System

Abstract

An object of the system according to the embodiment is to solve questions related to qualification acquisition and learning, and to support learning in accordance with individual needs.SOLUTION: A system includes a question answering part, a step proposing part, a curriculum proposing part, and an exercise providing part. The question answering unit generates an answer to a question of a user. The step proposal unit proposes steps for achieving the goal on the basis of the answer generated by the question and answer unit. The curriculum proposing section proposes an optimum curriculum based on the steps proposed by the step proposing section. The exercise providing unit provides an exercise and a confirmation test based on the curriculum suggested by the curriculum suggesting unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to efficiently resolve questions about obtaining qualifications and studying, and to provide learning support tailored to individual needs.

[0005] The system according to the embodiment aims to resolve questions about obtaining qualifications and studying, and to provide study support tailored to individual needs. [Means for solving the problem]

[0006] The system according to the embodiment includes a question answering unit, a step proposing unit, a curriculum proposing unit, and an exercise providing unit. The question answering unit generates answers to user questions. The step proposing unit proposes steps to achieve a goal based on the answers generated by the question answering unit. The curriculum proposing unit proposes an optimal curriculum based on the steps proposed by the step proposing unit. The exercise providing unit provides exercises and confirmation tests based on the curriculum proposed by the curriculum proposing unit. [Effects of the Invention]

[0007] The system according to the embodiment can resolve questions about obtaining qualifications and studying, and provide study support tailored to individual needs. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The AI ​​question and answer service according to an embodiment of the present invention is a system that supports questions and learning needs related to qualification acquisition. This system allows users to ask questions to the AI ​​and receive necessary information and explanations in real time, efficiently supporting the qualification acquisition learning process. As a result, the AI ​​question and answer service can support effective learning tailored to individual needs by proposing steps and curricula to users to achieve their goals and providing practice questions and confirmation tests.

[0029] An AI question-and-answer service according to an embodiment includes a question-and-answer unit, a step proposal unit, a curriculum proposal unit, and a practice question provision unit. The question-and-answer unit generates answers to user questions. For example, when a user asks about how to study for a qualification exam, the generation AI provides information about the qualification exam and suggests specific study methods. The step proposal unit proposes steps to achieve a goal based on the answers generated by the question-and-answer unit. For example, the generation AI proposes a schedule and study plan leading up to the exam date. The curriculum proposal unit proposes an optimal curriculum based on the steps proposed by the step proposal unit. For example, the generation AI proposes study content and teaching materials based on the exam scope. The practice question provision unit provides practice questions and confirmation tests based on the curriculum proposed by the curriculum proposal unit. For example, the generation AI generates and provides practice questions and confirmation tests according to the user's learning progress. This enables the AI ​​question-and-answer service according to an embodiment to efficiently support the qualification acquisition learning process.

[0030] The question answering unit can generate the optimal answer based on the user's past learning history and current level of understanding. For example, when a user inputs a question, the generation AI analyzes the background information of the question and references the user's past learning history. For example, it generates the optimal answer based on the content learned in the past and the level of understanding. In addition, when analyzing the background information of the question, it takes into account the user's current level of understanding. For example, it provides an answer of an appropriate level of difficulty based on what problems the user has tackled in the past. It also analyzes the user's learning history and associates the content learned in the past with the content of the current question. For example, it provides information related to topics learned in the past to deepen the user's understanding. This makes it possible to provide the optimal answer based on the user's learning history and level of understanding.

[0031] The question-answering unit can automatically insert related videos and illustrations when generating an answer to a question. For example, when a user inputs a question, the generation AI automatically inserts related videos and illustrations when generating an answer to that question. For example, in response to a question about how to study for a qualification exam, a video showing specific study methods is provided. In addition, when generating an answer to a question, visually easy-to-understand illustrations are inserted. For example, when explaining complex concepts, flowcharts and graphs are used for visual explanations. In addition, when a user inputs a question, the generation AI searches for videos and illustrations related to the question and incorporates them into the answer. For example, in response to a question about how to study for a specific qualification exam, a related video tutorial is provided. This makes it possible to provide answers that are visually easy to understand.

[0032] The question and answer unit can support different languages ​​and be available to international users. The question and answer unit, for example, makes the question and answer function multilingual so that it can support questions in different languages. For example, it provides appropriate answers to questions in multiple languages, such as English, Japanese, and French. In addition, to support different languages, a multilingual translation function is incorporated into the generation AI. For example, when a user inputs a question in English, the generation AI translates the question into Japanese and generates an appropriate answer. In addition, to support international users, the question and answer function is made multilingual. For example, when a user inputs a question in French, the generation AI provides an answer to the question in French. This allows it to support different languages ​​and be available to international users.

[0033] The question and answer unit also supports voice input, allowing users to input questions by voice. The question and answer unit, for example, adds a voice input function to the question and answer function, allowing users to input questions by voice. For example, when a user inputs a question by voice using a microphone, the generation AI analyzes the voice and provides an appropriate answer. The voice input function also allows users to input questions by voice. For example, when a user inputs a question by voice using a microphone on a smartphone, the generation AI converts the voice into text and generates an answer. The question and answer function also incorporates voice recognition technology, allowing users to input questions by voice. For example, when a user inputs a question by voice, the generation AI analyzes the voice and provides an appropriate answer. This allows users to input questions by voice.

[0034] The step suggestion unit can analyze the user's lifestyle and work schedule and propose an optimal study schedule based on that. The step suggestion unit, for example, analyzes the user's lifestyle and work schedule and proposes an optimal study schedule based on that. For example, it sets study times to avoid busy times for the user. The generation AI also analyzes the user's lifestyle and work schedule and proposes an efficient study schedule. For example, it creates a study plan that allows the user to make effective use of their free time. It also proposes an optimal study schedule taking the user's lifestyle and work schedule into consideration. For example, it concentrates study during times when the user is relaxed. This makes it possible to propose an optimal study schedule based on the user's lifestyle and work schedule.

[0035] The step suggestion unit can make customized suggestions according to the user's learning style. The step suggestion unit, for example, analyzes the user's learning style and makes customized step suggestions accordingly. For example, for a visual user, it proposes a study plan that makes extensive use of illustrations and videos. In addition, the generation AI takes the user's learning style into consideration and makes optimal step suggestions. For example, for an auditory user, it proposes a study plan that focuses on audio materials. In addition, it makes customized step suggestions according to the user's learning style. For example, for a tactile user, it proposes a study plan that includes many practical exercises. In this way, it makes customized suggestions according to the user's learning style.

[0036] The step proposal unit is also able to accommodate group learning and pair learning formats and propose collaborative learning schedules. For example, the step proposal unit adapts the step proposals to group learning and pair learning formats and proposes a collaborative learning schedule. For example, the schedule is adjusted so that multiple users can study simultaneously. The generation AI also makes step proposals that are compatible with group learning and pair learning formats. For example, a schedule is proposed for a user to advance their learning in cooperation with other learners. The step proposals are also adapted to collaborative learning formats so that the user can study together with other learners. For example, a schedule for group discussions or collaborative projects is proposed. This makes it possible to accommodate group learning and pair learning formats and propose collaborative learning schedules.

[0037] The step proposal unit can accommodate different qualification exams and learning goals, making it usable by a wide range of users. The step proposal unit, for example, can accommodate step proposals for different qualification exams and learning goals, making it usable by a wide range of users. For example, it proposes study plans that correspond to multiple qualification exams. In addition, the generation AI makes step proposals that correspond to different qualification exams and learning goals. For example, if a user is aiming for multiple qualification exams at the same time, it proposes study plans that correspond to each exam. In addition, it can accommodate step proposals for a wide range of learning goals, allowing users to create study plans that match their goals. For example, it can make step proposals that correspond to users who are aiming to acquire specific skills or advance their careers. This makes it possible to accommodate different qualification exams and learning goals, making it usable by a wide range of users.

[0038] The curriculum suggestion unit can analyze the user's past learning data and dynamically generate an optimal curriculum. The curriculum suggestion unit, for example, analyzes the user's past learning data and dynamically generates an optimal curriculum based on it. For example, it suggests what to study next, taking into account what has been learned in the past and the level of understanding. In addition, the generation AI analyzes the user's past learning data and generates a curriculum according to individual needs. For example, it adjusts the curriculum so that the user can focus on areas in which they are weak. It also analyzes the user's learning history and dynamically generates an optimal curriculum. For example, it proposes an effective learning plan based on past test results and learning progress. In this way, the user's past learning data is analyzed and an optimal curriculum is dynamically generated.

[0039] The curriculum proposal unit reflects the latest industry trends and technical information, allowing it to always provide the latest curriculum. For example, when proposing a curriculum, the curriculum proposal unit automatically collects the latest industry trends and technical information and reflects it in the curriculum. For example, it updates the learning content based on the latest technological trends and market needs. In addition, the generative AI analyzes the latest industry trends and technical information and proposes a curriculum based on that. For example, it provides a learning plan that incorporates new technologies and methodologies. It also proposes a curriculum that reflects the latest industry trends and technical information. For example, it regularly updates the curriculum so that users can always learn the latest information. This allows it to reflect the latest industry trends and technical information and always provide the latest content.

[0040] The curriculum proposal unit can accommodate different educational levels and provide them to a wide range of users. For example, the curriculum proposal unit adapts curriculum proposals to different educational levels and provides them to a wide range of users. For example, it proposes study plans suitable for high school students, university students, and working adults. In addition, the generation AI proposes curricula that correspond to different educational levels. For example, it provides a curriculum that includes basic content for high school students and specialized content for working adults. In addition, it proposes curricula that correspond to different educational levels and makes them available to a wide range of users. For example, it dynamically generates a curriculum that corresponds to the user's learning level. This allows it to accommodate different educational levels and provide them to a wide range of users.

[0041] The curriculum proposal unit can link with online courses and webinars to propose learning combined with actual lectures and seminars. For example, the curriculum proposal unit links the curriculum proposal with online courses and webinars to propose learning combined with actual lectures and seminars. For example, the content of the online course is incorporated into the curriculum. In addition, the generative AI collects information about online courses and webinars and proposes a curriculum based on that information. For example, webinars that users can participate in are included in the curriculum. In addition, a curriculum linked with the online course or webinar is proposed to provide learning combined with actual lectures and seminars. For example, a curriculum combining online and offline learning is proposed. This allows linking with online courses and webinars to propose learning combined with actual lectures and seminars.

[0042] The practice problem providing unit can analyze the user's learning progress and automatically generate practice problems of a difficulty level according to the level of understanding. The practice problem providing unit, for example, analyzes the user's learning progress and automatically generates practice problems of a difficulty level according to the level of understanding. For example, problems of an appropriate difficulty level are provided for areas in which the user is weak. In addition, the generation AI analyzes the user's learning progress and generates practice problems according to individual needs. For example, high-difficulty questions are provided for areas in which the user is strong. In addition, the user's learning history is analyzed and practice problems of a difficulty level according to the level of understanding are automatically generated. For example, questions of an appropriate difficulty level are provided based on past test results. In this way, the user's learning progress is analyzed and practice problems of a difficulty level according to the level of understanding are automatically generated.

[0043] The practice problem providing unit can analyze the results of the practice problems and confirmation tests, identify weak points, and provide feedback to help the user focus on learning. The practice problem providing unit, for example, analyzes the results of the practice problems and confirmation tests, and provides feedback to help the user identify weak points and focus on learning. For example, detailed explanations are provided for questions that the user got wrong. The generation AI also analyzes the results of the practice problems and confirmation tests, and provides feedback tailored to individual needs. For example, additional study materials are provided for areas in which the user is weak. The generation AI also identifies the user's weak points based on the results of the practice problems and confirmation tests, and provides feedback to help the user focus on learning. For example, supplementary explanations are provided for concepts that the user does not understand. In this way, the practice problem providing unit analyzes the results of the practice problems and confirmation tests, and provides feedback to help the user identify weak points and focus on learning.

[0044] The practice question providing unit can provide practice questions and confirmation tests in a game format, allowing users to study while having fun. The practice question providing unit, for example, provides practice questions and confirmation tests in a game format, allowing users to study while having fun. For example, quiz-style questions are provided, allowing users to earn points for each correct answer. Furthermore, the generation AI converts practice questions and confirmation tests into a game format, allowing users to study while having fun. For example, time attack-style questions are provided, allowing users to study with a competitive spirit. Furthermore, practice questions and confirmation tests are provided in a game format, allowing users to study while having fun. For example, a level-up system can be introduced, allowing users to study while feeling a sense of accomplishment. In this way, practice questions and confirmation tests can be provided in a game format, allowing users to study while having fun.

[0045] The practice problem providing unit can provide practice problems and confirmation tests in a competitive format with other users, thereby increasing motivation. The practice problem providing unit, for example, provides practice problems and confirmation tests in a competitive format with other users, thereby increasing user motivation. For example, a ranking system can be introduced so that users can compete with other learners. Furthermore, the generation AI converts practice problems and confirmation tests into a competitive format, thereby increasing user motivation. For example, battle-style problems can be provided so that users can compete with opponents. Furthermore, practice problems and confirmation tests can be provided in a competitive format with other users, thereby increasing user motivation. For example, a team competition can be introduced so that users can study cooperatively. In this way, practice problems and confirmation tests can be provided in a competitive format with other users, thereby increasing motivation.

[0046] The learning support unit can analyze the user's learning history and propose an individual learning plan based on their past level of understanding. For example, the learning support unit analyzes the user's learning history and proposes an individual learning plan based on their past level of understanding. For example, the plan is adjusted so that the user can focus on studying areas in which they are weak. In addition, the generation AI analyzes the user's learning history and proposes a learning plan that meets individual needs. For example, a plan that includes advanced content is provided for areas in which the user is strong. In addition, an individual learning plan based on the user's learning history and according to their past level of understanding is proposed. For example, an effective learning plan is created based on past test results. In this way, the learning support unit analyzes the user's learning history and proposes an individual learning plan based on their past level of understanding.

[0047] The learning support unit can automatically provide related examples and case studies during learning support to promote practical understanding. The learning support unit, for example, automatically provides related examples and case studies during learning support to promote practical understanding for the user. For example, examples related to a specific qualification exam are presented. In addition, the generative AI automatically provides related case studies during learning support. For example, actual cases related to the content the user is learning are introduced. In addition, during learning support, examples and case studies are automatically provided to deepen the user's understanding. For example, specific cases related to the learning content are presented. In this way, related examples and case studies are automatically provided during learning support to promote practical understanding.

[0048] The learning support unit can adapt learning support to different learning fields and provide it to a wide range of users. The learning support unit, for example, adapts learning support to different learning fields and provides it to a wide range of users. For example, it provides support tailored to language learning or programming learning. In addition, the generation AI provides learning support tailored to different learning fields. For example, it provides support tailored to the field the user wants to learn. In addition, learning support can be adapted to a wide range of learning fields, allowing users to advance in learning that suits their interests. For example, it provides support tailored to users who are aiming to acquire specific skills or advance their careers. In this way, learning support can be adapted to different learning fields and provided to a wide range of users.

[0049] The learning support unit can link the learning support with an online community to deepen learning through interactions with other users. The learning support unit, for example, links the learning support with an online community to enable users to interact with other learners. For example, it provides a discussion forum or group chat. The generative AI also links with the online community to enable users to cooperate with other learners to advance their learning. For example, it suggests joint projects or group discussions. The learning support also links with the online community to deepen learning through interactions with other learners. For example, it provides opportunities to share learning results and receive feedback. In this way, the learning support is linked with the online community to deepen learning through interactions with other users.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The question answering unit generates answers to user questions. For example, when a user asks about how to study for a qualification exam, the generation AI provides information about the qualification exam and suggests specific study methods. The step suggestion unit suggests steps to achieve a goal based on the answers generated by the question answering unit. For example, the generation AI suggests a schedule and study plan leading up to the exam date. The curriculum suggestion unit suggests an optimal curriculum based on the steps suggested by the step suggestion unit. For example, the generation AI suggests study content and teaching materials based on the exam scope. The practice question providing unit provides practice questions and confirmation tests based on the curriculum suggested by the curriculum suggestion unit. For example, the generation AI generates and provides practice questions and confirmation tests according to the user's learning progress. This allows the AI ​​question answering service according to the embodiment to efficiently support the learning process for obtaining qualifications.

[0052] The question-answering unit can generate optimal answers based on the user's past learning history and current level of understanding. For example, when a user inputs a question, the generation AI analyzes the background information of the question and references the user's past learning history. For example, it generates optimal answers based on the content learned in the past and the user's level of understanding. In addition, when analyzing the background information of the question, it takes into account the user's current level of understanding. For example, it provides answers of an appropriate level of difficulty based on the types of problems the user has tackled in the past. It also analyzes the user's learning history and associates the content learned in the past with the content of the current question. For example, it provides information related to topics learned in the past to deepen the user's understanding. This allows it to provide optimal answers based on the user's learning history and level of understanding.

[0053] The question-answering unit can automatically insert related videos and illustrations when generating an answer to a question. For example, when a user inputs a question, the generation AI automatically inserts related videos and illustrations when generating an answer to that question. For example, in response to a question about how to study for a qualification exam, a video showing specific study methods is provided. In addition, when generating an answer to a question, visually easy-to-understand illustrations are inserted. For example, when explaining complex concepts, flowcharts and graphs are used for visual explanations. In addition, when a user inputs a question, the generation AI searches for videos and illustrations related to the question and incorporates them into the answer. For example, in response to a question about how to study for a specific qualification exam, a related video tutorial is provided. This makes it possible to provide answers that are visually easy to understand.

[0054] The question-answering unit can support different languages ​​and be available to international users. For example, the question-answering function can be made multilingual so that it can handle questions in different languages. For example, it can provide appropriate answers to questions in multiple languages, such as English, Japanese, and French. In addition, to support different languages, a multilingual translation function can be incorporated into the generation AI. For example, when a user inputs a question in English, the generation AI translates the question into Japanese and generates an appropriate answer. In addition, to support international users, the question-answering function can be made multilingual. For example, when a user inputs a question in French, the generation AI can provide an answer to the question in French. This allows it to support different languages ​​and be available to international users.

[0055] The question and answer unit also supports voice input, allowing users to input questions by voice. For example, a voice input function can be added to the question and answer function, allowing users to input questions by voice. For example, when a user inputs a question by voice using a microphone, the generation AI analyzes the voice and provides an appropriate answer. In addition, the voice input function can be used to allow users to input questions by voice. For example, when a user inputs a question by voice using a smartphone microphone, the generation AI converts the voice into text and generates an answer. In addition, speech recognition technology can be incorporated into the question and answer function, allowing users to input questions by voice. For example, when a user inputs a question by voice, the generation AI analyzes the voice and provides an appropriate answer. This allows users to input questions by voice.

[0056] The step suggestion unit can analyze the user's lifestyle and work schedule and propose an optimal study schedule based on that. For example, it can analyze the user's lifestyle and work schedule and propose an optimal study schedule based on that. For example, it can set study times that avoid busy times for the user. The generation AI can also analyze the user's lifestyle and work schedule and propose an efficient study schedule. For example, it can create a study plan that allows the user to make effective use of their free time. It can also propose an optimal study schedule taking the user's lifestyle and work schedule into consideration. For example, it can concentrate study during times when the user is relaxed. This makes it possible to propose an optimal study schedule based on the user's lifestyle and work schedule.

[0057] The step suggestion unit can make customized suggestions according to the user's learning style. For example, it analyzes the user's learning style and makes customized step suggestions accordingly. For example, it proposes a study plan that makes extensive use of diagrams and videos to a visual user. In addition, the generation AI takes the user's learning style into consideration and makes optimal step suggestions. For example, it proposes a study plan that focuses on audio materials to an auditory user. In addition, it makes customized step suggestions according to the user's learning style. For example, it proposes a study plan that includes many practical exercises to a tactile user. In this way, it makes customized suggestions according to the user's learning style.

[0058] The step suggestion unit is also able to support group learning and pair learning formats and propose collaborative learning schedules. For example, the step suggestion unit can also support group learning and pair learning formats and propose collaborative learning schedules. For example, the unit can adjust the schedule so that multiple users can study at the same time. The generation AI also makes step suggestion compatible with group learning and pair learning formats. For example, it can propose a schedule for a user to cooperate with other learners to advance their studies. The step suggestion unit can also support collaborative learning formats so that a user can study together with other learners. For example, it can propose a schedule for group discussions or collaborative projects. This makes it possible to support group learning and pair learning formats and propose collaborative learning schedules.

[0059] The step suggestion unit can accommodate different qualification exams and learning goals, making it usable by a wide range of users. For example, the step suggestion unit can accommodate different qualification exams and learning goals, making it usable by a wide range of users. For example, it can propose study plans that correspond to multiple qualification exams. In addition, the generation AI makes step suggestions that correspond to different qualification exams and learning goals. For example, if a user is aiming for multiple qualification exams at the same time, it can propose study plans that correspond to each exam. In addition, the step suggestion unit can accommodate a wide range of learning goals, allowing users to create study plans that match their goals. For example, it can make step suggestions that correspond to users who are aiming to acquire specific skills or advance their careers. This makes it possible to accommodate different qualification exams and learning goals, making it usable by a wide range of users.

[0060] The curriculum suggestion unit can analyze the user's past learning data and dynamically generate an optimal curriculum. For example, it analyzes the user's past learning data and dynamically generates an optimal curriculum based on it. For example, it suggests what to study next, taking into account what has been learned in the past and the level of understanding. The generation AI also analyzes the user's past learning data and generates a curriculum that meets individual needs. For example, it adjusts the curriculum so that the user can focus on areas in which they are weak. It also analyzes the user's learning history and dynamically generates an optimal curriculum. For example, it suggests an effective learning plan based on past test results and learning progress. In this way, the user's past learning data is analyzed and an optimal curriculum is dynamically generated.

[0061] The curriculum proposal unit reflects the latest industry trends and technical information, allowing it to always provide the latest curriculum. For example, when proposing a curriculum, it automatically collects the latest industry trends and technical information and reflects it in the curriculum. For example, it updates the learning content based on the latest technological trends and market needs. In addition, the generative AI analyzes the latest industry trends and technical information and proposes a curriculum based on that. For example, it provides a learning plan that incorporates new technologies and methodologies. It also proposes a curriculum that reflects the latest industry trends and technical information. For example, it regularly updates the curriculum so that users can always learn the latest information. This allows it to reflect the latest industry trends and technical information and always provide the latest content.

[0062] The curriculum proposal unit can accommodate different educational levels and provide them to a wide range of users. For example, curriculum proposals can be adapted to different educational levels and provided to a wide range of users. For example, it can propose study plans suitable for high school students, university students, and working adults. In addition, the generation AI can propose curricula that correspond to different educational levels. For example, it can provide a curriculum that includes basic content for high school students and specialized content for working adults. In addition, it can propose curricula that correspond to different educational levels and make them available to a wide range of users. For example, it can dynamically generate curricula that correspond to the user's learning level. This allows it to accommodate different educational levels and provide them to a wide range of users.

[0063] The curriculum proposal unit can link with online courses and webinars to propose learning combined with actual lectures and seminars. For example, by linking a curriculum proposal with an online course or webinar, it proposes learning combined with actual lectures and seminars. For example, it incorporates the content of the online course into the curriculum. In addition, the generative AI collects information about online courses and webinars and proposes a curriculum based on that information. For example, it includes webinars that users can participate in in the curriculum. In addition, it proposes a curriculum linked with online courses and webinars to provide learning combined with actual lectures and seminars. For example, it proposes a curriculum that combines online and offline learning. This allows it to link with online courses and webinars and propose learning combined with actual lectures and seminars.

[0064] The practice problem providing unit can analyze the user's learning progress and automatically generate practice problems of a difficulty level according to the level of understanding. For example, it analyzes the user's learning progress and automatically generates practice problems of a difficulty level according to the level of understanding. For example, it provides problems of an appropriate difficulty level for areas in which the user is weak. In addition, the generation AI analyzes the user's learning progress and generates practice problems according to individual needs. For example, it provides high-difficulty questions for areas in which the user is strong. In addition, it analyzes the user's learning history and automatically generates practice problems of a difficulty level according to the level of understanding. For example, it provides questions of an appropriate difficulty level based on past test results. In this way, the user's learning progress is analyzed and practice problems of a difficulty level according to the level of understanding are automatically generated.

[0065] The practice problem providing unit can analyze the results of practice problems and confirmation tests, identify weak points, and provide feedback to help the user focus on learning. For example, it can analyze the results of practice problems and confirmation tests, identify the user's weak points, and provide feedback to help the user focus on learning. For example, it can provide detailed explanations for questions the user got wrong. The generation AI also analyzes the results of practice problems and confirmation tests, and provides feedback tailored to individual needs. For example, it can provide additional study materials for areas the user is weak in. It can also identify the user's weak points based on the results of practice problems and confirmation tests, and provide feedback to help the user focus on learning. For example, it can provide supplementary explanations for concepts that the user does not understand. In this way, the results of practice problems and confirmation tests can be analyzed, and feedback can be provided to help the user focus on learning.

[0066] The practice question providing unit can provide practice questions and confirmation tests in a game format, allowing users to study while having fun. For example, practice questions and confirmation tests can be provided in a game format, allowing users to study while having fun. For example, quiz-style questions can be provided, allowing users to earn points for each correct answer. In addition, the generation AI can convert practice questions and confirmation tests into a game format, allowing users to study while having fun. For example, time attack-style questions can be provided, allowing users to study with a competitive spirit. In addition, practice questions and confirmation tests can be provided in a game format, allowing users to study while having fun. For example, a level-up system can be introduced, allowing users to study while feeling a sense of accomplishment. In this way, practice questions and confirmation tests can be provided in a game format, allowing users to study while having fun.

[0067] The practice problem providing unit can provide practice problems and confirmation tests in a competitive format with other users, thereby increasing motivation. For example, by providing practice problems and confirmation tests in a competitive format with other users, the user's motivation is increased. For example, a ranking system can be introduced so that users can compete with other learners. Furthermore, the generation AI converts practice problems and confirmation tests into a competitive format to increase user motivation. For example, battle-style problems can be provided so that users can compete with opponents. Furthermore, by providing practice problems and confirmation tests in a competitive format with other users, the user's motivation is increased. For example, a team competition can be introduced so that users can study cooperatively. In this way, practice problems and confirmation tests can be provided in a competitive format with other users, thereby increasing motivation.

[0068] The learning support unit can analyze the user's learning history and propose an individual learning plan based on their past level of understanding. For example, it can analyze the user's learning history and propose an individual learning plan based on their past level of understanding. For example, it can adjust the plan so that the user can focus on learning areas in which they are weak. In addition, the generation AI analyzes the user's learning history and proposes a learning plan that meets individual needs. For example, it can provide a plan that includes advanced content for areas in which the user is strong. In addition, it can propose an individual learning plan based on the user's learning history and meets their past level of understanding. For example, it can create an effective learning plan based on past test results. In this way, it can analyze the user's learning history and propose an individual learning plan based on their past level of understanding.

[0069] The learning support unit can automatically provide related examples and case studies during learning support to promote practical understanding. For example, during learning support, related examples and case studies can be automatically provided to promote practical understanding for the user. For example, examples related to a specific qualification exam can be presented. In addition, the generative AI automatically provides related case studies during learning support. For example, actual cases related to the content the user is learning can be introduced. In addition, during learning support, examples and case studies can be automatically provided to deepen the user's understanding. For example, specific cases related to the learning content can be presented. In this way, during learning support, related examples and case studies can be automatically provided to promote practical understanding.

[0070] The learning support unit can adapt learning support to different learning fields and provide it to a wide range of users. For example, learning support can be adapted to different learning fields and provided to a wide range of users. For example, support can be provided for language learning or programming learning. In addition, the generation AI provides learning support adapted to different learning fields. For example, support can be provided according to the field that the user wants to learn. In addition, learning support can be adapted to a wide range of learning fields, allowing users to proceed with learning that suits their interests. For example, support can be provided for users who are aiming to acquire specific skills or advance their careers. In this way, learning support can be adapted to different learning fields and provided to a wide range of users.

[0071] The learning support unit can link the learning support with an online community to deepen learning through interactions with other users. For example, the learning support can be linked with an online community to enable users to interact with other learners. For example, discussion forums and group chats can be provided. The generative AI can also link with the online community to enable users to collaborate with other learners to advance their learning. For example, it can suggest joint projects and group discussions. The learning support can also be linked with an online community to deepen learning through interactions with other learners. For example, it can provide opportunities to share learning results and receive feedback. In this way, the learning support can be linked with an online community to deepen learning through interactions with other users.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The question-and-answer unit generates answers to user questions. For example, if a user asks how to study for a qualification exam, the generating AI provides information about the exam and suggests specific study methods. Step 2: The step suggestion unit proposes steps to achieve the goal based on the answers generated by the question answering unit. For example, the generation AI proposes a schedule and study plan leading up to the exam date. Step 3: The curriculum suggestion unit proposes an optimal curriculum based on the steps proposed by the step suggestion unit. For example, the generative AI proposes learning content and materials based on the exam scope. Step 4: The practice problem providing unit provides practice problems and confirmation tests based on the curriculum proposed by the curriculum suggestion unit. For example, the generation AI generates and provides practice problems and confirmation tests according to the user's learning progress.

[0074] (Example 2) The AI ​​question and answer service according to an embodiment of the present invention is a system that supports questions and learning needs related to qualification acquisition. This system allows users to ask questions to the AI ​​and receive necessary information and explanations in real time, efficiently supporting the qualification acquisition learning process. As a result, the AI ​​question and answer service can support effective learning tailored to individual needs by proposing steps and curricula to users to achieve their goals and providing practice questions and confirmation tests.

[0075] An AI question-and-answer service according to an embodiment includes a question-and-answer unit, a step proposal unit, a curriculum proposal unit, and a practice question provision unit. The question-and-answer unit generates answers to user questions. For example, when a user asks about how to study for a qualification exam, the generation AI provides information about the qualification exam and suggests specific study methods. The step proposal unit proposes steps to achieve a goal based on the answers generated by the question-and-answer unit. For example, the generation AI proposes a schedule and study plan leading up to the exam date. The curriculum proposal unit proposes an optimal curriculum based on the steps proposed by the step proposal unit. For example, the generation AI proposes study content and teaching materials based on the exam scope. The practice question provision unit provides practice questions and confirmation tests based on the curriculum proposed by the curriculum proposal unit. For example, the generation AI generates and provides practice questions and confirmation tests according to the user's learning progress. This enables the AI ​​question-and-answer service according to an embodiment to efficiently support the qualification acquisition learning process.

[0076] The question answering unit can generate the optimal answer based on the user's past learning history and current level of understanding. For example, when a user inputs a question, the generation AI analyzes the background information of the question and references the user's past learning history. For example, it generates the optimal answer based on the content learned in the past and the level of understanding. In addition, when analyzing the background information of the question, it takes into account the user's current level of understanding. For example, it provides an answer of an appropriate level of difficulty based on what problems the user has tackled in the past. It also analyzes the user's learning history and associates the content learned in the past with the content of the current question. For example, it provides information related to topics learned in the past to deepen the user's understanding. This makes it possible to provide the optimal answer based on the user's learning history and level of understanding.

[0077] The question-answering unit can automatically insert related videos and illustrations when generating an answer to a question. For example, when a user inputs a question, the generation AI automatically inserts related videos and illustrations when generating an answer to that question. For example, in response to a question about how to study for a qualification exam, a video showing specific study methods is provided. In addition, when generating an answer to a question, visually easy-to-understand illustrations are inserted. For example, when explaining complex concepts, flowcharts and graphs are used for visual explanations. In addition, when a user inputs a question, the generation AI searches for videos and illustrations related to the question and incorporates them into the answer. For example, in response to a question about how to study for a specific qualification exam, a related video tutorial is provided. This makes it possible to provide answers that are visually easy to understand.

[0078] The question answering unit can use the emotion estimation function to analyze the user's emotions when asking a question and generate an answer to reduce stress and anxiety. For example, when a user inputs a question, the generation AI uses the emotion estimation function to analyze the user's emotions. For example, if the user is feeling stressed, an answer that will help them relax is provided. The emotion estimation function can also be used to analyze the user's emotions when asking a question and generate an answer to reduce stress and anxiety. For example, if the user is feeling anxious, an answer including an encouraging message is provided. The user's emotions can also be analyzed and an answer to reduce stress and anxiety is generated. For example, if the user is nervous, advice to help them relax is provided. In this way, an answer can be provided to reduce the user's stress and anxiety.

[0079] The question and answer unit can support different languages ​​and be available to international users. The question and answer unit, for example, makes the question and answer function multilingual so that it can support questions in different languages. For example, it provides appropriate answers to questions in multiple languages, such as English, Japanese, and French. In addition, to support different languages, a multilingual translation function is incorporated into the generation AI. For example, when a user inputs a question in English, the generation AI translates the question into Japanese and generates an appropriate answer. In addition, to support international users, the question and answer function is made multilingual. For example, when a user inputs a question in French, the generation AI provides an answer to the question in French. This allows it to support different languages ​​and be available to international users.

[0080] The question and answer unit also supports voice input, allowing users to input questions by voice. The question and answer unit, for example, adds a voice input function to the question and answer function, allowing users to input questions by voice. For example, when a user inputs a question by voice using a microphone, the generation AI analyzes the voice and provides an appropriate answer. The voice input function also allows users to input questions by voice. For example, when a user inputs a question by voice using a microphone on a smartphone, the generation AI converts the voice into text and generates an answer. The question and answer function also incorporates voice recognition technology, allowing users to input questions by voice. For example, when a user inputs a question by voice, the generation AI analyzes the voice and provides an appropriate answer. This allows users to input questions by voice.

[0081] The question answering unit can use the emotion estimation function to analyze the emotion of the user when inputting a question in real time and provide positive feedback. The question answering unit, for example, uses the emotion estimation function to analyze the emotion of the user when inputting a question in real time. For example, if the user is feeling anxious, positive feedback is provided. Furthermore, when the user inputs a question, the emotion estimation function is used to analyze the emotion and provide positive feedback. For example, if the user is nervous, a message to help the user relax is displayed. Furthermore, the emotion estimation function is used to analyze the user's emotion in real time and provide positive feedback. For example, if the user is feeling stressed, an encouraging message is displayed. In this way, positive feedback according to the user's emotion can be provided.

[0082] The step suggestion unit can analyze the user's lifestyle and work schedule and propose an optimal study schedule based on that. The step suggestion unit, for example, analyzes the user's lifestyle and work schedule and proposes an optimal study schedule based on that. For example, it sets study times to avoid busy times for the user. The generation AI also analyzes the user's lifestyle and work schedule and proposes an efficient study schedule. For example, it creates a study plan that allows the user to make effective use of their free time. It also proposes an optimal study schedule taking the user's lifestyle and work schedule into consideration. For example, it concentrates study during times when the user is relaxed. This makes it possible to propose an optimal study schedule based on the user's lifestyle and work schedule.

[0083] The step suggestion unit can make customized suggestions according to the user's learning style. The step suggestion unit, for example, analyzes the user's learning style and makes customized step suggestions accordingly. For example, for a visual user, it proposes a study plan that makes extensive use of illustrations and videos. In addition, the generation AI takes the user's learning style into consideration and makes optimal step suggestions. For example, for an auditory user, it proposes a study plan that focuses on audio materials. In addition, it makes customized step suggestions according to the user's learning style. For example, for a tactile user, it proposes a study plan that includes many practical exercises. In this way, it makes customized suggestions according to the user's learning style.

[0084] The step suggestion unit can use the emotion estimation function to provide encouraging and supportive messages for each step to maintain the user's motivation. The step suggestion unit, for example, uses the emotion estimation function to provide encouraging and supportive messages for each step to maintain the user's motivation. For example, if the user is tired, an encouraging message is displayed. The step suggestion unit also analyzes the user's emotions and provides supportive messages to maintain motivation. For example, a message is displayed to inform the user that they are approaching a goal. The emotion estimation function also provides messages to increase the user's motivation for each step. For example, a message that makes the user feel like they are making progress is displayed. This makes it possible to provide encouraging and supportive messages to maintain the user's motivation.

[0085] The step proposal unit is also able to accommodate group learning and pair learning formats and propose collaborative learning schedules. For example, the step proposal unit adapts the step proposals to group learning and pair learning formats and proposes a collaborative learning schedule. For example, the schedule is adjusted so that multiple users can study simultaneously. The generation AI also makes step proposals that are compatible with group learning and pair learning formats. For example, a schedule is proposed for a user to advance their learning in cooperation with other learners. The step proposals are also adapted to collaborative learning formats so that the user can study together with other learners. For example, a schedule for group discussions or collaborative projects is proposed. This makes it possible to accommodate group learning and pair learning formats and propose collaborative learning schedules.

[0086] The step proposal unit can accommodate different qualification exams and learning goals, making it usable by a wide range of users. The step proposal unit, for example, can accommodate step proposals for different qualification exams and learning goals, making it usable by a wide range of users. For example, it proposes study plans that correspond to multiple qualification exams. In addition, the generation AI makes step proposals that correspond to different qualification exams and learning goals. For example, if a user is aiming for multiple qualification exams at the same time, it proposes study plans that correspond to each exam. In addition, it can accommodate step proposals for a wide range of learning goals, allowing users to create study plans that match their goals. For example, it can make step proposals that correspond to users who are aiming to acquire specific skills or advance their careers. This makes it possible to accommodate different qualification exams and learning goals, making it usable by a wide range of users.

[0087] The step suggestion unit uses the emotion estimation function to adjust steps in real time according to the user's emotional state, thereby optimizing learning progress. The step suggestion unit, for example, uses the emotion estimation function to adjust steps in real time according to the user's emotional state. For example, if the user is tired, the step suggestion unit suggests slowing down the pace of learning. The step suggestion unit also analyzes the user's emotional state and adjusts steps to optimize learning progress. For example, if the user is losing motivation, the step suggestion unit reviews the learning plan along with an encouraging message. The emotion estimation function also uses the step suggestion unit to adjust steps in real time according to the user's emotional state, thereby optimizing learning progress. For example, if the user is feeling stressed, the step suggestion unit suggests a relaxing activity. In this way, the step suggestion unit adjusts steps in real time according to the user's emotional state, thereby optimizing learning progress.

[0088] The curriculum suggestion unit can analyze the user's past learning data and dynamically generate an optimal curriculum. The curriculum suggestion unit, for example, analyzes the user's past learning data and dynamically generates an optimal curriculum based on it. For example, it suggests what to study next, taking into account what has been learned in the past and the level of understanding. In addition, the generation AI analyzes the user's past learning data and generates a curriculum according to individual needs. For example, it adjusts the curriculum so that the user can focus on areas in which they are weak. It also analyzes the user's learning history and dynamically generates an optimal curriculum. For example, it proposes an effective learning plan based on past test results and learning progress. In this way, the user's past learning data is analyzed and an optimal curriculum is dynamically generated.

[0089] The curriculum proposal unit reflects the latest industry trends and technical information, allowing it to always provide the latest curriculum. For example, when proposing a curriculum, the curriculum proposal unit automatically collects the latest industry trends and technical information and reflects it in the curriculum. For example, it updates the learning content based on the latest technological trends and market needs. In addition, the generative AI analyzes the latest industry trends and technical information and proposes a curriculum based on that. For example, it provides a learning plan that incorporates new technologies and methodologies. It also proposes a curriculum that reflects the latest industry trends and technical information. For example, it regularly updates the curriculum so that users can always learn the latest information. This allows it to reflect the latest industry trends and technical information and always provide the latest content.

[0090] The curriculum suggestion unit can use the emotion estimation function to suggest a curriculum based on the user's interests and concerns, thereby increasing motivation to learn. The curriculum suggestion unit, for example, uses the emotion estimation function to analyze the user's interests and concerns, and suggest a curriculum based on them. For example, it creates a study plan centered on topics that interest the user. It also analyzes the user's emotions and suggests a curriculum based on the interests and concerns. For example, it provides a curriculum that includes content that the user can enjoy learning. It also uses the emotion estimation function to suggest a curriculum that reflects the user's interests and concerns. For example, it provides learning content that keeps the user motivated. In this way, it suggests a curriculum based on the user's interests and concerns, increasing motivation to learn.

[0091] The curriculum proposal unit can accommodate different educational levels and provide them to a wide range of users. For example, the curriculum proposal unit adapts curriculum proposals to different educational levels and provides them to a wide range of users. For example, it proposes study plans suitable for high school students, university students, and working adults. In addition, the generation AI proposes curricula that correspond to different educational levels. For example, it provides a curriculum that includes basic content for high school students and specialized content for working adults. In addition, it proposes curricula that correspond to different educational levels and makes them available to a wide range of users. For example, it dynamically generates a curriculum that corresponds to the user's learning level. This allows it to accommodate different educational levels and provide them to a wide range of users.

[0092] The curriculum proposal unit can link with online courses and webinars to propose learning combined with actual lectures and seminars. For example, the curriculum proposal unit links the curriculum proposal with online courses and webinars to propose learning combined with actual lectures and seminars. For example, the content of the online course is incorporated into the curriculum. In addition, the generative AI collects information about online courses and webinars and proposes a curriculum based on that information. For example, webinars that users can participate in are included in the curriculum. In addition, a curriculum linked with the online course or webinar is proposed to provide learning combined with actual lectures and seminars. For example, a curriculum combining online and offline learning is proposed. This allows linking with online courses and webinars to propose learning combined with actual lectures and seminars.

[0093] The curriculum suggestion unit can use the emotion estimation function to adjust the curriculum in real time according to the user's emotional state, thereby maximizing the effectiveness of learning. The curriculum suggestion unit, for example, uses the emotion estimation function to adjust the curriculum in real time according to the user's emotional state. For example, if the user is tired, a suggestion is made to reduce the learning content. The curriculum suggestion unit also analyzes the user's emotional state and adjusts the curriculum to maximize the effectiveness of learning. For example, if the user is losing motivation, interesting content is added. The emotion estimation function also adjusts the curriculum in real time according to the user's emotional state, thereby maximizing the effectiveness of learning. For example, if the user is feeling stressed, a relaxing activity is suggested. In this way, the curriculum suggestion unit adjusts the curriculum in real time according to the user's emotional state, thereby maximizing the effectiveness of learning.

[0094] The practice problem providing unit can analyze the user's learning progress and automatically generate practice problems of a difficulty level according to the level of understanding. The practice problem providing unit, for example, analyzes the user's learning progress and automatically generates practice problems of a difficulty level according to the level of understanding. For example, problems of an appropriate difficulty level are provided for areas in which the user is weak. In addition, the generation AI analyzes the user's learning progress and generates practice problems according to individual needs. For example, high-difficulty questions are provided for areas in which the user is strong. In addition, the user's learning history is analyzed and practice problems of a difficulty level according to the level of understanding are automatically generated. For example, questions of an appropriate difficulty level are provided based on past test results. In this way, the user's learning progress is analyzed and practice problems of a difficulty level according to the level of understanding are automatically generated.

[0095] The practice problem providing unit can analyze the results of the practice problems and confirmation tests, identify weak points, and provide feedback to help the user focus on learning. The practice problem providing unit, for example, analyzes the results of the practice problems and confirmation tests, and provides feedback to help the user identify weak points and focus on learning. For example, detailed explanations are provided for questions that the user got wrong. The generation AI also analyzes the results of the practice problems and confirmation tests, and provides feedback tailored to individual needs. For example, additional study materials are provided for areas in which the user is weak. The generation AI also identifies the user's weak points based on the results of the practice problems and confirmation tests, and provides feedback to help the user focus on learning. For example, supplementary explanations are provided for concepts that the user does not understand. In this way, the practice problem providing unit analyzes the results of the practice problems and confirmation tests, and provides feedback to help the user identify weak points and focus on learning.

[0096] The exercise provision unit can use the emotion estimation function to analyze the user's stress level and suggest a break at an appropriate time. The exercise provision unit, for example, uses the emotion estimation function to analyze the user's stress level and suggest a break at an appropriate time. For example, if the user is tired, a message urging the user to take a break is displayed. The exercise provision unit also analyzes the user's emotional state and suggests a break if the stress level is high. For example, if the user is losing concentration, a relaxing activity is suggested. The emotion estimation function also analyzes the user's stress level in real time and suggests a break at an appropriate time. For example, if the user is feeling stressed, the exercise provision unit urges the user to take a short break. In this way, the exercise provision unit analyzes the user's stress level and suggests a break at an appropriate time.

[0097] The practice question providing unit can provide practice questions and confirmation tests in a game format, allowing users to study while having fun. The practice question providing unit, for example, provides practice questions and confirmation tests in a game format, allowing users to study while having fun. For example, quiz-style questions are provided, allowing users to earn points for each correct answer. Furthermore, the generation AI converts practice questions and confirmation tests into a game format, allowing users to study while having fun. For example, time attack-style questions are provided, allowing users to study with a competitive spirit. Furthermore, practice questions and confirmation tests are provided in a game format, allowing users to study while having fun. For example, a level-up system can be introduced, allowing users to study while feeling a sense of accomplishment. In this way, practice questions and confirmation tests can be provided in a game format, allowing users to study while having fun.

[0098] The practice problem providing unit can provide practice problems and confirmation tests in a competitive format with other users, thereby increasing motivation. The practice problem providing unit, for example, provides practice problems and confirmation tests in a competitive format with other users, thereby increasing user motivation. For example, a ranking system can be introduced so that users can compete with other learners. Furthermore, the generation AI converts practice problems and confirmation tests into a competitive format, thereby increasing user motivation. For example, battle-style problems can be provided so that users can compete with opponents. Furthermore, practice problems and confirmation tests can be provided in a competitive format with other users, thereby increasing user motivation. For example, a team competition can be introduced so that users can study cooperatively. In this way, practice problems and confirmation tests can be provided in a competitive format with other users, thereby increasing motivation.

[0099] The practice question providing unit can use the emotion estimation function to adjust the difficulty of the practice questions and confirmation tests according to the user's emotional state. The practice question providing unit, for example, uses the emotion estimation function to adjust the difficulty of the practice questions and confirmation tests according to the user's emotional state. For example, if the user is feeling stressed, questions with a lower level of difficulty are provided. The practice question providing unit also analyzes the user's emotional state and adjusts the difficulty of the practice questions and confirmation tests in real time. For example, if the user is relaxed, questions with a higher level of difficulty are provided. The emotion estimation function also adjusts the difficulty of the practice questions and confirmation tests according to the user's emotional state. For example, if the user is losing motivation, easy questions are provided to help them regain their confidence. In this way, the difficulty of the practice questions and confirmation tests is adjusted according to the user's emotional state.

[0100] The learning support unit can analyze the user's learning history and propose an individual learning plan based on their past level of understanding. For example, the learning support unit analyzes the user's learning history and proposes an individual learning plan based on their past level of understanding. For example, the plan is adjusted so that the user can focus on studying areas in which they are weak. In addition, the generation AI analyzes the user's learning history and proposes a learning plan that meets individual needs. For example, a plan that includes advanced content is provided for areas in which the user is strong. In addition, an individual learning plan based on the user's learning history and according to their past level of understanding is proposed. For example, an effective learning plan is created based on past test results. In this way, the learning support unit analyzes the user's learning history and proposes an individual learning plan based on their past level of understanding.

[0101] The learning support unit can automatically provide related examples and case studies during learning support to promote practical understanding. The learning support unit, for example, automatically provides related examples and case studies during learning support to promote practical understanding for the user. For example, examples related to a specific qualification exam are presented. In addition, the generative AI automatically provides related case studies during learning support. For example, actual cases related to the content the user is learning are introduced. In addition, during learning support, examples and case studies are automatically provided to deepen the user's understanding. For example, specific cases related to the learning content are presented. In this way, related examples and case studies are automatically provided during learning support to promote practical understanding.

[0102] The learning support unit can use the emotion estimation function to provide a motivational message to maintain the user's motivation to learn. The learning support unit, for example, uses the emotion estimation function to provide a motivational message to maintain the user's motivation to learn. For example, if the user is tired, an encouraging message is displayed. The learning support unit also analyzes the user's emotions and provides a message to maintain the user's motivation to learn. For example, a message is displayed informing the user that they are approaching their goal. The emotion estimation function also provides a message to increase the user's motivation to learn. For example, a message that makes the user feel like they are making progress is displayed. In this way, a motivational message is provided to maintain the user's motivation to learn.

[0103] The learning support unit can adapt learning support to different learning fields and provide it to a wide range of users. The learning support unit, for example, adapts learning support to different learning fields and provides it to a wide range of users. For example, it provides support tailored to language learning or programming learning. In addition, the generation AI provides learning support tailored to different learning fields. For example, it provides support tailored to the field the user wants to learn. In addition, learning support can be adapted to a wide range of learning fields, allowing users to advance in learning that suits their interests. For example, it provides support tailored to users who are aiming to acquire specific skills or advance their careers. In this way, learning support can be adapted to different learning fields and provided to a wide range of users.

[0104] The learning support unit can link the learning support with an online community to deepen learning through interactions with other users. The learning support unit, for example, links the learning support with an online community to enable users to interact with other learners. For example, it provides a discussion forum or group chat. The generative AI also links with the online community to enable users to cooperate with other learners to advance their learning. For example, it suggests joint projects or group discussions. The learning support also links with the online community to deepen learning through interactions with other learners. For example, it provides opportunities to share learning results and receive feedback. In this way, the learning support is linked with the online community to deepen learning through interactions with other users.

[0105] The learning support unit can use the emotion estimation function to adjust the content of learning support in real time according to the user's emotional state. The learning support unit, for example, uses the emotion estimation function to adjust the content of learning support in real time according to the user's emotional state. For example, if the user is feeling stressed, the learning support unit suggests a relaxing activity. The learning support unit also analyzes the user's emotional state and adjusts the content of learning support in real time. For example, if the user is losing motivation, the learning support unit reviews the study plan along with an encouraging message. The learning support unit also uses the emotion estimation function to adjust the content of learning support in real time according to the user's emotional state. For example, if the user is tired, the learning support unit suggests slowing down the pace of study. In this way, the learning support unit uses the emotion estimation function to adjust the content of learning support in real time according to the user's emotional state.

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

[0107] The question answering unit generates answers to user questions. For example, when a user asks about how to study for a qualification exam, the generation AI provides information about the qualification exam and suggests specific study methods. The step suggestion unit suggests steps to achieve a goal based on the answers generated by the question answering unit. For example, the generation AI suggests a schedule and study plan leading up to the exam date. The curriculum suggestion unit suggests an optimal curriculum based on the steps suggested by the step suggestion unit. For example, the generation AI suggests study content and teaching materials based on the exam scope. The practice question providing unit provides practice questions and confirmation tests based on the curriculum suggested by the curriculum suggestion unit. For example, the generation AI generates and provides practice questions and confirmation tests according to the user's learning progress. This allows the AI ​​question answering service according to the embodiment to efficiently support the learning process for obtaining qualifications.

[0108] The question-answering unit can generate optimal answers based on the user's past learning history and current level of understanding. For example, when a user inputs a question, the generation AI analyzes the background information of the question and references the user's past learning history. For example, it generates optimal answers based on the content learned in the past and the user's level of understanding. In addition, when analyzing the background information of the question, it takes into account the user's current level of understanding. For example, it provides answers of an appropriate level of difficulty based on the types of problems the user has tackled in the past. It also analyzes the user's learning history and associates the content learned in the past with the content of the current question. For example, it provides information related to topics learned in the past to deepen the user's understanding. This allows it to provide optimal answers based on the user's learning history and level of understanding.

[0109] The question-answering unit can automatically insert related videos and illustrations when generating an answer to a question. For example, when a user inputs a question, the generation AI automatically inserts related videos and illustrations when generating an answer to that question. For example, in response to a question about how to study for a qualification exam, a video showing specific study methods is provided. In addition, when generating an answer to a question, visually easy-to-understand illustrations are inserted. For example, when explaining complex concepts, flowcharts and graphs are used for visual explanations. In addition, when a user inputs a question, the generation AI searches for videos and illustrations related to the question and incorporates them into the answer. For example, in response to a question about how to study for a specific qualification exam, a related video tutorial is provided. This makes it possible to provide answers that are visually easy to understand.

[0110] The question answering unit can use the emotion estimation function to analyze the user's emotions when asking a question and generate an answer to reduce stress and anxiety. For example, when a user inputs a question, the generation AI uses the emotion estimation function to analyze the user's emotions. For example, if the user is feeling stressed, an answer that will help them relax is provided. The emotion estimation function can also be used to analyze the user's emotions when asking a question and generate an answer to reduce stress and anxiety. For example, if the user is feeling anxious, an answer that includes an encouraging message is provided. The user's emotions can also be analyzed and an answer to reduce stress and anxiety is generated. For example, if the user is nervous, advice to help them relax is provided. This makes it possible to provide an answer to reduce the user's stress and anxiety.

[0111] The question-answering unit can support different languages ​​and be available to international users. For example, the question-answering function can be made multilingual so that it can handle questions in different languages. For example, it can provide appropriate answers to questions in multiple languages, such as English, Japanese, and French. In addition, to support different languages, a multilingual translation function can be incorporated into the generation AI. For example, when a user inputs a question in English, the generation AI translates the question into Japanese and generates an appropriate answer. In addition, to support international users, the question-answering function can be made multilingual. For example, when a user inputs a question in French, the generation AI can provide an answer to the question in French. This allows it to support different languages ​​and be available to international users.

[0112] The question and answer unit also supports voice input, allowing users to input questions by voice. For example, a voice input function can be added to the question and answer function, allowing users to input questions by voice. For example, when a user inputs a question by voice using a microphone, the generation AI analyzes the voice and provides an appropriate answer. In addition, the voice input function can be used to allow users to input questions by voice. For example, when a user inputs a question by voice using a smartphone microphone, the generation AI converts the voice into text and generates an answer. In addition, speech recognition technology can be incorporated into the question and answer function, allowing users to input questions by voice. For example, when a user inputs a question by voice, the generation AI analyzes the voice and provides an appropriate answer. This allows users to input questions by voice.

[0113] The question answering unit can use the emotion estimation function to analyze the emotion of the user when inputting a question in real time and provide positive feedback. For example, the emotion estimation function is used to analyze the emotion of the user when inputting a question in real time. For example, if the user is feeling anxious, positive feedback is provided. Furthermore, when the user inputs a question, the emotion estimation function is used to analyze the emotion and provide positive feedback. For example, if the user is nervous, a message to help the user relax is displayed. Furthermore, the emotion estimation function is used to analyze the user's emotion in real time and provide positive feedback. For example, if the user is feeling stressed, an encouraging message is displayed. In this way, positive feedback can be provided according to the user's emotion.

[0114] The step suggestion unit can analyze the user's lifestyle and work schedule and propose an optimal study schedule based on that. For example, it can analyze the user's lifestyle and work schedule and propose an optimal study schedule based on that. For example, it can set study times that avoid busy times for the user. The generation AI can also analyze the user's lifestyle and work schedule and propose an efficient study schedule. For example, it can create a study plan that allows the user to make effective use of their free time. It can also propose an optimal study schedule taking the user's lifestyle and work schedule into consideration. For example, it can concentrate study during times when the user is relaxed. This makes it possible to propose an optimal study schedule based on the user's lifestyle and work schedule.

[0115] The step suggestion unit can make customized suggestions according to the user's learning style. For example, it analyzes the user's learning style and makes customized step suggestions accordingly. For example, it proposes a study plan that makes extensive use of diagrams and videos to a visual user. In addition, the generation AI takes the user's learning style into consideration and makes optimal step suggestions. For example, it proposes a study plan that focuses on audio materials to an auditory user. In addition, it makes customized step suggestions according to the user's learning style. For example, it proposes a study plan that includes many practical exercises to a tactile user. In this way, it makes customized suggestions according to the user's learning style.

[0116] The step suggestion unit can use the emotion estimation function to provide encouraging and supportive messages for each step to maintain the user's motivation. For example, the emotion estimation function can be used to provide encouraging and supportive messages for each step to maintain the user's motivation. For example, if the user is tired, an encouraging message can be displayed. The step suggestion unit can also analyze the user's emotions and provide supportive messages to maintain the user's motivation. For example, a message can be displayed to inform the user that the user is approaching a goal. The emotion estimation function can also be used to provide messages to increase the user's motivation for each step. For example, a message that makes the user feel like they are making progress can be displayed. This makes it possible to provide encouraging and supportive messages to maintain the user's motivation.

[0117] The step suggestion unit is also able to support group learning and pair learning formats and propose collaborative learning schedules. For example, the step suggestion unit can also support group learning and pair learning formats and propose collaborative learning schedules. For example, the unit can adjust the schedule so that multiple users can study at the same time. The generation AI also makes step suggestion compatible with group learning and pair learning formats. For example, it can propose a schedule for a user to cooperate with other learners to advance their studies. The step suggestion unit can also support collaborative learning formats so that a user can study together with other learners. For example, it can propose a schedule for group discussions or collaborative projects. This makes it possible to support group learning and pair learning formats and propose collaborative learning schedules.

[0118] The step suggestion unit can accommodate different qualification exams and learning goals, making it usable by a wide range of users. For example, the step suggestion unit can accommodate different qualification exams and learning goals, making it usable by a wide range of users. For example, it can propose study plans that correspond to multiple qualification exams. In addition, the generation AI makes step suggestions that correspond to different qualification exams and learning goals. For example, if a user is aiming for multiple qualification exams at the same time, it can propose study plans that correspond to each exam. In addition, the step suggestion unit can accommodate a wide range of learning goals, allowing users to create study plans that match their goals. For example, it can make step suggestions that correspond to users who are aiming to acquire specific skills or advance their careers. This makes it possible to accommodate different qualification exams and learning goals, making it usable by a wide range of users.

[0119] The step suggestion unit can use the emotion estimation function to adjust steps in real time according to the user's emotional state, thereby optimizing learning progress. For example, the emotion estimation function is used to adjust steps in real time according to the user's emotional state. For example, if the user is tired, a suggestion is made to slow down the pace of learning. The step suggestion unit also analyzes the user's emotional state and adjusts steps to optimize learning progress. For example, if the user is losing motivation, the step suggestion unit sends an encouraging message and reviews the learning plan. The emotion estimation function is also used to adjust steps in real time according to the user's emotional state, thereby optimizing learning progress. For example, if the user is feeling stressed, a relaxing activity is suggested. In this way, steps are adjusted in real time according to the user's emotional state, thereby optimizing learning progress.

[0120] The curriculum suggestion unit can analyze the user's past learning data and dynamically generate an optimal curriculum. For example, it analyzes the user's past learning data and dynamically generates an optimal curriculum based on it. For example, it suggests what to study next, taking into account what has been learned in the past and the level of understanding. The generation AI also analyzes the user's past learning data and generates a curriculum that meets individual needs. For example, it adjusts the curriculum so that the user can focus on areas in which they are weak. It also analyzes the user's learning history and dynamically generates an optimal curriculum. For example, it suggests an effective learning plan based on past test results and learning progress. In this way, the user's past learning data is analyzed and an optimal curriculum is dynamically generated.

[0121] The curriculum proposal unit reflects the latest industry trends and technical information, allowing it to always provide the latest curriculum. For example, when proposing a curriculum, it automatically collects the latest industry trends and technical information and reflects it in the curriculum. For example, it updates the learning content based on the latest technological trends and market needs. In addition, the generative AI analyzes the latest industry trends and technical information and proposes a curriculum based on that. For example, it provides a learning plan that incorporates new technologies and methodologies. It also proposes a curriculum that reflects the latest industry trends and technical information. For example, it regularly updates the curriculum so that users can always learn the latest information. This allows it to reflect the latest industry trends and technical information and always provide the latest content.

[0122] The curriculum suggestion unit can use the emotion estimation function to suggest a curriculum based on the user's interests and concerns, thereby increasing motivation to learn. For example, the emotion estimation function can be used to analyze the user's interests and concerns, and suggest a curriculum based on them. For example, a study plan can be created centered around topics that the user is interested in. The curriculum suggestion unit can also analyze the user's emotions and suggest a curriculum based on the user's interests and concerns. For example, a curriculum can be provided that includes content that the user can enjoy while studying. The emotion estimation function can also be used to suggest a curriculum that reflects the user's interests and concerns. For example, learning content can be provided that will help the user maintain their motivation. This allows for a curriculum based on the user's interests and concerns to be suggested, increasing motivation to learn.

[0123] The curriculum proposal unit can accommodate different educational levels and provide them to a wide range of users. For example, curriculum proposals can be adapted to different educational levels and provided to a wide range of users. For example, it can propose study plans suitable for high school students, university students, and working adults. In addition, the generation AI can propose curricula that correspond to different educational levels. For example, it can provide a curriculum that includes basic content for high school students and specialized content for working adults. In addition, it can propose curricula that correspond to different educational levels and make them available to a wide range of users. For example, it can dynamically generate curricula that correspond to the user's learning level. This allows it to accommodate different educational levels and provide them to a wide range of users.

[0124] The curriculum proposal unit can link with online courses and webinars to propose learning combined with actual lectures and seminars. For example, by linking a curriculum proposal with an online course or webinar, it proposes learning combined with actual lectures and seminars. For example, it incorporates the content of the online course into the curriculum. In addition, the generative AI collects information about online courses and webinars and proposes a curriculum based on that information. For example, it includes webinars that users can participate in in the curriculum. In addition, it proposes a curriculum linked with online courses and webinars to provide learning combined with actual lectures and seminars. For example, it proposes a curriculum that combines online and offline learning. This allows it to link with online courses and webinars and propose learning combined with actual lectures and seminars.

[0125] The curriculum suggestion unit can use the emotion estimation function to adjust the curriculum in real time according to the user's emotional state, thereby maximizing the effectiveness of learning. For example, the emotion estimation function is used to adjust the curriculum in real time according to the user's emotional state. For example, if the user is tired, a suggestion is made to reduce the learning content. The curriculum suggestion unit also analyzes the user's emotional state and adjusts the curriculum to maximize the effectiveness of learning. For example, if the user is losing motivation, interesting content is added. The emotion estimation function is also used to adjust the curriculum in real time according to the user's emotional state, thereby maximizing the effectiveness of learning. For example, if the user is feeling stressed, a relaxing activity is suggested. In this way, the curriculum suggestion unit adjusts the curriculum in real time according to the user's emotional state, thereby maximizing the effectiveness of learning.

[0126] The practice problem providing unit can analyze the user's learning progress and automatically generate practice problems of a difficulty level according to the level of understanding. For example, it analyzes the user's learning progress and automatically generates practice problems of a difficulty level according to the level of understanding. For example, it provides problems of an appropriate difficulty level for areas in which the user is weak. In addition, the generation AI analyzes the user's learning progress and generates practice problems according to individual needs. For example, it provides high-difficulty questions for areas in which the user is strong. In addition, it analyzes the user's learning history and automatically generates practice problems of a difficulty level according to the level of understanding. For example, it provides questions of an appropriate difficulty level based on past test results. In this way, the user's learning progress is analyzed and practice problems of a difficulty level according to the level of understanding are automatically generated.

[0127] The practice problem providing unit can analyze the results of practice problems and confirmation tests, identify weak points, and provide feedback to help the user focus on learning. For example, it can analyze the results of practice problems and confirmation tests, identify the user's weak points, and provide feedback to help the user focus on learning. For example, it can provide detailed explanations for questions the user got wrong. The generation AI also analyzes the results of practice problems and confirmation tests, and provides feedback tailored to individual needs. For example, it can provide additional study materials for areas the user is weak in. It can also identify the user's weak points based on the results of practice problems and confirmation tests, and provide feedback to help the user focus on learning. For example, it can provide supplementary explanations for concepts that the user does not understand. In this way, the results of practice problems and confirmation tests can be analyzed, and feedback can be provided to help the user focus on learning.

[0128] The practice problem providing unit can use the emotion estimation function to analyze the user's stress level and suggest a break at an appropriate time. For example, the emotion estimation function can be used to analyze the user's stress level and suggest a break at an appropriate time. For example, if the user is tired, a message urging the user to take a break can be displayed. The practice problem providing unit can also analyze the user's emotional state and suggest a break if the user's stress level is high. For example, if the user is losing concentration, a relaxing activity can be suggested. The emotion estimation function can also be used to analyze the user's stress level in real time and suggest a break at an appropriate time. For example, if the user is feeling stressed, the system can urge the user to take a short break. In this way, the practice problem providing unit can analyze the user's stress level and suggest a break at an appropriate time.

[0129] The practice question providing unit can provide practice questions and confirmation tests in a game format, allowing users to study while having fun. For example, practice questions and confirmation tests can be provided in a game format, allowing users to study while having fun. For example, quiz-style questions can be provided, allowing users to earn points for each correct answer. In addition, the generation AI can convert practice questions and confirmation tests into a game format, allowing users to study while having fun. For example, time attack-style questions can be provided, allowing users to study with a competitive spirit. In addition, practice questions and confirmation tests can be provided in a game format, allowing users to study while having fun. For example, a level-up system can be introduced, allowing users to study while feeling a sense of accomplishment. In this way, practice questions and confirmation tests can be provided in a game format, allowing users to study while having fun.

[0130] The practice problem providing unit can provide practice problems and confirmation tests in a competitive format with other users, thereby increasing motivation. For example, by providing practice problems and confirmation tests in a competitive format with other users, the user's motivation is increased. For example, a ranking system can be introduced so that users can compete with other learners. Furthermore, the generation AI converts practice problems and confirmation tests into a competitive format to increase user motivation. For example, battle-style problems can be provided so that users can compete with opponents. Furthermore, by providing practice problems and confirmation tests in a competitive format with other users, the user's motivation is increased. For example, a team competition can be introduced so that users can study cooperatively. In this way, practice problems and confirmation tests can be provided in a competitive format with other users, thereby increasing motivation.

[0131] The practice problem providing unit can use the emotion estimation function to adjust the difficulty of the practice problems and confirmation tests according to the user's emotional state. For example, the emotion estimation function is used to adjust the difficulty of the practice problems and confirmation tests according to the user's emotional state. For example, if the user is feeling stressed, questions with a lower level of difficulty are provided. The unit also analyzes the user's emotional state and adjusts the difficulty of the practice problems and confirmation tests in real time. For example, if the user is relaxed, questions with a higher level of difficulty are provided. The emotion estimation function is also used to adjust the difficulty of the practice problems and confirmation tests according to the user's emotional state. For example, if the user is losing motivation, easy questions are provided to help them regain their confidence. In this way, the difficulty of the practice problems and confirmation tests is adjusted according to the user's emotional state.

[0132] The learning support unit can analyze the user's learning history and propose an individual learning plan based on their past level of understanding. For example, it can analyze the user's learning history and propose an individual learning plan based on their past level of understanding. For example, it can adjust the plan so that the user can focus on learning areas in which they are weak. In addition, the generation AI analyzes the user's learning history and proposes a learning plan that meets individual needs. For example, it can provide a plan that includes advanced content for areas in which the user is strong. In addition, it can propose an individual learning plan based on the user's learning history and meets their past level of understanding. For example, it can create an effective learning plan based on past test results. In this way, it can analyze the user's learning history and propose an individual learning plan based on their past level of understanding.

[0133] The learning support unit can automatically provide related examples and case studies during learning support to promote practical understanding. For example, during learning support, related examples and case studies can be automatically provided to promote practical understanding for the user. For example, examples related to a specific qualification exam can be presented. In addition, the generative AI automatically provides related case studies during learning support. For example, actual cases related to the content the user is learning can be introduced. In addition, during learning support, examples and case studies can be automatically provided to deepen the user's understanding. For example, specific cases related to the learning content can be presented. In this way, during learning support, related examples and case studies can be automatically provided to promote practical understanding.

[0134] The learning support unit can use the emotion estimation function to provide a motivational message to maintain the user's motivation to learn. For example, the emotion estimation function is used to provide a motivational message to maintain the user's motivation to learn. For example, if the user is tired, an encouraging message is displayed. The learning support unit also analyzes the user's emotions and provides a message to maintain the user's motivation to learn. For example, a message is displayed informing the user that the user is approaching a goal. The emotion estimation function is also used to provide a message to increase the user's motivation to learn. For example, a message that makes the user feel like they are making progress is displayed. In this way, a motivational message is provided to maintain the user's motivation to learn.

[0135] The learning support unit can adapt learning support to different learning fields and provide it to a wide range of users. For example, learning support can be adapted to different learning fields and provided to a wide range of users. For example, support can be provided for language learning or programming learning. In addition, the generation AI provides learning support adapted to different learning fields. For example, support can be provided according to the field that the user wants to learn. In addition, learning support can be adapted to a wide range of learning fields, allowing users to proceed with learning that suits their interests. For example, support can be provided for users who are aiming to acquire specific skills or advance their careers. In this way, learning support can be adapted to different learning fields and provided to a wide range of users.

[0136] The learning support unit can link the learning support with an online community to deepen learning through interactions with other users. For example, the learning support can be linked with an online community to enable users to interact with other learners. For example, discussion forums and group chats can be provided. The generative AI can also link with the online community to enable users to collaborate with other learners to advance their learning. For example, it can suggest joint projects and group discussions. The learning support can also be linked with an online community to deepen learning through interactions with other learners. For example, it can provide opportunities to share learning results and receive feedback. In this way, the learning support can be linked with an online community to deepen learning through interactions with other users.

[0137] The learning support unit can use the emotion estimation function to adjust the content of learning support in real time according to the user's emotional state. For example, the emotion estimation function is used to adjust the content of learning support in real time according to the user's emotional state. For example, if the user is feeling stressed, a relaxing activity is suggested. The learning support unit also analyzes the user's emotional state and adjusts the content of learning support in real time. For example, if the user is losing motivation, the learning plan is revised along with an encouraging message. The emotion estimation function is also used to adjust the content of learning support in real time according to the user's emotional state. For example, if the user is tired, a suggestion is made to slow down the pace of learning. In this way, the emotion estimation function is used to adjust the content of learning support in real time according to the user's emotional state.

[0138] The processing flow of the second embodiment will be briefly explained below.

[0139] Step 1: The question-and-answer unit generates answers to user questions. For example, if a user asks how to study for a qualification exam, the generating AI provides information about the exam and suggests specific study methods. Step 2: The step suggestion unit proposes steps to achieve the goal based on the answers generated by the question answering unit. For example, the generation AI proposes a schedule and study plan leading up to the exam date. Step 3: The curriculum suggestion unit proposes an optimal curriculum based on the steps proposed by the step suggestion unit. For example, the generative AI proposes learning content and materials based on the exam scope. Step 4: The practice problem providing unit provides practice problems and confirmation tests based on the curriculum proposed by the curriculum suggestion unit. For example, the generation AI generates and provides practice problems and confirmation tests according to the user's learning progress.

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0142] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0143] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0144] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0145] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0146] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0147] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0150] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0159] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0165] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0166] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0167] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0168] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0170] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0172] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0173] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0176] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0177] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0179] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0180] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0181] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0182] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0183] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0184] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0185] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0186] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0187] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0189] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0190] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0191] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0192] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0193] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0194] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0195] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0196] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0197] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0198] 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.

[0199] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0200] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0201] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0202] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0203] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0204] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0205] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0206] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0207] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a question answering unit that generates answers to user questions; a step suggestion unit that suggests steps to achieve a goal based on the answers generated by the question answering unit; a curriculum suggestion unit that proposes an optimal curriculum based on the steps proposed by the step suggestion unit; a practice question providing unit that provides practice questions and confirmation tests based on the curriculum proposed by the curriculum suggesting unit. A system characterized by:

2. The question and answer unit Generate optimal answers based on the user's past learning history and current level of understanding 2. The system of claim 1.

3. The question and answer unit Automatically inserting relevant videos and illustrations when generating the answer to the question.

2. The system of claim 1.

4. The question and answer unit Analyzing the user's emotions when asking a question and generating an answer to reduce stress and anxiety 2. The system of claim 1.

5. The question and answer unit Support different languages ​​and make it available to international users 2. The system of claim 1.

6. The question and answer unit It also supports voice input, allowing users to enter questions by voice.

2. The system of claim 1.

Images