system

Abstract

The system according to this embodiment aims to enable examinees to learn while competing with appropriate rivals and receiving optimal stimulation. [Solution] The system according to the embodiment comprises a collection unit, a generation unit, and a navigation unit. The collection unit collects data on the examinee's state, changes, personality, test and match results, daily lesson content, and goals. The generation unit analyzes the data collected by the collection unit and generates rival agents. The navigation unit enables the rival agents generated by the generation unit to interact with the examinee and provide advice and encouragement.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to provide an environment where examinees can compete with appropriate rivals, and excessive competition may have an adverse effect on stress and human relationships.

[0005] The system according to the embodiment aims to enable examinees to compete with appropriate rivals and proceed with learning while receiving optimal stimulation.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a generation unit, and a navigation unit. The collection unit collects data on the examinee's state, changes, personality, test and match results, daily lesson content, and goals. The generation unit analyzes the data collected by the collection unit and generates rival agents. The navigation unit enables the rival agents generated by the generation unit to interact with the examinee and provide advice and encouragement. [Effects of the Invention]

[0007] The system according to this embodiment allows examinees to learn while competing with appropriate rivals and receiving optimal stimulation. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The rival agent system according to an embodiment of the present invention is an AI system that functions as a good rival for students studying for exams, enabling them to learn from and improve together. This rival agent system generates an optimal rival agent based on data such as the student's state, changes, personality, exam and competition results, daily lesson content, and goals. The rival agent system provides appropriate stimulation while preventing stress and deterioration of relationships due to excessive competition, thereby maximizing the student's potential. For example, the rival agent system collects data such as the student's state, changes, personality, exam and competition results, daily lesson content, and goals. This includes information such as facial expressions, voice, conversation, grades, and learning content. Next, the AI ​​generates an optimal rival agent based on the collected data. This rival agent is a presence that can learn from, encourage, and advise the student. The rival agent system provides appropriate stimulation to maximize the student's potential and guide them towards their goals. For example, when a student is working towards a goal, the rival agent system maintains the student's motivation by offering appropriate advice and words of encouragement. Furthermore, when a student faces difficulties, the rival agent system proposes appropriate solutions and supports the student. In addition, the rival agent system proposes an optimal study plan based on the student's performance and learning content. This allows students to study efficiently and effectively work towards achieving their goals. The rival agent system also monitors the student's progress in real time and adjusts the study plan as needed. In this way, the rival agent system acts as the best classmate to maximize the student's potential and guide them to their goals. Students can reduce stress and study efficiently by competing and collaborating with the rival agent system. This allows the rival agent system to maximize the student's potential and guide them to their goals.

[0029] The rival agent system according to this embodiment comprises a collection unit, a generation unit, and a navigation unit. The collection unit collects data on the examinee's status, changes, personality, test and match results, daily lesson content, and goals they are aiming for. For example, the collection unit can collect information such as the examinee's health status, mental state, and motivation to learn. The collection unit can also collect information such as fluctuations in grades and changes in learning attitude. Furthermore, the collection unit can collect information on the examinee's personality. For example, the collection unit can collect information such as whether the examinee is introverted or extroverted, and whether they are proactive or passive. The collection unit can also collect information on test and match results. For example, the collection unit can collect information such as the examinee's test scores, ranking, and pass / fail status. The collection unit can also collect information on the daily lesson content. For example, the collection unit can collect information such as the progress of lessons, learning content, and level of understanding. The collection unit can also collect information on the goals the examinee is aiming for. For example, the collection unit can collect information such as the examinee's desired school, target score, and future dreams. The generation unit analyzes the data collected by the collection unit and generates the optimal rival agent. For example, the generation unit can generate a rival agent tailored to the characteristics of the test-taker based on the collected data. The generation unit can generate a rival agent suitable for the test-taker using an AI algorithm. For example, the generation unit can adjust the characteristics of the rival agent based on the test-taker's personality and motivation to learn. The generation unit can adjust the behavioral patterns of the rival agent based on the test-taker's performance and learning content. The generation unit can adjust the response methods of the rival agent based on the test-taker's goals. The navigation unit allows the rival agent generated by the generation unit to interact with the test-taker and provide advice and encouragement. For example, the navigation unit allows the rival agent to chat or have voice conversations with the test-taker. The navigation unit allows the rival agent to provide feedback to the test-taker. The navigation unit allows the rival agent to provide suggestions for learning methods and words to improve motivation to the test-taker.The navigation unit monitors the examinee's progress in real time and adjusts the learning plan as needed. For example, the navigation unit can adjust the learning plan based on the examinee's learning progress and level of understanding. The navigation unit can adjust the learning plan based on the examinee's level of achievement. The navigation unit can collect examinee data in real time and provide feedback. The navigation unit proposes an optimal learning plan based on the examinee's grades and learning content. For example, the navigation unit can propose specific learning methods to improve the examinee's grades. The navigation unit can propose an effective learning plan based on the examinee's learning content. The navigation unit can adjust the learning plan based on the examinee's goals. As a result, the rival agent system according to this embodiment can maximize the examinee's potential and guide them to their goals.

[0030] The data collection department collects data on the examinee's condition, changes, personality, test and competition results, daily lesson content, and goals. Specifically, it can collect information on the examinee's health, mental state, and motivation to learn. For example, it monitors the examinee's health using devices that measure body temperature, heart rate, and stress levels. It can also understand the examinee's mental state and motivation to learn through questionnaires and self-assessment sheets. Furthermore, the data collection department can collect information on fluctuations in grades and changes in learning attitudes. For example, it records scores on regular tests, mock exam results, the number of times students participate in class, and homework submission status to track changes in learning attitudes. The data collection department can also collect information on the examinee's personality. For example, it conducts personality tests and psychological tests to collect information on whether the examinee is introverted or extroverted, and whether they are proactive or passive. This allows for the provision of appropriate support tailored to the examinee's personality. The data collection department can also collect information on test and competition results. For example, it collects information on the examinee's test scores, rankings, and pass / fail status, and analyzes trends in grades by comparing them with past performance data. The data collection unit can also collect information related to the content of daily lessons. For example, it collects information such as the progress of lessons, learning content, and level of understanding to grasp the learning situation of students preparing for exams. It digitizes notes taken during lessons, homework content, and teacher feedback, and stores them in a database. The data collection unit can also collect information related to the goals that students are aiming for. For example, it collects information such as students' desired schools, target scores, and future dreams, and uses this as basic data to develop concrete plans for achieving those goals. In this way, the data collection unit can comprehensively collect diverse information about students and build a foundation for providing support tailored to their individual needs.

[0031] The generation unit analyzes the data collected by the collection unit and generates the optimal rival agent. Specifically, it can generate a rival agent tailored to the characteristics of the test-taker based on the collected data. The generation unit uses an AI algorithm to generate a rival agent suitable for the test-taker. For example, it can use a machine learning model to adjust the characteristics of the rival agent based on the test-taker's personality and motivation to learn. For introverted test-takers, it generates an agent that is gentle and offers many words of encouragement, while for extroverted test-takers, it generates an agent that stimulates a competitive spirit. Furthermore, the generation unit can adjust the behavior patterns of the rival agent based on the test-taker's grades and learning content. For example, for test-takers whose grades are improving, it generates an agent that presents increasingly difficult problems, while for test-takers whose grades are stagnating, it generates an agent that repeatedly presents basic problems. In addition, the generation unit can adjust the response method of the rival agent based on the test-taker's goals. For example, for test-takers aiming to pass the entrance exam for their desired school, it generates an agent that provides specific advice for passing the exam, while for test-takers with long-term goals for their future dreams, it generates an agent that provides words of encouragement to maintain motivation. This allows the generation unit to create the optimal rival agent for each test-taker and provide support tailored to their individual needs.

[0032] The Navigation Unit allows rival agents generated by the Generation Unit to interact with test-takers, providing advice and encouragement. Specifically, rival agents can chat and have voice conversations with test-takers. For example, if a test-taker has questions during their studies, the rival agent can provide real-time answers to help them deepen their understanding. Also, when a test-taker is losing motivation to study, the rival agent can boost their motivation through words of encouragement and sharing of success stories. The Navigation Unit allows rival agents to provide feedback to test-takers. For example, based on mock exam results and daily study progress, it can suggest specific areas for improvement and tasks to tackle next. The Navigation Unit allows rival agents to offer suggestions for study methods and words to boost motivation. For example, it can suggest efficient time management methods and effective review methods to help test-takers establish a study style that suits them. The Navigation Unit monitors the test-taker's progress in real time and adjusts the study plan as needed. For example, it can adjust the study plan based on the test-taker's learning progress and level of understanding. If a student is ahead of schedule, the navigation system will present new challenges to help them move on to the next step; conversely, if they are behind, it will suggest review or supplementary lessons. The navigation system can adjust the learning plan based on the student's progress. For example, if a student has not reached their target score, it will identify areas that need more focus and suggest intensive study. The navigation system can collect student data in real time and provide feedback. This allows the navigation system to propose the optimal learning plan based on the student's performance and learning content, maximizing their potential.

[0033] The data collection unit can collect information on facial expressions, voice, conversation, grades, and learning content. For example, the data collection unit can capture a test-taker's facial expressions with a camera and analyze changes in facial expressions using facial expression analysis technology. The data collection unit can record a test-taker's voice and analyze the tone of voice and speaking style using voice analysis technology. The data collection unit can record a test-taker's conversations and analyze the content and topics of the conversations using conversation analysis technology. The data collection unit can collect a test-taker's grades and analyze test scores and evaluations using grade analysis technology. The data collection unit can collect a test-taker's learning content and analyze subjects, units, and level of understanding using learning content analysis technology. As a result, the data collection unit can generate more accurate rival agents by collecting diverse information on test-takers. Some or all of the above-described processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input facial expression data captured by a camera into a generating AI and have the generating AI perform an analysis of changes in facial expressions.

[0034] The generation unit can generate optimal rival agents based on collected data. For example, the generation unit can analyze the collected data and generate rival agents tailored to the characteristics of the test-taker. The generation unit can use an AI algorithm to generate rival agents suitable for the test-taker. For example, the generation unit can adjust the characteristics of the rival agents based on the test-taker's personality and motivation to learn. The generation unit can adjust the behavioral patterns of the rival agents based on the test-taker's performance and learning content. The generation unit can adjust the response methods of the rival agents based on the test-taker's goals. In this way, the generation unit can provide appropriate stimulation to the test-taker by generating optimal rival agents based on collected data. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the collected data into a generation AI and have the generation AI perform the generation of rival agents.

[0035] The navigation unit allows the generated rival agents to interact with the test-taker and provide appropriate advice and words of encouragement. For example, the navigation unit allows rival agents to chat or have voice conversations with the test-taker. The navigation unit allows rival agents to provide feedback to the test-taker. The navigation unit allows rival agents to provide the test-taker with suggestions for learning methods and words to improve motivation. In this way, the navigation unit can maintain the test-taker's motivation and improve learning effectiveness by interacting with the test-taker. Some or all of the above processes in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input the response data of the rival agents into a generating AI and have the generating AI perform the generation of advice and words of encouragement.

[0036] The navigation unit can monitor the student's progress in real time and adjust the learning plan as needed. For example, the navigation unit can adjust the learning plan based on the student's learning progress and understanding. The navigation unit can adjust the learning plan based on the student's achievement level. The navigation unit can collect student data in real time and provide feedback. The navigation unit can propose an optimal learning plan based on the student's grades and learning content. For example, the navigation unit can propose specific learning methods to improve the student's grades. The navigation unit can propose an effective learning plan based on the student's learning content. The navigation unit can adjust the learning plan based on the student's goals. This allows the navigation unit to support efficient learning by adjusting the learning plan according to the student's progress. Some or all of the above processes in the navigation unit may be performed using AI, or not. For example, the navigation unit can input data collected in real time into a generating AI and have the generating AI adjust the learning plan.

[0037] The generation unit can propose an optimal learning plan based on the student's grades and learning content. For example, the generation unit can analyze the student's grades and propose specific learning methods to improve them. The generation unit can analyze the student's learning content and propose an effective learning plan. The generation unit can adjust the learning plan based on the student's goals. In this way, the generation unit can maximize learning effectiveness by proposing an optimal learning plan based on the student's grades and learning content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input grade data and learning content data into a generation AI and have the generation AI propose a learning plan.

[0038] The data collection unit can analyze the past learning history of test takers and select the optimal data collection method. For example, the data collection unit can select a data collection method based on learning methods that have been effective for the test taker in the past. The data collection unit can analyze the past performance improvement patterns of test takers and select the optimal data collection method. The data collection unit can select a data collection method based on the learning tools that the test taker has used in the past. As a result, the data collection unit can select the optimal data collection method by analyzing past learning history, enabling efficient data collection. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input past learning history data into a generating AI and have the generating AI select the data collection method.

[0039] The data collection unit can filter data based on the examinee's current learning status and areas of interest during data collection. For example, the data collection unit can prioritize the collection of data related to the subject the examinee is currently studying. The data collection unit can filter and collect relevant data based on the examinee's areas of interest. The data collection unit can collect only the necessary data according to the examinee's learning progress. In this way, the data collection unit can efficiently collect only the necessary data by filtering the data based on the examinee's current learning status and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input current learning status data and areas of interest data into a generating AI and have the generating AI perform data filtering.

[0040] The data collection unit can prioritize the collection of highly relevant data by considering the geographical location information of the test takers during data collection. For example, if the test taker is at home, the data collection unit can prioritize the collection of data related to home study. If the test taker is at school, the data collection unit can prioritize the collection of data related to school lessons. If the test taker is at the library, the data collection unit can prioritize the collection of data related to studying at the library. In this way, the data collection unit can efficiently collect highly relevant data by considering the geographical location information of the test takers. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input geographical location data into a generating AI and have the generating AI perform the collection of highly relevant data.

[0041] The data collection unit can analyze the social media activities of test takers and collect relevant data during data collection. For example, the data collection unit can collect data based on learning content shared by test takers on social media. The data collection unit can collect information on educational accounts that test takers follow on social media. The data collection unit can collect information on learning groups that test takers participate in on social media. This allows the data collection unit to efficiently collect data related to test takers by analyzing their social media activities. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input social media activity data into a generating AI and have the generating AI perform the collection of relevant data.

[0042] The generation unit can adjust the level of detail generated when generating rival agents based on the student's learning progress. For example, if the student's learning progress is good, the generation unit can generate rival agents that provide detailed advice. If the student's learning progress is slow, the generation unit can generate rival agents that provide basic advice. The generation unit can generate rival agents that provide an appropriate level of advice depending on the student's learning progress. Thus, the generation unit can generate rival agents that provide an appropriate level of advice by adjusting the level of detail generated based on the student's learning progress. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input learning progress data into a generation AI and have the generation AI perform the adjustment of the level of detail generated.

[0043] The generation unit can apply different generation algorithms depending on the test-taker's goals when generating rival agents. For example, if the test-taker has short-term goals, the generation unit can generate rival agents that provide short-term advice. If the test-taker has long-term goals, the generation unit can generate rival agents that provide long-term advice. The generation unit can generate rival agents that apply the appropriate generation algorithm depending on the test-taker's goals. In this way, the generation unit can generate rival agents that are suitable for the test-taker's goals by applying different generation algorithms depending on the test-taker's goals. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input goal data into a generation AI and have the generation AI execute the application of the generation algorithm.

[0044] The generation unit can determine the generation priority based on the applicant's submission timing when generating rival agents. For example, if an applicant is preparing for an exam soon, the generation unit can prioritize generating rival agents specifically tailored to exam preparation. If an applicant has a long-term study plan, the generation unit can generate rival agents aligned with that plan. The generation unit can generate rival agents at the appropriate time depending on the applicant's submission timing. In this way, the generation unit can generate rival agents at the appropriate time by determining the generation priority based on the applicant's submission timing. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input submission timing data into a generation AI and have the generation AI determine the generation priority.

[0045] The generation unit can adjust the generation order of rival agents based on the relevance of the test-takers when generating them. For example, if a test-taker is focusing on a particular subject, the generation unit can prioritize generating rival agents related to that subject. If a test-taker is studying multiple subjects, the generation unit can generate rival agents according to their learning progress. The generation unit can generate rival agents in an appropriate order based on the test-taker's learning plan. In this way, the generation unit can generate rival agents in an appropriate order by adjusting the generation order based on the relevance of the test-takers. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input relevance data into a generation AI and have the generation AI perform the adjustment of the generation order.

[0046] The navigation unit can adjust the level of detail of advice based on the student's learning progress during navigation. For example, if the student's learning progress is good, the navigation unit can provide detailed advice. If the student's learning progress is behind, the navigation unit can provide basic advice. The navigation unit can provide an appropriate level of advice according to the student's learning progress. In this way, the navigation unit can provide an appropriate level of advice by adjusting the level of detail of advice based on the student's learning progress. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input learning progress data into a generating AI and have the generating AI perform the adjustment of the level of detail of the advice.

[0047] The navigation unit can apply different navigation algorithms during navigation depending on the examinee's goals. For example, if the examinee has short-term goals, the navigation unit can apply a navigation algorithm that provides short-term advice. If the examinee has long-term goals, the navigation unit can apply a navigation algorithm that provides long-term advice. The navigation unit can apply an appropriate navigation algorithm depending on the examinee's goals. In this way, the navigation unit can provide advice that is appropriate to the examinee's goals by applying different navigation algorithms depending on the examinee's goals. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input goal data into a generating AI and have the generating AI execute the application of the navigation algorithm.

[0048] The navigation unit can prioritize advice based on the applicant's submission timing during navigation. For example, if an applicant is close to the exam, the navigation unit can prioritize advice specifically tailored to exam preparation. If an applicant has a long-term study plan, the navigation unit can provide advice aligned with that plan. The navigation unit can provide advice at the appropriate time depending on the applicant's submission timing. Thus, by prioritizing advice based on the applicant's submission timing, the navigation unit can provide advice at the appropriate time. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not using AI. For example, the navigation unit can input submission timing data into a generating AI and have the generating AI determine the priority of advice.

[0049] The navigation unit can adjust the order of advice based on the examinee's relevance during navigation. For example, if an examinee is focusing on a particular subject, the navigation unit can prioritize providing advice related to that subject. If an examinee is studying multiple subjects, the navigation unit can adjust the order of advice according to their learning progress. The navigation unit can provide advice in an appropriate order based on the examinee's learning plan. In this way, the navigation unit can provide advice in an appropriate order by adjusting the order of advice based on the examinee's relevance. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input relevance data into a generating AI and have the generating AI perform the adjustment of the advice order.

[0050] The navigation unit can monitor the student's progress in real time and, when necessary, adjust the learning plan by referring to the student's past learning history to select the optimal adjustment method. For example, the navigation unit can propose an effective learning plan based on the student's past learning history. The navigation unit can analyze the student's past performance improvement patterns and propose an optimal learning plan. The navigation unit can adjust the learning plan based on the learning tools the student has used in the past. In this way, the navigation unit can provide an optimal learning plan by referring to the student's past learning history. Some or all of the above processes in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input past learning history data into a generating AI and have the generating AI select an adjustment method.

[0051] The navigation unit can monitor the student's progress in real time and, when adjusting the learning plan as needed, customize the means of adjustment based on the student's current learning status. For example, the navigation unit can suggest a learning plan related to the subject the student is currently studying. The navigation unit can make necessary adjustments according to the student's learning progress. The navigation unit can customize the optimal learning plan based on the student's learning status. In this way, the navigation unit can provide the optimal learning plan by customizing the means of adjustment based on the student's current learning status. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not using AI. For example, the navigation unit can input current learning status data into a generating AI and have the generating AI perform the customization of the means of adjustment.

[0052] The navigation unit can monitor the student's progress in real time and, when adjusting the study plan as needed, can select the optimal adjustment method by considering the student's geographical location. For example, if the student is at home, the navigation unit can suggest a plan best suited for home study. If the student is at school, the navigation unit can suggest a plan related to school lessons. If the student is at the library, the navigation unit can suggest a plan best suited for studying at the library. In this way, the navigation unit can provide the optimal study plan by considering the student's geographical location. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input geographical location data into a generating AI and have the generating AI select the optimal adjustment method.

[0053] The navigation unit can monitor the student's progress in real time and, when necessary, adjust the learning plan by analyzing the student's social media activity to suggest adjustments. For example, the navigation unit can adjust the learning plan based on the learning content the student shares on social media. The navigation unit can adjust the learning plan based on information from educational accounts the student follows on social media. The navigation unit can adjust the learning plan based on information from learning groups the student participates in on social media. In this way, the navigation unit can provide an optimal learning plan by analyzing the student's social media activity. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input social media activity data into a generating AI and have the generating AI propose adjustment methods.

[0054] The generation unit can analyze a student's past performance and select the most suitable suggestion method when proposing an optimal learning plan based on the student's grades and learning content. For example, the generation unit can propose an effective learning plan based on the student's past performance. The generation unit can analyze a student's past performance improvement patterns and propose an optimal learning plan. The generation unit can propose a learning plan based on the learning tools the student has used in the past. In this way, the generation unit can provide an optimal learning plan by analyzing the student's past performance. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input past performance data into a generation AI and have the generation AI select a suggestion method.

[0055] The generation unit can customize the suggestion method based on the examinee's current learning status when proposing an optimal learning plan based on the examinee's grades and learning content. For example, the generation unit can propose a learning plan related to the subject the examinee is currently studying. The generation unit can make necessary adjustments according to the examinee's learning progress. The generation unit can customize the optimal learning plan based on the examinee's learning status. In this way, the generation unit can provide an optimal learning plan by customizing the suggestion method based on the examinee's current learning status. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI. For example, the generation unit can input current learning status data into a generation AI and have the generation AI perform the customization of the suggestion method.

[0056] The generation unit can select the optimal suggestion method when proposing an optimal study plan based on the examinee's grades and learning content, taking into account the examinee's geographical location. For example, if the examinee is at home, the generation unit can propose a plan best suited for home study. If the examinee is at school, the generation unit can propose a plan related to school lessons. If the examinee is at the library, the generation unit can propose a plan best suited for studying at the library. In this way, the generation unit can provide an optimal study plan by taking into account the examinee's geographical location. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input geographical location data into a generation AI and have the generation AI select the optimal suggestion method.

[0057] The generation unit can propose an optimal learning plan based on the student's grades and learning content, by analyzing the student's social media activity. For example, the generation unit can propose a learning plan based on the learning content the student has shared on social media. The generation unit can propose a learning plan based on information from educational accounts the student follows on social media. The generation unit can propose a learning plan based on information from learning groups the student participates in on social media. In this way, the generation unit can provide an optimal learning plan by analyzing the student's social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input social media activity data into a generation AI and have the generation AI execute suggestions for proposal methods.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] The rival agent system can provide a customized learning environment based on the learner's learning style. For example, if the learner is a visual learner, the collection unit can collect learning materials that heavily utilize visual aids and graphics. If the learner is an auditory learner, it can collect audio materials and podcasts. Furthermore, if the learner is an experiential learner, it can collect practical exercises and simulations. In this way, the rival agent system can provide an optimal learning environment tailored to the learner's learning style.

[0060] The rival agent system can predict a student's learning progress and provide appropriate feedback based on their learning history. For example, the data collection unit can analyze past learning data to identify which subjects a student tends to struggle with. Next, the generation unit can use this information to generate rival agents that provide special support for the subjects the student struggles with. Furthermore, the navigation unit can suggest specific learning methods and resources for the subjects the student tends to struggle with. In this way, the rival agent system can maximize learning effectiveness by predicting the student's learning progress and providing appropriate feedback.

[0061] The rival agent system can incorporate gamification elements to enhance students' motivation to learn. For example, the collection unit can award points and badges based on students' learning progress and performance. Next, the generation unit can generate special rival agents according to the points and badges students have earned. Furthermore, the navigation unit can provide rewards and benefits for goals students have achieved. In this way, the rival agent system can enhance students' motivation to learn and improve learning effectiveness by incorporating gamification elements.

[0062] The rival agent system can utilize environmental sensors to optimize the learning environment for test-takers. For example, the data collection unit can collect data such as temperature, humidity, and lighting in the test-taker's learning environment. Next, the generation unit can generate a rival agent that provides the optimal learning environment based on the collected environmental data. Furthermore, the navigation unit can suggest specific advice and adjustment methods according to the test-taker's learning environment. In this way, the rival agent system can maximize learning effectiveness by optimizing the test-taker's learning environment.

[0063] The rival agent system can utilize biofeedback technology to improve the learning performance of test-takers. For example, the data collection unit can collect physiological data such as the test-taker's heart rate, skin electrical activity, and electroencephalogram (EEG). Next, the generation unit can evaluate the test-taker's stress level and concentration level based on the collected physiological data and generate the optimal rival agent. Furthermore, the navigation unit can suggest relaxation methods and ways to improve concentration based on the test-taker's physiological data. In this way, the rival agent system can improve the learning performance of test-takers by utilizing biofeedback technology.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The data collection unit collects data on the student's condition, changes, personality, test and competition results, daily lesson content, and goals they are aiming for. For example, it can collect information such as the student's health, mental state, motivation to learn, fluctuations in grades, changes in learning attitude, personality (introverted or extroverted, active or passive), test and competition results (test scores and rankings, pass / fail), daily lesson content (progress of lessons, learning content, level of understanding), and goals they are aiming for (desired school, target score, future dreams). Step 2: The generation unit analyzes the data collected by the collection unit and generates the optimal rival agent. For example, based on the collected data, it can generate a rival agent tailored to the characteristics of the test taker, and use an AI algorithm to adjust the characteristics, behavioral patterns, and response methods of the rival agent to suit the test taker. Step 3: The navigation unit interacts with the test-taker using rival agents generated by the generation unit, providing advice and encouragement. For example, rival agents chat or have voice conversations with the test-taker, providing feedback, suggesting learning methods, and offering words of motivation. They also monitor the test-taker's progress in real time and adjust the learning plan as needed.

[0066] (Example of form 2) The rival agent system according to an embodiment of the present invention is an AI system that functions as a good rival for students studying for exams, enabling them to learn from and improve together. This rival agent system generates an optimal rival agent based on data such as the student's state, changes, personality, exam and competition results, daily lesson content, and goals. The rival agent system provides appropriate stimulation while preventing stress and deterioration of relationships due to excessive competition, thereby maximizing the student's potential. For example, the rival agent system collects data such as the student's state, changes, personality, exam and competition results, daily lesson content, and goals. This includes information such as facial expressions, voice, conversation, grades, and learning content. Next, the AI ​​generates an optimal rival agent based on the collected data. This rival agent is a presence that can learn from, encourage, and advise the student. The rival agent system provides appropriate stimulation to maximize the student's potential and guide them towards their goals. For example, when a student is working towards a goal, the rival agent system maintains the student's motivation by offering appropriate advice and words of encouragement. Furthermore, when a student faces difficulties, the rival agent system proposes appropriate solutions and supports the student. In addition, the rival agent system proposes an optimal study plan based on the student's performance and learning content. This allows students to study efficiently and effectively work towards achieving their goals. The rival agent system also monitors the student's progress in real time and adjusts the study plan as needed. In this way, the rival agent system acts as the best classmate to maximize the student's potential and guide them to their goals. Students can reduce stress and study efficiently by competing and collaborating with the rival agent system. This allows the rival agent system to maximize the student's potential and guide them to their goals.

[0067] The rival agent system according to this embodiment comprises a collection unit, a generation unit, and a navigation unit. The collection unit collects data on the examinee's status, changes, personality, test and match results, daily lesson content, and goals they are aiming for. For example, the collection unit can collect information such as the examinee's health status, mental state, and motivation to learn. The collection unit can also collect information such as fluctuations in grades and changes in learning attitude. Furthermore, the collection unit can collect information on the examinee's personality. For example, the collection unit can collect information such as whether the examinee is introverted or extroverted, and whether they are proactive or passive. The collection unit can also collect information on test and match results. For example, the collection unit can collect information such as the examinee's test scores, ranking, and pass / fail status. The collection unit can also collect information on the daily lesson content. For example, the collection unit can collect information such as the progress of lessons, learning content, and level of understanding. The collection unit can also collect information on the goals the examinee is aiming for. For example, the collection unit can collect information such as the examinee's desired school, target score, and future dreams. The generation unit analyzes the data collected by the collection unit and generates the optimal rival agent. For example, the generation unit can generate a rival agent tailored to the characteristics of the test-taker based on the collected data. The generation unit can generate a rival agent suitable for the test-taker using an AI algorithm. For example, the generation unit can adjust the characteristics of the rival agent based on the test-taker's personality and motivation to learn. The generation unit can adjust the behavioral patterns of the rival agent based on the test-taker's performance and learning content. The generation unit can adjust the response methods of the rival agent based on the test-taker's goals. The navigation unit allows the rival agent generated by the generation unit to interact with the test-taker and provide advice and encouragement. For example, the navigation unit allows the rival agent to chat or have voice conversations with the test-taker. The navigation unit allows the rival agent to provide feedback to the test-taker. The navigation unit allows the rival agent to provide suggestions for learning methods and words to improve motivation to the test-taker.The navigation unit monitors the examinee's progress in real time and adjusts the learning plan as needed. For example, the navigation unit can adjust the learning plan based on the examinee's learning progress and level of understanding. The navigation unit can adjust the learning plan based on the examinee's level of achievement. The navigation unit can collect examinee data in real time and provide feedback. The navigation unit proposes an optimal learning plan based on the examinee's grades and learning content. For example, the navigation unit can propose specific learning methods to improve the examinee's grades. The navigation unit can propose an effective learning plan based on the examinee's learning content. The navigation unit can adjust the learning plan based on the examinee's goals. As a result, the rival agent system according to this embodiment can maximize the examinee's potential and guide them to their goals.

[0068] The data collection department collects data on the examinee's condition, changes, personality, test and competition results, daily lesson content, and goals. Specifically, it can collect information on the examinee's health, mental state, and motivation to learn. For example, it monitors the examinee's health using devices that measure body temperature, heart rate, and stress levels. It can also understand the examinee's mental state and motivation to learn through questionnaires and self-assessment sheets. Furthermore, the data collection department can collect information on fluctuations in grades and changes in learning attitudes. For example, it records scores on regular tests, mock exam results, the number of times students participate in class, and homework submission status to track changes in learning attitudes. The data collection department can also collect information on the examinee's personality. For example, it conducts personality tests and psychological tests to collect information on whether the examinee is introverted or extroverted, and whether they are proactive or passive. This allows for the provision of appropriate support tailored to the examinee's personality. The data collection department can also collect information on test and competition results. For example, it collects information on the examinee's test scores, rankings, and pass / fail status, and analyzes trends in grades by comparing them with past performance data. The data collection unit can also collect information related to the content of daily lessons. For example, it collects information such as the progress of lessons, learning content, and level of understanding to grasp the learning situation of students preparing for exams. It digitizes notes taken during lessons, homework content, and teacher feedback, and stores them in a database. The data collection unit can also collect information related to the goals that students are aiming for. For example, it collects information such as students' desired schools, target scores, and future dreams, and uses this as basic data to develop concrete plans for achieving those goals. In this way, the data collection unit can comprehensively collect diverse information about students and build a foundation for providing support tailored to their individual needs.

[0069] The generation unit analyzes the data collected by the collection unit and generates the optimal rival agent. Specifically, it can generate a rival agent tailored to the characteristics of the test-taker based on the collected data. The generation unit uses an AI algorithm to generate a rival agent suitable for the test-taker. For example, it can use a machine learning model to adjust the characteristics of the rival agent based on the test-taker's personality and motivation to learn. For introverted test-takers, it generates an agent that is gentle and offers many words of encouragement, while for extroverted test-takers, it generates an agent that stimulates a competitive spirit. Furthermore, the generation unit can adjust the behavior patterns of the rival agent based on the test-taker's grades and learning content. For example, for test-takers whose grades are improving, it generates an agent that presents increasingly difficult problems, while for test-takers whose grades are stagnating, it generates an agent that repeatedly presents basic problems. In addition, the generation unit can adjust the response method of the rival agent based on the test-taker's goals. For example, for test-takers aiming to pass the entrance exam for their desired school, it generates an agent that provides specific advice for passing the exam, while for test-takers with long-term goals for their future dreams, it generates an agent that provides words of encouragement to maintain motivation. This allows the generation unit to create the optimal rival agent for each test-taker and provide support tailored to their individual needs.

[0070] The Navigation Unit allows rival agents generated by the Generation Unit to interact with test-takers, providing advice and encouragement. Specifically, rival agents can chat and have voice conversations with test-takers. For example, if a test-taker has questions during their studies, the rival agent can provide real-time answers to help them deepen their understanding. Also, when a test-taker is losing motivation to study, the rival agent can boost their motivation through words of encouragement and sharing of success stories. The Navigation Unit allows rival agents to provide feedback to test-takers. For example, based on mock exam results and daily study progress, it can suggest specific areas for improvement and tasks to tackle next. The Navigation Unit allows rival agents to offer suggestions for study methods and words to boost motivation. For example, it can suggest efficient time management methods and effective review methods to help test-takers establish a study style that suits them. The Navigation Unit monitors the test-taker's progress in real time and adjusts the study plan as needed. For example, it can adjust the study plan based on the test-taker's learning progress and level of understanding. If a student is ahead of schedule, the navigation system will present new challenges to help them move on to the next step; conversely, if they are behind, it will suggest review or supplementary lessons. The navigation system can adjust the learning plan based on the student's progress. For example, if a student has not reached their target score, it will identify areas that need more focus and suggest intensive study. The navigation system can collect student data in real time and provide feedback. This allows the navigation system to propose the optimal learning plan based on the student's performance and learning content, maximizing their potential.

[0071] The data collection unit can collect information on facial expressions, voice, conversation, grades, and learning content. For example, the data collection unit can capture a test-taker's facial expressions with a camera and analyze changes in facial expressions using facial expression analysis technology. The data collection unit can record a test-taker's voice and analyze the tone of voice and speaking style using voice analysis technology. The data collection unit can record a test-taker's conversations and analyze the content and topics of the conversations using conversation analysis technology. The data collection unit can collect a test-taker's grades and analyze test scores and evaluations using grade analysis technology. The data collection unit can collect a test-taker's learning content and analyze subjects, units, and level of understanding using learning content analysis technology. As a result, the data collection unit can generate more accurate rival agents by collecting diverse information on test-takers. Some or all of the above-described processes in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input facial expression data captured by a camera into a generating AI and have the generating AI perform an analysis of changes in facial expressions.

[0072] The generation unit can generate optimal rival agents based on collected data. For example, the generation unit can analyze the collected data and generate rival agents tailored to the characteristics of the test-taker. The generation unit can use an AI algorithm to generate rival agents suitable for the test-taker. For example, the generation unit can adjust the characteristics of the rival agents based on the test-taker's personality and motivation to learn. The generation unit can adjust the behavioral patterns of the rival agents based on the test-taker's performance and learning content. The generation unit can adjust the response methods of the rival agents based on the test-taker's goals. In this way, the generation unit can provide appropriate stimulation to the test-taker by generating optimal rival agents based on collected data. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the collected data into a generation AI and have the generation AI perform the generation of rival agents.

[0073] The navigation unit allows the generated rival agents to interact with the test-taker and provide appropriate advice and words of encouragement. For example, the navigation unit allows rival agents to chat or have voice conversations with the test-taker. The navigation unit allows rival agents to provide feedback to the test-taker. The navigation unit allows rival agents to provide the test-taker with suggestions for learning methods and words to improve motivation. In this way, the navigation unit can maintain the test-taker's motivation and improve learning effectiveness by interacting with the test-taker. Some or all of the above processes in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input the response data of the rival agents into a generating AI and have the generating AI perform the generation of advice and words of encouragement.

[0074] The navigation unit can monitor the student's progress in real time and adjust the learning plan as needed. For example, the navigation unit can adjust the learning plan based on the student's learning progress and understanding. The navigation unit can adjust the learning plan based on the student's achievement level. The navigation unit can collect student data in real time and provide feedback. The navigation unit can propose an optimal learning plan based on the student's grades and learning content. For example, the navigation unit can propose specific learning methods to improve the student's grades. The navigation unit can propose an effective learning plan based on the student's learning content. The navigation unit can adjust the learning plan based on the student's goals. This allows the navigation unit to support efficient learning by adjusting the learning plan according to the student's progress. Some or all of the above processes in the navigation unit may be performed using AI, or not. For example, the navigation unit can input data collected in real time into a generating AI and have the generating AI adjust the learning plan.

[0075] The generation unit can propose an optimal learning plan based on the student's grades and learning content. For example, the generation unit can analyze the student's grades and propose specific learning methods to improve them. The generation unit can analyze the student's learning content and propose an effective learning plan. The generation unit can adjust the learning plan based on the student's goals. In this way, the generation unit can maximize learning effectiveness by proposing an optimal learning plan based on the student's grades and learning content. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input grade data and learning content data into a generation AI and have the generation AI propose a learning plan.

[0076] The data collection unit can estimate the emotions of test-takers and adjust the timing of data collection based on the estimated emotions. For example, if a test-taker is feeling stressed, the data collection unit can collect data during times when they are relaxed. If a test-taker is concentrating, the data collection unit can collect detailed data at that time. If a test-taker is tired, the data collection unit can collect data during breaks. In this way, the data collection unit can collect more accurate data by adjusting the timing of data collection according to the emotions of the test-takers. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input facial expression data captured by a camera into a generative AI and have the generative AI perform emotion estimation.

[0077] The data collection unit can analyze the past learning history of test takers and select the optimal data collection method. For example, the data collection unit can select a data collection method based on learning methods that have been effective for the test taker in the past. The data collection unit can analyze the past performance improvement patterns of test takers and select the optimal data collection method. The data collection unit can select a data collection method based on the learning tools that the test taker has used in the past. As a result, the data collection unit can select the optimal data collection method by analyzing past learning history, enabling efficient data collection. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input past learning history data into a generating AI and have the generating AI select the data collection method.

[0078] The data collection unit can filter data based on the examinee's current learning status and areas of interest during data collection. For example, the data collection unit can prioritize the collection of data related to the subject the examinee is currently studying. The data collection unit can filter and collect relevant data based on the examinee's areas of interest. The data collection unit can collect only the necessary data according to the examinee's learning progress. In this way, the data collection unit can efficiently collect only the necessary data by filtering the data based on the examinee's current learning status and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input current learning status data and areas of interest data into a generating AI and have the generating AI perform data filtering.

[0079] The data collection unit can estimate the emotions of test-takers and determine the priority of data to collect based on the estimated emotions. For example, if a test-taker is stressed, the data collection unit can prioritize collecting data related to relaxation. If a test-taker is focused, the data collection unit can prioritize collecting data related to learning. If a test-taker is tired, the data collection unit can prioritize collecting data related to rest. In this way, the data collection unit can prioritize collecting important data by prioritizing data based on the emotions of the test-taker. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input facial expression data captured by a camera into a generative AI and have the generative AI perform emotion estimation.

[0080] The data collection unit can prioritize the collection of highly relevant data by considering the geographical location information of the test takers during data collection. For example, if the test taker is at home, the data collection unit can prioritize the collection of data related to home study. If the test taker is at school, the data collection unit can prioritize the collection of data related to school lessons. If the test taker is at the library, the data collection unit can prioritize the collection of data related to studying at the library. In this way, the data collection unit can efficiently collect highly relevant data by considering the geographical location information of the test takers. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input geographical location data into a generating AI and have the generating AI perform the collection of highly relevant data.

[0081] The data collection unit can analyze the social media activities of test takers and collect relevant data during data collection. For example, the data collection unit can collect data based on learning content shared by test takers on social media. The data collection unit can collect information on educational accounts that test takers follow on social media. The data collection unit can collect information on learning groups that test takers participate in on social media. This allows the data collection unit to efficiently collect data related to test takers by analyzing their social media activities. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input social media activity data into a generating AI and have the generating AI perform the collection of relevant data.

[0082] The generation unit can estimate the emotions of the test-taker and adjust the method of generating rival agents based on the estimated emotions of the test-taker. For example, if the test-taker is relaxed, the generation unit can generate rival agents with a calm personality. If the test-taker is stressed, the generation unit can generate rival agents that contain many words of encouragement. If the test-taker is focused, the generation unit can generate rival agents that stimulate competitiveness. In this way, the generation unit can generate rival agents that are suitable for the test-taker by adjusting the method of generating rival agents based on the emotions of the test-taker. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input emotion data into the generation AI and have the generation AI perform the adjustment of the rival agent generation method.

[0083] The generation unit can adjust the level of detail generated when generating rival agents based on the student's learning progress. For example, if the student's learning progress is good, the generation unit can generate rival agents that provide detailed advice. If the student's learning progress is slow, the generation unit can generate rival agents that provide basic advice. The generation unit can generate rival agents that provide an appropriate level of advice depending on the student's learning progress. Thus, the generation unit can generate rival agents that provide an appropriate level of advice by adjusting the level of detail generated based on the student's learning progress. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input learning progress data into a generation AI and have the generation AI perform the adjustment of the level of detail generated.

[0084] The generation unit can apply different generation algorithms depending on the test-taker's goals when generating rival agents. For example, if the test-taker has short-term goals, the generation unit can generate rival agents that provide short-term advice. If the test-taker has long-term goals, the generation unit can generate rival agents that provide long-term advice. The generation unit can generate rival agents that apply the appropriate generation algorithm depending on the test-taker's goals. In this way, the generation unit can generate rival agents that are suitable for the test-taker's goals by applying different generation algorithms depending on the test-taker's goals. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input goal data into a generation AI and have the generation AI execute the application of the generation algorithm.

[0085] The generation unit can estimate the emotions of the test-taker and adjust the characteristics of rival agents based on the estimated emotions of the test-taker. For example, if the test-taker is relaxed, the generation unit can generate rival agents with a calm personality. If the test-taker is stressed, the generation unit can generate rival agents that include many encouraging words. If the test-taker is focused, the generation unit can generate rival agents that stimulate competitiveness. In this way, the generation unit can generate rival agents that are suitable for the test-taker by adjusting the characteristics of rival agents based on the test-taker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input emotion data into the generation AI and have the generation AI perform the adjustment of rival agent characteristics.

[0086] The generation unit can determine the generation priority based on the applicant's submission timing when generating rival agents. For example, if an applicant is preparing for an exam soon, the generation unit can prioritize generating rival agents specifically tailored to exam preparation. If an applicant has a long-term study plan, the generation unit can generate rival agents aligned with that plan. The generation unit can generate rival agents at the appropriate time depending on the applicant's submission timing. In this way, the generation unit can generate rival agents at the appropriate time by determining the generation priority based on the applicant's submission timing. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input submission timing data into a generation AI and have the generation AI determine the generation priority.

[0087] The generation unit can adjust the generation order of rival agents based on the relevance of the test-takers when generating them. For example, if a test-taker is focusing on a particular subject, the generation unit can prioritize generating rival agents related to that subject. If a test-taker is studying multiple subjects, the generation unit can generate rival agents according to their learning progress. The generation unit can generate rival agents in an appropriate order based on the test-taker's learning plan. In this way, the generation unit can generate rival agents in an appropriate order by adjusting the generation order based on the relevance of the test-takers. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input relevance data into a generation AI and have the generation AI perform the adjustment of the generation order.

[0088] The navigation unit can estimate the emotions of test-takers and adjust the way advice and encouragement are expressed based on the estimated emotions. For example, if a test-taker is relaxed, the navigation unit can provide advice in gentle language. If a test-taker is stressed, the navigation unit can provide advice that includes many words of encouragement. If a test-taker is focused, the navigation unit can provide specific and practical advice. In this way, the navigation unit can provide advice that is appropriate for the test-taker by adjusting the way advice and encouragement are expressed based on the test-taker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not using AI. For example, the navigation unit can input emotion data into a generative AI and have the generative AI adjust the way advice and encouragement are expressed.

[0089] The navigation unit can adjust the level of detail of advice based on the student's learning progress during navigation. For example, if the student's learning progress is good, the navigation unit can provide detailed advice. If the student's learning progress is behind, the navigation unit can provide basic advice. The navigation unit can provide an appropriate level of advice according to the student's learning progress. In this way, the navigation unit can provide an appropriate level of advice by adjusting the level of detail of advice based on the student's learning progress. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input learning progress data into a generating AI and have the generating AI perform the adjustment of the level of detail of the advice.

[0090] The navigation unit can apply different navigation algorithms during navigation depending on the examinee's goals. For example, if the examinee has short-term goals, the navigation unit can apply a navigation algorithm that provides short-term advice. If the examinee has long-term goals, the navigation unit can apply a navigation algorithm that provides long-term advice. The navigation unit can apply an appropriate navigation algorithm depending on the examinee's goals. In this way, the navigation unit can provide advice that is appropriate to the examinee's goals by applying different navigation algorithms depending on the examinee's goals. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input goal data into a generating AI and have the generating AI execute the application of the navigation algorithm.

[0091] The navigation unit can estimate the examinee's emotions and adjust the length of advice and encouragement based on the estimated emotions. For example, if the examinee is relaxed, the navigation unit can provide detailed advice. If the examinee is stressed, the navigation unit can provide short, concise advice. If the examinee is focused, the navigation unit can provide specific and practical advice. In this way, the navigation unit can provide advice tailored to the examinee by adjusting the length of advice and encouragement based on the examinee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the navigation unit may be performed using AI or not using AI. For example, the navigation unit can input emotion data into the generative AI and have the generative AI adjust the length of advice and encouragement.

[0092] The navigation unit can prioritize advice based on the applicant's submission timing during navigation. For example, if an applicant is close to the exam, the navigation unit can prioritize advice specifically tailored to exam preparation. If an applicant has a long-term study plan, the navigation unit can provide advice aligned with that plan. The navigation unit can provide advice at the appropriate time depending on the applicant's submission timing. Thus, by prioritizing advice based on the applicant's submission timing, the navigation unit can provide advice at the appropriate time. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not using AI. For example, the navigation unit can input submission timing data into a generating AI and have the generating AI determine the priority of advice.

[0093] The navigation unit can adjust the order of advice based on the examinee's relevance during navigation. For example, if an examinee is focusing on a particular subject, the navigation unit can prioritize providing advice related to that subject. If an examinee is studying multiple subjects, the navigation unit can adjust the order of advice according to their learning progress. The navigation unit can provide advice in an appropriate order based on the examinee's learning plan. In this way, the navigation unit can provide advice in an appropriate order by adjusting the order of advice based on the examinee's relevance. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input relevance data into a generating AI and have the generating AI perform the adjustment of the advice order.

[0094] The navigation unit can monitor the student's progress in real time and, when adjusting the study plan as needed, estimate the student's emotions and change how the study plan is adjusted based on the estimated emotions. For example, if the student is feeling stressed, the navigation unit can suggest a relaxing study plan. If the student is focused, the navigation unit can suggest an intensive study plan. If the student is tired, the navigation unit can suggest a study plan that includes rest. In this way, the navigation unit can provide a study plan that is appropriate for the student by changing how the study plan is adjusted based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not using AI. For example, the navigation unit can input emotion data into the generative AI and have the generative AI perform changes to how the study plan is adjusted.

[0095] The navigation unit can monitor the student's progress in real time and, when necessary, adjust the learning plan by referring to the student's past learning history to select the optimal adjustment method. For example, the navigation unit can propose an effective learning plan based on the student's past learning history. The navigation unit can analyze the student's past performance improvement patterns and propose an optimal learning plan. The navigation unit can adjust the learning plan based on the learning tools the student has used in the past. In this way, the navigation unit can provide an optimal learning plan by referring to the student's past learning history. Some or all of the above processes in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input past learning history data into a generating AI and have the generating AI select an adjustment method.

[0096] The navigation unit can monitor the student's progress in real time and, when adjusting the learning plan as needed, customize the means of adjustment based on the student's current learning status. For example, the navigation unit can suggest a learning plan related to the subject the student is currently studying. The navigation unit can make necessary adjustments according to the student's learning progress. The navigation unit can customize the optimal learning plan based on the student's learning status. In this way, the navigation unit can provide the optimal learning plan by customizing the means of adjustment based on the student's current learning status. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not using AI. For example, the navigation unit can input current learning status data into a generating AI and have the generating AI perform the customization of the means of adjustment.

[0097] The navigation unit can monitor the student's progress in real time and adjust the study plan as needed, estimating the student's emotions and prioritizing the study plan based on the estimated emotions. For example, if the student is stressed, the navigation unit can prioritize suggesting a relaxing study plan. If the student is focused, the navigation unit can prioritize suggesting an intensive study plan. If the student is tired, the navigation unit can prioritize suggesting a study plan that includes rest. In this way, the navigation unit can provide a study plan that is appropriate for the student by prioritizing the study plan based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the navigation unit may be performed using AI, for example, or not using AI. For example, the navigation unit can input emotion data into a generative AI and have the generative AI determine the priority of the study plan.

[0098] The navigation unit can monitor the student's progress in real time and, when adjusting the study plan as needed, can select the optimal adjustment method by considering the student's geographical location. For example, if the student is at home, the navigation unit can suggest a plan best suited for home study. If the student is at school, the navigation unit can suggest a plan related to school lessons. If the student is at the library, the navigation unit can suggest a plan best suited for studying at the library. In this way, the navigation unit can provide the optimal study plan by considering the student's geographical location. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input geographical location data into a generating AI and have the generating AI select the optimal adjustment method.

[0099] The navigation unit can monitor the student's progress in real time and, when necessary, adjust the learning plan by analyzing the student's social media activity to suggest adjustments. For example, the navigation unit can adjust the learning plan based on the learning content the student shares on social media. The navigation unit can adjust the learning plan based on information from educational accounts the student follows on social media. The navigation unit can adjust the learning plan based on information from learning groups the student participates in on social media. In this way, the navigation unit can provide an optimal learning plan by analyzing the student's social media activity. Some or all of the above processing in the navigation unit may be performed using AI, for example, or without AI. For example, the navigation unit can input social media activity data into a generating AI and have the generating AI propose adjustment methods.

[0100] The generation unit can estimate the student's emotions when proposing an optimal study plan based on the student's performance and learning content, and adjust the method of proposing the study plan based on the estimated emotions. For example, if the student is feeling stressed, the generation unit can propose a relaxing study plan. If the student is focused, the generation unit can propose an intensive study plan. If the student is tired, the generation unit can propose a study plan that includes rest. In this way, the generation unit can provide a study plan that is suitable for the student by adjusting the method of proposing the study plan based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input emotion data into the generation AI and have the generation AI adjust the method of proposing the study plan.

[0101] The generation unit can analyze a student's past performance and select the most suitable suggestion method when proposing an optimal learning plan based on the student's grades and learning content. For example, the generation unit can propose an effective learning plan based on the student's past performance. The generation unit can analyze a student's past performance improvement patterns and propose an optimal learning plan. The generation unit can propose a learning plan based on the learning tools the student has used in the past. In this way, the generation unit can provide an optimal learning plan by analyzing the student's past performance. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input past performance data into a generation AI and have the generation AI select a suggestion method.

[0102] The generation unit can customize the suggestion method based on the examinee's current learning status when proposing an optimal learning plan based on the examinee's grades and learning content. For example, the generation unit can propose a learning plan related to the subject the examinee is currently studying. The generation unit can make necessary adjustments according to the examinee's learning progress. The generation unit can customize the optimal learning plan based on the examinee's learning status. In this way, the generation unit can provide an optimal learning plan by customizing the suggestion method based on the examinee's current learning status. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI. For example, the generation unit can input current learning status data into a generation AI and have the generation AI perform the customization of the suggestion method.

[0103] The generation unit can estimate the student's emotions when proposing an optimal study plan based on the student's performance and learning content, and can determine the priority of the study plan based on the estimated emotions. For example, if the student is feeling stressed, the generation unit can prioritize suggesting a relaxing study plan. If the student is concentrating, the generation unit can prioritize suggesting an intensive study plan. If the student is tired, the generation unit can prioritize suggesting a study plan that includes rest. In this way, the generation unit can provide a study plan that is appropriate for the student by determining the priority of the study plan based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input emotion data into a generation AI and have the generation AI determine the priority of the study plan.

[0104] The generation unit can select the optimal suggestion method when proposing an optimal study plan based on the examinee's grades and learning content, taking into account the examinee's geographical location. For example, if the examinee is at home, the generation unit can propose a plan best suited for home study. If the examinee is at school, the generation unit can propose a plan related to school lessons. If the examinee is at the library, the generation unit can propose a plan best suited for studying at the library. In this way, the generation unit can provide an optimal study plan by taking into account the examinee's geographical location. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input geographical location data into a generation AI and have the generation AI select the optimal suggestion method.

[0105] The generation unit can propose an optimal learning plan based on the student's grades and learning content, by analyzing the student's social media activity. For example, the generation unit can propose a learning plan based on the learning content the student has shared on social media. The generation unit can propose a learning plan based on information from educational accounts the student follows on social media. The generation unit can propose a learning plan based on information from learning groups the student participates in on social media. In this way, the generation unit can provide an optimal learning plan by analyzing the student's social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input social media activity data into a generation AI and have the generation AI execute suggestions for proposal methods.

[0106] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0107] The rival agent system can provide a customized learning environment based on the learner's learning style. For example, if the learner is a visual learner, the collection unit can collect learning materials that heavily utilize visual aids and graphics. If the learner is an auditory learner, it can collect audio materials and podcasts. Furthermore, if the learner is an experiential learner, it can collect practical exercises and simulations. In this way, the rival agent system can provide an optimal learning environment tailored to the learner's learning style.

[0108] The rival agent system can predict a student's learning progress and provide appropriate feedback based on their learning history. For example, the data collection unit can analyze past learning data to identify which subjects a student tends to struggle with. Next, the generation unit can use this information to generate rival agents that provide special support for the subjects the student struggles with. Furthermore, the navigation unit can suggest specific learning methods and resources for the subjects the student tends to struggle with. In this way, the rival agent system can maximize learning effectiveness by predicting the student's learning progress and providing appropriate feedback.

[0109] The rival agent system can incorporate gamification elements to enhance students' motivation to learn. For example, the collection unit can award points and badges based on students' learning progress and performance. Next, the generation unit can generate special rival agents according to the points and badges students have earned. Furthermore, the navigation unit can provide rewards and benefits for goals students have achieved. In this way, the rival agent system can enhance students' motivation to learn and improve learning effectiveness by incorporating gamification elements.

[0110] The rival agent system can utilize environmental sensors to optimize the learning environment for test-takers. For example, the data collection unit can collect data such as temperature, humidity, and lighting in the test-taker's learning environment. Next, the generation unit can generate a rival agent that provides the optimal learning environment based on the collected environmental data. Furthermore, the navigation unit can suggest specific advice and adjustment methods according to the test-taker's learning environment. In this way, the rival agent system can maximize learning effectiveness by optimizing the test-taker's learning environment.

[0111] The rival agent system can utilize biofeedback technology to improve the learning performance of test-takers. For example, the data collection unit can collect physiological data such as the test-taker's heart rate, skin electrical activity, and electroencephalogram (EEG). Next, the generation unit can evaluate the test-taker's stress level and concentration level based on the collected physiological data and generate the optimal rival agent. Furthermore, the navigation unit can suggest relaxation methods and ways to improve concentration based on the test-taker's physiological data. In this way, the rival agent system can improve the learning performance of test-takers by utilizing biofeedback technology.

[0112] The rival agent system can estimate the emotions of test-takers and adjust the timing of their learning based on those emotions. For example, the data collection unit can estimate emotions from the test-takers' facial expressions and voice, and start learning during times when the test-takers are relaxed. Next, the generation unit can generate rival agents that adjust the learning content and difficulty level according to the test-takers' emotions. Furthermore, the navigation unit can suggest learning and break times based on the test-takers' emotions. In this way, the rival agent system can maximize learning effectiveness by adjusting the timing of learning based on the test-takers' emotions.

[0113] The rival agent system can estimate a student's emotions and provide support to maintain their motivation based on those emotions. For example, the data collection unit can estimate emotions from the student's facial expressions and voice, and provide words of encouragement if the student is losing motivation. Next, the generation unit can generate special rival agents to boost motivation according to the student's emotions. Furthermore, the navigation unit can provide specific advice and resources to maintain motivation based on the student's emotions. In this way, the rival agent system can improve learning effectiveness by providing support to maintain motivation based on the student's emotions.

[0114] The rival agent system can estimate a test-taker's emotions and provide support to reduce learning stress based on those estimated emotions. For example, the data collection unit can estimate emotions from the test-taker's facial expressions and voice, and suggest relaxation methods if the test-taker is feeling stressed. Next, the generation unit can generate special rival agents to reduce stress according to the test-taker's emotions. Furthermore, the navigation unit can provide specific advice and resources to reduce stress based on the test-taker's emotions. In this way, the rival agent system can improve learning effectiveness by providing support to reduce learning stress based on the test-taker's emotions.

[0115] The rival agent system can estimate a student's emotions and provide support to enhance their concentration based on those emotions. For example, the data collection unit can estimate emotions from the student's facial expressions and voice, and suggest ways to improve concentration if the student is lacking it. Next, the generation unit can generate special rival agents to enhance concentration according to the student's emotions. Furthermore, the navigation unit can provide specific advice and resources to improve concentration based on the student's emotions. In this way, the rival agent system can improve learning effectiveness by providing support to enhance concentration based on the student's emotions.

[0116] The rival agent system can estimate the emotions of test-takers and provide support to improve learning efficiency based on those estimated emotions. For example, the data collection unit can estimate emotions from the test-taker's facial expressions and voice, and suggest rest if the test-taker is tired. Next, the generation unit can generate a special rival agent that suggests efficient learning methods according to the test-taker's emotions. Furthermore, the navigation unit can provide efficient learning methods and resources based on the test-taker's emotions. In this way, the rival agent system can maximize learning effectiveness by providing support to improve learning efficiency based on the test-taker's emotions.

[0117] The following briefly describes the processing flow for example form 2.

[0118] Step 1: The data collection unit collects data on the student's condition, changes, personality, test and competition results, daily lesson content, and goals they are aiming for. For example, it can collect information such as the student's health, mental state, motivation to learn, fluctuations in grades, changes in learning attitude, personality (introverted or extroverted, active or passive), test and competition results (test scores and rankings, pass / fail), daily lesson content (progress of lessons, learning content, level of understanding), and goals they are aiming for (desired school, target score, future dreams). Step 2: The generation unit analyzes the data collected by the collection unit and generates the optimal rival agent. For example, based on the collected data, it can generate a rival agent tailored to the characteristics of the test taker, and use an AI algorithm to adjust the characteristics, behavioral patterns, and response methods of the rival agent to suit the test taker. Step 3: The navigation unit interacts with the test-taker using rival agents generated by the generation unit, providing advice and encouragement. For example, rival agents chat or have voice conversations with the test-taker, providing feedback, suggesting learning methods, and offering words of motivation. They also monitor the test-taker's progress in real time and adjust the learning plan as needed.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0121] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0122] Each of the multiple elements described above, including the collection unit, generation unit, and navigation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit uses the camera 42 and microphone 38B of the smart device 14 to detect the examinee's state and changes, and the control unit 46A collects the data. The generation unit is implemented in the identification processing unit 290 of the data processing unit 12, which analyzes the collected data to generate an optimal rival agent. The navigation unit is implemented in the control unit 46A of the smart device 14, which allows the generated rival agent to interact with the examinee and provide advice and encouragement. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0123] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0124] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0125] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0126] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0127] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0129] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0130] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0131] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0132] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0133] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0134] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0137] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0138] Each of the multiple elements described above, including the data collection unit, generation unit, and navigation unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit uses the camera 42 and microphone 238 of the smart glasses 214 to detect the examinee's state and changes, and the control unit 46A collects the data. The generation unit is implemented, for example, in the identification processing unit 290 of the data processing unit 12, which analyzes the collected data to generate an optimal rival agent. The navigation unit is implemented, for example, in the control unit 46A of the smart glasses 214, which allows the generated rival agent to interact with the examinee and provide advice and encouragement. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0139] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0140] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0141] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0142] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0143] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0145] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0146] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements described above, including the collection unit, generation unit, and navigation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit uses the camera 42 and microphone 238 of the headset terminal 314 to detect the examinee's state and changes, and the control unit 46A collects the data. The generation unit is implemented in the identification processing unit 290 of the data processing unit 12, which analyzes the collected data to generate an optimal rival agent. The navigation unit is implemented in the control unit 46A of the headset terminal 314, which allows the generated rival agent to interact with the examinee and provide advice and encouragement. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0155] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0156] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0157] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0158] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0159] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0161] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0162] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0163] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0164] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0165] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0166] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0167] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0168] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0169] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0170] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0171] Each of the multiple elements described above, including the data collection unit, generation unit, and navigation unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the data collection unit uses the camera 42 and microphone 238 of the robot 414 to detect the examinee's state and changes, and the control unit 46A collects the data. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which analyzes the collected data to generate an optimal rival agent. The navigation unit is implemented, for example, by the control unit 46A of the robot 414, which allows the generated rival agent to interact with the examinee and provide advice and encouragement. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0172] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0173] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0174] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0175] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0176] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0177] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0179] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0180] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0181] 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.

[0182] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0183] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0184] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0185] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0186] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0187] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0188] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0189] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0190] (Note 1) The data collection department collects data on the examinees' condition, changes, personality, exam and competition results, daily class content, and goals they are aiming for. A generation unit analyzes the data collected by the aforementioned collection unit and generates rival agents, The system comprises a navigation unit in which rival agents generated by the generation unit interact with the test taker and provide advice and words of encouragement. A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect information on facial expressions, voice, conversation, grades, and learning content. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Based on the collected data, generate the optimal rival agent. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned navigation unit is The generated rival agents interact with the test takers, providing appropriate advice and words of encouragement. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned navigation unit is The system monitors the progress of test-takers in real time and adjusts their study plans as needed. The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is We propose the optimal study plan based on the student's academic performance and learning content. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate the emotions of test-takers and adjust the timing of data collection based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the past learning history of test-takers and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting data, filtering is performed based on the examinee's current learning situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is We estimate the emotions of test-takers and determine the priority of data to collect based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting data, the system prioritizes the collection of highly relevant data, taking into account the geographical location of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is During data collection, the social media activity of test-takers will be analyzed and relevant data will be collected. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is The system estimates the emotions of test-takers and adjusts the method of generating rival agents based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating rival agents, adjust the level of detail based on the test-taker's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating rival agents, different generation algorithms are applied depending on the test taker's goals. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is The system estimates the emotions of test-takers and adjusts the characteristics of rival agents based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating rival agents, the generation priority is determined based on the submission timing of the test takers. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating rival agents, the generation order is adjusted based on the relevance of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned navigation unit is The system estimates the emotions of test-takers and adjusts the way advice and encouragement are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned navigation unit is During navigation, the level of detail in the advice is adjusted based on the student's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned navigation unit is During navigation, different navigation algorithms are applied depending on the test-taker's goals. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned navigation unit is The system estimates the emotions of test-takers and adjusts the length of advice and encouragement based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned navigation unit is During navigation, the priority of advice is determined based on the applicant's submission date. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned navigation unit is During navigation, the order of advice is adjusted based on the relevance of the test-taker. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned navigation unit is The system monitors the progress of test-takers in real time and adjusts their study plans as needed. It also estimates the test-takers' emotions and modifies how the study plans are adjusted based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned navigation unit is The system monitors the progress of test-takers in real time and, when adjusting their study plans as needed, selects the optimal adjustment method by referring to the test-takers' past study history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned navigation unit is The system monitors the progress of test-takers in real time and, when adjusting their study plans as needed, customizes the adjustment methods based on the test-takers' current learning status. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned navigation unit is The system monitors the progress of test-takers in real time, adjusts their study plans as needed, estimates their emotions, and prioritizes the study plans based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned navigation unit is The system monitors the progress of test-takers in real time and, when adjusting their study plans as needed, selects the optimal adjustment method while considering the test-takers' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned navigation unit is The system monitors students' progress in real time and, when adjusting their study plans as needed, analyzes their social media activity to suggest ways to make those adjustments. The system described in Appendix 1, characterized by the features described herein. (Note 31) The generating unit is When proposing an optimal study plan based on a student's academic performance and learning content, the system estimates the student's emotions and adjusts the method of proposing the study plan based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The generating unit is When proposing an optimal study plan based on a student's academic performance and learning content, we analyze the student's past performance to select the most suitable proposal method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The generating unit is When proposing an optimal study plan based on a student's grades and learning content, the method of proposal is customized based on the student's current learning situation. The system described in Appendix 1, characterized by the features described herein. (Note 34) The generating unit is When proposing an optimal study plan based on a student's academic performance and learning content, the system estimates the student's emotions and determines the priority of the study plan based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The generating unit is When proposing an optimal study plan based on the student's academic performance and learning content, the most suitable proposal method is selected by considering the student's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The generating unit is When proposing an optimal study plan based on a student's academic performance and learning content, we analyze the student's social media activity to suggest appropriate methods for making the proposal. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The data collection department collects data on the examinees' condition, changes, personality, exam and competition results, daily class content, and goals they are aiming for. A generation unit analyzes the data collected by the aforementioned collection unit and generates rival agents, The system comprises a navigation unit in which rival agents generated by the generation unit interact with the test taker and provide advice and words of encouragement. A system characterized by the following features.

2. The aforementioned collection unit is Collect information on facial expressions, voice, conversation, grades, and learning content. The system according to feature 1.

3. The generating unit is Based on the collected data, generate the optimal rival agent. The system according to feature 1.

4. The aforementioned navigation unit is The generated rival agents interact with the test takers, providing appropriate advice and words of encouragement. The system according to feature 1.

5. The aforementioned navigation unit is The system monitors the progress of test-takers in real time and adjusts their study plans as needed. The system according to feature 1.

6. The generating unit is We propose the optimal study plan based on the student's academic performance and learning content. The system according to feature 1.

7. The aforementioned collection unit is We estimate the emotions of test-takers and adjust the timing of data collection based on the estimated emotions of the test-takers. The system according to feature 1.

8. The aforementioned collection unit is Analyze the past learning history of test-takers and select the optimal data collection method. The system according to feature 1.

Images