System

Abstract

An object of a system according to an embodiment is to effectively practice interviews by utilizing AI and reduce tension and anxiety.SOLUTION: A system includes a generation unit, a training unit, a scoring unit, a regeneration unit, a repetition unit, and an evaluation unit. The generating unit generates an interviewer model in which specific elements are listed. The training unit performs training with the AI interviewer based on the model generated by the generating unit. The scoring unit automatically scores a result of the practice performed by the practice unit. The regeneration unit re-generates a model based on the result obtained by the scoring unit. The repeating unit repeatedly performs training based on the model generated by the regenerating unit. The evaluation unit evaluates facial expressions and clothing during the practice performed by the practice unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to reduce tension and anxiety during interview practice and to prepare effectively.

[0005] The system of the embodiment aims to use AI to effectively practice interviews and reduce tension and anxiety. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation unit, a practice unit, a scoring unit, a regeneration unit, a repetition unit, and an evaluation unit. The generation unit generates an interviewer model that lists specific elements. The practice unit practices with an AI interviewer based on the model generated by the generation unit. The scoring unit automatically scores the results of the practice conducted by the practice unit. The regeneration unit regenerates a model based on the results obtained by the scoring unit. The repetition unit conducts repeated practice based on the model generated by the regeneration unit. The evaluation unit evaluates facial expressions and clothing during practice conducted by the practice unit. [Effects of the Invention]

[0007] The system according to the embodiment utilizes AI to effectively practice for interviews and reduce tension and anxiety. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) An interview practice system according to an embodiment of the present invention uses an AI interviewer to solve problems encountered in various interview situations, such as university entrance exams, high school entrance exams, job hunting, career changes, and qualification acquisition. The interview practice system generates an interviewer model that combines general elements and categorized elements, allows users to practice with the AI ​​interviewer, and clarifies the user's "weaknesses" and "strengths" using automatic AI scoring. The system then regenerates a model that incorporates the user's "weaknesses" and allows the user to practice repeatedly. The system also uses the image recognition technology of the generating AI to evaluate facial expressions, clothing, and other aspects of the interview, providing support for areas for improvement. For example, the interview practice system generates a model that includes questions and evaluation criteria for categories such as entrance exams, job hunting, and qualifications. Next, the user practices interactively with the AI ​​interviewer, providing an environment that closely resembles a real interview. Furthermore, the AI ​​analyzes the user's responses, facial expressions, tone of voice, and other factors to evaluate the user's strengths and weaknesses. The system then regenerates a model to focus on the user's weak areas and allows the user to practice repeatedly. Furthermore, the system uses the image recognition technology of the generating AI to evaluate facial expressions, clothing, and other aspects of the interview, providing support for areas for improvement. This allows the interview practice system to solve problems such as becoming too nervous to speak, not being able to answer quickly, not being able to speak well, and being anxious about what questions will be asked. Furthermore, by offering subscriptions, users can practice repeatedly and be fully prepared for the interview. This allows the interview practice system to efficiently enable users to practice for interviews, overcome weak areas, and strengthen strong areas. For example, this allows the system to solve problems such as becoming too nervous to speak, not being able to answer quickly, not being able to speak well, and being anxious about what questions will be asked. Furthermore, by offering subscriptions, users can practice repeatedly and be fully prepared for the interview.

[0029] An interview practice system according to an embodiment includes a generation unit, a practice unit, a scoring unit, a regeneration unit, a repeat unit, and an evaluation unit. The generation unit generates an interviewer model that lists specific elements. For example, the generation unit generates a model including questions and evaluation criteria according to categories such as entrance exams, employment, and qualifications. The practice unit conducts practice with an AI interviewer based on the model generated by the generation unit. For example, the practice unit conducts practice with the AI ​​interviewer in an interactive format. The scoring unit automatically scores the results of the practice conducted by the practice unit. For example, the scoring unit analyzes the content of the user's answers, facial expressions, tone of voice, etc., and evaluates the user's strengths and weaknesses. The regeneration unit regenerates a model based on the results obtained by the scoring unit. For example, the regeneration unit regenerates a model to focus practice on the user's weak areas. The repeat unit conducts repeated practice based on the model generated by the regeneration unit. For example, the repeat unit enables the user to conduct repeated practice through subscription deployment. The evaluation unit evaluates the facial expressions and clothing used during the practice conducted by the practice unit. For example, the evaluation unit analyzes the user's facial expressions and clothing and provides advice on how to make a good impression during an interview. This allows the interview practice system according to the embodiment to efficiently conduct interview practice for the user, enabling the user to overcome weak areas and strengthen strong areas.

[0030] The generation unit can generate models including questions and evaluation criteria according to categories such as entrance exams, employment, and qualifications. The generation unit generates models including questions and evaluation criteria according to categories such as entrance exams, employment, and qualifications. For example, in the case of university entrance exams, the generation unit generates a model including questions about academic ability and reasons for applying. In addition, in the case of employment, the generation unit can also generate a model including questions about work experience and skills. Furthermore, in the case of qualification acquisition, the generation unit can also generate a model including questions about the exam content and practical experience. In this way, by generating models including questions and evaluation criteria according to categories, more appropriate interview practice is possible.

[0031] The practice unit can conduct practice in an interactive format with an AI interviewer. For example, the practice unit conducts practice in an interactive format with an AI interviewer. For example, the practice unit conducts practice in a format where the AI ​​interviewer asks questions and the user answers them. The practice unit can also conduct practice in a simulation format. For example, the practice unit conducts practice in a format where an actual interview scenario is simulated and the user answers based on that scenario. Furthermore, the practice unit has a function to adjust the progress of the practice so that the user can proceed with the practice at their own pace. As a result, practicing in an interactive format makes it possible to practice in an environment that is closer to an actual interview.

[0032] The scoring unit can analyze the content of the user's answers, facial expressions, and tone of voice to evaluate the user's strengths and weaknesses. The scoring unit, for example, analyzes the content of the user's answers to evaluate the user's strengths and weaknesses. For example, the scoring unit evaluates the accuracy and logic of the user's answers. The scoring unit can also analyze the user's facial expressions to evaluate the user's level of nervousness or confidence. For example, the scoring unit can analyze changes in the user's facial expressions to evaluate whether the user is nervous. The scoring unit can also analyze the user's tone of voice to evaluate the user's emotional state. For example, the scoring unit can analyze changes in the user's tone of voice to evaluate whether the user is speaking with confidence. In this way, by analyzing the content of the user's answers, facial expressions, and tone of voice, it is possible to clarify the user's strengths and weaknesses.

[0033] The regeneration unit can regenerate a model for focused practice in areas where the user is weak. The regeneration unit regenerates, for example, a model for focused practice in areas where the user is weak. For example, if the user is unable to answer quickly, the regeneration unit provides practice to improve that point. Furthermore, if the user is nervous and unable to speak, the regeneration unit can also provide practice to improve that point. Furthermore, if the user is unable to speak well, the regeneration unit can also provide practice to improve that point. In this way, by focused practice in areas where the user is weak, it is possible to overcome the weak areas.

[0034] The evaluation unit can analyze the user's facial expression and clothing and provide advice for making a good impression at the interview. The evaluation unit, for example, analyzes the user's facial expression and provides advice for making a good impression at the interview. For example, if the user is nervous, the evaluation unit can suggest ways to relax. The evaluation unit can also analyze the user's clothing and suggest appropriate clothing for the interview. For example, if the user's clothing is too casual, the evaluation unit can suggest more formal clothing. The evaluation unit can also comprehensively evaluate the user's facial expression and clothing and provide advice for making a good impression at the interview. In this way, by analyzing the user's facial expression and clothing, advice for making a good impression at the interview can be provided.

[0035] The repeating unit can enable a user to repeatedly practice using a subscription service. The repeating unit can enable a user to repeatedly practice using a subscription service. For example, the repeating unit can provide a service that allows a user to practice unlimitedly by paying a monthly fee. The repeating unit can also provide a service that allows a user to periodically receive new practice content. Furthermore, the repeating unit has a function to adjust the progress of practice so that the user can proceed with the practice at their own pace. As a result, the subscription service can enable a user to repeatedly practice and thoroughly prepare for an interview.

[0036] The generation unit can customize the model during generation by taking into account the user's past interview experience. For example, the generation unit customizes the model during generation by taking into account the user's past interview experience. For example, the generation unit generates a model including similar questions based on the content of questions asked in interviews the user has taken in the past. The generation unit can also generate a model that focuses on questions that the user has had difficulty with in the past. Furthermore, the generation unit can generate a model that includes questions that the user has had difficulty with in the past. This allows for more effective interview practice by taking into account the user's past interview experience.

[0037] The generation unit can optimize the question content according to the user's goals and desired employers at the time of generation. The generation unit, for example, optimizes the question content according to the user's goals and desired employers at the time of generation. For example, the generation unit generates a model including questions that frequently appear in interviews at companies the user is applying to. The generation unit can also generate a model including questions that frequently appear in qualification exams the user is aiming for. Furthermore, the generation unit can generate a model including questions that frequently appear in interviews at universities the user is applying to. This enables more effective interview practice by optimizing the question content according to the user's goals and desired employers.

[0038] The generation unit can apply different generation algorithms depending on the user's learning style during generation. For example, the generation unit applies different generation algorithms depending on the user's learning style during generation. For example, if the user prefers visual learning, the generation unit can generate a model including visual aids. Also, if the user prefers auditory learning, the generation unit can generate a model including audio guides. Furthermore, if the user prefers practical learning, the generation unit can generate a model including role-playing style questions. This allows for more effective interview practice by applying a generation algorithm depending on the user's learning style.

[0039] The generation unit can generate a model including region-specific questions by taking into account the user's geographical location information at the time of generation. For example, the generation unit generates a model including region-specific questions by taking into account the user's geographical location information at the time of generation. For example, the generation unit generates a model including questions related to the culture and customs of the region where the user lives. The generation unit can also generate a model including questions related to the location of a company the user is applying to. Furthermore, the generation unit can generate a model including questions related to the location of the university the user is applying to. In this way, a model including region-specific questions can be generated by taking into account the user's geographical location information.

[0040] The generation unit can analyze the user's social media activity at the time of generation and generate a model including related questions. For example, the generation unit analyzes the user's social media activity at the time of generation and generates a model including related questions. For example, the generation unit generates a model including questions related to topics in which the user has shown interest on social media. The generation unit can also generate a model including questions related to companies the user follows on social media. Furthermore, the generation unit can generate a model including questions related to events the user has participated in on social media. In this way, a model including related questions can be generated by analyzing the user's social media activity.

[0041] The generation unit can customize the model by reflecting the user's past feedback at the time of generation. For example, the generation unit customizes the model by reflecting the user's past feedback at the time of generation. For example, the generation unit generates a model including areas for improvement based on feedback the user has received in the past. The generation unit can also generate a model that strengthens areas of strength based on positive feedback the user has received in the past. Furthermore, the generation unit can also generate a model that overcomes areas of weakness based on negative feedback the user has received in the past. This allows for more effective interview practice by reflecting the user's past feedback.

[0042] The practice unit can optimize the practice content by referring to the user's past practice results during practice. The practice unit, for example, optimizes the practice content by referring to the user's past practice results during practice. For example, the practice unit provides practice that focuses on questions that the user found difficult in the past. The practice unit can also provide practice that includes questions that the user found easy in the past. Furthermore, the practice unit can provide an optimal practice plan based on the user's past practice results. This allows for more effective interview practice by referring to the user's past practice results.

[0043] The practice unit can adjust the difficulty of the practice according to the user's current skill level during practice. For example, the practice unit adjusts the difficulty of the practice according to the user's current skill level during practice. For example, if the user is a beginner, the practice unit can provide practice including basic questions. If the user is an intermediate learner, the practice unit can also provide practice including applied questions. Furthermore, if the user is an advanced learner, the practice unit can also provide practice including difficult questions. This allows for more effective interview practice by adjusting the difficulty of the practice according to the user's current skill level.

[0044] The practice unit can improve the practice method by reflecting the user's feedback during practice. For example, the practice unit improves the practice method by reflecting the user's feedback during practice. For example, the practice unit adjusts the content of the next practice based on the feedback provided by the user after practice. The practice unit can also improve the practice method based on problems the user felt during practice. Furthermore, the practice unit can adjust the way the practice proceeds based on the feedback the user received after practice. In this way, by reflecting the user's feedback, more effective interview practice is possible.

[0045] The practice unit can provide practice including region-specific scenarios by taking into account the user's geographical location information during practice. For example, the practice unit provides practice including region-specific scenarios by taking into account the user's geographical location information during practice. For example, the practice unit provides practice including scenarios related to the culture and customs of the region in which the user lives. The practice unit can also provide practice including scenarios related to the location of a company the user is applying to. Furthermore, the practice unit can provide practice including scenarios related to the location of a university the user is taking an entrance exam for. This makes it possible to provide practice including region-specific scenarios by taking into account the user's geographical location information.

[0046] The practice unit can analyze the user's social media activity during practice and provide practice including related scenarios. For example, the practice unit can analyze the user's social media activity during practice and provide practice including related scenarios. For example, the practice unit can provide practice including scenarios related to topics in which the user has shown interest on social media. The practice unit can also provide practice including scenarios related to companies the user follows on social media. Furthermore, the practice unit can provide practice including scenarios related to events the user has participated in on social media. In this way, by analyzing the user's social media activity, practice including related scenarios is possible.

[0047] The practice unit can customize the practice content by reflecting the user's past feedback during practice. For example, the practice unit customizes the practice content by reflecting the user's past feedback during practice. For example, the practice unit adjusts the practice content based on feedback provided by the user in the past. The practice unit can also improve the practice content based on problems the user has felt in the past. Furthermore, the practice unit can adjust the way the practice progresses based on feedback the user has received in the past. In this way, by reflecting the user's past feedback, more effective interview practice is possible.

[0048] The scoring unit can improve the accuracy of scoring by referring to the user's past scoring results when scoring. For example, the scoring unit can improve the accuracy of scoring by referring to the user's past scoring results when scoring. For example, the scoring unit can adjust the scoring criteria based on the user's past scoring results. The scoring unit can also tighten the scoring criteria for questions that the user was weak at in the past. Furthermore, the scoring unit can loosen the scoring criteria for questions that the user was strong at in the past. In this way, by referring to the user's past scoring results, more accurate scoring is possible.

[0049] The scoring unit can apply different scoring algorithms depending on the content of the user's answer when scoring. For example, the scoring unit applies different scoring algorithms depending on the content of the user's answer when scoring. For example, if the user gives a detailed answer, the scoring unit applies a detailed scoring algorithm. Also, if the user gives a concise answer, the scoring unit can apply a concise scoring algorithm. Furthermore, if the user gives an ambiguous answer, the scoring unit can apply a scoring algorithm that evaluates the ambiguity. In this way, by applying a scoring algorithm depending on the content of the user's answer, more appropriate scoring is possible.

[0050] The scoring unit can improve the scoring criteria by reflecting user feedback during scoring. For example, the scoring unit improves the scoring criteria by reflecting user feedback during scoring. For example, the scoring unit adjusts the next scoring criteria based on feedback provided by the user after scoring. The scoring unit can also improve the scoring criteria based on problems the user feels during scoring. Furthermore, the scoring unit can adjust the scoring progress method based on feedback obtained by the user after scoring. In this way, more appropriate scoring is possible by reflecting user feedback.

[0051] The scoring unit can perform scoring including region-specific criteria by taking into account the user's geographical location information when scoring. For example, the scoring unit can perform scoring including region-specific criteria by taking into account the user's geographical location information when scoring. For example, the scoring unit sets scoring criteria based on the culture and customs of the region in which the user lives. The scoring unit can also set scoring criteria related to the location of the company the user is applying to. Furthermore, the scoring unit can set scoring criteria related to the location of the university the user is taking the exam for. In this way, by taking into account the user's geographical location information, scoring including region-specific criteria is possible.

[0052] The scoring unit can analyze the user's social media activity during scoring and provide scoring including related criteria. For example, the scoring unit can analyze the user's social media activity during scoring and provide scoring including related criteria. For example, the scoring unit can set scoring criteria related to topics in which the user has shown interest on social media. The scoring unit can also set scoring criteria related to companies the user follows on social media. Furthermore, the scoring unit can set scoring criteria related to events the user has participated in on social media. This makes it possible to provide scoring including related criteria by analyzing the user's social media activity.

[0053] The scoring unit can customize the scoring criteria by reflecting the user's past feedback when scoring. For example, the scoring unit customizes the scoring criteria by reflecting the user's past feedback when scoring. For example, the scoring unit adjusts the scoring criteria based on feedback provided by the user in the past. The scoring unit can also improve the scoring criteria based on problems the user has felt in the past. Furthermore, the scoring unit can adjust the scoring progress method based on feedback the user has received in the past. In this way, more appropriate scoring is possible by reflecting the user's past feedback.

[0054] The regeneration unit can optimize the regeneration content by referring to the user's past practice results during regeneration. The regeneration unit, for example, optimizes the regeneration content by referring to the user's past practice results during regeneration. For example, the regeneration unit performs regeneration that focuses on questions that the user had difficulty with in the past. The regeneration unit can also perform regeneration that includes questions that the user had difficulty with in the past. Furthermore, the regeneration unit can provide an optimal regeneration plan based on the user's past practice results. This enables more effective regeneration by referring to the user's past practice results.

[0055] The regeneration unit can adjust the difficulty of regeneration in accordance with the user's current skill level during regeneration. For example, the regeneration unit adjusts the difficulty of regeneration in accordance with the user's current skill level during regeneration. For example, if the user is a beginner, the regeneration unit performs regeneration including basic questions. Furthermore, if the user is an intermediate user, the regeneration unit can also perform regeneration including applied questions. Furthermore, if the user is an advanced user, the regeneration unit can also perform regeneration including questions with a high level of difficulty. In this way, by adjusting the difficulty of regeneration in accordance with the user's current skill level, more effective regeneration is possible.

[0056] The regeneration unit can improve the regeneration method by reflecting user feedback during regeneration. For example, the regeneration unit improves the regeneration method by reflecting user feedback during regeneration. For example, the regeneration unit adjusts the content of the next regeneration based on feedback provided by the user after regeneration. The regeneration unit can also improve the regeneration method based on problems the user feels during regeneration. Furthermore, the regeneration unit can adjust the method of proceeding with regeneration based on feedback obtained by the user after regeneration. In this way, more effective regeneration is possible by reflecting user feedback.

[0057] The regeneration unit can perform regeneration including a region-specific scenario by taking into account the user's geographical location information during regeneration. For example, the regeneration unit performs regeneration including a region-specific scenario by taking into account the user's geographical location information during regeneration. For example, the regeneration unit performs regeneration including a scenario related to the culture and customs of the region where the user lives. The regeneration unit can also perform regeneration including a scenario related to the location of a company the user is applying to. Furthermore, the regeneration unit can perform regeneration including a scenario related to the location of a university the user is applying to. In this way, regeneration including a region-specific scenario is possible by taking into account the user's geographical location information.

[0058] The regeneration unit can analyze the user's social media activity during regeneration and perform regeneration including related scenarios. For example, the regeneration unit analyzes the user's social media activity during regeneration and performs regeneration including related scenarios. For example, the regeneration unit performs regeneration including scenarios related to topics in which the user has shown interest on social media. The regeneration unit can also perform regeneration including scenarios related to companies the user follows on social media. Furthermore, the regeneration unit can also perform regeneration including scenarios related to events the user has participated in on social media. This makes it possible to perform regeneration including related scenarios by analyzing the user's social media activity.

[0059] The regeneration unit can customize the regenerated content by reflecting the user's past feedback during regeneration. The regeneration unit, for example, customizes the regenerated content by reflecting the user's past feedback during regeneration. For example, the regeneration unit adjusts the regenerated content based on feedback provided by the user in the past. The regeneration unit can also improve the regenerated content based on problems the user has felt in the past. Furthermore, the regeneration unit can adjust the method of proceeding with the regeneration based on feedback the user has received in the past. This enables more effective regeneration by reflecting the user's past feedback.

[0060] The repetition unit can optimize the practice content by referring to the user's past practice results during repeated practice. For example, the repetition unit optimizes the practice content by referring to the user's past practice results during repeated practice. For example, the repetition unit provides repeated practice that focuses on questions that the user found difficult in the past. The repetition unit can also provide repeated practice that includes questions that the user found easy in the past. Furthermore, the repetition unit can provide an optimal repeated practice plan based on the user's past practice results. This allows for more effective repeated practice by referring to the user's past practice results.

[0061] The repetition unit can adjust the difficulty of the practice according to the user's current skill level during repeated practice. For example, the repetition unit adjusts the difficulty of the practice according to the user's current skill level during repeated practice. For example, if the user is a beginner, the repetition unit can provide repeated practice including basic questions. If the user is an intermediate learner, the repetition unit can also provide repeated practice including applied questions. Furthermore, if the user is an advanced learner, the repetition unit can also provide repeated practice including difficult questions. This allows for more effective repeated practice by adjusting the difficulty of the practice according to the user's current skill level.

[0062] The repetition unit can improve the practice method by reflecting the user's feedback during repeated practice. For example, the repetition unit improves the practice method by reflecting the user's feedback during repeated practice. For example, the repetition unit adjusts the content of the next practice based on the feedback provided by the user after repeated practice. The repetition unit can also improve the practice method based on problems the user feels during repeated practice. Furthermore, the repetition unit can adjust the way the practice progresses based on the feedback the user receives after repeated practice. In this way, more effective repeated practice is possible by reflecting the user's feedback.

[0063] The repetition unit can provide practice including region-specific scenarios during repeated practice by taking into account the user's geographical location information. For example, the repetition unit provides practice including region-specific scenarios by taking into account the user's geographical location information during repeated practice. For example, the repetition unit provides practice including scenarios related to the culture and customs of the region in which the user lives. The repetition unit can also provide practice including scenarios related to the location of a company the user is applying to. Furthermore, the repetition unit can provide practice including scenarios related to the location of a university the user is applying to. In this way, practice including region-specific scenarios is possible by taking into account the user's geographical location information.

[0064] The repetition unit can analyze the user's social media activity during repeated practice and provide practice including related scenarios. For example, the repetition unit can analyze the user's social media activity during repeated practice and provide practice including related scenarios. For example, the repetition unit can provide practice including scenarios related to topics in which the user has shown interest on social media. The repetition unit can also provide practice including scenarios related to companies the user follows on social media. Furthermore, the repetition unit can provide practice including scenarios related to events the user has participated in on social media. In this way, practice including related scenarios can be provided by analyzing the user's social media activity.

[0065] The repetition unit can customize the practice content by reflecting the user's past feedback during repeated practice. The repetition unit, for example, customizes the practice content by reflecting the user's past feedback during repeated practice. For example, the repetition unit adjusts the practice content based on feedback provided by the user in the past. The repetition unit can also improve the practice content based on problems the user has felt in the past. Furthermore, the repetition unit can adjust the way the practice progresses based on feedback the user has received in the past. This allows for more effective repeated practice by reflecting the user's past feedback.

[0066] The evaluation unit can improve the accuracy of the evaluation by referring to the user's past evaluation results during evaluation. The evaluation unit can improve the accuracy of the evaluation by referring to the user's past evaluation results during evaluation, for example. For example, the evaluation unit can adjust the evaluation criteria based on the evaluation results obtained by the user in the past. The evaluation unit can also tighten the evaluation criteria for questions that the user was weak at in the past. Furthermore, the evaluation unit can loosen the evaluation criteria for questions that the user was strong at in the past. In this way, by referring to the user's past evaluation results, more accurate evaluation is possible.

[0067] The evaluation unit can apply different evaluation algorithms depending on the user's facial expression and clothing during evaluation. The evaluation unit, for example, applies different evaluation algorithms depending on the user's facial expression and clothing during evaluation. For example, the evaluation unit applies an algorithm that gives a positive evaluation when the user is smiling. The evaluation unit can also apply an evaluation algorithm that gives a good impression when the user is appropriately dressed. Furthermore, the evaluation unit can also apply an evaluation algorithm that makes the user feel relaxed when the user is nervous. In this way, applying an evaluation algorithm depending on the user's facial expression and clothing enables a more appropriate evaluation.

[0068] The evaluation unit can improve the evaluation criteria by reflecting user feedback during evaluation. For example, the evaluation unit improves the evaluation criteria by reflecting user feedback during evaluation. For example, the evaluation unit adjusts the next evaluation criteria based on feedback provided by the user after the evaluation. The evaluation unit can also improve the evaluation criteria based on problems the user felt during the evaluation. Furthermore, the evaluation unit can adjust the method of proceeding with the evaluation based on feedback obtained by the user after the evaluation. In this way, by reflecting user feedback, more appropriate evaluation is possible.

[0069] The evaluation unit can perform evaluations that include region-specific criteria by taking into account the user's geographical location information during evaluation. For example, the evaluation unit can perform evaluations that include region-specific criteria by taking into account the user's geographical location information during evaluation. For example, the evaluation unit sets evaluation criteria based on the culture and customs of the region in which the user lives. The evaluation unit can also set evaluation criteria related to the location of the company the user is applying to. Furthermore, the evaluation unit can set evaluation criteria related to the location of the university the user is applying to. In this way, by taking into account the user's geographical location information, evaluations that include region-specific criteria are possible.

[0070] The evaluation unit can analyze the user's social media activity during the evaluation and perform an evaluation including related criteria. For example, the evaluation unit can analyze the user's social media activity during the evaluation and perform an evaluation including related criteria. For example, the evaluation unit can set evaluation criteria related to topics in which the user has shown interest on social media. The evaluation unit can also set evaluation criteria related to companies the user follows on social media. Furthermore, the evaluation unit can also set evaluation criteria related to events the user has participated in on social media. This makes it possible to perform an evaluation including related criteria by analyzing the user's social media activity.

[0071] The evaluation unit can customize the evaluation criteria by reflecting the user's past feedback during evaluation. The evaluation unit, for example, customizes the evaluation criteria by reflecting the user's past feedback during evaluation. For example, the evaluation unit adjusts the evaluation criteria based on feedback provided by the user in the past. The evaluation unit can also improve the evaluation criteria based on problems the user has felt in the past. Furthermore, the evaluation unit can adjust the method of proceeding with the evaluation based on feedback the user has received in the past. In this way, by reflecting the user's past feedback, more appropriate evaluation is possible.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The generation unit can customize the model taking into account the user's past interview experience. For example, the generation unit generates a model that includes similar questions based on the content of questions asked in interviews the user has taken in the past. The generation unit can also generate a model that focuses on questions that the user has had difficulty with in the past. Furthermore, the generation unit can also generate a model that includes questions that the user has had difficulty with in the past. This allows for more effective interview practice by taking into account the user's past interview experience.

[0074] The practice unit can adjust the difficulty of the practice depending on the user's current skill level. For example, if the user is a beginner, the practice unit can provide practice that includes basic questions. If the user is an intermediate learner, the practice unit can also provide practice that includes applied questions. Furthermore, if the user is an advanced learner, the practice unit can also provide practice that includes difficult questions. This allows for more effective interview practice by adjusting the difficulty of the practice depending on the user's current skill level.

[0075] The scoring unit can apply different scoring algorithms depending on the content of the user's answer. For example, if the user gives a detailed answer, the scoring unit can apply a detailed scoring algorithm. If the user gives a concise answer, the scoring unit can also apply a concise scoring algorithm. Furthermore, if the user gives an ambiguous answer, the scoring unit can also apply a scoring algorithm that evaluates the ambiguity. In this way, applying a scoring algorithm according to the content of the user's answer enables more appropriate scoring.

[0076] During regeneration, the regeneration unit can optimize the regeneration content by referring to the user's past practice results. For example, the regeneration unit performs regeneration that focuses on questions that the user found difficult in the past. The regeneration unit can also perform regeneration that includes questions that the user found easy in the past. Furthermore, the regeneration unit can provide an optimal regeneration plan based on the user's past practice results. This allows for more effective regeneration by referring to the user's past practice results.

[0077] When making an evaluation, the evaluation unit can apply different evaluation algorithms depending on the user's facial expression and clothing. For example, if the user is smiling, the evaluation unit applies an algorithm that gives a positive evaluation. In addition, if the user is appropriately dressed, the evaluation unit can also apply an evaluation algorithm that gives a good impression. Furthermore, if the user is nervous, the evaluation unit can also apply an evaluation algorithm that helps the user to relax. In this way, applying an evaluation algorithm that depends on the user's facial expression and clothing enables a more appropriate evaluation.

[0078] The processing flow of the first embodiment will be briefly explained below.

[0079] Step 1: The generator generates an interviewer model that lists specific elements. For example, the generator generates a model that includes questions and evaluation criteria according to categories such as entrance exams, employment, and qualifications. Step 2: The practice unit practices with an AI interviewer based on the model generated by the generation unit. For example, the practice unit practices with the AI ​​interviewer in an interactive format. Step 3: The scoring unit automatically scores the practice results performed by the practice unit. For example, the scoring unit analyzes the content of the user's answers, facial expressions, tone of voice, etc., and evaluates areas of strength and weakness. Step 4: The regeneration unit regenerates a model based on the results obtained by the scoring unit. For example, the regeneration unit regenerates a model to focus on practicing areas where the user is weak. Step 5: The iteration unit performs iterative training based on the model generated by the regeneration unit. For example, the iteration unit allows the user to perform iterative training through subscription deployment. Step 6: The evaluation unit evaluates the facial expressions and clothing used during the practice session. For example, the evaluation unit analyzes the user's facial expressions and clothing and provides advice on how to make a good impression during an interview.

[0080] (Example 2) An interview practice system according to an embodiment of the present invention uses an AI interviewer to solve problems encountered in various interview situations, such as university entrance exams, high school entrance exams, job hunting, career changes, and qualification acquisition. The interview practice system generates an interviewer model that combines general elements and categorized elements, allows users to practice with the AI ​​interviewer, and clarifies the user's "weaknesses" and "strengths" using automatic AI scoring. The system then regenerates a model that incorporates the user's "weaknesses" and allows the user to practice repeatedly. The system also uses the image recognition technology of the generating AI to evaluate facial expressions, clothing, and other aspects of the interview, providing support for areas for improvement. For example, the interview practice system generates a model that includes questions and evaluation criteria for categories such as entrance exams, job hunting, and qualifications. Next, the user practices interactively with the AI ​​interviewer, providing an environment that closely resembles a real interview. Furthermore, the AI ​​analyzes the user's responses, facial expressions, tone of voice, and other factors to evaluate the user's strengths and weaknesses. The system then regenerates a model to focus on the user's weak areas and allows the user to practice repeatedly. Furthermore, the system uses the image recognition technology of the generating AI to evaluate facial expressions, clothing, and other aspects of the interview, providing support for areas for improvement. This allows the interview practice system to solve problems such as becoming too nervous to speak, not being able to answer quickly, not being able to speak well, and being anxious about what questions will be asked. Furthermore, by offering subscriptions, users can practice repeatedly and be fully prepared for the interview. This allows the interview practice system to efficiently enable users to practice for interviews, overcome weak areas, and strengthen strong areas. For example, this allows the system to solve problems such as becoming too nervous to speak, not being able to answer quickly, not being able to speak well, and being anxious about what questions will be asked. Furthermore, by offering subscriptions, users can practice repeatedly and be fully prepared for the interview.

[0081] An interview practice system according to an embodiment includes a generation unit, a practice unit, a scoring unit, a regeneration unit, a repeat unit, and an evaluation unit. The generation unit generates an interviewer model that lists specific elements. For example, the generation unit generates a model including questions and evaluation criteria according to categories such as entrance exams, employment, and qualifications. The practice unit conducts practice with an AI interviewer based on the model generated by the generation unit. For example, the practice unit conducts practice with the AI ​​interviewer in an interactive format. The scoring unit automatically scores the results of the practice conducted by the practice unit. For example, the scoring unit analyzes the content of the user's answers, facial expressions, tone of voice, etc., and evaluates the user's strengths and weaknesses. The regeneration unit regenerates a model based on the results obtained by the scoring unit. For example, the regeneration unit regenerates a model to focus practice on the user's weak areas. The repeat unit conducts repeated practice based on the model generated by the regeneration unit. For example, the repeat unit enables the user to conduct repeated practice through subscription deployment. The evaluation unit evaluates the facial expressions and clothing used during the practice conducted by the practice unit. For example, the evaluation unit analyzes the user's facial expressions and clothing and provides advice on how to make a good impression during an interview. This allows the interview practice system according to the embodiment to efficiently conduct interview practice for the user, enabling the user to overcome weak areas and strengthen strong areas.

[0082] The generation unit can generate models including questions and evaluation criteria according to categories such as entrance exams, employment, and qualifications. The generation unit generates models including questions and evaluation criteria according to categories such as entrance exams, employment, and qualifications. For example, in the case of university entrance exams, the generation unit generates a model including questions about academic ability and reasons for applying. In addition, in the case of employment, the generation unit can also generate a model including questions about work experience and skills. Furthermore, in the case of qualification acquisition, the generation unit can also generate a model including questions about the exam content and practical experience. In this way, by generating models including questions and evaluation criteria according to categories, more appropriate interview practice is possible.

[0083] The practice unit can conduct practice in an interactive format with an AI interviewer. For example, the practice unit conducts practice in an interactive format with an AI interviewer. For example, the practice unit conducts practice in a format where the AI ​​interviewer asks questions and the user answers them. The practice unit can also conduct practice in a simulation format. For example, the practice unit conducts practice in a format where an actual interview scenario is simulated and the user answers based on that scenario. Furthermore, the practice unit has a function to adjust the progress of the practice so that the user can proceed with the practice at their own pace. As a result, practicing in an interactive format makes it possible to practice in an environment that is closer to an actual interview.

[0084] The scoring unit can analyze the content of the user's answers, facial expressions, and tone of voice to evaluate the user's strengths and weaknesses. The scoring unit, for example, analyzes the content of the user's answers to evaluate the user's strengths and weaknesses. For example, the scoring unit evaluates the accuracy and logic of the user's answers. The scoring unit can also analyze the user's facial expressions to evaluate the user's level of nervousness or confidence. For example, the scoring unit can analyze changes in the user's facial expressions to evaluate whether the user is nervous. The scoring unit can also analyze the user's tone of voice to evaluate the user's emotional state. For example, the scoring unit can analyze changes in the user's tone of voice to evaluate whether the user is speaking with confidence. In this way, by analyzing the content of the user's answers, facial expressions, and tone of voice, it is possible to clarify the user's strengths and weaknesses.

[0085] The regeneration unit can regenerate a model for focused practice in areas where the user is weak. The regeneration unit regenerates, for example, a model for focused practice in areas where the user is weak. For example, if the user is unable to answer quickly, the regeneration unit provides practice to improve that point. Furthermore, if the user is nervous and unable to speak, the regeneration unit can also provide practice to improve that point. Furthermore, if the user is unable to speak well, the regeneration unit can also provide practice to improve that point. In this way, by focused practice in areas where the user is weak, it is possible to overcome the weak areas.

[0086] The evaluation unit can analyze the user's facial expression and clothing and provide advice for making a good impression at the interview. The evaluation unit, for example, analyzes the user's facial expression and provides advice for making a good impression at the interview. For example, if the user is nervous, the evaluation unit can suggest ways to relax. The evaluation unit can also analyze the user's clothing and suggest appropriate clothing for the interview. For example, if the user's clothing is too casual, the evaluation unit can suggest more formal clothing. The evaluation unit can also comprehensively evaluate the user's facial expression and clothing and provide advice for making a good impression at the interview. In this way, by analyzing the user's facial expression and clothing, advice for making a good impression at the interview can be provided.

[0087] The repeating unit can enable a user to repeatedly practice using a subscription service. The repeating unit can enable a user to repeatedly practice using a subscription service. For example, the repeating unit can provide a service that allows a user to practice unlimitedly by paying a monthly fee. The repeating unit can also provide a service that allows a user to periodically receive new practice content. Furthermore, the repeating unit has a function to adjust the progress of practice so that the user can proceed with the practice at their own pace. As a result, the subscription service can enable a user to repeatedly practice and thoroughly prepare for an interview.

[0088] The generation unit can estimate the user's emotions and adjust the generation method of the interviewer model based on the estimated user emotions. For example, the generation unit can estimate the user's emotions and adjust the generation method of the interviewer model based on the estimated user emotions. For example, if the user is nervous, the generation unit can generate a model including questions that will help the user relax. Furthermore, if the user is confident, the generation unit can generate a model including difficult questions. Furthermore, if the user is anxious, the generation unit can generate a model including questions that will give the user a sense of security. This allows for more appropriate interview practice by adjusting the model generation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0089] The generation unit can customize the model during generation by taking into account the user's past interview experience. For example, the generation unit customizes the model during generation by taking into account the user's past interview experience. For example, the generation unit generates a model including similar questions based on the content of questions asked in interviews the user has taken in the past. The generation unit can also generate a model that focuses on questions that the user has had difficulty with in the past. Furthermore, the generation unit can generate a model that includes questions that the user has had difficulty with in the past. This allows for more effective interview practice by taking into account the user's past interview experience.

[0090] The generation unit can optimize the question content according to the user's goals and desired employers at the time of generation. The generation unit, for example, optimizes the question content according to the user's goals and desired employers at the time of generation. For example, the generation unit generates a model including questions that frequently appear in interviews at companies the user is applying to. The generation unit can also generate a model including questions that frequently appear in qualification exams the user is aiming for. Furthermore, the generation unit can generate a model including questions that frequently appear in interviews at universities the user is applying to. This enables more effective interview practice by optimizing the question content according to the user's goals and desired employers.

[0091] The generation unit can apply different generation algorithms depending on the user's learning style during generation. For example, the generation unit applies different generation algorithms depending on the user's learning style during generation. For example, if the user prefers visual learning, the generation unit can generate a model including visual aids. Also, if the user prefers auditory learning, the generation unit can generate a model including audio guides. Furthermore, if the user prefers practical learning, the generation unit can generate a model including role-playing style questions. This allows for more effective interview practice by applying a generation algorithm depending on the user's learning style.

[0092] The generation unit can estimate the user's emotions and determine the priority of models to be generated based on the estimated user emotions. The generation unit, for example, estimates the user's emotions and determines the priority of models to be generated based on the estimated user emotions. For example, if the user is nervous, the generation unit can generate a model that prioritizes questions that will help the user relax. Furthermore, if the user is confident, the generation unit can generate a model that prioritizes questions that are difficult. Furthermore, if the user is anxious, the generation unit can generate a model that prioritizes questions that will give the user a sense of security. This enables more effective interview practice by determining the priority of models based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] The generation unit can generate a model including region-specific questions by taking into account the user's geographical location information at the time of generation. For example, the generation unit generates a model including region-specific questions by taking into account the user's geographical location information at the time of generation. For example, the generation unit generates a model including questions related to the culture and customs of the region where the user lives. The generation unit can also generate a model including questions related to the location of a company the user is applying to. Furthermore, the generation unit can generate a model including questions related to the location of the university the user is applying to. In this way, a model including region-specific questions can be generated by taking into account the user's geographical location information.

[0094] The generation unit can analyze the user's social media activity at the time of generation and generate a model including related questions. For example, the generation unit analyzes the user's social media activity at the time of generation and generates a model including related questions. For example, the generation unit generates a model including questions related to topics in which the user has shown interest on social media. The generation unit can also generate a model including questions related to companies the user follows on social media. Furthermore, the generation unit can generate a model including questions related to events the user has participated in on social media. In this way, a model including related questions can be generated by analyzing the user's social media activity.

[0095] The generation unit can customize the model by reflecting the user's past feedback at the time of generation. For example, the generation unit customizes the model by reflecting the user's past feedback at the time of generation. For example, the generation unit generates a model including areas for improvement based on feedback the user has received in the past. The generation unit can also generate a model that strengthens areas of strength based on positive feedback the user has received in the past. Furthermore, the generation unit can also generate a model that overcomes areas of weakness based on negative feedback the user has received in the past. This allows for more effective interview practice by reflecting the user's past feedback.

[0096] The practice unit can estimate the user's emotions and adjust the way the practice proceeds based on the estimated user emotions. For example, the practice unit can estimate the user's emotions and adjust the way the practice proceeds based on the estimated user emotions. For example, if the user is nervous, the practice unit can provide a practice method that helps the user relax. Furthermore, if the user is confident, the practice unit can provide a more difficult practice method. Furthermore, if the user is feeling anxious, the practice unit can provide a practice method that gives the user a sense of security. This allows for more effective interview practice by adjusting the way the practice proceeds based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0097] The practice unit can optimize the practice content by referring to the user's past practice results during practice. The practice unit, for example, optimizes the practice content by referring to the user's past practice results during practice. For example, the practice unit provides practice that focuses on questions that the user found difficult in the past. The practice unit can also provide practice that includes questions that the user found easy in the past. Furthermore, the practice unit can provide an optimal practice plan based on the user's past practice results. This allows for more effective interview practice by referring to the user's past practice results.

[0098] The practice unit can adjust the difficulty of the practice according to the user's current skill level during practice. For example, the practice unit adjusts the difficulty of the practice according to the user's current skill level during practice. For example, if the user is a beginner, the practice unit can provide practice including basic questions. If the user is an intermediate learner, the practice unit can also provide practice including applied questions. Furthermore, if the user is an advanced learner, the practice unit can also provide practice including difficult questions. This allows for more effective interview practice by adjusting the difficulty of the practice according to the user's current skill level.

[0099] The practice unit can improve the practice method by reflecting the user's feedback during practice. For example, the practice unit improves the practice method by reflecting the user's feedback during practice. For example, the practice unit adjusts the content of the next practice based on the feedback provided by the user after practice. The practice unit can also improve the practice method based on problems the user felt during practice. Furthermore, the practice unit can adjust the way the practice proceeds based on the feedback the user received after practice. In this way, by reflecting the user's feedback, more effective interview practice is possible.

[0100] The practice unit can estimate the user's emotions and determine the priority of practice sessions based on the estimated user emotions. For example, the practice unit can estimate the user's emotions and determine the priority of practice sessions based on the estimated user emotions. For example, if the user is nervous, the practice unit can prioritize providing relaxing practice sessions. Furthermore, if the user is confident, the practice unit can prioritize providing more difficult practice sessions. Furthermore, if the user is anxious, the practice unit can prioritize providing reassuring practice sessions. This enables more effective interview practice sessions by prioritizing practice sessions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0101] The practice unit can provide practice including region-specific scenarios by taking into account the user's geographical location information during practice. For example, the practice unit provides practice including region-specific scenarios by taking into account the user's geographical location information during practice. For example, the practice unit provides practice including scenarios related to the culture and customs of the region in which the user lives. The practice unit can also provide practice including scenarios related to the location of a company the user is applying to. Furthermore, the practice unit can provide practice including scenarios related to the location of a university the user is taking an entrance exam for. This makes it possible to provide practice including region-specific scenarios by taking into account the user's geographical location information.

[0102] The practice unit can analyze the user's social media activity during practice and provide practice including related scenarios. For example, the practice unit can analyze the user's social media activity during practice and provide practice including related scenarios. For example, the practice unit can provide practice including scenarios related to topics in which the user has shown interest on social media. The practice unit can also provide practice including scenarios related to companies the user follows on social media. Furthermore, the practice unit can provide practice including scenarios related to events the user has participated in on social media. In this way, by analyzing the user's social media activity, practice including related scenarios is possible.

[0103] The practice unit can customize the practice content by reflecting the user's past feedback during practice. For example, the practice unit customizes the practice content by reflecting the user's past feedback during practice. For example, the practice unit adjusts the practice content based on feedback provided by the user in the past. The practice unit can also improve the practice content based on problems the user has felt in the past. Furthermore, the practice unit can adjust the way the practice progresses based on feedback the user has received in the past. In this way, by reflecting the user's past feedback, more effective interview practice is possible.

[0104] The scoring unit can estimate the user's emotions and adjust the scoring criteria based on the estimated user emotions. For example, the scoring unit can estimate the user's emotions and adjust the scoring criteria based on the estimated user emotions. For example, if the user is nervous, the scoring unit can set scoring criteria that help the user relax. If the user is confident, the scoring unit can also set stricter scoring criteria. Furthermore, if the user is anxious, the scoring unit can also set scoring criteria that give the user a sense of security. This allows for more appropriate scoring by adjusting the scoring criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0105] The scoring unit can improve the accuracy of scoring by referring to the user's past scoring results when scoring. For example, the scoring unit can improve the accuracy of scoring by referring to the user's past scoring results when scoring. For example, the scoring unit can adjust the scoring criteria based on the user's past scoring results. The scoring unit can also tighten the scoring criteria for questions that the user was weak at in the past. Furthermore, the scoring unit can loosen the scoring criteria for questions that the user was strong at in the past. In this way, by referring to the user's past scoring results, more accurate scoring is possible.

[0106] The scoring unit can apply different scoring algorithms depending on the content of the user's answer when scoring. For example, the scoring unit applies different scoring algorithms depending on the content of the user's answer when scoring. For example, if the user gives a detailed answer, the scoring unit applies a detailed scoring algorithm. Also, if the user gives a concise answer, the scoring unit can apply a concise scoring algorithm. Furthermore, if the user gives an ambiguous answer, the scoring unit can apply a scoring algorithm that evaluates the ambiguity. In this way, by applying a scoring algorithm depending on the content of the user's answer, more appropriate scoring is possible.

[0107] The scoring unit can improve the scoring criteria by reflecting user feedback during scoring. For example, the scoring unit improves the scoring criteria by reflecting user feedback during scoring. For example, the scoring unit adjusts the next scoring criteria based on feedback provided by the user after scoring. The scoring unit can also improve the scoring criteria based on problems the user feels during scoring. Furthermore, the scoring unit can adjust the scoring progress method based on feedback obtained by the user after scoring. In this way, more appropriate scoring is possible by reflecting user feedback.

[0108] The scoring unit can estimate the user's emotions and determine the priority of scoring based on the estimated user emotions. For example, the scoring unit can estimate the user's emotions and determine the priority of scoring based on the estimated user emotions. For example, if the user is nervous, the scoring unit can prioritize scoring that makes the user feel relaxed. Also, if the user is confident, the scoring unit can prioritize scoring that makes the user feel strict. Furthermore, if the user is anxious, the scoring unit can prioritize scoring that gives the user a sense of security. This enables more appropriate scoring by determining the priority of scoring based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0109] The scoring unit can perform scoring including region-specific criteria by taking into account the user's geographical location information when scoring. For example, the scoring unit can perform scoring including region-specific criteria by taking into account the user's geographical location information when scoring. For example, the scoring unit sets scoring criteria based on the culture and customs of the region in which the user lives. The scoring unit can also set scoring criteria related to the location of the company the user is applying to. Furthermore, the scoring unit can set scoring criteria related to the location of the university the user is taking the exam for. In this way, by taking into account the user's geographical location information, scoring including region-specific criteria is possible.

[0110] The scoring unit can analyze the user's social media activity during scoring and provide scoring including related criteria. For example, the scoring unit can analyze the user's social media activity during scoring and provide scoring including related criteria. For example, the scoring unit can set scoring criteria related to topics in which the user has shown interest on social media. The scoring unit can also set scoring criteria related to companies the user follows on social media. Furthermore, the scoring unit can set scoring criteria related to events the user has participated in on social media. This makes it possible to provide scoring including related criteria by analyzing the user's social media activity.

[0111] The scoring unit can customize the scoring criteria by reflecting the user's past feedback when scoring. For example, the scoring unit customizes the scoring criteria by reflecting the user's past feedback when scoring. For example, the scoring unit adjusts the scoring criteria based on feedback provided by the user in the past. The scoring unit can also improve the scoring criteria based on problems the user has felt in the past. Furthermore, the scoring unit can adjust the scoring progress method based on feedback the user has received in the past. In this way, more appropriate scoring is possible by reflecting the user's past feedback.

[0112] The regeneration unit can estimate the user's emotions and adjust the regeneration method based on the estimated user emotions. For example, the regeneration unit can estimate the user's emotions and adjust the regeneration method based on the estimated user emotions. For example, if the user is nervous, the regeneration unit can provide a regeneration method that helps the user relax. Furthermore, if the user is confident, the regeneration unit can provide a more difficult regeneration method. Furthermore, if the user is anxious, the regeneration unit can provide a regeneration method that gives the user a sense of security. This allows for more effective interview practice by adjusting the regeneration method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0113] The regeneration unit can optimize the regeneration content by referring to the user's past practice results during regeneration. The regeneration unit, for example, optimizes the regeneration content by referring to the user's past practice results during regeneration. For example, the regeneration unit performs regeneration that focuses on questions that the user had difficulty with in the past. The regeneration unit can also perform regeneration that includes questions that the user had difficulty with in the past. Furthermore, the regeneration unit can provide an optimal regeneration plan based on the user's past practice results. This enables more effective regeneration by referring to the user's past practice results.

[0114] The regeneration unit can adjust the difficulty of regeneration in accordance with the user's current skill level during regeneration. For example, the regeneration unit adjusts the difficulty of regeneration in accordance with the user's current skill level during regeneration. For example, if the user is a beginner, the regeneration unit performs regeneration including basic questions. Furthermore, if the user is an intermediate user, the regeneration unit can also perform regeneration including applied questions. Furthermore, if the user is an advanced user, the regeneration unit can also perform regeneration including questions with a high level of difficulty. In this way, by adjusting the difficulty of regeneration in accordance with the user's current skill level, more effective regeneration is possible.

[0115] The regeneration unit can improve the regeneration method by reflecting user feedback during regeneration. For example, the regeneration unit improves the regeneration method by reflecting user feedback during regeneration. For example, the regeneration unit adjusts the content of the next regeneration based on feedback provided by the user after regeneration. The regeneration unit can also improve the regeneration method based on problems the user feels during regeneration. Furthermore, the regeneration unit can adjust the method of proceeding with regeneration based on feedback obtained by the user after regeneration. In this way, more effective regeneration is possible by reflecting user feedback.

[0116] The regeneration unit can estimate the user's emotions and determine the priority of regeneration based on the estimated user's emotions. The regeneration unit, for example, estimates the user's emotions and determines the priority of regeneration based on the estimated user's emotions. For example, if the user is nervous, the regeneration unit can prioritize regeneration that will relax the user. Also, if the user is confident, the regeneration unit can prioritize regeneration that is more difficult. Furthermore, if the user is anxious, the regeneration unit can prioritize regeneration that will give the user a sense of security. This enables more effective regeneration by determining the priority of regeneration based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0117] The regeneration unit can perform regeneration including a region-specific scenario by taking into account the user's geographical location information during regeneration. For example, the regeneration unit performs regeneration including a region-specific scenario by taking into account the user's geographical location information during regeneration. For example, the regeneration unit performs regeneration including a scenario related to the culture and customs of the region where the user lives. The regeneration unit can also perform regeneration including a scenario related to the location of a company the user is applying to. Furthermore, the regeneration unit can perform regeneration including a scenario related to the location of a university the user is applying to. In this way, regeneration including a region-specific scenario is possible by taking into account the user's geographical location information.

[0118] The regeneration unit can analyze the user's social media activity during regeneration and perform regeneration including related scenarios. For example, the regeneration unit analyzes the user's social media activity during regeneration and performs regeneration including related scenarios. For example, the regeneration unit performs regeneration including scenarios related to topics in which the user has shown interest on social media. The regeneration unit can also perform regeneration including scenarios related to companies the user follows on social media. Furthermore, the regeneration unit can also perform regeneration including scenarios related to events the user has participated in on social media. This makes it possible to perform regeneration including related scenarios by analyzing the user's social media activity.

[0119] The regeneration unit can customize the regenerated content by reflecting the user's past feedback during regeneration. The regeneration unit, for example, customizes the regenerated content by reflecting the user's past feedback during regeneration. For example, the regeneration unit adjusts the regenerated content based on feedback provided by the user in the past. The regeneration unit can also improve the regenerated content based on problems the user has felt in the past. Furthermore, the regeneration unit can adjust the method of proceeding with the regeneration based on feedback the user has received in the past. This enables more effective regeneration by reflecting the user's past feedback.

[0120] The repetition unit can estimate the user's emotions and adjust the repetitive practice method based on the estimated user emotions. For example, the repetition unit can estimate the user's emotions and adjust the repetitive practice method based on the estimated user emotions. For example, if the user is nervous, the repetition unit can provide a repetitive practice method that helps the user relax. Furthermore, if the user is confident, the repetition unit can provide a more difficult repetitive practice method. Furthermore, if the user is anxious, the repetition unit can provide a repetitive practice method that gives the user a sense of security. This allows for more effective interview practice by adjusting the repetitive practice method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0121] The repetition unit can optimize the practice content by referring to the user's past practice results during repeated practice. For example, the repetition unit optimizes the practice content by referring to the user's past practice results during repeated practice. For example, the repetition unit provides repeated practice that focuses on questions that the user found difficult in the past. The repetition unit can also provide repeated practice that includes questions that the user found easy in the past. Furthermore, the repetition unit can provide an optimal repeated practice plan based on the user's past practice results. This allows for more effective repeated practice by referring to the user's past practice results.

[0122] The repetition unit can adjust the difficulty of the practice according to the user's current skill level during repeated practice. For example, the repetition unit adjusts the difficulty of the practice according to the user's current skill level during repeated practice. For example, if the user is a beginner, the repetition unit can provide repeated practice including basic questions. If the user is an intermediate learner, the repetition unit can also provide repeated practice including applied questions. Furthermore, if the user is an advanced learner, the repetition unit can also provide repeated practice including difficult questions. This allows for more effective repeated practice by adjusting the difficulty of the practice according to the user's current skill level.

[0123] The repetition unit can improve the practice method by reflecting the user's feedback during repeated practice. For example, the repetition unit improves the practice method by reflecting the user's feedback during repeated practice. For example, the repetition unit adjusts the content of the next practice based on the feedback provided by the user after repeated practice. The repetition unit can also improve the practice method based on problems the user feels during repeated practice. Furthermore, the repetition unit can adjust the way the practice progresses based on the feedback the user receives after repeated practice. In this way, more effective repeated practice is possible by reflecting the user's feedback.

[0124] The repetition unit can estimate the user's emotions and determine the priority of repeated practice based on the estimated user emotions. The repetition unit, for example, estimates the user's emotions and determines the priority of repeated practice based on the estimated user emotions. For example, if the user is nervous, the repetition unit can prioritize providing relaxing practice. Furthermore, if the user is confident, the repetition unit can prioritize providing more difficult practice. Furthermore, if the user is anxious, the repetition unit can prioritize providing reassuring practice. This enables more effective interview practice by determining the priority of repeated practice based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0125] The repetition unit can provide practice including region-specific scenarios during repeated practice by taking into account the user's geographical location information. For example, the repetition unit provides practice including region-specific scenarios by taking into account the user's geographical location information during repeated practice. For example, the repetition unit provides practice including scenarios related to the culture and customs of the region in which the user lives. The repetition unit can also provide practice including scenarios related to the location of a company the user is applying to. Furthermore, the repetition unit can provide practice including scenarios related to the location of a university the user is applying to. In this way, practice including region-specific scenarios is possible by taking into account the user's geographical location information.

[0126] The repetition unit can analyze the user's social media activity during repeated practice and provide practice including related scenarios. For example, the repetition unit can analyze the user's social media activity during repeated practice and provide practice including related scenarios. For example, the repetition unit can provide practice including scenarios related to topics in which the user has shown interest on social media. The repetition unit can also provide practice including scenarios related to companies the user follows on social media. Furthermore, the repetition unit can provide practice including scenarios related to events the user has participated in on social media. In this way, practice including related scenarios can be provided by analyzing the user's social media activity.

[0127] The repetition unit can customize the practice content by reflecting the user's past feedback during repeated practice. The repetition unit, for example, customizes the practice content by reflecting the user's past feedback during repeated practice. For example, the repetition unit adjusts the practice content based on feedback provided by the user in the past. The repetition unit can also improve the practice content based on problems the user has felt in the past. Furthermore, the repetition unit can adjust the way the practice progresses based on feedback the user has received in the past. This allows for more effective repeated practice by reflecting the user's past feedback.

[0128] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated user emotions. For example, the evaluation unit estimates the user's emotions and adjusts the evaluation criteria based on the estimated user emotions. For example, if the user is nervous, the evaluation unit sets evaluation criteria that allow the user to relax. Furthermore, if the user is confident, the evaluation unit can set strict evaluation criteria. Furthermore, if the user is anxious, the evaluation unit can set evaluation criteria that give the user a sense of security. This allows for more appropriate evaluation by adjusting the evaluation criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0129] The evaluation unit can improve the accuracy of the evaluation by referring to the user's past evaluation results during evaluation. The evaluation unit can improve the accuracy of the evaluation by referring to the user's past evaluation results during evaluation, for example. For example, the evaluation unit can adjust the evaluation criteria based on the evaluation results obtained by the user in the past. The evaluation unit can also tighten the evaluation criteria for questions that the user was weak at in the past. Furthermore, the evaluation unit can loosen the evaluation criteria for questions that the user was strong at in the past. In this way, by referring to the user's past evaluation results, more accurate evaluation is possible.

[0130] The evaluation unit can apply different evaluation algorithms depending on the user's facial expression and clothing during evaluation. The evaluation unit, for example, applies different evaluation algorithms depending on the user's facial expression and clothing during evaluation. For example, the evaluation unit applies an algorithm that gives a positive evaluation when the user is smiling. The evaluation unit can also apply an evaluation algorithm that gives a good impression when the user is appropriately dressed. Furthermore, the evaluation unit can also apply an evaluation algorithm that makes the user feel relaxed when the user is nervous. In this way, applying an evaluation algorithm depending on the user's facial expression and clothing enables a more appropriate evaluation.

[0131] The evaluation unit can improve the evaluation criteria by reflecting user feedback during evaluation. For example, the evaluation unit improves the evaluation criteria by reflecting user feedback during evaluation. For example, the evaluation unit adjusts the next evaluation criteria based on feedback provided by the user after the evaluation. The evaluation unit can also improve the evaluation criteria based on problems the user felt during the evaluation. Furthermore, the evaluation unit can adjust the method of proceeding with the evaluation based on feedback obtained by the user after the evaluation. In this way, by reflecting user feedback, more appropriate evaluation is possible.

[0132] The evaluation unit can estimate the user's emotions and determine the priority of evaluations based on the estimated user emotions. The evaluation unit, for example, estimates the user's emotions and determines the priority of evaluations based on the estimated user emotions. For example, if the user is nervous, the evaluation unit can prioritize evaluations that will make the user feel relaxed. Furthermore, if the user is confident, the evaluation unit can prioritize evaluations that will give the user a sense of security. In this way, by determining the priority of evaluations based on the user's emotions, more appropriate evaluations can be made. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0133] The evaluation unit can perform evaluations that include region-specific criteria by taking into account the user's geographical location information during evaluation. For example, the evaluation unit can perform evaluations that include region-specific criteria by taking into account the user's geographical location information during evaluation. For example, the evaluation unit sets evaluation criteria based on the culture and customs of the region in which the user lives. The evaluation unit can also set evaluation criteria related to the location of the company the user is applying to. Furthermore, the evaluation unit can set evaluation criteria related to the location of the university the user is applying to. In this way, by taking into account the user's geographical location information, evaluations that include region-specific criteria are possible.

[0134] The evaluation unit can analyze the user's social media activity during the evaluation and perform an evaluation including related criteria. For example, the evaluation unit can analyze the user's social media activity during the evaluation and perform an evaluation including related criteria. For example, the evaluation unit can set evaluation criteria related to topics in which the user has shown interest on social media. The evaluation unit can also set evaluation criteria related to companies the user follows on social media. Furthermore, the evaluation unit can also set evaluation criteria related to events the user has participated in on social media. This makes it possible to perform an evaluation including related criteria by analyzing the user's social media activity.

[0135] The evaluation unit can customize the evaluation criteria by reflecting the user's past feedback during evaluation. The evaluation unit, for example, customizes the evaluation criteria by reflecting the user's past feedback during evaluation. For example, the evaluation unit adjusts the evaluation criteria based on feedback provided by the user in the past. The evaluation unit can also improve the evaluation criteria based on problems the user has felt in the past. Furthermore, the evaluation unit can adjust the method of proceeding with the evaluation based on feedback the user has received in the past. In this way, by reflecting the user's past feedback, more appropriate evaluation is possible. === Hard Collateral 1-1 === Each of the multiple elements, including the generation unit, practice unit, scoring unit, regeneration unit, repeat unit, and evaluation unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an interviewer model. The practice unit is realized by the control unit 46A of the smart device 14 and performs practice with an AI interviewer. The scoring unit is realized by the specific processing unit 290 of the data processing device 12 and automatically scores the practice results. The regeneration unit is realized by the specific processing unit 290 of the data processing device 12 and generates a new model. The repeat unit is realized by the control unit 46A of the smart device 14 and performs repeated practice. The evaluation unit is realized by the control unit 46A of the smart device 14 and evaluates facial expressions and clothing. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned generation unit, practice unit, scoring unit, regeneration unit, repeat unit, and evaluation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an interviewer model. The practice unit is realized by the control unit 46A of the smart glasses 214 and performs practice with an AI interviewer. The scoring unit is realized by the specific processing unit 290 of the data processing device 12 and automatically scores the practice results. The regeneration unit is realized by the specific processing unit 290 of the data processing device 12 and performs remodel generation. The repeat unit is realized by the control unit 46A of the smart glasses 214 and performs repeated practice. The evaluation unit is realized by the control unit 46A of the smart glasses 214 and evaluates facial expressions and clothing. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned generation unit, practice unit, scoring unit, regeneration unit, repeat unit, and evaluation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an interviewer model. The practice unit is realized by the control unit 46A of the headset type terminal 314 and performs practice with an AI interviewer. The scoring unit is realized by the specific processing unit 290 of the data processing device 12 and automatically scores the practice results. The regeneration unit is realized by the specific processing unit 290 of the data processing device 12 and generates a new model. The repeat unit is realized by the control unit 46A of the headset type terminal 314 and performs repeated practice. The evaluation unit is realized by the control unit 46A of the headset type terminal 314 and evaluates facial expressions and clothing. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned generation unit, practice unit, scoring unit, regeneration unit, repeat unit, and evaluation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates an interviewer model. The practice unit is realized by the control unit 46A of the robot 414 and performs practice with an AI interviewer. The scoring unit is realized by the specific processing unit 290 of the data processing device 12 and automatically scores the practice results. The regeneration unit is realized by the specific processing unit 290 of the data processing device 12 and performs remodel generation. The repeat unit is realized by the control unit 46A of the robot 414 and performs repeated practice. The evaluation unit is realized by the control unit 46A of the robot 414 and evaluates facial expressions and clothing.

[0136] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0137] The generation unit can customize the model taking into account the user's past interview experience. For example, the generation unit generates a model that includes similar questions based on the content of questions asked in interviews the user has taken in the past. The generation unit can also generate a model that focuses on questions that the user has had difficulty with in the past. Furthermore, the generation unit can also generate a model that includes questions that the user has had difficulty with in the past. This allows for more effective interview practice by taking into account the user's past interview experience.

[0138] The practice unit can adjust the difficulty of the practice depending on the user's current skill level. For example, if the user is a beginner, the practice unit can provide practice that includes basic questions. If the user is an intermediate learner, the practice unit can also provide practice that includes applied questions. Furthermore, if the user is an advanced learner, the practice unit can also provide practice that includes difficult questions. This allows for more effective interview practice by adjusting the difficulty of the practice depending on the user's current skill level.

[0139] The scoring unit can apply different scoring algorithms depending on the content of the user's answer. For example, if the user gives a detailed answer, the scoring unit can apply a detailed scoring algorithm. If the user gives a concise answer, the scoring unit can also apply a concise scoring algorithm. Furthermore, if the user gives an ambiguous answer, the scoring unit can also apply a scoring algorithm that evaluates the ambiguity. In this way, applying a scoring algorithm according to the content of the user's answer enables more appropriate scoring.

[0140] During regeneration, the regeneration unit can optimize the regeneration content by referring to the user's past practice results. For example, the regeneration unit performs regeneration that focuses on questions that the user found difficult in the past. The regeneration unit can also perform regeneration that includes questions that the user found easy in the past. Furthermore, the regeneration unit can provide an optimal regeneration plan based on the user's past practice results. This allows for more effective regeneration by referring to the user's past practice results.

[0141] When making an evaluation, the evaluation unit can apply different evaluation algorithms depending on the user's facial expression and clothing. For example, if the user is smiling, the evaluation unit applies an algorithm that gives a positive evaluation. In addition, if the user is appropriately dressed, the evaluation unit can also apply an evaluation algorithm that gives a good impression. Furthermore, if the user is nervous, the evaluation unit can also apply an evaluation algorithm that helps the user to relax. In this way, applying an evaluation algorithm that depends on the user's facial expression and clothing enables a more appropriate evaluation.

[0142] The generation unit can estimate the user's emotions and adjust the generation method of the interviewer model based on the estimated user's emotions. For example, if the user is nervous, the generation unit can generate a model including questions that will help the user relax. Also, if the user is confident, the generation unit can generate a model including difficult questions. Furthermore, if the user is feeling anxious, the generation unit can generate a model including questions that will give the user a sense of security. In this way, adjusting the model generation method based on the user's emotions enables more appropriate interview practice.

[0143] The practice unit can estimate the user's emotions and adjust the way the practice proceeds based on the estimated user's emotions. For example, if the practice unit is nervous, it can provide a practice method that helps the user relax. If the user is confident, it can also provide a practice method that is more difficult. Furthermore, if the user is feeling anxious, it can also provide a practice method that gives the user a sense of security. In this way, by adjusting the way the practice proceeds based on the user's emotions, more effective interview practice is possible.

[0144] The scoring unit can estimate the user's emotions and adjust the scoring criteria based on the estimated user's emotions. For example, if the user is nervous, the scoring unit can set scoring criteria that help the user to relax. If the user is confident, the scoring unit can also set strict scoring criteria. Furthermore, if the user is feeling anxious, the scoring unit can also set scoring criteria that give the user a sense of security. In this way, adjusting the scoring criteria based on the user's emotions enables more appropriate scoring.

[0145] The regeneration unit can estimate the user's emotions and adjust the regeneration method based on the estimated user's emotions. For example, if the user is nervous, the regeneration unit can provide a regeneration method that helps the user relax. Also, if the user is confident, the regeneration unit can provide a more difficult regeneration method. Furthermore, if the user is feeling anxious, the regeneration unit can provide a regeneration method that gives the user a sense of security. This allows for more effective interview practice by adjusting the regeneration method based on the user's emotions.

[0146] The repetition unit can estimate the user's emotions and adjust the repetitive practice method based on the estimated user's emotions. For example, if the user is nervous, the repetition unit can provide a repetitive practice method that helps the user relax. If the user is confident, the repetition unit can also provide a repetitive practice method that is more difficult. Furthermore, if the user is feeling anxious, the repetition unit can also provide a repetitive practice method that gives the user a sense of security. This allows for more effective interview practice by adjusting the repetitive practice method based on the user's emotions.

[0147] The processing flow of the second embodiment will be briefly explained below.

[0148] Step 1: The generator generates an interviewer model that lists specific elements. For example, the generator generates a model that includes questions and evaluation criteria according to categories such as entrance exams, employment, and qualifications. Step 2: The practice unit practices with an AI interviewer based on the model generated by the generation unit. For example, the practice unit practices with the AI ​​interviewer in an interactive format. Step 3: The scoring unit automatically scores the practice results performed by the practice unit. For example, the scoring unit analyzes the content of the user's answers, facial expressions, tone of voice, etc., and evaluates areas of strength and weakness. Step 4: The regeneration unit regenerates a model based on the results obtained by the scoring unit. For example, the regeneration unit regenerates a model to focus on practicing areas where the user is weak. Step 5: The iteration unit performs iterative training based on the model generated by the regeneration unit. For example, the iteration unit allows the user to perform iterative training through subscription deployment. Step 6: The evaluation unit evaluates the facial expressions and clothing used during the practice session. For example, the evaluation unit analyzes the user's facial expressions and clothing and provides advice on how to make a good impression during an interview.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0152] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0153] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0154] 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.

[0155] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to 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 imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0169] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0170] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0171] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0177] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0178] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0179] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0180] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0181] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0182] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0183] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0184] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0185] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0186] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0187] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0188] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0189] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0191] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0192] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0193] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0194] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0195] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0196] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0197] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0198] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0199] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0200] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0201] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0202] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0203] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0204] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0205] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0206] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0207] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0208] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0209] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0210] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0211] 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.

[0212] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0213] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0214] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0215] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0216] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0217] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0218] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0219] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0220] [Explanation of symbols]

[0221] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a generation unit that generates an interviewer model that lists specific elements; A practice unit that practices with an AI interviewer based on the model generated by the generation unit; a scoring unit that automatically scores the results of the practice performed by the practice unit; a regeneration unit that regenerates a model based on the results obtained by the scoring unit; a repetition unit that performs repeated practice based on the model generated by the regeneration unit; an evaluation unit that evaluates facial expressions and clothing during practice performed by the practice unit; A system characterized by:

2. The generation unit Generate models with questions and assessment criteria for exam, employment, and certification categories 2. The system of claim 1.

3. The practice section: Practice in an interactive format with an AI interviewer 2. The system of claim 1.

4. The scoring unit Analyze the user's responses, facial expressions, and tone of voice to assess their strengths and weaknesses 2. The system of claim 1.

5. The regeneration unit Regenerate models to focus practice on areas where the user is weak 2. The system of claim 1.

6. The evaluation unit Analyzes the user's facial expressions and clothing to provide advice on how to make a good impression during an interview 2. The system of claim 1.

7. The repeating section Subscription service allows users to practice repeatedly 2. The system of claim 1.

8. The generation unit Estimate the user's emotions and adjust the generation method of the interviewer model based on the estimated user emotions.

2. The system of claim 1.

Images