System

Abstract

An object of a system according to an embodiment is to enable an examinee and a protector to efficiently take measures for an examination.SOLUTION: A system includes an advice unit, a communication unit, and a countermeasure unit. The advice unit advises contents to be memorized by the examinee and the guardian. The communication unit repeats communication between the examinee and the AI avatar based on the content advised by the advice unit to find an improvement point. The countermeasure unit allows the protector to take a countermeasure in the spare time on the basis of the improvement point obtained by the communication 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 technology makes it difficult for test takers and their parents to prepare for exams efficiently, and there is a particular problem in dual-income households where it is difficult to allocate sufficient time to preparation.

[0005] The system according to the embodiment aims to enable test takers and their parents to efficiently prepare for the test. [Means for solving the problem]

[0006] The system according to the embodiment includes an advice unit, a communication unit, and a countermeasure unit. The advice unit advises the test taker and their guardians on what they should remember. The communication unit finds areas for improvement through repeated communication between the test taker and an AI avatar based on the advice provided by the advice unit. The countermeasure unit allows guardians to take countermeasures in their spare time based on the areas for improvement identified by the communication unit. [Effects of the Invention]

[0007] The system according to the embodiment allows test takers and their parents to efficiently prepare for the test. [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 allows test takers (children) and their guardians to understand their respective roles and efficiently prepare for the exam. The interview practice system provides advice to test takers (children) and their guardians on what they need to memorize, and the test takers (children) communicate repeatedly with an AI avatar to identify areas for improvement, allowing the guardians to prepare in their spare time. For example, in an interview practice system, a generation AI advises test takers (children) and their guardians on what they need to memorize. The generation AI provides the advice in terms that the test takers (children) can understand. Next, the test takers (children) and an AI avatar conduct a mock interview, and the generation AI advises on areas for improvement based on the results. By repeating this process, test takers (children) can improve their interview skills. Furthermore, guardians can receive advice from the generation AI using their smartphones in between work shifts. This allows guardians to efficiently prepare for the exam. This interview practice system allows test takers (children) to improve their interview skills and guardians to efficiently prepare for the exam. For example, if a test-taker (child) takes a mock interview with an AI avatar and the generating AI gives advice on areas for improvement based on the results, the test-taker (child) can approach the interview with confidence. Parents can also receive advice from the generating AI, helping them understand how to support their children and provide effective support.

[0029] An interview practice system according to an embodiment includes an advising unit, a communication unit, and a preparation unit. The advising unit provides advice to the examinee (child) and their guardian on what they should remember. For example, the advising unit explains to the examinee (child) in simple terms how to greet others during an interview and how to answer questions. The advising unit can also provide specific advice to guardians on what to wear to an interview and how to support their children. For example, the advising unit can teach the examinee (child) how to say "hello." The advising unit can also advise guardians that "it is desirable to wear a suit during the interview." The communication unit allows the examinee (child) and an AI avatar to repeatedly communicate with each other to find areas for improvement. For example, the communication unit allows the examinee (child) to conduct a mock interview with the AI ​​avatar, and the generating AI provides advice on areas for improvement based on the results. The communication unit can also allow the examinee (child) to improve their interview skills by repeatedly interacting with the AI ​​avatar. For example, the communication unit allows the examinee (child) to practice giving an appropriate answer to the question, "Please introduce yourself." The preparation unit allows parents to prepare in their spare time. For example, parents can receive advice from the generation AI using their smartphone during breaks at work. The preparation unit also allows parents to understand how to support their children and provide effective support by receiving advice from the generation AI. For example, the preparation unit allows parents to learn "how to deal with a child who is nervous." As a result, the interview practice system according to the embodiment allows test takers (children) and parents to understand their respective roles and prepare for the exam efficiently.

[0030] The advice unit can provide advice on areas for improvement in terms that even the test taker can understand. Examples of understandable expressions include, but are not limited to, simple words, illustrations, and examples. For example, the advice unit can explain to the test taker (child) in simple words "how to greet in an interview." The advice unit can also explain to the test taker (child) "how to answer questions" using illustrations. The advice unit can also explain to the test taker (child) "the flow of the interview" using examples. This allows the test taker (child) to receive advice in terms that are easy to understand. Some or all of the above-described processing in the advice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the advice unit can input the test taker's (child's) answers into a generation AI, which then provides advice on areas for improvement.

[0031] The communication unit can conduct a mock interview between the test taker and an AI avatar and provide advice on areas for improvement based on the results. Examples of mock interviews include, but are not limited to, the types of questions, the interview format, and evaluation criteria. For example, the communication unit can have the test taker (child) conduct a mock interview with an AI avatar, and the generation AI can provide advice on areas for improvement based on the results. The communication unit can also improve the test taker's (child's) interview skills by having the test taker (child) repeatedly interact with the AI ​​avatar. For example, the communication unit can have the test taker (child) practice giving an appropriate response to the question, "Tell me about yourself." The communication unit can also have the test taker (child) practice giving a specific response to the question, "What is your dream for the future?" The communication unit can also have the test taker (child) practice giving a detailed response to the question, "What is your favorite book?" This allows the test taker's (child's) skills to be improved through the mock interview. Some or all of the above-described processing in the communication unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the communications department can input the results of a mock interview conducted by a test-taker (child) into the generation AI, which can then provide advice on areas for improvement.

[0032] The countermeasures unit allows parents to receive advice from the generating AI using a smartphone. Examples of the generating AI include, but are not limited to, natural language processing, machine learning algorithms, and dialogue systems. For example, parents can receive advice from the generating AI using a smartphone between work hours. By receiving advice from the generating AI, the countermeasures unit can also help parents understand how to support their children and provide effective support. For example, the countermeasures unit can teach parents how to deal with nervousness. The countermeasures unit can also teach parents how to prepare for their children's interviews. The countermeasures unit can also teach parents things to pay attention to on the day of the interview. This allows parents to efficiently prepare for the exam. Some or all of the above-mentioned processing in the countermeasures unit may be performed using, or without, the generating AI. For example, the countermeasures unit can input parents' questions into the generating AI, which then provides advice.

[0033] The advice unit can explain in easy-to-understand terms how to greet people in an interview and how to answer questions. Examples of easy-to-understand terms include, but are not limited to, simple words, examples, and diagrams. For example, the advice unit can explain to the examinee (child) in easy-to-understand terms "how to greet people in an interview." The advice unit can also explain to the examinee (child) "how to answer questions" using examples. The advice unit can also explain to the examinee (child) "the flow of an interview" using diagrams. This allows the examinee (child) to easily understand basic interview skills. Some or all of the above-described processing in the advice unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the advice unit can input the examinee's (child's) questions into the generation AI, which can then answer in easy-to-understand terms.

[0034] The advice unit can provide detailed advice on what to wear for the interview and how to support the child. Detailed advice includes, for example, specific procedures, examples, checklists, etc., but is not limited to these examples. For example, the advice unit provides specific advice to the parent on "what to wear for the interview." The advice unit can also provide advice to the parent on "how to support the child" using examples. The advice unit can also provide advice to the parent on "things to pay attention to on the day of the interview" using a checklist. This allows the parent to receive specific advice and effectively support the child. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the advice unit can input the parent's question into the generation AI, which then provides detailed advice.

[0035] The advice unit can analyze the test taker's (child's) past learning history and select the optimal advice method. Examples of optimal advice methods include, but are not limited to, individual instruction, group instruction, online resources, etc. For example, the advice unit can have the generation AI provide focused advice on questions that the test taker (child) previously struggled with. The advice unit can also have the generation AI provide specific advice to strengthen the test taker's (child's) areas of strength. The advice unit can also have the generation AI identify areas for improvement based on the test taker's (child's) past mock interview results and provide effective advice. This allows for effective advice based on the test taker's (child's) past learning history. Some or all of the above-described processing in the advice unit can be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) learning history data into the generation AI, which can then select the optimal advice method.

[0036] When providing advice, the advice unit can adjust the level of detail of the advice based on the test taker's (child's) current level of understanding. Examples of adjustments based on the level of understanding include, but are not limited to, test results, feedback, and observation results. For example, if the test taker's (child's) level of understanding is high, the advice unit's generation AI can provide detailed advice to further improve the test taker's (child's) skills. Furthermore, if the test taker's (child's) level of understanding is low, the advice unit's generation AI can provide advice that focuses on basic points. Furthermore, the advice unit's generation AI can gradually adjust the difficulty of the advice depending on the test taker's (child's) level of understanding. This allows appropriate advice to be provided according to the test taker's (child's) level of understanding. Some or all of the above-described processing in the advice unit may be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) level of understanding data into the generation AI, which can then adjust the level of detail of the advice.

[0037] When providing advice, the advice unit can customize the advice content based on the interests and concerns of the test-taker (child). Examples of customization based on interests and concerns include, but are not limited to, questionnaire results, past behavioral history, and hobbies. For example, the advice unit provides advice by having the generation AI incorporate questions related to topics that interest the test-taker (child). The advice unit can also provide advice by having the generation AI use specific examples based on the test-taker's (child's) areas of interest. The advice unit can also incorporate content related to the test-taker's (child's) hobbies and special skills into the advice. This allows advice to be provided that is tailored to the test-taker's (child's) interests and concerns. Some or all of the above-described processing in the advice unit may be performed using, or without, the generation AI. For example, the advice unit can input the test-taker's (child's) interests and concerns data into the generation AI, which can then customize the advice content.

[0038] When providing advice, the advice unit can provide highly relevant advice by taking into account the geographical location information of the test taker (child). Geographical location information includes, but is not limited to, GPS data, address information, and location sensor data. In the advice unit, for example, the generation AI provides specific advice based on the characteristics of the area where the test taker (child) lives. In addition, the advice unit can incorporate information related to the location of the test taker's (child's) school into the advice. In addition, the advice unit can provide appropriate advice based on the culture and customs of the test taker's (child's) area. This makes it possible to provide appropriate advice based on the test taker's (child's) geographical location information. Some or all of the above-mentioned processing in the advice unit may be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) geographical location information data into the generation AI, which can then provide highly relevant advice.

[0039] When providing advice, the advice unit can analyze the social media activity of the test taker (child) and provide relevant advice. Social media activity includes, but is not limited to, post content, number of followers, and engagement rate. In the advice unit, for example, the generation AI provides advice based on topics the test taker (child) is interested in on social media. The advice unit can also analyze the test taker's (child's) social media activity history and provide appropriate advice. The advice unit can also provide relevant advice based on the test taker's (child's) social media friendships. This allows appropriate advice to be provided based on the test taker's (child's) social media activity. Some or all of the above-described processing in the advice unit may be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) social media activity data into the generation AI, and the generation AI can provide relevant advice.

[0040] When providing advice, the advice unit can customize the advice method by reflecting the test taker's (child's) past feedback. Past feedback includes, but is not limited to, questionnaire results, evaluation comments, and observation results. In the advice unit, for example, the generation AI adjusts the content of the advice based on feedback the test taker (child) has received in the past. In addition, the advice unit can identify areas for improvement from the test taker's (child's) past feedback and provide specific advice. In addition, the advice unit can analyze the test taker's (child's) feedback history and select the optimal advice method. This allows appropriate advice to be provided based on the test taker's (child's) past feedback. Some or all of the above-mentioned processing in the advice unit can be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) past feedback data into the generation AI, which can then customize the advice method.

[0041] During a mock interview, the communication unit can analyze the examinee's (child's) past interview results and provide advice on optimal areas for improvement. Past interview results include, but are not limited to, evaluation sheets, interviewer comments, and video recording data. For example, the communication unit uses the generation AI to identify specific areas for improvement based on the examinee's (child's) past interview results and provide advice. The communication unit can also analyze the examinee's (child's) past interview failures and provide effective improvement measures. The communication unit can also identify areas for improvement based on the examinee's (child's) past interview results and provide advice. This allows the examinee to receive effective advice based on their past interview results. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the examinee's (child's) past interview result data into the generation AI, which then provides advice on optimal areas for improvement.

[0042] During the mock interview, the communication unit can adjust the difficulty of the interview based on the current skill level of the examinee (child). Examples of adjustments based on skill level include, but are not limited to, test results, observation results, and feedback. For example, if the examinee (child) has a high skill level, the communication unit can cause the generation AI to ask more difficult questions. Furthermore, if the examinee (child) has a low skill level, the communication unit can cause the generation AI to ask more basic questions. Furthermore, the communication unit can cause the generation AI to gradually adjust the difficulty of the questions according to the skill level of the examinee (child). This allows for an appropriate mock interview to be provided according to the skill level of the examinee (child). Some or all of the above-described processing in the communication unit can be performed using, or without, the generation AI. For example, the communication unit can input the skill level data of the examinee (child) into the generation AI, which can then adjust the difficulty of the interview.

[0043] During the mock interview, the communication unit can customize the interview content based on the interests and concerns of the test taker (child). Customization of the interview content includes, but is not limited to, the type of questions, scenarios, and evaluation criteria. For example, the communication unit allows the generation AI to ask questions related to topics that interest the test taker (child). The communication unit can also allow the generation AI to ask questions using specific examples based on the test taker's (child's) areas of interest. The communication unit can also allow the generation AI to incorporate content related to the test taker's (child's) hobbies and special skills into the interview. This allows for an appropriate mock interview tailored to the test taker's (child's) interests and concerns. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the test taker's (child's) interests and concerns data into the generation AI, which can then customize the interview content.

[0044] During a mock interview, the communication unit can provide relevant questions by taking into account the geographic location information of the test taker (child). Relevant questions include, but are not limited to, regional characteristics, cultural background, and local news. For example, the communication unit allows the generation AI to ask specific questions based on the regional characteristics of the test taker (child). The communication unit can also allow the generation AI to incorporate information related to the location of the test taker's (child's) school into the questions. The communication unit can also allow the generation AI to provide appropriate questions based on the culture and customs of the test taker's (child's) region. This allows appropriate questions to be provided based on the test taker's (child's) geographic location information. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the test taker's (child's) geographic location information data into the generation AI, which can then provide relevant questions.

[0045] During the mock interview, the communication unit can analyze the social media activity of the test taker (child) and provide relevant questions. Examples of analyzing social media activity include, but are not limited to, analyzing post content, analyzing followers, and evaluating engagement. For example, the communication unit allows the generation AI to ask questions based on topics the test taker (child) is interested in on social media. The communication unit can also analyze the test taker's (child's) social media activity history and provide appropriate questions. The communication unit can also allow the generation AI to ask relevant questions based on the test taker's (child's) social media friendships. This allows appropriate questions to be provided based on the test taker's (child's) social media activity. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the test taker's (child's) social media activity data into the generation AI, which then provides relevant questions.

[0046] During a mock interview, the communication unit can customize the interview method by reflecting the examinee's (child's) past feedback. Customization of the interview method includes, but is not limited to, the type of questions, the scenario, and the evaluation criteria. For example, the communication unit allows the generation AI to adjust the content of the interview based on the examinee's (child's) past feedback. The communication unit can also allow the generation AI to identify areas for improvement based on the examinee's (child's) past feedback and ask specific questions. The communication unit can also analyze the examinee's (child's) feedback history and select the optimal interview method. This allows an appropriate interview method to be provided based on the examinee's (child's) past feedback. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the examinee's (child's) past feedback data into the generation AI, which can then customize the interview method.

[0047] The countermeasure unit can analyze the guardian's past countermeasure history and select the optimal countermeasure method. The past countermeasure history includes, for example, but is not limited to, the content of the countermeasure, the implementation date and time, and the results. For example, the countermeasure unit analyzes the effectiveness of countermeasures taken by the guardian in the past, and the generation AI proposes the optimal countermeasure method. The countermeasure unit can also identify effective countermeasures from the guardian's past countermeasure history and provide specific advice. The countermeasure unit can also identify areas for improvement based on the guardian's countermeasure history and propose effective countermeasures. This makes it possible to provide effective countermeasures based on the guardian's past countermeasure history. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the guardian's past countermeasure history data into the generation AI, and the generation AI can select the optimal countermeasure method.

[0048] When implementing countermeasures, the countermeasure unit can adjust the level of detail of the countermeasures based on the parent's current level of understanding. Examples of adjustments based on the parent's level of understanding include, but are not limited to, test results, feedback, and observation results. For example, if the parent's level of understanding is high, the countermeasure unit can have the generation AI provide detailed countermeasures to further improve the parent's skills. Furthermore, if the parent's level of understanding is low, the countermeasure unit can have the generation AI implement countermeasures that focus on basic points. Furthermore, the countermeasure unit can have the generation AI gradually adjust the difficulty of the countermeasures based on the parent's level of understanding. This allows appropriate countermeasures to be provided according to the parent's level of understanding. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the parent's level of understanding data into the generation AI, which can then adjust the level of detail of the countermeasures.

[0049] When implementing the measures, the countermeasure unit can customize the countermeasure content based on the parents' interests and concerns. Examples of customizing the countermeasure content include, but are not limited to, individual instruction, group instruction, online resources, etc. In the countermeasure unit, for example, the generation AI incorporates countermeasures related to topics of interest to the parents and provides advice. The countermeasure unit can also implement countermeasures using specific examples based on the parents' areas of interest. The countermeasure unit can also incorporate content related to the parents' hobbies and special skills into the countermeasures. This makes it possible to provide appropriate countermeasures tailored to the parents' interests and concerns. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the parents' interest data into the generation AI, which then customizes the countermeasure content.

[0050] When taking countermeasures, the countermeasure unit can provide highly relevant countermeasures by taking into account the guardian's geographical location information. Geographical location information includes, but is not limited to, GPS data, address information, and location sensor data. In the countermeasure unit, for example, the generation AI can take specific countermeasures based on the characteristics of the area where the guardian lives. The countermeasure unit can also incorporate information related to the location of the guardian's school into the countermeasure. The countermeasure unit can also provide appropriate countermeasures based on the culture and customs of the guardian's area. This makes it possible to provide appropriate countermeasures based on the guardian's geographical location information. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the guardian's geographical location information data into the generation AI, which can then provide highly relevant countermeasures.

[0051] When taking countermeasures, the countermeasure unit can analyze the parent's social media activity and provide relevant countermeasures. Examples of analyzing social media activity include, but are not limited to, analyzing post content, analyzing followers, and evaluating engagement. For example, the countermeasure unit uses a generation AI to take countermeasures based on topics the parent is interested in on social media. The countermeasure unit can also analyze the parent's social media activity history and provide appropriate countermeasures. The countermeasure unit can also use the parent's social media friendships as a reference to take relevant countermeasures. This allows appropriate countermeasures to be provided based on the parent's social media activity. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the parent's social media activity data into the generation AI, which then provides relevant countermeasures.

[0052] When taking countermeasures, the countermeasure unit can customize the countermeasure method by reflecting the parent's past feedback. Past feedback includes, but is not limited to, for example, survey results, evaluation comments, and observation results. In the countermeasure unit, for example, the generation AI adjusts the content of the countermeasure based on the parent's past feedback. In addition, the countermeasure unit can have the generation AI identify areas for improvement from the parent's past feedback and implement specific countermeasures. In addition, the countermeasure unit can analyze the parent's feedback history and have the generation AI select the optimal countermeasure method. This makes it possible to provide appropriate countermeasures based on the parent's past feedback. Some or all of the above-mentioned processing in the countermeasure unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the countermeasure unit can input the parent's past feedback data into the generation AI, and the generation AI can customize the countermeasure method.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The advice department can analyze the learning style of the test-taker (child) and provide the most appropriate advice method. For example, visual learners can receive advice using diagrams and videos, while auditory learners can receive audio guides. Experiential learners can also receive advice through an actual interview simulation. This allows for effective advice to be provided according to the test-taker's (child's) learning style.

[0055] The countermeasures department can provide a community function that allows parents to share information with other parents. For example, parents can post successful countermeasures, which other parents can use as reference. Parents can also post questions about countermeasures, which other parents or the generation AI can answer. Furthermore, parents can share their progress in countermeasures and encourage each other. This allows parents to cooperate with each other to implement effective countermeasures.

[0056] The communication department can analyze the past mock interview results of the test taker (child) and provide the optimal feedback method. For example, the generation AI will advise specific areas for improvement for questions that the test taker (child) had difficulty with in the past. The generation AI can also provide detailed feedback to strengthen the areas in which the test taker (child) excels. Furthermore, the generation AI can select an effective feedback method based on the test taker's (child's) past mock interview results. This allows for effective feedback to be provided based on the test taker's (child's) past results.

[0057] The countermeasures department allows the generation AI to provide real-time support to parents as they implement countermeasures. For example, if a parent has a question while implementing countermeasures, the generation AI can provide an immediate answer. The generation AI can also provide real-time feedback so that parents can check the progress of the countermeasures. Furthermore, the generation AI can also provide real-time evaluation so that parents can check the effectiveness of the countermeasures. This allows parents to implement countermeasures efficiently.

[0058] When parents implement countermeasures, the generation AI can monitor the progress of the countermeasures in real time and provide advice as needed. For example, the generation AI can provide real-time feedback so that parents can check the progress of the countermeasures. The generation AI can also evaluate the countermeasures in real time so that parents can check their effectiveness. Furthermore, if parents have any questions while the countermeasures are in progress, the generation AI can provide immediate answers. This allows parents to implement countermeasures efficiently.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The Advice Department provides advice to the applicants (children) and their parents on what they need to remember. For example, they explain to the applicants (children) in simple terms how to greet and answer questions at the interview, and they give specific advice to the parents on what to wear to the interview and how to support their child. Step 2: In the communication department, the test-taker (child) and the AI ​​avatar communicate repeatedly to identify areas for improvement. For example, the test-taker (child) conducts a mock interview with the AI ​​avatar, and the generating AI gives advice on areas for improvement based on the results. Step 3: The countermeasures department allows parents to implement countermeasures in their spare time. For example, parents can use their smartphones to receive advice from the AI ​​generator during breaks at work.

[0061] (Example 2) An interview practice system according to an embodiment of the present invention allows test takers (children) and their guardians to understand their respective roles and efficiently prepare for the exam. The interview practice system provides advice to test takers (children) and their guardians on what they need to memorize, and the test takers (children) communicate repeatedly with an AI avatar to identify areas for improvement, allowing the guardians to prepare in their spare time. For example, in an interview practice system, a generation AI advises test takers (children) and their guardians on what they need to memorize. The generation AI provides the advice in terms that the test takers (children) can understand. Next, the test takers (children) and an AI avatar conduct a mock interview, and the generation AI advises on areas for improvement based on the results. By repeating this process, test takers (children) can improve their interview skills. Furthermore, guardians can receive advice from the generation AI using their smartphones in between work shifts. This allows guardians to efficiently prepare for the exam. This interview practice system allows test takers (children) to improve their interview skills and guardians to efficiently prepare for the exam. For example, if a test-taker (child) takes a mock interview with an AI avatar and the generating AI gives advice on areas for improvement based on the results, the test-taker (child) can approach the interview with confidence. Parents can also receive advice from the generating AI, helping them understand how to support their children and provide effective support.

[0062] An interview practice system according to an embodiment includes an advising unit, a communication unit, and a preparation unit. The advising unit provides advice to the examinee (child) and their guardian on what they should remember. For example, the advising unit explains to the examinee (child) in simple terms how to greet others during an interview and how to answer questions. The advising unit can also provide specific advice to guardians on what to wear to an interview and how to support their children. For example, the advising unit can teach the examinee (child) how to say "hello." The advising unit can also advise guardians that "it is desirable to wear a suit during the interview." The communication unit allows the examinee (child) and an AI avatar to repeatedly communicate with each other to find areas for improvement. For example, the communication unit allows the examinee (child) to conduct a mock interview with the AI ​​avatar, and the generating AI provides advice on areas for improvement based on the results. The communication unit can also allow the examinee (child) to improve their interview skills by repeatedly interacting with the AI ​​avatar. For example, the communication unit allows the examinee (child) to practice giving an appropriate answer to the question, "Please introduce yourself." The preparation unit allows parents to prepare in their spare time. For example, parents can receive advice from the generation AI using their smartphone during breaks at work. The preparation unit also allows parents to understand how to support their children and provide effective support by receiving advice from the generation AI. For example, the preparation unit allows parents to learn "how to deal with a child who is nervous." As a result, the interview practice system according to the embodiment allows test takers (children) and parents to understand their respective roles and prepare for the exam efficiently.

[0063] The advice unit can provide advice on areas for improvement in terms that even the test taker can understand. Examples of understandable expressions include, but are not limited to, simple words, illustrations, and examples. For example, the advice unit can explain to the test taker (child) in simple words "how to greet in an interview." The advice unit can also explain to the test taker (child) "how to answer questions" using illustrations. The advice unit can also explain to the test taker (child) "the flow of the interview" using examples. This allows the test taker (child) to receive advice in terms that are easy to understand. Some or all of the above-described processing in the advice unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the advice unit can input the test taker's (child's) answers into a generation AI, which then provides advice on areas for improvement.

[0064] The communication unit can conduct a mock interview between the test taker and an AI avatar and provide advice on areas for improvement based on the results. Examples of mock interviews include, but are not limited to, the types of questions, the interview format, and evaluation criteria. For example, the communication unit can have the test taker (child) conduct a mock interview with an AI avatar, and the generation AI can provide advice on areas for improvement based on the results. The communication unit can also improve the test taker's (child's) interview skills by having the test taker (child) repeatedly interact with the AI ​​avatar. For example, the communication unit can have the test taker (child) practice giving an appropriate response to the question, "Tell me about yourself." The communication unit can also have the test taker (child) practice giving a specific response to the question, "What is your dream for the future?" The communication unit can also have the test taker (child) practice giving a detailed response to the question, "What is your favorite book?" This allows the test taker's (child's) skills to be improved through the mock interview. Some or all of the above-described processing in the communication unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the communications department can input the results of a mock interview conducted by a test-taker (child) into the generation AI, which can then provide advice on areas for improvement.

[0065] The countermeasures unit allows parents to receive advice from the generating AI using a smartphone. Examples of the generating AI include, but are not limited to, natural language processing, machine learning algorithms, and dialogue systems. For example, parents can receive advice from the generating AI using a smartphone between work hours. By receiving advice from the generating AI, the countermeasures unit can also help parents understand how to support their children and provide effective support. For example, the countermeasures unit can teach parents how to deal with nervousness. The countermeasures unit can also teach parents how to prepare for their children's interviews. The countermeasures unit can also teach parents things to pay attention to on the day of the interview. This allows parents to efficiently prepare for the exam. Some or all of the above-mentioned processing in the countermeasures unit may be performed using, or without, the generating AI. For example, the countermeasures unit can input parents' questions into the generating AI, which then provides advice.

[0066] The advice unit can explain in easy-to-understand terms how to greet people in an interview and how to answer questions. Examples of easy-to-understand terms include, but are not limited to, simple words, examples, and diagrams. For example, the advice unit can explain to the examinee (child) in easy-to-understand terms "how to greet people in an interview." The advice unit can also explain to the examinee (child) "how to answer questions" using examples. The advice unit can also explain to the examinee (child) "the flow of an interview" using diagrams. This allows the examinee (child) to easily understand basic interview skills. Some or all of the above-described processing in the advice unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the advice unit can input the examinee's (child's) questions into the generation AI, which can then answer in easy-to-understand terms.

[0067] The advice unit can provide detailed advice on what to wear for the interview and how to support the child. Detailed advice includes, for example, specific procedures, examples, checklists, etc., but is not limited to these examples. For example, the advice unit provides specific advice to the parent on "what to wear for the interview." The advice unit can also provide advice to the parent on "how to support the child" using examples. The advice unit can also provide advice to the parent on "things to pay attention to on the day of the interview" using a checklist. This allows the parent to receive specific advice and effectively support the child. Some or all of the above-mentioned processing in the advice unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the advice unit can input the parent's question into the generation AI, which then provides detailed advice.

[0068] The advice unit can estimate the emotions of the test-taker (child) and adjust the way the advice is presented based on the estimated emotions. Examples of emotion estimation include, but are not limited to, facial expression recognition, voice analysis, and behavior analysis. For example, if the test-taker (child) is nervous, the generation AI can provide gentle advice to help the test-taker (child) relax. For example, if the test-taker (child) is excited, the advice unit can provide calm advice to help the test-taker (child) concentrate. For example, if the test-taker (child) is tired, the generation AI can provide concise and easy-to-understand advice to reduce the test-taker's burden. This allows appropriate advice to be provided based on the test-taker's (child's) emotions. The emotion estimation is achieved using, for example, an emotion engine or a generation AI with an emotion estimation function. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the advice unit may be performed using, for example, the generation AI, or without the generation AI. For example, the advice unit can input the test-taker's (child's) emotional data into the generation AI, which can then adjust the way the advice is expressed.

[0069] The advice unit can analyze the test taker's (child's) past learning history and select the optimal advice method. Examples of optimal advice methods include, but are not limited to, individual instruction, group instruction, online resources, etc. For example, the advice unit can have the generation AI provide focused advice on questions that the test taker (child) previously struggled with. The advice unit can also have the generation AI provide specific advice to strengthen the test taker's (child's) areas of strength. The advice unit can also have the generation AI identify areas for improvement based on the test taker's (child's) past mock interview results and provide effective advice. This allows for effective advice based on the test taker's (child's) past learning history. Some or all of the above-described processing in the advice unit can be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) learning history data into the generation AI, which can then select the optimal advice method.

[0070] When providing advice, the advice unit can adjust the level of detail of the advice based on the test taker's (child's) current level of understanding. Examples of adjustments based on the level of understanding include, but are not limited to, test results, feedback, and observation results. For example, if the test taker's (child's) level of understanding is high, the advice unit's generation AI can provide detailed advice to further improve the test taker's (child's) skills. Furthermore, if the test taker's (child's) level of understanding is low, the advice unit's generation AI can provide advice that focuses on basic points. Furthermore, the advice unit's generation AI can gradually adjust the difficulty of the advice depending on the test taker's (child's) level of understanding. This allows appropriate advice to be provided according to the test taker's (child's) level of understanding. Some or all of the above-described processing in the advice unit may be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) level of understanding data into the generation AI, which can then adjust the level of detail of the advice.

[0071] When providing advice, the advice unit can customize the advice content based on the interests and concerns of the test-taker (child). Examples of customization based on interests and concerns include, but are not limited to, questionnaire results, past behavioral history, and hobbies. For example, the advice unit provides advice by having the generation AI incorporate questions related to topics that interest the test-taker (child). The advice unit can also provide advice by having the generation AI use specific examples based on the test-taker's (child's) areas of interest. The advice unit can also incorporate content related to the test-taker's (child's) hobbies and special skills into the advice. This allows advice to be provided that is tailored to the test-taker's (child's) interests and concerns. Some or all of the above-described processing in the advice unit may be performed using, or without, the generation AI. For example, the advice unit can input the test-taker's (child's) interests and concerns data into the generation AI, which can then customize the advice content.

[0072] The advice unit can estimate the emotions of the test taker (child) and prioritize advice based on the estimated emotions. Prioritization can be based on, for example, importance, urgency, and impact, but is not limited to these examples. For example, if the test taker (child) is feeling anxious, the generation AI can prioritize advice that provides a sense of security. Furthermore, if the test taker (child) is confident, the advice unit can prioritize advice that encourages further challenges. Furthermore, if the test taker (child) is confused, the generation AI can provide advice starting with basic points. This allows advice to be provided in a prioritized order based on the test taker's (child's) emotions. The emotion estimation is achieved using, for example, an emotion engine or a generation AI with an emotion estimation function. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the advice unit can be performed using, for example, the generation AI, or without the generation AI. For example, the advice unit can input emotional data of the examinee (child) into the generation AI, which can then determine the priority of advice.

[0073] When providing advice, the advice unit can provide highly relevant advice by taking into account the geographical location information of the test taker (child). Geographical location information includes, but is not limited to, GPS data, address information, and location sensor data. In the advice unit, for example, the generation AI provides specific advice based on the characteristics of the area where the test taker (child) lives. In addition, the advice unit can incorporate information related to the location of the test taker's (child's) school into the advice. In addition, the advice unit can provide appropriate advice based on the culture and customs of the test taker's (child's) area. This makes it possible to provide appropriate advice based on the test taker's (child's) geographical location information. Some or all of the above-mentioned processing in the advice unit may be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) geographical location information data into the generation AI, which can then provide highly relevant advice.

[0074] When providing advice, the advice unit can analyze the social media activity of the test taker (child) and provide relevant advice. Social media activity includes, but is not limited to, post content, number of followers, and engagement rate. In the advice unit, for example, the generation AI provides advice based on topics the test taker (child) is interested in on social media. The advice unit can also analyze the test taker's (child's) social media activity history and provide appropriate advice. The advice unit can also provide relevant advice based on the test taker's (child's) social media friendships. This allows appropriate advice to be provided based on the test taker's (child's) social media activity. Some or all of the above-described processing in the advice unit may be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) social media activity data into the generation AI, and the generation AI can provide relevant advice.

[0075] When providing advice, the advice unit can customize the advice method by reflecting the test taker's (child's) past feedback. Past feedback includes, but is not limited to, questionnaire results, evaluation comments, and observation results. In the advice unit, for example, the generation AI adjusts the content of the advice based on feedback the test taker (child) has received in the past. In addition, the advice unit can identify areas for improvement from the test taker's (child's) past feedback and provide specific advice. In addition, the advice unit can analyze the test taker's (child's) feedback history and select the optimal advice method. This allows appropriate advice to be provided based on the test taker's (child's) past feedback. Some or all of the above-mentioned processing in the advice unit can be performed using, or without, the generation AI. For example, the advice unit can input the test taker's (child's) past feedback data into the generation AI, which can then customize the advice method.

[0076] The communication unit can estimate the emotions of the examinee (child) and adjust the way the mock interview proceeds based on the estimated emotions. Examples of how the mock interview proceeds include, but are not limited to, the order of questions, time allocation, and timing of feedback. For example, if the examinee (child) is nervous, the communication unit can have the generation AI proceed with the mock interview at a slow pace. Furthermore, if the examinee (child) is relaxed, the communication unit can have the generation AI proceed with the mock interview at a normal pace. Furthermore, if the examinee (child) is excited, the communication unit can have the generation AI proceed with the mock interview in a calm tone. This allows for an appropriate mock interview to be provided according to the examinee's (child's) emotions. The emotion estimation is achieved using, for example, an emotion engine or a generation AI with an emotion estimation function. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the communication unit can be performed using, for example, the generation AI, or without the generation AI. For example, the communications department can input the emotional data of the test-taker (child) into the generation AI, which can then adjust how the mock interview proceeds.

[0077] During a mock interview, the communication unit can analyze the examinee's (child's) past interview results and provide advice on optimal areas for improvement. Past interview results include, but are not limited to, evaluation sheets, interviewer comments, and video recording data. For example, the communication unit uses the generation AI to identify specific areas for improvement based on the examinee's (child's) past interview results and provide advice. The communication unit can also analyze the examinee's (child's) past interview failures and provide effective improvement measures. The communication unit can also identify areas for improvement based on the examinee's (child's) past interview results and provide advice. This allows the examinee to receive effective advice based on their past interview results. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the examinee's (child's) past interview result data into the generation AI, which then provides advice on optimal areas for improvement.

[0078] During the mock interview, the communication unit can adjust the difficulty of the interview based on the current skill level of the examinee (child). Examples of adjustments based on skill level include, but are not limited to, test results, observation results, and feedback. For example, if the examinee (child) has a high skill level, the communication unit can cause the generation AI to ask more difficult questions. Furthermore, if the examinee (child) has a low skill level, the communication unit can cause the generation AI to ask more basic questions. Furthermore, the communication unit can cause the generation AI to gradually adjust the difficulty of the questions according to the skill level of the examinee (child). This allows for an appropriate mock interview to be provided according to the skill level of the examinee (child). Some or all of the above-described processing in the communication unit can be performed using, or without, the generation AI. For example, the communication unit can input the skill level data of the examinee (child) into the generation AI, which can then adjust the difficulty of the interview.

[0079] During the mock interview, the communication unit can customize the interview content based on the interests and concerns of the test taker (child). Customization of the interview content includes, but is not limited to, the type of questions, scenarios, and evaluation criteria. For example, the communication unit allows the generation AI to ask questions related to topics that interest the test taker (child). The communication unit can also allow the generation AI to ask questions using specific examples based on the test taker's (child's) areas of interest. The communication unit can also allow the generation AI to incorporate content related to the test taker's (child's) hobbies and special skills into the interview. This allows for an appropriate mock interview tailored to the test taker's (child's) interests and concerns. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the test taker's (child's) interests and concerns data into the generation AI, which can then customize the interview content.

[0080] The communication unit can estimate the emotions of the test taker (child) and adjust the feedback method for the mock interview based on the estimated emotions. Examples of adjusting the feedback method include, but are not limited to, oral feedback, written feedback, and video feedback. For example, if the test taker (child) is nervous, the communication unit can have the generation AI provide feedback in a gentle tone. Furthermore, if the test taker (child) is relaxed, the communication unit can have the generation AI provide detailed feedback. Furthermore, if the test taker (child) is excited, the communication unit can have the generation AI provide feedback in a calm tone. This allows appropriate feedback to be provided according to the test taker's (child's) emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the communication unit can be performed using, for example, the generation AI, or without the generation AI. For example, the communication department can input the test-taker's (child's) emotional data into the generation AI, which can then adjust the feedback method.

[0081] During a mock interview, the communication unit can provide relevant questions by taking into account the geographic location information of the test taker (child). Relevant questions include, but are not limited to, regional characteristics, cultural background, and local news. For example, the communication unit allows the generation AI to ask specific questions based on the regional characteristics of the test taker (child). The communication unit can also allow the generation AI to incorporate information related to the location of the test taker's (child's) school into the questions. The communication unit can also allow the generation AI to provide appropriate questions based on the culture and customs of the test taker's (child's) region. This allows appropriate questions to be provided based on the test taker's (child's) geographic location information. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the test taker's (child's) geographic location information data into the generation AI, which can then provide relevant questions.

[0082] During the mock interview, the communication unit can analyze the social media activity of the test taker (child) and provide relevant questions. Examples of analyzing social media activity include, but are not limited to, analyzing post content, analyzing followers, and evaluating engagement. For example, the communication unit allows the generation AI to ask questions based on topics the test taker (child) is interested in on social media. The communication unit can also analyze the test taker's (child's) social media activity history and provide appropriate questions. The communication unit can also allow the generation AI to ask relevant questions based on the test taker's (child's) social media friendships. This allows appropriate questions to be provided based on the test taker's (child's) social media activity. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the test taker's (child's) social media activity data into the generation AI, which then provides relevant questions.

[0083] During a mock interview, the communication unit can customize the interview method by reflecting the examinee's (child's) past feedback. Customization of the interview method includes, but is not limited to, the type of questions, the scenario, and the evaluation criteria. For example, the communication unit allows the generation AI to adjust the content of the interview based on the examinee's (child's) past feedback. The communication unit can also allow the generation AI to identify areas for improvement based on the examinee's (child's) past feedback and ask specific questions. The communication unit can also analyze the examinee's (child's) feedback history and select the optimal interview method. This allows an appropriate interview method to be provided based on the examinee's (child's) past feedback. Some or all of the above-described processing in the communication unit may be performed using, or without, the generation AI. For example, the communication unit can input the examinee's (child's) past feedback data into the generation AI, which can then customize the interview method.

[0084] The countermeasure unit can estimate the guardian's emotions and adjust the way in which the countermeasure is expressed based on the estimated emotions. Estimating emotions includes, but is not limited to, facial expression recognition, voice analysis, and behavioral analysis. For example, if the guardian is feeling anxious, the countermeasure unit can have the generation AI advise the guardian on countermeasures using expressions that provide a sense of security. Furthermore, if the guardian is relaxed, the countermeasure unit can have the generation AI provide detailed countermeasures. Furthermore, if the guardian is busy, the countermeasure unit can have the generation AI provide concise and easy-to-understand countermeasures. This allows appropriate countermeasures to be provided according to the guardian's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the countermeasure unit can be performed using, for example, the generation AI, or without the generation AI. For example, the countermeasure unit can input the guardian's emotion data into the generation AI, which can then adjust the way in which the countermeasure is expressed.

[0085] The countermeasure unit can analyze the guardian's past countermeasure history and select the optimal countermeasure method. The past countermeasure history includes, for example, but is not limited to, the content of the countermeasure, the implementation date and time, and the results. For example, the countermeasure unit analyzes the effectiveness of countermeasures taken by the guardian in the past, and the generation AI proposes the optimal countermeasure method. The countermeasure unit can also identify effective countermeasures from the guardian's past countermeasure history and provide specific advice. The countermeasure unit can also identify areas for improvement based on the guardian's countermeasure history and propose effective countermeasures. This makes it possible to provide effective countermeasures based on the guardian's past countermeasure history. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the guardian's past countermeasure history data into the generation AI, and the generation AI can select the optimal countermeasure method.

[0086] When implementing countermeasures, the countermeasure unit can adjust the level of detail of the countermeasures based on the parent's current level of understanding. Examples of adjustments based on the parent's level of understanding include, but are not limited to, test results, feedback, and observation results. For example, if the parent's level of understanding is high, the countermeasure unit can have the generation AI provide detailed countermeasures to further improve the parent's skills. Furthermore, if the parent's level of understanding is low, the countermeasure unit can have the generation AI implement countermeasures that focus on basic points. Furthermore, the countermeasure unit can have the generation AI gradually adjust the difficulty of the countermeasures based on the parent's level of understanding. This allows appropriate countermeasures to be provided according to the parent's level of understanding. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the parent's level of understanding data into the generation AI, which can then adjust the level of detail of the countermeasures.

[0087] When implementing the measures, the countermeasure unit can customize the countermeasure content based on the parents' interests and concerns. Examples of customizing the countermeasure content include, but are not limited to, individual instruction, group instruction, online resources, etc. In the countermeasure unit, for example, the generation AI incorporates countermeasures related to topics of interest to the parents and provides advice. The countermeasure unit can also implement countermeasures using specific examples based on the parents' areas of interest. The countermeasure unit can also incorporate content related to the parents' hobbies and special skills into the countermeasures. This makes it possible to provide appropriate countermeasures tailored to the parents' interests and concerns. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the parents' interest data into the generation AI, which then customizes the countermeasure content.

[0088] The countermeasure unit can estimate the guardian's emotions and prioritize countermeasures based on the estimated emotions. Prioritization can be based on, for example, importance, urgency, and impact, but is not limited to these examples. For example, if the guardian is feeling anxious, the countermeasure unit can have the generation AI prioritize countermeasures that provide a sense of security. Furthermore, if the guardian is feeling confident, the countermeasure unit can also prioritize countermeasures that encourage further challenges. Furthermore, if the guardian is confused, the countermeasure unit can have the generation AI implement countermeasures in order, starting with basic points. This allows countermeasures to be provided in a prioritized order based on the guardian's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the countermeasure unit can be performed using, for example, the generation AI. For example, the countermeasure unit can input the guardian's emotion data into the generation AI, which can then prioritize the countermeasures.

[0089] When taking countermeasures, the countermeasure unit can provide highly relevant countermeasures by taking into account the guardian's geographical location information. Geographical location information includes, but is not limited to, GPS data, address information, and location sensor data. In the countermeasure unit, for example, the generation AI can take specific countermeasures based on the characteristics of the area where the guardian lives. The countermeasure unit can also incorporate information related to the location of the guardian's school into the countermeasure. The countermeasure unit can also provide appropriate countermeasures based on the culture and customs of the guardian's area. This makes it possible to provide appropriate countermeasures based on the guardian's geographical location information. Some or all of the above-mentioned processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the guardian's geographical location information data into the generation AI, which can then provide highly relevant countermeasures.

[0090] When taking countermeasures, the countermeasure unit can analyze the parent's social media activity and provide relevant countermeasures. Examples of analyzing social media activity include, but are not limited to, analyzing post content, analyzing followers, and evaluating engagement. For example, the countermeasure unit uses a generation AI to take countermeasures based on topics the parent is interested in on social media. The countermeasure unit can also analyze the parent's social media activity history and provide appropriate countermeasures. The countermeasure unit can also use the parent's social media friendships as a reference to take relevant countermeasures. This allows appropriate countermeasures to be provided based on the parent's social media activity. Some or all of the above-described processing in the countermeasure unit may be performed using, or without, the generation AI. For example, the countermeasure unit can input the parent's social media activity data into the generation AI, which then provides relevant countermeasures.

[0091] When taking countermeasures, the countermeasure unit can customize the countermeasure method by reflecting the parent's past feedback. Past feedback includes, but is not limited to, for example, survey results, evaluation comments, and observation results. In the countermeasure unit, for example, the generation AI adjusts the content of the countermeasure based on the parent's past feedback. In addition, the countermeasure unit can have the generation AI identify areas for improvement from the parent's past feedback and implement specific countermeasures. In addition, the countermeasure unit can analyze the parent's feedback history and have the generation AI select the optimal countermeasure method. This makes it possible to provide appropriate countermeasures based on the parent's past feedback. Some or all of the above-mentioned processing in the countermeasure unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the countermeasure unit can input the parent's past feedback data into the generation AI, and the generation AI can customize the countermeasure method. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned advice unit, communication unit, and countermeasure unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the advice unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the communication unit realizes a dialogue between the test taker (child) and an AI avatar using the camera 42 and microphone 38B of the smart device 14, and identifies areas for improvement using the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the countermeasure unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, allowing a parent or guardian to receive advice from the generation AI using a smartphone. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned advice unit, communication unit, and countermeasure unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the advice unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the communication unit realizes a dialogue between the test taker (child) and the AI ​​avatar using the camera 42 and microphone 238 of the smart glasses 214, and finds areas for improvement by the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the countermeasure unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and a parent or guardian can receive advice from the generation AI using a smartphone. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned advice unit, communication unit, and countermeasure unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the advice unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the communication unit realizes a dialogue between the test taker (child) and the AI ​​avatar using the camera 42 and microphone 238 of the headset type terminal 314, and finds areas for improvement by the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the countermeasure unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and a parent or guardian can receive advice from the generation AI using a smartphone. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned advice unit, communication unit, and countermeasure unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the advice unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the communication unit realizes a dialogue between the test taker (child) and the AI ​​avatar using the camera 42 and microphone 238 of the robot 414, and finds areas for improvement by the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the countermeasure unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and a parent or guardian can receive advice from the generation AI using a smartphone.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The advice department can analyze the learning style of the test-taker (child) and provide the most appropriate advice method. For example, visual learners can receive advice using diagrams and videos, while auditory learners can receive audio guides. Experiential learners can also receive advice through an actual interview simulation. This allows for effective advice to be provided according to the test-taker's (child's) learning style.

[0094] The communication department can estimate the emotions of the test-taker (child) and adjust the questions asked in the mock interview based on the estimated emotions. For example, if the test-taker (child) is nervous, the generation AI will start with simple questions to relax the test-taker (child). If the test-taker (child) is confident, the generation AI can ask more challenging questions. Furthermore, if the test-taker (child) is tired, the generation AI can select questions that can be completed in a short time. This allows the system to provide appropriate questions according to the test-taker's (child's) emotions.

[0095] The countermeasures department can provide a community function that allows parents to share information with other parents. For example, parents can post successful countermeasures, which other parents can use as reference. Parents can also post questions about countermeasures, which other parents or the generation AI can answer. Furthermore, parents can share their progress in countermeasures and encourage each other. This allows parents to cooperate with each other to implement effective countermeasures.

[0096] The advice unit can estimate the emotions of the test-taker (child) and adjust the timing of advice based on the estimated emotions. For example, if the test-taker (child) is concentrating, the generation AI can provide detailed advice. If the test-taker (child) is tired, the generation AI can also provide short, concise advice. Furthermore, if the test-taker (child) is relaxed, the generation AI can also provide advice on how to proceed to the next step. This allows advice to be provided at the appropriate time according to the test-taker's (child's) emotions.

[0097] The communication department can analyze the past mock interview results of the test taker (child) and provide the optimal feedback method. For example, the generation AI will advise specific areas for improvement for questions that the test taker (child) had difficulty with in the past. The generation AI can also provide detailed feedback to strengthen the areas in which the test taker (child) excels. Furthermore, the generation AI can select an effective feedback method based on the test taker's (child's) past mock interview results. This allows for effective feedback to be provided based on the test taker's (child's) past results.

[0098] The countermeasures department allows the generation AI to provide real-time support to parents as they implement countermeasures. For example, if a parent has a question while implementing countermeasures, the generation AI can provide an immediate answer. The generation AI can also provide real-time feedback so that parents can check the progress of the countermeasures. Furthermore, the generation AI can also provide real-time evaluation so that parents can check the effectiveness of the countermeasures. This allows parents to implement countermeasures efficiently.

[0099] The advice unit can estimate the emotions of the test-taker (child) and adjust the content of the advice based on the estimated emotions. For example, if the test-taker (child) is feeling anxious, the generation AI can provide advice that reassures them. Alternatively, if the test-taker (child) is confident, the generation AI can provide advice that encourages them to try harder. Furthermore, if the test-taker (child) is confused, the generation AI can provide advice starting with the basic points. This allows the system to provide appropriate advice according to the test-taker's (child's) emotions.

[0100] The communication department can estimate the emotions of the examinee (child) and adjust the feedback method during the mock interview based on the estimated emotions. For example, if the examinee (child) is nervous, the generation AI can provide feedback in a gentle tone. Alternatively, if the examinee (child) is relaxed, the generation AI can provide detailed feedback. Furthermore, if the examinee (child) is excited, the generation AI can provide feedback in a calm tone. This allows the system to provide appropriate feedback according to the examinee's (child's) emotions.

[0101] When parents implement countermeasures, the generation AI can monitor the progress of the countermeasures in real time and provide advice as needed. For example, the generation AI can provide real-time feedback so that parents can check the progress of the countermeasures. The generation AI can also evaluate the countermeasures in real time so that parents can check their effectiveness. Furthermore, if parents have any questions while the countermeasures are in progress, the generation AI can provide immediate answers. This allows parents to implement countermeasures efficiently.

[0102] The advice unit can estimate the emotions of the test-taker (child) and prioritize advice based on the estimated emotions. For example, if the test-taker (child) is feeling anxious, the generation AI will first prioritize advice that provides reassurance. Alternatively, if the test-taker (child) is confident, the generation AI can prioritize advice that encourages further challenges. Furthermore, if the test-taker (child) is confused, the generation AI can provide advice starting with the basic points. This allows advice to be provided in order of priority according to the test-taker's (child's) emotions.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The Advice Department provides advice to the applicants (children) and their parents on what they need to remember. For example, they explain to the applicants (children) in simple terms how to greet and answer questions at the interview, and they give specific advice to the parents on what to wear to the interview and how to support their child. Step 2: In the communication department, the test-taker (child) and the AI ​​avatar communicate repeatedly to identify areas for improvement. For example, the test-taker (child) conducts a mock interview with the AI ​​avatar, and the generating AI gives advice on areas for improvement based on the results. Step 3: The countermeasures department allows parents to implement countermeasures in their spare time. For example, parents can use their smartphones to receive advice from the AI ​​generator during breaks at work.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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 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.

[0123] 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.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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 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.

[0139] 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.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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 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.

[0156] 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.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0175] 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.

[0176] [Explanation of symbols]

[0177] 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. An advice department that gives advice to test takers and their parents on what they should remember, a communication unit in which the examinee and the AI ​​avatar repeatedly communicate with each other based on the advice given by the advising unit to find areas for improvement; and a countermeasure section for allowing parents to take measures in their spare time based on the improvements obtained by the communication section. A system characterized by:

2. The advice unit Advise on areas for improvement in a way that test takers can understand 2. The system of claim 1.

3. The communication unit Candidates and AI avatars will conduct mock interviews, and advice on areas for improvement will be provided based on the results.

2. The system of claim 1.

4. The countermeasure unit Parents can use their smartphones to receive advice from the AI ​​generator.

2. The system of claim 1.

5. The advice unit Explain in simple terms how to greet people and answer questions during an interview 2. The system of claim 1.

6. The advice unit Detailed advice on how to dress for the interview and how to support your children 2. The system of claim 1.

7. The advice unit Estimate the emotions of the test-taker (child) and adjust the way advice is expressed based on the estimated emotions 2. The system of claim 1.

8. The advice unit Analyze the test taker's (child's) past learning history and select the most appropriate advice method 2. The system of claim 1.

Images