisition methods that were effective in specific situations based on the interviewer's past interview history. Furthermore, the data acquisition unit can analyze the interviewer's past interview history and select the most efficient data acquisition method. In this way, the optimal data acquisition method can be selected by analyzing the interviewer's past interview history. Some or all of the above processing in the data acquisition unit may be performed using AI, for example, or without AI. For example, the data acquisition unit can input the interviewer's past interview history data into a generating AI and have the generating AI select the optimal data acquisition method.

[0038] The acquisition unit filters the information for emotion estimation based on the interviewer's current psychological state and the progress of the interview. For example, if the interviewer is nervous, the acquisition unit refrains from acquiring emotion estimation information until the interviewer relaxes. The acquisition unit can also prioritize acquiring only important information depending on the progress of the interview. Furthermore, the acquisition unit can adjust the frequency of acquiring emotion estimation information based on the interviewer's psychological state. This allows for the priority acquisition of only important information based on the interviewer's psychological state and the progress of the interview. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the interviewer's psychological state data into a generating AI and have the generating AI perform the filtering.

[0039] The acquisition unit prioritizes acquiring highly relevant information when acquiring information for sentiment estimation, taking into account the interviewer's geographical location. For example, if the interviewer is in a specific region, the acquisition unit prioritizes acquiring information related to that region. The acquisition unit can also filter highly relevant information based on the interviewer's geographical location. Furthermore, if the interviewer is on the move, the acquisition unit can acquire the most relevant information based on their current location. This allows the acquisition of highly relevant information based on the interviewer's geographical location. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the interviewer's geographical location data into a generating AI and have the generating AI acquire highly relevant information.

[0040] The acquisition unit analyzes the interviewer's social media activity and obtains relevant information when acquiring information for sentiment estimation. For example, the acquisition unit acquires sentiment estimation information from the interviewer's social media activity. The acquisition unit can also acquire sentiment estimation information based on information shared by the interviewer on social media. Furthermore, the acquisition unit can analyze the interviewer's social media activity and prioritize the acquisition of relevant information. This allows for the priority acquisition of relevant information by analyzing the interviewer's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the interviewer's social media data into a generating AI and have the generating AI perform the acquisition of relevant information.

[0041] The emotion estimation unit estimates emotions by integrating the interviewer's facial expressions, tone of voice, word choice, and other multiple factors during emotion estimation. For example, the emotion estimation unit can estimate emotions by integrating the interviewer's facial expressions and tone of voice. It can also estimate emotions by integrating the interviewer's word choice and tone of voice. Furthermore, the emotion estimation unit can estimate emotions by integrating the interviewer's facial expressions, tone of voice, and word choice. This allows for more accurate emotion estimation by integrating the interviewer's facial expressions, tone of voice, and word choice. Some or all of the above processing in the emotion estimation unit may be performed using AI, for example, or without AI. For example, the emotion estimation unit can input the interviewer's facial expression data, tone of voice data, and word choice data into a generating AI and have the generating AI perform integrated emotion estimation.

[0042] The emotion estimation unit improves the accuracy of its estimation by referring to the interviewer's past emotion data during emotion estimation. For example, the emotion estimation unit estimates the current emotion by referring to the interviewer's past emotion data. The emotion estimation unit can also analyze the interviewer's past emotion data to improve the accuracy of its estimation. Furthermore, the emotion estimation unit can adjust the emotion estimation algorithm based on the interviewer's past emotion data. This improves the accuracy of emotion estimation by referring to the interviewer's past emotion data. Some or all of the above processing in the emotion estimation unit may be performed using AI, for example, or without AI. For example, the emotion estimation unit can input the interviewer's past emotion data into a generating AI and have the generating AI perform the task of improving the accuracy of emotion estimation.

[0043] The emotion estimation unit estimates emotions by considering the interviewer's geographical and cultural background. For example, the emotion estimation unit can estimate emotions by considering the interviewer's geographical background. It can also estimate emotions by considering the interviewer's cultural background. Furthermore, the emotion estimation unit can estimate emotions by integrating the interviewer's geographical and cultural backgrounds. This allows for more accurate emotion estimation by considering the interviewer's geographical and cultural backgrounds. Some or all of the above processing in the emotion estimation unit may be performed using AI, for example, or without AI. For example, the emotion estimation unit can input the interviewer's geographical and cultural background data into a generating AI and have the generating AI perform emotion estimation.

[0044] The sentiment estimation unit improves the accuracy of its estimation by referring to the interviewer's relevant literature during sentiment estimation. For example, the sentiment estimation unit can improve the accuracy of sentiment estimation by referring to the interviewer's relevant literature. The sentiment estimation unit can also analyze the interviewer's relevant literature and adjust the sentiment estimation algorithm. Furthermore, the sentiment estimation unit can improve the accuracy of sentiment estimation based on the interviewer's relevant literature. Thus, the accuracy of sentiment estimation is improved by referring to the interviewer's relevant literature. Some or all of the above processing in the sentiment estimation unit may be performed using AI, for example, or without AI. For example, the sentiment estimation unit can input the interviewer's relevant literature data into a generating AI and have the generating AI perform the sentiment estimation accuracy improvement.

[0045] The feedback collection unit selects the optimal collection method by referring to the interviewer's past feedback history when collecting feedback. For example, the feedback collection unit can select the optimal collection method by referring to the interviewer's past feedback history. The feedback collection unit can also analyze the interviewer's past feedback history and select an effective collection method. Furthermore, the feedback collection unit can adjust the collection method based on the interviewer's past feedback history. This allows the optimal collection method to be selected by referring to the interviewer's past feedback history. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can input the interviewer's past feedback history data into a generating AI and have the generating AI select the optimal collection method.

[0046] The feedback collection unit adjusts the level of detail in the feedback based on the interviewer's current psychological state when collecting feedback. For example, if the interviewer is nervous, the feedback collection unit will collect concise feedback. Conversely, if the interviewer is relaxed, the feedback collection unit may also collect detailed feedback. Furthermore, the feedback collection unit can adjust the level of detail in the feedback based on the interviewer's psychological state. This allows for the collection of more appropriate feedback by adjusting the level of detail based on the interviewer's psychological state. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can input the interviewer's psychological state data into a generating AI and have the generating AI perform the adjustment of the level of detail in the feedback.

[0047] The feedback collection unit prioritizes collecting highly relevant feedback by considering the interviewer's geographical location information during feedback collection. For example, if the interviewer is in a specific region, the feedback collection unit prioritizes collecting feedback relevant to that region. The feedback collection unit can also filter highly relevant feedback based on the interviewer's geographical location information. Furthermore, if the interviewer is on the move, the feedback collection unit can collect the most relevant feedback based on their current location. This allows for the collection of highly relevant feedback based on the interviewer's geographical location information. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can input the interviewer's geographical location data into a generating AI and have the generating AI collect highly relevant feedback.

[0048] The feedback collection unit analyzes the interviewer's social media activity and collects relevant feedback during the feedback collection process. For example, the feedback collection unit collects feedback from the interviewer's social media activity. The feedback collection unit can also collect feedback based on information shared by the interviewer on social media. Furthermore, the feedback collection unit can analyze the interviewer's social media activity and prioritize the collection of relevant feedback. This allows for the priority collection of relevant feedback by analyzing the interviewer's social media activity. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can input the interviewer's social media data into a generating AI and have the generating AI collect relevant feedback.

[0049] The advice-providing unit adjusts the level of detail of its advice based on the progress of the interview. For example, in the early stages of the interview, the advice-providing unit provides basic advice. In the middle of the interview, it can also provide advice on specific questions and dialogue. Furthermore, in the final stages of the interview, it can provide comprehensive advice. This allows the advice-providing unit to provide advice with an appropriate level of detail based on the progress of the interview. Some or all of the above processes in the advice-providing unit may be performed using AI, for example, or not. For example, the advice-providing unit can input interview progress data into a generating AI and have the generating AI adjust the level of detail of the advice.

[0050] The advice-providing unit provides optimal advice by referring to the interviewer's past advice history when providing advice. For example, the advice-providing unit provides effective advice by referring to the interviewer's past advice history. The advice-providing unit can also analyze the interviewer's past advice history and select the most appropriate advice. Furthermore, the advice-providing unit can adjust the content of the advice based on the interviewer's past advice history. This allows the advice-providing unit to provide optimal advice by referring to the interviewer's past advice history. Some or all of the above processes in the advice-providing unit may be performed using AI, for example, or not using AI. For example, the advice-providing unit can input the interviewer's past advice history data into a generating AI and have the generating AI perform the task of providing optimal advice.

[0051] The advice-providing unit provides optimal advice by considering the interviewer's geographical location when providing advice. For example, if the interviewer is in a specific region, the advice-providing unit will provide advice relevant to that region. The advice-providing unit can also provide highly relevant advice based on the interviewer's geographical location. Furthermore, if the interviewer is on the move, the advice-providing unit can provide optimal advice based on their current location. This allows the advice-providing unit to provide highly relevant advice based on the interviewer's geographical location. Some or all of the above processing in the advice-providing unit may be performed using AI, for example, or without AI. For example, the advice-providing unit can input the interviewer's geographical location data into a generating AI and have the generating AI perform the task of providing optimal advice.

[0052] The advice-providing unit analyzes the interviewer's social media activity when providing advice and provides relevant advice. For example, the advice-providing unit provides relevant advice based on the interviewer's social media activity. The advice-providing unit can also provide advice based on information shared by the interviewer on social media. Furthermore, the advice-providing unit can analyze the interviewer's social media activity and prioritize the provision of relevant advice. This allows for the priority provision of relevant advice by analyzing the interviewer's social media activity. Some or all of the above processing in the advice-providing unit may be performed using AI, for example, or not using AI. For example, the advice-providing unit can input the interviewer's social media data into a generating AI and have the generating AI perform the provision of relevant advice.

[0053] The aptitude evaluation unit selects the optimal evaluation method by referring to the interviewer's past evaluation history during the aptitude evaluation process. For example, the aptitude evaluation unit can select the optimal evaluation method by referring to the interviewer's past evaluation history. Furthermore, the aptitude evaluation unit can analyze the interviewer's past evaluation history to select an effective evaluation method. In addition, the aptitude evaluation unit can adjust the evaluation method based on the interviewer's past evaluation history. This allows for the selection of the optimal evaluation method by referring to the interviewer's past evaluation history. Some or all of the above processes in the aptitude evaluation unit may be performed using AI, for example, or without AI. For example, the aptitude evaluation unit can input the interviewer's past evaluation history data into a generating AI and have the generating AI select the optimal evaluation method.

[0054] The aptitude assessment unit adjusts the level of detail in the assessment based on the interviewer's current psychological state during the assessment. For example, if the interviewer is nervous, the aptitude assessment unit will provide a concise assessment. Conversely, if the interviewer is relaxed, the aptitude assessment unit can also provide a detailed assessment. Furthermore, the aptitude assessment unit can adjust the level of detail in the assessment based on the interviewer's psychological state. This allows for a more appropriate assessment by adjusting the level of detail in the assessment based on the interviewer's psychological state. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the aptitude assessment unit may be performed using AI, for example, or without AI. For example, the aptitude assessment unit can input the interviewer's psychological state data into the generative AI and have the generative AI perform the adjustment of the level of detail in the assessment.

[0055] The aptitude assessment unit selects the optimal assessment method during aptitude assessment, taking into account the interviewer's geographical location information. For example, if the interviewer is in a specific region, the aptitude assessment unit selects an assessment method relevant to that region. The aptitude assessment unit can also select a highly relevant assessment method based on the interviewer's geographical location information. Furthermore, if the interviewer is on the move, the aptitude assessment unit can select the optimal assessment method based on their current location. This allows for the selection of a highly relevant assessment method based on the interviewer's geographical location information. Some or all of the above processing in the aptitude assessment unit may be performed using AI, for example, or without AI. For example, the aptitude assessment unit can input the interviewer's geographical location data into a generating AI and have the generating AI select the optimal assessment method.

[0056] The aptitude evaluation unit analyzes the interviewer's social media activity during the aptitude evaluation and provides relevant evaluations. For example, the aptitude evaluation unit provides relevant evaluations based on the interviewer's social media activity. The aptitude evaluation unit can also provide evaluations based on information shared by the interviewer on social media. Furthermore, the aptitude evaluation unit can analyze the interviewer's social media activity and prioritize the provision of relevant evaluations. This allows for the priority provision of relevant evaluations by analyzing the interviewer's social media activity. Some or all of the above processing in the aptitude evaluation unit may be performed using AI, for example, or without AI. For example, the aptitude evaluation unit can input the interviewer's social media data into a generating AI and have the generating AI perform the provision of relevant evaluations.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The recruitment support robot can analyze an interviewer's past interview history and optimize the interview process without having to estimate the interviewer's emotions. For example, it can prioritize suggesting question patterns that the interviewer has preferred to use in the past. It can also incorporate interview techniques that the interviewer has found effective in the past. Furthermore, it can adjust the interview process based on the interviewer's past interview history. For example, if the interviewer has disliked long interviews in the past, the interview time can be shortened. In this way, by analyzing the interviewer's past interview history and optimizing the interview process, more effective interviews can be achieved.

[0059] The recruitment support robot can optimize the interview process by considering the interviewer's geographical location without having to estimate the interviewer's emotions. For example, if the interviewer is in a specific region, it will prioritize providing information relevant to that region. It can also suggest the most suitable interview method based on the interviewer's current location if they are on the move. Furthermore, it can adjust the interview process based on the interviewer's geographical location. For instance, if the interviewer is on the move, it can pause the interview and wait until the interviewer arrives at a stable location. This allows for more effective interviews by optimizing the interview process based on the interviewer's geographical location.

[0060] The recruitment support robot can analyze the interviewer's social media activity and optimize the interview process without having to estimate the interviewer's emotions. For example, it can adjust the interview process based on information the interviewer shares on social media. It can also understand the interviewer's interests and concerns from their social media activity and adjust the interview process accordingly. Furthermore, it can optimize the interview process based on the interviewer's social media activity. For example, if the interviewer is interested in a particular topic, it can prioritize suggesting questions related to that topic. By analyzing the interviewer's social media activity and optimizing the interview process, it is possible to achieve more effective interviews.

[0061] The recruitment support robot can optimize the interview process by referencing the interviewer's past feedback history without having to estimate the interviewer's emotions. For example, it can adjust the interview process based on the feedback the interviewer has provided in the past. It can also incorporate effective interview techniques from the interviewer's past feedback history. Furthermore, it can optimize the interview process based on the interviewer's past feedback history. For example, it can prioritize suggesting feedback methods that the interviewer has preferred to use in the past. By referencing the interviewer's past feedback history and optimizing the interview process, it can achieve more effective interviews.

[0062] The recruitment support robot can optimize the interview process by referencing the interviewer's relevant literature without having to estimate the interviewer's emotions. For example, it can adjust the interview process based on papers and articles the interviewer has previously written. It can also understand the interviewer's expertise and interests from their relevant literature and adjust the interview process accordingly. Furthermore, it can optimize the interview process based on the interviewer's relevant literature. For example, if the interviewer is knowledgeable in a particular field, it can prioritize suggesting questions related to that field. In this way, by referencing the interviewer's relevant literature and optimizing the interview process, a more effective interview can be achieved.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The acquisition unit acquires emotion estimation information, which is information used to estimate the interviewer's emotions. Emotion estimation information includes, for example, the interviewer's facial expression data, voice data, and text data. For example, the acquisition unit can capture the interviewer's facial expression with a camera and acquire facial expression data. The acquisition unit can also record the interviewer's voice tone with a microphone and acquire voice data. Furthermore, the acquisition unit can acquire the interviewer's word choices as text data. For example, the acquisition unit converts the interviewer's statements into text data in real time and acquires it as emotion estimation information. Step 2: The emotion estimation unit estimates the interviewer's emotions based on the emotion estimation information acquired by the acquisition unit. The emotion estimation unit can, for example, use a machine learning algorithm to analyze the acquired facial expression data and estimate the interviewer's emotions. The emotion estimation unit can also analyze audio data and estimate emotions from the interviewer's tone of voice. Furthermore, the emotion estimation unit can analyze text data and estimate emotions from the interviewer's choice of words. For example, the emotion estimation unit can use a machine learning algorithm to analyze the content of the interviewer's statements and estimate their emotions. Step 3: The feedback collection unit collects the emotions estimated by the emotion estimation unit and shares them with other interviewers and the recruitment team. The feedback collection unit can, for example, store the estimated emotions in a database and make them accessible to other interviewers and the recruitment team. The feedback collection unit can also share the estimated emotions in real time. For example, the feedback collection unit can notify other interviewers and the recruitment team of the estimated emotions in real time. Step 4: The Advice-Providing Department provides question suggestions and communication advice based on the sentiments gathered by the Feedback Collection Department. For example, the Advice-Providing Department may suggest questions that are relevant to the progress of the interview. The Advice-Providing Department may also provide communication advice to ease the atmosphere of the interview. For example, if the interviewer is nervous, the Advice-Providing Department may offer advice on how to relax.

[0065] (Example of form 2) The recruitment support robot according to an embodiment of the present invention is a system that estimates the emotions of interviewers and supports the recruitment process. This system estimates the emotions of interviewers and supports the recruitment process. For example, if an interviewer has a favorable impression of a candidate, it collects that impression as specific feedback and shares it with other interviewers and the recruitment team. This allows for a unified evaluation standard for candidates, even when multiple interviewers are involved or when different people make the final decision. In addition, based on the estimation of the interviewer's emotions, it also provides suggestions for questions appropriate to the progress of the interview and communication advice to ease the atmosphere of the interview. Furthermore, it estimates the candidate's suitability and compatibility with members of the department to be recruited based on the interviewer's emotions and the interaction with the candidate, and provides this information to the interviewer. For example, it acquires information to estimate the interviewer's emotions. This information is obtained from the interviewer's facial expressions, tone of voice, and choice of words. For example, if the interviewer is smiling while speaking, this information is acquired as information for emotion estimation. Next, the system estimates the interviewer's emotions based on the acquired information. The emotion estimation unit analyzes the acquired information and estimates what kind of emotions the interviewer is feeling. For example, if an interviewer is smiling while speaking, the emotion estimation unit estimates that the interviewer has positive emotions. The estimated emotions are collected and shared with other interviewers and the hiring team. The feedback collection unit collects the estimated emotions and shares them with other interviewers and the hiring team. This allows for a unified evaluation standard for candidates, even when multiple interviewers are involved or different people make the final decision. Based on the estimated interviewer's emotions, the system also provides suggestions for questions appropriate to the progress of the interview and communication advice to ease the interview atmosphere. The advice provision unit provides suggestions for questions appropriate to the progress of the interview and communication advice to ease the interview atmosphere based on the estimated emotions. For example, if an interviewer is nervous, the advice provision unit provides advice to help them relax. Furthermore, based on the interviewer's emotions and their interaction with the candidate, the system estimates the candidate's suitability and compatibility with members of the department they are being hired for, and provides this information to the interviewers.The aptitude assessment unit evaluates a candidate's suitability based on the interviewer's emotions and their interaction with the candidate, and estimates their compatibility with the members of the department where they are being hired. For example, if the interviewer has positive feelings towards the candidate, the aptitude assessment unit will evaluate the candidate as suitable for that department. This allows the recruitment support robot to estimate the interviewer's emotions and support the recruitment process.

[0066] The recruitment support robot according to this embodiment comprises an acquisition unit, an emotion estimation unit, a feedback collection unit, and an advice provision unit. The acquisition unit acquires emotion estimation information, which is information used to estimate the emotions of interviewers. Emotion estimation information includes, for example, the interviewer's facial expression data, voice data, and text data. The acquisition unit can, for example, capture the interviewer's facial expression with a camera and acquire facial expression data. The acquisition unit can also record the interviewer's voice tone with a microphone and acquire voice data. Furthermore, the acquisition unit can acquire the interviewer's choice of words as text data. For example, the acquisition unit converts the interviewer's statements into text data in real time and acquires it as emotion estimation information. The emotion estimation unit estimates the interviewer's emotions based on the emotion estimation information acquired by the acquisition unit. The emotion estimation unit can, for example, use a machine learning algorithm to analyze the acquired facial expression data and estimate the interviewer's emotions. The emotion estimation unit can also analyze voice data and estimate emotions from the interviewer's voice tone. Furthermore, the emotion estimation unit can analyze text data and estimate emotions from the interviewer's choice of words. For example, the emotion estimation unit uses machine learning algorithms to analyze the interviewer's statements and estimate their emotions. The feedback collection unit collects the emotions estimated by the emotion estimation unit and shares them with other interviewers and the recruitment team. For example, the feedback collection unit stores the estimated emotions in a database, making them accessible to other interviewers and the recruitment team. The feedback collection unit can also share the estimated emotions in real time. For example, the feedback collection unit notifies other interviewers and the recruitment team of the estimated emotions in real time. The advice provision unit provides question suggestions and communication advice based on the emotions collected by the feedback collection unit. For example, the advice provision unit suggests questions according to the progress of the interview. The advice provision unit can also provide communication advice to ease the atmosphere of the interview. For example, if the interviewer is nervous, the advice provision unit provides advice on how to relax.As a result, the recruitment support robot according to this embodiment can estimate the emotions of the interviewer and support the recruitment process.

[0067] The acquisition unit acquires emotion estimation information, which is information used to estimate the interviewer's emotions. This emotion estimation information includes, for example, the interviewer's facial expression data, voice data, and text data. For example, the acquisition unit can capture the interviewer's facial expression with a camera and acquire facial expression data. Specifically, it uses a high-resolution camera to capture subtle changes in the interviewer's facial expression and analyzes this in real time. The acquisition unit can also record the interviewer's voice tone with a microphone and acquire voice data. The voice data includes parameters such as pitch, intensity, speed, and rhythm, and by analyzing these, changes in emotion can be captured. Furthermore, the acquisition unit can acquire the interviewer's word choice as text data. For example, the acquisition unit converts the interviewer's statements into text data in real time and acquires it as emotion estimation information. This involves using speech recognition technology to transcribe the content of the statements into text and analyzing the word choice and context to capture the nuances of emotion. In this way, the acquisition unit collects multifaceted data and provides a foundation for estimating the interviewer's emotions with high accuracy.

[0068] The emotion estimation unit estimates the interviewer's emotions based on the emotion estimation information acquired by the acquisition unit. For example, the emotion estimation unit uses machine learning algorithms to analyze the acquired facial expression data and estimate the interviewer's emotions. Specifically, it utilizes deep learning-based image recognition technology to analyze subtle changes in facial expressions, thereby estimating emotions such as joy, anger, sadness, and surprise with high accuracy. The emotion estimation unit can also analyze audio data and estimate emotions from the interviewer's voice tone. Audio analysis includes the extraction of acoustic features and the subsequent emotion classification, which allows it to capture changes in emotion from voice tone and rhythm. Furthermore, the emotion estimation unit can analyze text data and estimate emotions from the interviewer's word choices. For example, it uses natural language processing technology to analyze the emotional nuances of the statements and classify them into positive, negative, neutral, etc. As a result, the emotion estimation unit can comprehensively analyze facial expression, audio, and text data to estimate the interviewer's emotions from multiple perspectives.

[0069] The Feedback Collection Unit collects the emotions estimated by the Emotion Estimation Unit and shares them with other interviewers and the recruitment team. For example, the Feedback Collection Unit stores the estimated emotions in a database, making them accessible to other interviewers and the recruitment team. Specifically, it uses a cloud-based database to securely store the estimated emotion data and sets access rights as needed, ensuring both data sharing and protection. The Feedback Collection Unit can also share estimated emotions in real time. For example, it can notify other interviewers and the recruitment team of the estimated emotions in real time. This includes visually displaying emotion data using a dedicated dashboard or notification system to support real-time decision-making. Furthermore, the Feedback Collection Unit can analyze changes and trends in interviewers' emotions by comparing them with past interview data, helping to improve the recruitment process. This allows the Feedback Collection Unit to efficiently collect and share emotion data, supporting decision-making across the entire recruitment team.

[0070] The Advice Department provides question suggestions and communication advice based on the emotions collected by the Feedback Collection Department. For example, the Advice Department suggests questions that are appropriate to the progress of the interview. Specifically, it selects appropriate questions based on the interviewer's emotional state and provides advice to ensure the interview flows smoothly. The Advice Department can also provide communication advice to ease the atmosphere of the interview. For example, if the interviewer is nervous, the Advice Department will offer advice to help them relax. This may include suggesting relaxation techniques such as deep breathing or light stretching. Furthermore, if the interviewer has positive emotions, the Advice Department can suggest communication strategies to maintain those emotions. For example, if the interviewer has favorable feelings towards the candidate, the Advice Department will suggest specific feedback and compliments to reinforce those feelings. In this way, the Advice Department can provide appropriate advice tailored to the interviewer's emotional state and improve the quality of the interview.

[0071] The aptitude evaluation department assesses a candidate's suitability based on the interviewer's emotions and the candidate's dialogue. For example, the department analyzes the interviewer's emotional data and the candidate's dialogue data to evaluate the candidate's suitability. For instance, if the interviewer has positive feelings towards the candidate, the department will evaluate the candidate as suitable for that department. Conversely, if the interviewer has negative feelings towards the candidate, the department may evaluate the candidate as unsuitable for that department. Furthermore, the department can combine the interviewer's emotional data and the candidate's dialogue data to comprehensively evaluate the candidate's suitability. For example, the department can score the candidate's suitability based on the interviewer's emotional data and the candidate's dialogue data, and then make an evaluation based on that score. This allows for an assessment of the candidate's suitability and an estimation of their compatibility with the members of the department they are being recruited for.

[0072] The feedback collection unit shares the emotions estimated by the emotion estimation unit with other interviewers and the hiring team. For example, the feedback collection unit can store the estimated emotions in a database, making them accessible to other interviewers and the hiring team. The feedback collection unit can also share the estimated emotions in real time. For instance, it can notify other interviewers and the hiring team of the estimated emotions in real time. This allows for a consistent evaluation standard for candidates, even when multiple interviewers are involved or when different people make the final decision.

[0073] The Advice Department provides suggested questions and communication advice tailored to the progress of the interview. For example, the Advice Department can suggest questions appropriate to the stage of the interview. It can also provide communication advice to ease the interview atmosphere. For instance, if the interviewer appears nervous, the Advice Department can offer advice to help them relax. This allows for the provision of suggested questions tailored to the stage of the interview and communication advice to ease the interview atmosphere.

[0074] The acquisition unit estimates the interviewer's emotions and adjusts the timing of acquiring emotion estimation information based on the estimated emotions. For example, if the interviewer is nervous, the acquisition unit may delay acquiring emotion estimation information until the interviewer relaxes. Conversely, if the interviewer is relaxed, the acquisition unit can acquire emotion estimation information more frequently to collect detailed data. Furthermore, if the interviewer is in a hurry, the acquisition unit can acquire emotion estimation information quickly and estimate the emotions rapidly. This allows for the acquisition of more appropriate information by adjusting the timing of acquiring emotion estimation information according to the interviewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the acquisition unit may be performed using AI, or not. For example, the acquisition unit can input the interviewer's emotion data into the generative AI and have the generative AI execute the timing of acquiring emotion estimation information.

[0075] The data acquisition unit analyzes the interviewer's past interview history and selects the optimal data acquisition method. For example, the data acquisition unit prioritizes selecting data acquisition methods for sentiment estimation that the interviewer has preferred to use in the past. The data acquisition unit can also select data acquisition methods that were effective in specific situations based on the interviewer's past interview history. Furthermore, the data acquisition unit can analyze the interviewer's past interview history and select the most efficient data acquisition method. In this way, the optimal data acquisition method can be selected by analyzing the interviewer's past interview history. Some or all of the above processing in the data acquisition unit may be performed using AI, for example, or without AI. For example, the data acquisition unit can input the interviewer's past interview history data into a generating AI and have the generating AI select the optimal data acquisition method.

[0076] The acquisition unit filters the information for emotion estimation based on the interviewer's current psychological state and the progress of the interview. For example, if the interviewer is nervous, the acquisition unit refrains from acquiring emotion estimation information until the interviewer relaxes. The acquisition unit can also prioritize acquiring only important information depending on the progress of the interview. Furthermore, the acquisition unit can adjust the frequency of acquiring emotion estimation information based on the interviewer's psychological state. This allows for the priority acquisition of only important information based on the interviewer's psychological state and the progress of the interview. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the interviewer's psychological state data into a generating AI and have the generating AI perform the filtering.

[0077] The acquisition unit estimates the interviewer's emotions and determines the priority of emotion estimation information to acquire based on the estimated emotions. For example, if the interviewer has positive emotions, the acquisition unit prioritizes acquiring positive information. The acquisition unit can also prioritize acquiring negative information if the interviewer has negative emotions. Furthermore, the acquisition unit can prioritize acquiring information of high importance based on the interviewer's emotions. This allows for the prioritization of information of high importance based on the interviewer's emotions. Emotion estimation is implemented using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the acquisition unit may be performed using AI, or not using AI. For example, the acquisition unit can input the interviewer's emotion data into the generative AI and have the generative AI prioritize the emotion estimation information.

[0078] The acquisition unit prioritizes acquiring highly relevant information when acquiring information for sentiment estimation, taking into account the interviewer's geographical location. For example, if the interviewer is in a specific region, the acquisition unit prioritizes acquiring information related to that region. The acquisition unit can also filter highly relevant information based on the interviewer's geographical location. Furthermore, if the interviewer is on the move, the acquisition unit can acquire the most relevant information based on their current location. This allows the acquisition of highly relevant information based on the interviewer's geographical location. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the interviewer's geographical location data into a generating AI and have the generating AI acquire highly relevant information.

[0079] The acquisition unit analyzes the interviewer's social media activity and obtains relevant information when acquiring information for sentiment estimation. For example, the acquisition unit acquires sentiment estimation information from the interviewer's social media activity. The acquisition unit can also acquire sentiment estimation information based on information shared by the interviewer on social media. Furthermore, the acquisition unit can analyze the interviewer's social media activity and prioritize the acquisition of relevant information. This allows for the priority acquisition of relevant information by analyzing the interviewer's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can input the interviewer's social media data into a generating AI and have the generating AI perform the acquisition of relevant information.

[0080] The emotion estimation unit estimates the interviewer's emotions and adjusts the emotion estimation algorithm based on the estimated emotions. For example, if the interviewer is nervous, the emotion estimation unit adjusts the emotion estimation algorithm to match a relaxed state. The emotion estimation unit can also adjust the emotion estimation algorithm to obtain more detailed information if the interviewer is relaxed. Furthermore, if the interviewer is in a hurry, the emotion estimation unit can adjust the emotion estimation algorithm to estimate emotions quickly. This allows for more accurate emotion estimation by adjusting the emotion estimation algorithm according to the interviewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the emotion estimation unit may be performed using AI or not. For example, the emotion estimation unit can input the interviewer's emotion data into the generative AI and have the generative AI adjust the emotion estimation algorithm.

[0081] The emotion estimation unit estimates emotions by integrating the interviewer's facial expressions, tone of voice, word choice, and other multiple factors during emotion estimation. For example, the emotion estimation unit can estimate emotions by integrating the interviewer's facial expressions and tone of voice. It can also estimate emotions by integrating the interviewer's word choice and tone of voice. Furthermore, the emotion estimation unit can estimate emotions by integrating the interviewer's facial expressions, tone of voice, and word choice. This allows for more accurate emotion estimation by integrating the interviewer's facial expressions, tone of voice, and word choice. Some or all of the above processing in the emotion estimation unit may be performed using AI, for example, or without AI. For example, the emotion estimation unit can input the interviewer's facial expression data, tone of voice data, and word choice data into a generating AI and have the generating AI perform integrated emotion estimation.

[0082] The emotion estimation unit improves the accuracy of its estimation by referring to the interviewer's past emotion data during emotion estimation. For example, the emotion estimation unit estimates the current emotion by referring to the interviewer's past emotion data. The emotion estimation unit can also analyze the interviewer's past emotion data to improve the accuracy of its estimation. Furthermore, the emotion estimation unit can adjust the emotion estimation algorithm based on the interviewer's past emotion data. This improves the accuracy of emotion estimation by referring to the interviewer's past emotion data. Some or all of the above processing in the emotion estimation unit may be performed using AI, for example, or without AI. For example, the emotion estimation unit can input the interviewer's past emotion data into a generating AI and have the generating AI perform the task of improving the accuracy of emotion estimation.

[0083] The emotion estimation unit estimates the interviewer's emotions and adjusts the display method of the emotion estimation result based on the estimated emotions of the interviewer. For example, if the interviewer is nervous, the emotion estimation unit provides a simple and highly visible display method. If the interviewer is relaxed, the emotion estimation unit can also provide a display method that includes detailed information. Furthermore, if the interviewer is in a hurry, the emotion estimation unit can provide a concise display method. By adjusting the display method of the emotion estimation result according to the interviewer's emotions, a more appropriate display 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, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the emotion estimation unit may be performed using AI, for example, or without AI. For example, the emotion estimation unit can input the interviewer's emotion data into the generative AI and have the generative AI perform the adjustment of the display method of the emotion estimation result.

[0084] The emotion estimation unit estimates emotions by considering the interviewer's geographical and cultural background. For example, the emotion estimation unit can estimate emotions by considering the interviewer's geographical background. It can also estimate emotions by considering the interviewer's cultural background. Furthermore, the emotion estimation unit can estimate emotions by integrating the interviewer's geographical and cultural backgrounds. This allows for more accurate emotion estimation by considering the interviewer's geographical and cultural backgrounds. Some or all of the above processing in the emotion estimation unit may be performed using AI, for example, or without AI. For example, the emotion estimation unit can input the interviewer's geographical and cultural background data into a generating AI and have the generating AI perform emotion estimation.

[0085] The sentiment estimation unit improves the accuracy of its estimation by referring to the interviewer's relevant literature during sentiment estimation. For example, the sentiment estimation unit can improve the accuracy of sentiment estimation by referring to the interviewer's relevant literature. The sentiment estimation unit can also analyze the interviewer's relevant literature and adjust the sentiment estimation algorithm. Furthermore, the sentiment estimation unit can improve the accuracy of sentiment estimation based on the interviewer's relevant literature. Thus, the accuracy of sentiment estimation is improved by referring to the interviewer's relevant literature. Some or all of the above processing in the sentiment estimation unit may be performed using AI, for example, or without AI. For example, the sentiment estimation unit can input the interviewer's relevant literature data into a generating AI and have the generating AI perform the sentiment estimation accuracy improvement.

[0086] The feedback collection unit estimates the interviewer's emotions and adjusts the feedback collection method based on the estimated emotions. For example, if the interviewer is nervous, the feedback collection unit will refrain from collecting feedback until the interviewer relaxes. Conversely, if the interviewer is relaxed, the feedback collection unit can collect detailed feedback. Furthermore, if the interviewer is in a hurry, the feedback collection unit can collect feedback in a short amount of time. This allows for the collection of more appropriate feedback by adjusting the feedback collection method according to the interviewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the feedback collection unit may be performed using AI or not. For example, the feedback collection unit can input the interviewer's emotion data into the generative AI and have the generative AI adjust the feedback collection method.

[0087] The feedback collection unit selects the optimal collection method by referring to the interviewer's past feedback history when collecting feedback. For example, the feedback collection unit can select the optimal collection method by referring to the interviewer's past feedback history. The feedback collection unit can also analyze the interviewer's past feedback history and select an effective collection method. Furthermore, the feedback collection unit can adjust the collection method based on the interviewer's past feedback history. This allows the optimal collection method to be selected by referring to the interviewer's past feedback history. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can input the interviewer's past feedback history data into a generating AI and have the generating AI select the optimal collection method.

[0088] The feedback collection unit adjusts the level of detail in the feedback based on the interviewer's current psychological state when collecting feedback. For example, if the interviewer is nervous, the feedback collection unit will collect concise feedback. Conversely, if the interviewer is relaxed, the feedback collection unit may also collect detailed feedback. Furthermore, the feedback collection unit can adjust the level of detail in the feedback based on the interviewer's psychological state. This allows for the collection of more appropriate feedback by adjusting the level of detail based on the interviewer's psychological state. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can input the interviewer's psychological state data into a generating AI and have the generating AI perform the adjustment of the level of detail in the feedback.

[0089] The feedback collection unit estimates the interviewer's emotions and determines the priority of feedback based on the estimated emotions. For example, if the interviewer has positive emotions, the feedback collection unit will prioritize collecting positive feedback. It can also prioritize collecting negative feedback if the interviewer has negative emotions. Furthermore, based on the interviewer's emotions, the feedback collection unit can prioritize collecting feedback of high importance. This allows for the prioritization of high-importance feedback based on the interviewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, 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 collection unit may be performed using AI, or not. For example, the feedback collection unit can input interviewer emotion data into a generative AI and have the generative AI determine the priority of feedback.

[0090] The feedback collection unit prioritizes collecting highly relevant feedback by considering the interviewer's geographical location information during feedback collection. For example, if the interviewer is in a specific region, the feedback collection unit prioritizes collecting feedback relevant to that region. The feedback collection unit can also filter highly relevant feedback based on the interviewer's geographical location information. Furthermore, if the interviewer is on the move, the feedback collection unit can collect the most relevant feedback based on their current location. This allows for the collection of highly relevant feedback based on the interviewer's geographical location information. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can input the interviewer's geographical location data into a generating AI and have the generating AI collect highly relevant feedback.

[0091] The feedback collection unit analyzes the interviewer's social media activity and collects relevant feedback during the feedback collection process. For example, the feedback collection unit collects feedback from the interviewer's social media activity. The feedback collection unit can also collect feedback based on information shared by the interviewer on social media. Furthermore, the feedback collection unit can analyze the interviewer's social media activity and prioritize the collection of relevant feedback. This allows for the priority collection of relevant feedback by analyzing the interviewer's social media activity. Some or all of the above processing in the feedback collection unit may be performed using AI, for example, or without AI. For example, the feedback collection unit can input the interviewer's social media data into a generating AI and have the generating AI collect relevant feedback.

[0092] The advice-providing unit estimates the interviewer's emotions and adjusts the way it expresses advice based on the estimated emotions. For example, if the interviewer is nervous, the advice-providing unit will provide advice to help them relax. If the interviewer is relaxed, the advice-providing unit can also provide more detailed advice. Furthermore, if the interviewer is in a hurry, the advice-providing unit can provide concise and quick advice. This allows for the provision of more appropriate advice by adjusting the way it is expressed according to the interviewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the advice-providing unit may be performed using AI or not. For example, the advice-providing unit can input the interviewer's emotion data into the generative AI and have the generative AI adjust the way it expresses the advice.

[0093] The advice-providing unit adjusts the level of detail of its advice based on the progress of the interview. For example, in the early stages of the interview, the advice-providing unit provides basic advice. In the middle of the interview, it can also provide advice on specific questions and dialogue. Furthermore, in the final stages of the interview, it can provide comprehensive advice. This allows the advice-providing unit to provide advice with an appropriate level of detail based on the progress of the interview. Some or all of the above processes in the advice-providing unit may be performed using AI, for example, or not. For example, the advice-providing unit can input interview progress data into a generating AI and have the generating AI adjust the level of detail of the advice.

[0094] The advice-providing unit provides optimal advice by referring to the interviewer's past advice history when providing advice. For example, the advice-providing unit provides effective advice by referring to the interviewer's past advice history. The advice-providing unit can also analyze the interviewer's past advice history and select the most appropriate advice. Furthermore, the advice-providing unit can adjust the content of the advice based on the interviewer's past advice history. This allows the advice-providing unit to provide optimal advice by referring to the interviewer's past advice history. Some or all of the above processes in the advice-providing unit may be performed using AI, for example, or not using AI. For example, the advice-providing unit can input the interviewer's past advice history data into a generating AI and have the generating AI perform the task of providing optimal advice.

[0095] The advice-providing unit estimates the interviewer's emotions and determines the priority of advice based on the estimated emotions. For example, if the interviewer has positive emotions, the advice-providing unit will prioritize providing positive advice. It can also prioritize providing negative advice if the interviewer has negative emotions. Furthermore, the advice-providing unit can prioritize providing advice of high importance based on the interviewer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advice-providing unit may be performed using AI or not. For example, the advice-providing unit can input the interviewer's emotion data into a generative AI and have the generative AI determine the priority of advice.

[0096] The advice-providing unit provides optimal advice by considering the interviewer's geographical location when providing advice. For example, if the interviewer is in a specific region, the advice-providing unit will provide advice relevant to that region. The advice-providing unit can also provide highly relevant advice based on the interviewer's geographical location. Furthermore, if the interviewer is on the move, the advice-providing unit can provide optimal advice based on their current location. This allows the advice-providing unit to provide highly relevant advice based on the interviewer's geographical location. Some or all of the above processing in the advice-providing unit may be performed using AI, for example, or without AI. For example, the advice-providing unit can input the interviewer's geographical location data into a generating AI and have the generating AI perform the task of providing optimal advice.

[0097] The advice-providing unit analyzes the interviewer's social media activity when providing advice and provides relevant advice. For example, the advice-providing unit provides relevant advice based on the interviewer's social media activity. The advice-providing unit can also provide advice based on information shared by the interviewer on social media. Furthermore, the advice-providing unit can analyze the interviewer's social media activity and prioritize the provision of relevant advice. This allows for the priority provision of relevant advice by analyzing the interviewer's social media activity. Some or all of the above processing in the advice-providing unit may be performed using AI, for example, or not using AI. For example, the advice-providing unit can input the interviewer's social media data into a generating AI and have the generating AI perform the provision of relevant advice.

[0098] The aptitude assessment unit estimates the interviewer's emotions and adjusts the candidate's aptitude assessment method based on the estimated interviewer's emotions. For example, if the interviewer has positive emotions, the aptitude assessment unit prioritizes positive evaluation criteria. Conversely, if the interviewer has negative emotions, the aptitude assessment unit can also prioritize negative evaluation criteria. Furthermore, the aptitude assessment unit can adjust the level of detail of the evaluation criteria based on the interviewer's emotions. This allows for a more appropriate assessment by adjusting the candidate's aptitude assessment method based on the interviewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the aptitude assessment unit may be performed using AI, for example, or without AI. For example, the aptitude assessment unit can input interviewer emotion data into a generative AI and have the generative AI perform the adjustment of the aptitude assessment method.

[0099] The aptitude evaluation unit selects the optimal evaluation method by referring to the interviewer's past evaluation history during the aptitude evaluation process. For example, the aptitude evaluation unit can select the optimal evaluation method by referring to the interviewer's past evaluation history. Furthermore, the aptitude evaluation unit can analyze the interviewer's past evaluation history to select an effective evaluation method. In addition, the aptitude evaluation unit can adjust the evaluation method based on the interviewer's past evaluation history. This allows for the selection of the optimal evaluation method by referring to the interviewer's past evaluation history. Some or all of the above processes in the aptitude evaluation unit may be performed using AI, for example, or without AI. For example, the aptitude evaluation unit can input the interviewer's past evaluation history data into a generating AI and have the generating AI select the optimal evaluation method.

[0100] The aptitude assessment unit adjusts the level of detail in the assessment based on the interviewer's current psychological state during the assessment. For example, if the interviewer is nervous, the aptitude assessment unit will provide a concise assessment. Conversely, if the interviewer is relaxed, the aptitude assessment unit can also provide a detailed assessment. Furthermore, the aptitude assessment unit can adjust the level of detail in the assessment based on the interviewer's psychological state. This allows for a more appropriate assessment by adjusting the level of detail in the assessment based on the interviewer's psychological state. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the aptitude assessment unit may be performed using AI, for example, or without AI. For example, the aptitude assessment unit can input the interviewer's psychological state data into the generative AI and have the generative AI perform the adjustment of the level of detail in the assessment.

[0101] The aptitude evaluation unit estimates the interviewer's emotions and determines the priority of the aptitude evaluation based on the estimated interviewer's emotions. For example, if the interviewer has positive emotions, the aptitude evaluation unit will prioritize positive evaluations. The aptitude evaluation unit can also prioritize negative evaluations if the interviewer has negative emotions. Furthermore, the aptitude evaluation unit can also prioritize evaluations of high importance based on the interviewer's emotions. This allows for prioritization of evaluations of high importance based on the interviewer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the aptitude evaluation unit may be performed using AI, or not using AI. For example, the aptitude evaluation unit can input the interviewer's emotion data into a generative AI and have the generative AI determine the priority of the aptitude evaluation.

[0102] The aptitude assessment unit selects the optimal assessment method during aptitude assessment, taking into account the interviewer's geographical location information. For example, if the interviewer is in a specific region, the aptitude assessment unit selects an assessment method relevant to that region. The aptitude assessment unit can also select a highly relevant assessment method based on the interviewer's geographical location information. Furthermore, if the interviewer is on the move, the aptitude assessment unit can select the optimal assessment method based on their current location. This allows for the selection of a highly relevant assessment method based on the interviewer's geographical location information. Some or all of the above processing in the aptitude assessment unit may be performed using AI, for example, or without AI. For example, the aptitude assessment unit can input the interviewer's geographical location data into a generating AI and have the generating AI select the optimal assessment method.

[0103] The aptitude evaluation unit analyzes the interviewer's social media activity during the aptitude evaluation and provides relevant evaluations. For example, the aptitude evaluation unit provides relevant evaluations based on the interviewer's social media activity. The aptitude evaluation unit can also provide evaluations based on information shared by the interviewer on social media. Furthermore, the aptitude evaluation unit can analyze the interviewer's social media activity and prioritize the provision of relevant evaluations. This allows for the priority provision of relevant evaluations by analyzing the interviewer's social media activity. Some or all of the above processing in the aptitude evaluation unit may be performed using AI, for example, or without AI. For example, the aptitude evaluation unit can input the interviewer's social media data into a generating AI and have the generating AI perform the provision of relevant evaluations.

[0104] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0105] The recruitment support robot can also estimate the interviewer's emotions and evaluate their stress level based on those estimates. For example, if the interviewer is nervous, their stress level will be evaluated as high. Conversely, if the interviewer is relaxed, their stress level will be evaluated as low. Furthermore, the robot can adjust the interview process based on the interviewer's stress level. For instance, if the interviewer's stress level is high, the interview can be slowed down. This allows for a more appropriate interview environment by evaluating the interviewer's stress level and adjusting the interview process accordingly.

[0106] The recruitment support robot can also estimate the interviewer's emotions and assess their fatigue level based on those estimates. For example, if the interviewer is tired, it will be rated as having a high fatigue level. Conversely, if the interviewer is energetic, it will be rated as having a low fatigue level. Furthermore, it can adjust the interview schedule based on the interviewer's fatigue level. For instance, if the interviewer is highly fatigued, the interview break time can be increased. This allows for a more appropriate interview environment by assessing the interviewer's fatigue level and adjusting the interview schedule accordingly.

[0107] The recruitment support robot can also estimate the interviewer's emotions and evaluate their level of concentration based on those emotions. For example, if the interviewer is focused, it will be rated as having a high level of concentration. Conversely, if the interviewer is easily distracted, it will be rated as having a low level of concentration. Furthermore, it can adjust the interview process based on the interviewer's level of concentration. For example, if the interviewer is not focused, the interview can be paused to allow the interviewer to regain their focus. This allows for a more appropriate interview environment by evaluating the interviewer's concentration and adjusting the interview process accordingly.

[0108] The recruitment support robot can also estimate the interviewer's emotions and evaluate their motivation based on those emotions. For example, if the interviewer is highly motivated, they will be rated as highly motivated. Conversely, if the interviewer is unmotivated, they will be rated as unmotivated. Furthermore, the robot can adjust the interview process based on the interviewer's motivation. For instance, if the interviewer is unmotivated, the interview can be paused to allow them to regain their enthusiasm. This allows the robot to provide a more appropriate interview environment by evaluating the interviewer's motivation and adjusting the interview process accordingly.

[0109] The recruitment support robot can estimate the interviewer's emotions and track changes in those emotions based on the estimate. For example, if an interviewer is initially nervous but gradually relaxes, the robot can track that change. Similarly, if an interviewer is initially relaxed but gradually becomes nervous, the robot can track that change as well. Furthermore, it can adjust the interview process based on the interviewer's emotional changes. For instance, if an interviewer's emotions change abruptly, the robot can pause the interview to allow the interviewer to regain a stable emotional state. This allows the robot to provide a more appropriate interview environment by tracking changes in the interviewer's emotions and adjusting the interview process accordingly.

[0110] The recruitment support robot can analyze an interviewer's past interview history and optimize the interview process without having to estimate the interviewer's emotions. For example, it can prioritize suggesting question patterns that the interviewer has preferred to use in the past. It can also incorporate interview techniques that the interviewer has found effective in the past. Furthermore, it can adjust the interview process based on the interviewer's past interview history. For example, if the interviewer has disliked long interviews in the past, the interview time can be shortened. In this way, by analyzing the interviewer's past interview history and optimizing the interview process, more effective interviews can be achieved.

[0111] The recruitment support robot can optimize the interview process by considering the interviewer's geographical location without having to estimate the interviewer's emotions. For example, if the interviewer is in a specific region, it will prioritize providing information relevant to that region. It can also suggest the most suitable interview method based on the interviewer's current location if they are on the move. Furthermore, it can adjust the interview process based on the interviewer's geographical location. For instance, if the interviewer is on the move, it can pause the interview and wait until the interviewer arrives at a stable location. This allows for more effective interviews by optimizing the interview process based on the interviewer's geographical location.

[0112] The recruitment support robot can analyze the interviewer's social media activity and optimize the interview process without having to estimate the interviewer's emotions. For example, it can adjust the interview process based on information the interviewer shares on social media. It can also understand the interviewer's interests and concerns from their social media activity and adjust the interview process accordingly. Furthermore, it can optimize the interview process based on the interviewer's social media activity. For example, if the interviewer is interested in a particular topic, it can prioritize suggesting questions related to that topic. By analyzing the interviewer's social media activity and optimizing the interview process, it is possible to achieve more effective interviews.

[0113] The recruitment support robot can optimize the interview process by referencing the interviewer's past feedback history without having to estimate the interviewer's emotions. For example, it can adjust the interview process based on the feedback the interviewer has provided in the past. It can also incorporate effective interview techniques from the interviewer's past feedback history. Furthermore, it can optimize the interview process based on the interviewer's past feedback history. For example, it can prioritize suggesting feedback methods that the interviewer has preferred to use in the past. By referencing the interviewer's past feedback history and optimizing the interview process, it can achieve more effective interviews.

[0114] The recruitment support robot can optimize the interview process by referencing the interviewer's relevant literature without having to estimate the interviewer's emotions. For example, it can adjust the interview process based on papers and articles the interviewer has previously written. It can also understand the interviewer's expertise and interests from their relevant literature and adjust the interview process accordingly. Furthermore, it can optimize the interview process based on the interviewer's relevant literature. For example, if the interviewer is knowledgeable in a particular field, it can prioritize suggesting questions related to that field. In this way, by referencing the interviewer's relevant literature and optimizing the interview process, a more effective interview can be achieved.

[0115] The following briefly describes the processing flow for example form 2.

[0116] Step 1: The acquisition unit acquires emotion estimation information, which is information used to estimate the interviewer's emotions. Emotion estimation information includes, for example, the interviewer's facial expression data, voice data, and text data. For example, the acquisition unit can capture the interviewer's facial expression with a camera and acquire facial expression data. The acquisition unit can also record the interviewer's voice tone with a microphone and acquire voice data. Furthermore, the acquisition unit can acquire the interviewer's word choices as text data. For example, the acquisition unit converts the interviewer's statements into text data in real time and acquires it as emotion estimation information. Step 2: The emotion estimation unit estimates the interviewer's emotions based on the emotion estimation information acquired by the acquisition unit. The emotion estimation unit can, for example, use a machine learning algorithm to analyze the acquired facial expression data and estimate the interviewer's emotions. The emotion estimation unit can also analyze audio data and estimate emotions from the interviewer's tone of voice. Furthermore, the emotion estimation unit can analyze text data and estimate emotions from the interviewer's choice of words. For example, the emotion estimation unit can use a machine learning algorithm to analyze the content of the interviewer's statements and estimate their emotions. Step 3: The feedback collection unit collects the emotions estimated by the emotion estimation unit and shares them with other interviewers and the recruitment team. The feedback collection unit can, for example, store the estimated emotions in a database and make them accessible to other interviewers and the recruitment team. The feedback collection unit can also share the estimated emotions in real time. For example, the feedback collection unit can notify other interviewers and the recruitment team of the estimated emotions in real time. Step 4: The Advice-Providing Department provides question suggestions and communication advice based on the sentiments gathered by the Feedback Collection Department. For example, the Advice-Providing Department may suggest questions that are relevant to the progress of the interview. The Advice-Providing Department may also provide communication advice to ease the atmosphere of the interview. For example, if the interviewer is nervous, the Advice-Providing Department may offer advice on how to relax.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] For example, the acquisition unit can acquire facial expression data and voice data of the interviewer using the camera 42 and microphone 38B of the smart device 14. The emotion estimation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and analyzes the acquired data to estimate the interviewer's emotions. The feedback collection unit collects the emotions estimated by the identification processing unit 290 of the data processing device 12 and stores them in the database 24. The advice provision unit is implemented, for example, by the control unit 46A of the smart device 14, and provides suggestions for questions and communication advice according to the progress of the interview. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0121] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] For example, the acquisition unit can acquire facial expression data and voice data of the interviewer using the camera 42 and microphone 238 of the smart glasses 214. The emotion estimation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and analyzes the acquired data to estimate the interviewer's emotions. The feedback collection unit collects the emotions estimated by the identification processing unit 290 of the data processing device 12 and stores them in the database 24. The advice provision unit is implemented, for example, by the control unit 46A of the smart glasses 214, and provides suggestions for questions and communication advice according to the progress of the interview. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0137] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] For example, the acquisition unit can acquire facial expression data and voice data of the interviewer using the camera 42 and microphone 238 of the headset terminal 314. The emotion estimation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and analyzes the acquired data to estimate the interviewer's emotions. The feedback collection unit collects the emotions estimated by the identification processing unit 290 of the data processing device 12 and stores them in the database 24. The advice provision unit is implemented, for example, by the control unit 46A of the headset terminal 314, and provides suggestions for questions and communication advice according to the progress of the interview. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0153] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] For example, the acquisition unit can acquire facial expression data and voice data of the interviewer using the camera 42 and microphone 238 of the robot 414. The emotion estimation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and analyzes the acquired data to estimate the interviewer's emotions. The feedback collection unit collects the emotions estimated by the identification processing unit 290 of the data processing device 12 and stores them in the database 24. The advice provision unit is implemented, for example, by the control unit 46A of the robot 414, and provides suggestions for questions and communication advice according to the progress of the interview. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] (Note 1) An acquisition unit that acquires emotion estimation information, which is information used to estimate the emotions of the interviewer, An emotion estimation unit estimates the emotions of the interviewer based on the emotion estimation information acquired by the acquisition unit, A feedback collection unit collects and shares emotions estimated by the emotion estimation unit, The system includes an advice provision unit that provides suggested questions and communication advice based on the emotions collected by the aforementioned feedback collection unit. A system characterized by the following features. (Note 2) The company has an aptitude assessment department that evaluates candidates' suitability based on the interviewer's emotions and the dialogue with the candidate. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned feedback collection unit is The emotions estimated by the emotion estimation unit are shared with other interviewers and the recruitment team. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned advice-providing unit, We provide suggestions for interview questions and communication advice tailored to the progress of the interview. The system described in Appendix 1, characterized by the features described herein. (Note 5) The acquisition unit is, The system estimates the interviewer's emotions and adjusts the timing of acquiring emotion estimation information based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The acquisition unit is, Analyze the interviewer's past interview history and select the appropriate method for obtaining the information. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, When acquiring information for emotion estimation, filtering is performed based on the interviewer's current psychological state and the progress of the interview. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, The system estimates the interviewer's emotions and prioritizes the emotion estimation information to be obtained based on the estimated emotions of the interviewer. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, When acquiring information for emotion estimation, the system prioritizes acquiring highly relevant information by considering the interviewer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, When acquiring information for sentiment estimation, the interviewer's social media activity is analyzed to obtain relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 11) The emotion estimation unit, The system estimates the interviewer's emotions and adjusts the emotion estimation algorithm based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The emotion estimation unit, When estimating emotions, the system integrates the interviewer's facial expressions, tone of voice, word choice, and several other factors to estimate their feelings. The system described in Appendix 1, characterized by the features described herein. (Note 13) The emotion estimation unit, When estimating emotions, referencing the interviewer's past emotional data improves the accuracy of the estimation. The system described in Appendix 1, characterized by the features described herein. (Note 14) The emotion estimation unit, The system estimates the interviewer's emotions and adjusts how the emotion estimation results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The emotion estimation unit, When estimating emotions, the interviewer's geographical and cultural background should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 16) The emotion estimation unit, When estimating emotions, referencing relevant literature from the interviewer can improve the accuracy of the estimation. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned feedback collection unit is We estimate the interviewer's emotions and adjust the feedback collection method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned feedback collection unit is When collecting feedback, refer to the interviewer's past feedback history to select the most suitable collection method. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned feedback collection unit is When collecting feedback, adjust the level of detail in the feedback based on the interviewer's current psychological state. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned feedback collection unit is The system estimates the interviewer's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned feedback collection unit is When collecting feedback, the geographical location of the interviewer will be taken into consideration to prioritize the collection of highly relevant feedback. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned feedback collection unit is When collecting feedback, analyze the interviewer's social media activity and gather relevant feedback. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned advice-providing unit, We estimate the interviewer's emotions and adjust the way we express advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned advice-providing unit, When providing advice, adjust the level of detail based on the progress of the interview. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned advice-providing unit, When providing advice, refer to the interviewer's past advice history to provide the most appropriate advice. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned advice-providing unit, Estimate the interviewer's emotions and prioritize advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned advice-providing unit, When providing advice, we take into account the interviewer's geographical location to provide the most appropriate advice. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned advice-providing unit, When providing advice, analyze the interviewer's social media activity and offer relevant advice. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned suitability evaluation unit is, The system estimates the interviewer's emotions and adjusts the candidate's suitability assessment method based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned suitability evaluation unit is, During aptitude assessments, the interviewer's past evaluation history is referenced to select the most suitable evaluation method. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned suitability evaluation unit is, During the aptitude assessment, the level of detail in the evaluation will be adjusted based on the interviewer's current psychological state. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned suitability evaluation unit is, The system estimates the interviewer's emotions and determines the priority of aptitude evaluations based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned suitability evaluation unit is, When evaluating aptitude, the most suitable evaluation method will be selected, taking into account the geographical location of the interviewer. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned suitability evaluation unit is, During the aptitude assessment, we analyze the interviewer's social media activity and provide relevant evaluations. The system described in Appendix 2, characterized by the features described herein. [Explanation of symbols]

[0189] 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. An acquisition unit that acquires emotion estimation information, which is information used to estimate the emotions of the interviewer, An emotion estimation unit estimates the emotions of the interviewer based on the emotion estimation information acquired by the acquisition unit, A feedback collection unit collects and shares emotions estimated by the emotion estimation unit, The system includes an advice provision unit that provides suggested questions and communication advice based on the emotions collected by the aforementioned feedback collection unit. A system characterized by the following features.

2. The system includes an aptitude assessment unit that evaluates the candidate's suitability based on the interviewer's emotions and the dialogue with the candidate. The system according to feature 1.

3. The aforementioned feedback collection unit is The emotions estimated by the emotion estimation unit are shared with other interviewers and the recruitment team. The system according to feature 1.

4. The aforementioned advice-providing unit, We provide suggestions for interview questions and communication advice tailored to the progress of the interview. The system according to feature 1.

5. The acquisition unit is, The system estimates the interviewer's emotions and adjusts the timing of acquiring emotion estimation information based on the estimated emotions of the interviewer. The system according to feature 1.

6. The acquisition unit is, The interviewer's past interview history is analyzed, and an appropriate method of obtaining the information is selected. The system according to feature 1.

7. The acquisition unit is, When acquiring information for emotion estimation, filtering is performed based on the interviewer's current psychological state and the progress of the interview. The system according to feature 1.

8. The acquisition unit is, The system estimates the interviewer's emotions and determines the priority of emotion estimation information to be obtained based on the estimated emotions of the interviewer. The system according to feature 1.

9. The acquisition unit is, When acquiring information for emotion estimation, the geographical location information of the interviewer is taken into consideration to prioritize the acquisition of highly relevant information. The system according to feature 1.

Images