system

Abstract

The system according to this embodiment aims to enable students to participate in actual AI projects and acquire practical skills. [Solution] The system according to the embodiment comprises a verification unit, a development unit, and a testing unit. The verification unit verifies hypotheses in which students participate in an AI project. The development unit develops an AI model based on the hypotheses verified by the verification unit. The testing unit tests the AI ​​model developed by the development unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that students have limited opportunities to participate in actual AI projects and acquire practical skills.

[0005] The system according to the embodiment aims to enable students to participate in actual AI projects and acquire practical skills.

Means for Solving the Problems

[0006] The system according to the embodiment includes a verification unit, a development unit, and a test unit. The verification unit allows students to participate in an AI project and verify a hypothesis. The development unit develops an AI model based on the hypothesis verified by the verification unit. The test unit tests the AI model developed by the development unit. [Effects of the Invention]

[0007] The system according to this embodiment allows students to participate in actual AI projects and acquire practical skills. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​project participation system according to an embodiment of the present invention is a system in which students participate in an actual AI project and conduct hypothesis testing, model development, and testing together with engineers. This AI project participation system allows students to practically learn the AI ​​development process by participating in an AI project, formulating hypotheses, testing them, developing AI models, and conducting tests. Features of this system include a real-time feedback and evaluation system, integration of AI project management tools, and a function for customizing individual learning plans. This allows students to check their progress in real time and receive necessary feedback. Furthermore, the project management tool enables efficient management of the project's progress. In addition, the individual learning plan customization function allows students to create learning plans tailored to their learning style and progress. For example, students participate in an AI project, formulate hypotheses, test them, develop AI models, and conduct tests. This allows students to practically learn the AI ​​development process. For example, the real-time feedback and evaluation system allows students to check their progress in real time and receive necessary feedback. Furthermore, the project management tool enables efficient management of the project's progress. Furthermore, the customizable individual learning plan feature allows students to create learning plans tailored to their own learning style and progress. This is expected to improve student employment rates, with 80% of participating students securing jobs in AI-related fields. Additionally, the success rate of student-participated projects is projected to increase by 50%, and the technical evaluation of participating students is expected to improve by an average of 30%. This system is highly beneficial for students who want to learn AI technology, those seeking practical project experience, and those aiming for a career in the AI ​​field. By participating in real projects, students can gain experience at the forefront of AI development and cultivate creative problem-solving skills. Thus, the AI ​​project participation system enhances students' practical skills and fosters a real-world understanding of AI development.

[0029] The AI ​​project participation system according to the embodiment comprises a verification unit, a development unit, and a testing unit. The verification unit allows students to participate in an AI project and verify hypotheses. The verification unit can, for example, verify hypotheses formulated by students through experiments and data analysis. The verification unit can, for example, verify hypotheses using experimental methods. The verification unit can, for example, verify hypotheses using data analysis methods. The development unit develops an AI model based on the hypotheses verified by the verification unit. The development unit can, for example, develop an AI model using machine learning algorithms. The development unit can, for example, develop an AI model using deep learning technology. The development unit can, for example, develop an AI model using natural language processing technology. The testing unit tests the AI ​​model developed by the development unit. The testing unit can, for example, create test cases to evaluate the performance of the AI ​​model. The testing unit can, for example, use test datasets to evaluate the accuracy of the AI ​​model. The testing unit can, for example, apply test methods to evaluate the generalization performance of the AI ​​model. As a result, the AI ​​project participation system according to this embodiment allows students to participate in AI projects and acquire practical skills by conducting hypothesis testing, model development, and testing.

[0030] The Verification Department allows students to participate in AI projects and test hypotheses. Students first formulate hypotheses based on their interests and research topics. These hypotheses relate to problems they want to solve or phenomena they want to predict using AI technology. The Verification Department provides an environment for verifying student hypotheses through experiments and data analysis. For example, when using experimental methods to verify a hypothesis, students plan the experiment, collect the necessary data, and conduct the experiment. The experimental results are analyzed using statistical methods to evaluate the validity of the hypothesis. When using data analysis methods to verify a hypothesis, students utilize existing datasets to perform data preprocessing, feature selection, model construction, and evaluation. Data analysis techniques such as regression analysis, clustering, and classification are used. The Verification Department provides tools and resources to support these processes, enabling students to efficiently verify hypotheses. For example, data analysis software, cloud computing resources, and database access are provided. Furthermore, the Verification Department provides expert advice and support for challenges and questions students face during the hypothesis testing process. This allows students to acquire practical skills and deepen their understanding of AI technology.

[0031] The Development Department develops AI models based on hypotheses validated by the Verification Department. Students design and implement specific AI models based on the results obtained by the Verification Department. The Development Department develops models using a variety of AI technologies, including machine learning algorithms, deep learning techniques, and natural language processing techniques. For example, when using machine learning algorithms, students train the model using a dataset and optimize the parameters. When using deep learning techniques, students design the architecture of the neural network and train the model using training data. When using natural language processing techniques, students preprocess text data, extract features, and train the model to build a model that can handle language understanding and generation tasks. The Development Department provides development environments and tools to support these processes. For example, an integrated development environment (IDE), version control systems, and cloud-based training resources are provided. The Development Department also provides expert advice and support for technical challenges that students face during the model development process. This allows students to practically learn advanced AI technologies and acquire the ability to apply them in real projects.

[0032] The Test Department tests the AI ​​models developed by the Development Department. Students create various test cases to evaluate the performance of their developed models and use test datasets to assess the model's accuracy and generalization performance. The Test Department provides the necessary environment and tools for evaluating the performance of AI models. For example, evaluation metrics are used to compare the output the model should predict with the actual output when creating test cases. Evaluation metrics such as accuracy, recall, and F1 score are used to quantitatively evaluate the model's predictive performance. Test datasets use data different from the training dataset and are used to evaluate the model's generalization performance. This verifies how accurately the model can predict on new data. Furthermore, the Test Department also performs anomaly detection and edge case evaluation. For example, it identifies cases where the model fails to predict or where the prediction results are unstable, and identifies areas for improvement in the model. The Test Department provides testing environments and tools to support these processes, enabling students to efficiently evaluate the performance of their models. For example, test automation tools, cloud-based test resources, and data visualization tools are provided. The Test Department also provides expert advice and support for any challenges or questions students may encounter during the testing process. This allows students to acquire the skills necessary to evaluate the performance of AI models and gain practical knowledge to improve the quality of the models.

[0033] The Feedback Department provides real-time feedback. For example, when a student is working on an AI project, the Feedback Department can evaluate their progress in real time and provide feedback. For example, the Feedback Department can immediately evaluate the work performed by a student and point out areas for improvement. For example, the Feedback Department can evaluate the deliverables submitted by a student in real time and provide feedback. This allows students to receive feedback in real time. Some or all of the above processes in the Feedback Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Feedback Department can input the student's work into a generative AI, which can then generate evaluations and feedback.

[0034] The Integration Department integrates project management tools. For example, the Integration Department can provide task management functions for managing project progress. For example, the Integration Department can provide Gantt charts for visualizing project progress. For example, the Integration Department can provide resource management functions for managing project resources. This allows for efficient management of project progress. Some or all of the above processes in the Integration Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Integration Department can input project progress data into a generative AI, which can analyze the progress and propose the optimal management method.

[0035] The customization unit customizes individual learning plans. For example, the customization unit can create learning plans tailored to a student's learning style and progress. For example, the customization unit can propose an optimal learning plan based on a student's learning goals. For example, the customization unit can evaluate a student's progress in real time and adjust the learning plan. This allows students to create learning plans that suit their own learning style and progress. Some or all of the above processes in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input student learning data into a generative AI, which can then generate an optimal learning plan.

[0036] The verification unit verifies hypotheses. For example, the verification unit can verify hypotheses formulated by students through experiments and data analysis. For example, the verification unit can verify hypotheses using experimental methods. For example, the verification unit can verify hypotheses using data analysis methods. In this way, it supports the progress of the AI ​​project by verifying hypotheses. Some or all of the above processes in the verification unit may be performed using, for example, generative AI, or without generative AI. For example, the verification unit can input hypotheses formulated by students into a generative AI, and the generative AI can generate the results of hypothesis verification.

[0037] The development department develops AI models. The development department can develop AI models using, for example, machine learning algorithms. The development department can develop AI models using, for example, deep learning technology. The development department can develop AI models using, for example, natural language processing technology. By developing AI models in this way, the project deliverables are created. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input AI model development data into a generative AI, and the generative AI can generate an optimal AI model.

[0038] The testing unit tests the AI ​​model. The testing unit can, for example, create test cases to evaluate the performance of the AI ​​model. The testing unit can, for example, use a test dataset to evaluate the accuracy of the AI ​​model. The testing unit can, for example, apply a test method to evaluate the generalization performance of the AI ​​model. By testing the AI ​​model, the performance of the model is evaluated. Some or all of the above processes in the testing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the testing unit can input test data for the AI ​​model into a generative AI, and the generative AI can generate test results.

[0039] The verification unit selects the optimal verification method by referring to past verification data. For example, the verification unit can propose the optimal verification method for a similar project based on past successful verification data. For example, the verification unit can analyze past failed verification data and propose improvements to avoid the same mistakes. For example, the verification unit can select a verification method appropriate to the students' level of expertise by referring to past verification data. In this way, the optimal verification method can be selected by utilizing past data. Some or all of the above processes in the verification unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the verification unit can input past verification data into a generative AI, and the generative AI can propose the optimal verification method.

[0040] The verification unit customizes the verification method according to the student's level of expertise during verification. For example, the verification unit can provide beginner students with basic verification methods and add step-by-step guides. For example, the verification unit can provide intermediate students with more complex verification methods and hints to encourage independent learning. For example, the verification unit can provide advanced students with the latest verification methods and resources to promote self-learning. This enhances learning effectiveness by providing verification methods tailored to the student's level of expertise. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the verification unit can input the student's level of expertise into a generative AI, which can then suggest the optimal verification method.

[0041] The verification unit prioritizes testing relevant hypotheses during verification, taking into account the student's learning history. For example, the verification unit can prioritize testing hypotheses related to what the student has learned in the past. For example, the verification unit can analyze the student's learning history and prioritize testing hypotheses in areas where the student has a low level of understanding. For example, the verification unit can prioritize testing hypotheses that the student might be interested in, based on their learning history. In this way, relevant hypotheses can be prioritized by considering the student's learning history. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the verification unit can input the student's learning history data into a generative AI, which can then propose the most suitable hypothesis.

[0042] The verification unit optimizes the verification method by referring to the student's project participation history during verification. For example, the verification unit can refer to data from projects the student has participated in in the past and propose the optimal verification method. For example, the verification unit can analyze the student's project participation history and reuse successful methods. For example, the verification unit can suggest improvements to avoid failed methods based on the student's project participation history. In this way, the optimal verification method can be selected by referring to the student's project participation history. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the verification unit can input the student's project participation history data into a generative AI, and the generative AI can propose the optimal verification method.

[0043] The development department selects the optimal development method by referring to past development data. For example, the development department can propose the optimal development method for a similar project based on past successful development data. For example, the development department can analyze past failed development data and propose improvements to avoid the same mistakes. For example, the development department can select a development method appropriate to the students' level of expertise by referring to past development data. In this way, the optimal development method can be selected by utilizing past data. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input past development data into a generative AI, and the generative AI can propose the optimal development method.

[0044] The development department customizes development methods according to the students' level of expertise during development. For example, the development department can provide beginner students with basic development methods and add step-by-step guides. For example, the development department can provide intermediate students with more complex development methods and hints to encourage independent learning. For example, the development department can provide advanced students with the latest development methods and resources to promote self-learning. This enhances learning effectiveness by providing development methods tailored to the students' level of expertise. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not. For example, the development department can input the students' level of expertise into a generative AI, which can then suggest the optimal development method.

[0045] The development department prioritizes the application of relevant development methods during development, taking into account the students' learning history. For example, the development department can prioritize development methods related to what the students have learned in the past. For example, the development department can analyze the students' learning history and prioritize the application of development methods in areas where the students have a low level of understanding. For example, the development department can prioritize the application of development methods that the students are likely to be interested in, based on their learning history. In this way, relevant development methods can be prioritized by considering the students' learning history. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input student learning history data into a generative AI, which can then propose the optimal development method.

[0046] The development department optimizes development methods by referring to students' project participation history during development. For example, the development department can refer to data from projects students have previously participated in and propose the optimal development method. For example, the development department can analyze students' project participation history and reuse successful methods. For example, the development department can suggest improvements to avoid failed methods based on students' project participation history. In this way, the optimal development method can be selected by referring to students' project participation history. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input student project participation history data into generative AI, and the generative AI can propose the optimal development method.

[0047] The testing department selects the optimal testing method by referring to past test data. For example, the testing department can propose the most suitable testing method for a similar project based on past successful test data. For example, the testing department can analyze past failed test data and propose improvements to avoid the same mistakes. For example, the testing department can select a testing method appropriate to the students' level of expertise by referring to past test data. In this way, the optimal testing method can be selected by utilizing past data. Some or all of the above processes in the testing department may be performed using, for example, generative AI, or not using generative AI. For example, the testing department can input past test data into a generative AI, and the generative AI can propose the optimal testing method.

[0048] The testing department customizes the testing methodology according to the students' level of expertise during testing. For example, it can provide beginner students with basic testing methodology and add step-by-step guidance. For intermediate students, it can provide more complex testing methodology and hints to encourage independent learning. For advanced students, it can provide the latest testing methodology and resources to facilitate self-study. This enhances learning effectiveness by providing testing methodology tailored to the students' level of expertise. Some or all of the above processes in the testing department may be performed using, for example, generative AI, or not. For example, the testing department can input the students' level of expertise into a generative AI, which can then suggest the most suitable testing methodology.

[0049] The testing unit prioritizes the application of relevant testing methods during testing, taking into account the student's learning history. For example, the testing unit can prioritize the application of testing methods related to content the student has previously learned. For example, the testing unit can analyze the student's learning history and prioritize the application of testing methods in areas where the student's understanding is weak. For example, the testing unit can prioritize the application of testing methods that the student is likely to be interested in, based on the student's learning history. In this way, relevant testing methods can be prioritized by considering the student's learning history. Some or all of the above processing in the testing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the testing unit can input student learning history data into a generative AI, which can then suggest the optimal testing method.

[0050] The testing unit optimizes testing methods by referring to students' project participation history during testing. For example, the testing unit can refer to data from projects students have previously participated in and propose the optimal testing method. For example, the testing unit can analyze students' project participation history and reuse successful methods. For example, the testing unit can suggest improvements to avoid failed methods based on students' project participation history. This allows for the selection of the optimal testing method by referring to students' project participation history. Some or all of the above processes in the testing unit may be performed using, for example, generative AI, or without generative AI. For example, the testing unit can input student project participation history data into a generative AI, which can then propose the optimal testing method.

[0051] The feedback unit provides optimal feedback by referring to the student's past performance data during the feedback process. For example, the feedback unit can analyze the student's past performance data and provide feedback that allows the student to feel a sense of growth. For example, the feedback unit can identify the student's past weaknesses and provide specific advice for improvement. For example, the feedback unit can provide motivational feedback based on the student's past successes. In this way, optimal feedback can be provided by referring to the student's past performance data. Some or all of the above processes in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input the student's past performance data into a generative AI, and the generative AI can suggest optimal feedback.

[0052] The feedback unit, when providing feedback, prioritizes relevant feedback by considering the student's learning history. For example, the feedback unit can analyze the student's learning history and provide feedback related to what they have learned in the past. For example, the feedback unit can prioritize providing feedback on areas where the student's understanding is weak, based on their learning history. For example, the feedback unit can refer to the student's learning history and provide feedback on topics that might interest them. This allows the feedback unit to prioritize providing relevant feedback by considering the student's learning history. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input student learning history data into a generative AI, which can then suggest the most appropriate feedback.

[0053] The integration unit selects the optimal integration method by referring to the student's past project data during integration. The integration unit can, for example, analyze the student's past project data and reuse successful integration methods. The integration unit can, for example, suggest improvements to avoid failed integration methods based on the student's past project data. The integration unit can, for example, refer to the student's past project data and select the optimal integration method. This allows the optimal integration method to be selected by referring to the student's past project data. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the student's past project data into a generative AI, and the generative AI can suggest the optimal integration method.

[0054] The integration unit, during integration, prioritizes the application of relevant integration methods, taking into account the student's learning history. For example, the integration unit can analyze the student's learning history and prioritize the application of integration methods related to what the student has learned in the past. For example, based on the student's learning history, the integration unit can prioritize the application of integration methods in areas where the student has a low level of understanding. For example, the integration unit can refer to the student's learning history and prioritize the application of integration methods that the student might be interested in. In this way, relevant integration methods can be prioritized by considering the student's learning history. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input student learning history data into a generative AI, which can then propose the optimal integration method.

[0055] The customization unit provides an optimal learning plan by referring to the student's past learning data during the customization process. For example, the customization unit can analyze the student's past learning data and provide a learning plan that allows the student to feel a sense of growth. For example, the customization unit can identify the student's past weaknesses and provide a specific learning plan for improvement. For example, the customization unit can provide a learning plan that increases motivation based on the student's past successes. In this way, the optimal learning plan can be provided by referring to the student's past learning data. Some or all of the above processing in the customization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the customization unit can input the student's past learning data into a generative AI, and the generative AI can propose an optimal learning plan.

[0056] The customization unit prioritizes providing relevant learning plans by considering the student's learning history during the customization process. For example, the customization unit can analyze the student's learning history and prioritize providing learning plans related to what they have learned in the past. For example, based on the student's learning history, the customization unit can prioritize providing learning plans in areas where the student has a low level of understanding. For example, the customization unit can refer to the student's learning history and prioritize providing learning plans that are likely to interest them. In this way, relevant learning plans can be prioritized by considering the student's learning history. Some or all of the above processing in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input the student's learning history data into a generative AI, which can then propose an optimal learning plan.

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

[0058] The verification unit can select the optimal verification method by referring to past verification data. For example, it can propose the most suitable verification method for similar projects based on past successful verification data. It can also analyze past failed verification data and propose improvements to avoid the same mistakes. It can select verification methods that match the students' level of expertise. In this way, the optimal verification method can be selected by utilizing past data.

[0059] The development department can select the optimal development method by referring to past development data. For example, based on past successful development data, they can propose the most suitable development method for similar projects. They can also analyze past failed development data and propose improvements to avoid the same mistakes. They can select development methods that match the students' level of expertise. In this way, the optimal development method can be selected by utilizing past data.

[0060] The testing department can select the optimal testing method by referring to past test data. For example, based on past successful test data, they can propose the most suitable testing method for similar projects. They can analyze past failed test data and propose improvements to avoid the same mistakes. They can select testing methods appropriate to the students' level of expertise. In this way, the optimal testing method can be selected by utilizing past data.

[0061] The feedback department can provide optimal feedback by referring to students' past performance data. For example, it can analyze students' past performance data and provide feedback that allows them to feel their growth. It can identify students' past weaknesses and provide specific advice for improvement. It can provide motivational feedback based on students' past successes. In this way, by referring to students' past performance data, it can provide optimal feedback.

[0062] The customization function can provide an optimal learning plan by referencing the student's past learning data during the customization process. For example, it can analyze the student's past learning data and provide a learning plan that allows them to feel a sense of growth. It can identify the student's past weaknesses and provide a specific learning plan for improvement. It can provide a learning plan that increases motivation based on the student's past successes. In this way, by referring to the student's past learning data, the optimal learning plan can be provided.

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

[0064] Step 1: The verification section involves students participating in AI projects and testing hypotheses. For example, students can verify their hypotheses through experiments and data analysis. They can use experimental and data analysis techniques to test their hypotheses. Step 2: The development department develops an AI model based on the hypotheses verified by the verification department. For example, they can develop an AI model using machine learning algorithms, deep learning techniques, and natural language processing techniques. Step 3: The testing department tests the AI ​​model developed by the development department. For example, they can create test cases to evaluate the performance of the AI ​​model, use test datasets to evaluate accuracy, and apply test methods to evaluate generalization performance.

[0065] (Example of form 2) The AI ​​project participation system according to an embodiment of the present invention is a system in which students participate in an actual AI project and conduct hypothesis testing, model development, and testing together with engineers. This AI project participation system allows students to practically learn the AI ​​development process by participating in an AI project, formulating hypotheses, testing them, developing AI models, and conducting tests. Features of this system include a real-time feedback and evaluation system, integration of AI project management tools, and a function for customizing individual learning plans. This allows students to check their progress in real time and receive necessary feedback. Furthermore, the project management tool enables efficient management of the project's progress. In addition, the individual learning plan customization function allows students to create learning plans tailored to their learning style and progress. For example, students participate in an AI project, formulate hypotheses, test them, develop AI models, and conduct tests. This allows students to practically learn the AI ​​development process. For example, the real-time feedback and evaluation system allows students to check their progress in real time and receive necessary feedback. Furthermore, the project management tool enables efficient management of the project's progress. Furthermore, the customizable individual learning plan feature allows students to create learning plans tailored to their own learning style and progress. This is expected to improve student employment rates, with 80% of participating students securing jobs in AI-related fields. Additionally, the success rate of student-participated projects is projected to increase by 50%, and the technical evaluation of participating students is expected to improve by an average of 30%. This system is highly beneficial for students who want to learn AI technology, those seeking practical project experience, and those aiming for a career in the AI ​​field. By participating in real projects, students can gain experience at the forefront of AI development and cultivate creative problem-solving skills. Thus, the AI ​​project participation system enhances students' practical skills and fosters a real-world understanding of AI development.

[0066] The AI ​​project participation system according to the embodiment comprises a verification unit, a development unit, and a testing unit. The verification unit allows students to participate in an AI project and verify hypotheses. The verification unit can, for example, verify hypotheses formulated by students through experiments and data analysis. The verification unit can, for example, verify hypotheses using experimental methods. The verification unit can, for example, verify hypotheses using data analysis methods. The development unit develops an AI model based on the hypotheses verified by the verification unit. The development unit can, for example, develop an AI model using machine learning algorithms. The development unit can, for example, develop an AI model using deep learning technology. The development unit can, for example, develop an AI model using natural language processing technology. The testing unit tests the AI ​​model developed by the development unit. The testing unit can, for example, create test cases to evaluate the performance of the AI ​​model. The testing unit can, for example, use test datasets to evaluate the accuracy of the AI ​​model. The testing unit can, for example, apply test methods to evaluate the generalization performance of the AI ​​model. As a result, the AI ​​project participation system according to this embodiment allows students to participate in AI projects and acquire practical skills by conducting hypothesis testing, model development, and testing.

[0067] The Verification Department allows students to participate in AI projects and test hypotheses. Students first formulate hypotheses based on their interests and research topics. These hypotheses relate to problems they want to solve or phenomena they want to predict using AI technology. The Verification Department provides an environment for verifying student hypotheses through experiments and data analysis. For example, when using experimental methods to verify a hypothesis, students plan the experiment, collect the necessary data, and conduct the experiment. The experimental results are analyzed using statistical methods to evaluate the validity of the hypothesis. When using data analysis methods to verify a hypothesis, students utilize existing datasets to perform data preprocessing, feature selection, model construction, and evaluation. Data analysis techniques such as regression analysis, clustering, and classification are used. The Verification Department provides tools and resources to support these processes, enabling students to efficiently verify hypotheses. For example, data analysis software, cloud computing resources, and database access are provided. Furthermore, the Verification Department provides expert advice and support for challenges and questions students face during the hypothesis testing process. This allows students to acquire practical skills and deepen their understanding of AI technology.

[0068] The Development Department develops AI models based on hypotheses validated by the Verification Department. Students design and implement specific AI models based on the results obtained by the Verification Department. The Development Department develops models using a variety of AI technologies, including machine learning algorithms, deep learning techniques, and natural language processing techniques. For example, when using machine learning algorithms, students train the model using a dataset and optimize the parameters. When using deep learning techniques, students design the architecture of the neural network and train the model using training data. When using natural language processing techniques, students preprocess text data, extract features, and train the model to build a model that can handle language understanding and generation tasks. The Development Department provides development environments and tools to support these processes. For example, an integrated development environment (IDE), version control systems, and cloud-based training resources are provided. The Development Department also provides expert advice and support for technical challenges that students face during the model development process. This allows students to practically learn advanced AI technologies and acquire the ability to apply them in real projects.

[0069] The Test Department tests the AI ​​models developed by the Development Department. Students create various test cases to evaluate the performance of their developed models and use test datasets to assess the model's accuracy and generalization performance. The Test Department provides the necessary environment and tools for evaluating the performance of AI models. For example, evaluation metrics are used to compare the output the model should predict with the actual output when creating test cases. Evaluation metrics such as accuracy, recall, and F1 score are used to quantitatively evaluate the model's predictive performance. Test datasets use data different from the training dataset and are used to evaluate the model's generalization performance. This verifies how accurately the model can predict on new data. Furthermore, the Test Department also performs anomaly detection and edge case evaluation. For example, it identifies cases where the model fails to predict or where the prediction results are unstable, and identifies areas for improvement in the model. The Test Department provides testing environments and tools to support these processes, enabling students to efficiently evaluate the performance of their models. For example, test automation tools, cloud-based test resources, and data visualization tools are provided. The Test Department also provides expert advice and support for any challenges or questions students may encounter during the testing process. This allows students to acquire the skills necessary to evaluate the performance of AI models and gain practical knowledge to improve the quality of the models.

[0070] The Feedback Department provides real-time feedback. For example, when a student is working on an AI project, the Feedback Department can evaluate their progress in real time and provide feedback. For example, the Feedback Department can immediately evaluate the work performed by a student and point out areas for improvement. For example, the Feedback Department can evaluate the deliverables submitted by a student in real time and provide feedback. This allows students to receive feedback in real time. Some or all of the above processes in the Feedback Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Feedback Department can input the student's work into a generative AI, which can then generate evaluations and feedback.

[0071] The Integration Department integrates project management tools. For example, the Integration Department can provide task management functions for managing project progress. For example, the Integration Department can provide Gantt charts for visualizing project progress. For example, the Integration Department can provide resource management functions for managing project resources. This allows for efficient management of project progress. Some or all of the above processes in the Integration Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Integration Department can input project progress data into a generative AI, which can analyze the progress and propose the optimal management method.

[0072] The customization unit customizes individual learning plans. For example, the customization unit can create learning plans tailored to a student's learning style and progress. For example, the customization unit can propose an optimal learning plan based on a student's learning goals. For example, the customization unit can evaluate a student's progress in real time and adjust the learning plan. This allows students to create learning plans that suit their own learning style and progress. Some or all of the above processes in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input student learning data into a generative AI, which can then generate an optimal learning plan.

[0073] The verification unit verifies hypotheses. For example, the verification unit can verify hypotheses formulated by students through experiments and data analysis. For example, the verification unit can verify hypotheses using experimental methods. For example, the verification unit can verify hypotheses using data analysis methods. In this way, it supports the progress of the AI ​​project by verifying hypotheses. Some or all of the above processes in the verification unit may be performed using, for example, generative AI, or without generative AI. For example, the verification unit can input hypotheses formulated by students into a generative AI, and the generative AI can generate the results of hypothesis verification.

[0074] The development department develops AI models. The development department can develop AI models using, for example, machine learning algorithms. The development department can develop AI models using, for example, deep learning technology. The development department can develop AI models using, for example, natural language processing technology. By developing AI models in this way, the project deliverables are created. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input AI model development data into a generative AI, and the generative AI can generate an optimal AI model.

[0075] The testing unit tests the AI ​​model. The testing unit can, for example, create test cases to evaluate the performance of the AI ​​model. The testing unit can, for example, use a test dataset to evaluate the accuracy of the AI ​​model. The testing unit can, for example, apply a test method to evaluate the generalization performance of the AI ​​model. By testing the AI ​​model, the performance of the model is evaluated. Some or all of the above processes in the testing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the testing unit can input test data for the AI ​​model into a generative AI, and the generative AI can generate test results.

[0076] The verification unit estimates the student's emotions and adjusts the pace of hypothesis testing based on the estimated emotions. For example, if the student is stressed, the verification unit can slow down the pace of hypothesis testing and provide additional materials to deepen understanding. For example, if the student is relaxed, the verification unit can speed up the pace of hypothesis testing to move to the next step sooner. For example, if the student is excited, the verification unit can adjust the pace of hypothesis testing and suggest a break to maintain concentration. This enhances learning effectiveness by adjusting the pace of hypothesis testing according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the verification unit may be performed using a generative AI, for example, or without a generative AI. For example, the verification unit can input student emotion data into a generative AI, and the generative AI can generate emotion estimation results.

[0077] The verification unit selects the optimal verification method by referring to past verification data. For example, the verification unit can propose the optimal verification method for a similar project based on past successful verification data. For example, the verification unit can analyze past failed verification data and propose improvements to avoid the same mistakes. For example, the verification unit can select a verification method appropriate to the students' level of expertise by referring to past verification data. In this way, the optimal verification method can be selected by utilizing past data. Some or all of the above processes in the verification unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the verification unit can input past verification data into a generative AI, and the generative AI can propose the optimal verification method.

[0078] The verification unit customizes the verification method according to the student's level of expertise during verification. For example, the verification unit can provide beginner students with basic verification methods and add step-by-step guides. For example, the verification unit can provide intermediate students with more complex verification methods and hints to encourage independent learning. For example, the verification unit can provide advanced students with the latest verification methods and resources to promote self-learning. This enhances learning effectiveness by providing verification methods tailored to the student's level of expertise. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the verification unit can input the student's level of expertise into a generative AI, which can then suggest the optimal verification method.

[0079] The verification unit estimates the student's emotions and adjusts the presentation method of the verification results based on the estimated emotions. For example, if the student is stressed, the verification unit can present simple and visually easy-to-understand verification results. For example, if the student is relaxed, the verification unit can present verification results including detailed data and graphs. For example, if the student is excited, the verification unit can present the verification results in an interactive format to maintain interest. This deepens understanding by adjusting the presentation method of the verification results according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the verification unit may be performed using a generative AI, or not using a generative AI. For example, the verification unit can input student emotion data into a generative AI, and the generative AI can generate emotion estimation results.

[0080] The verification unit prioritizes testing relevant hypotheses during verification, taking into account the student's learning history. For example, the verification unit can prioritize testing hypotheses related to what the student has learned in the past. For example, the verification unit can analyze the student's learning history and prioritize testing hypotheses in areas where the student has a low level of understanding. For example, the verification unit can prioritize testing hypotheses that the student might be interested in, based on their learning history. In this way, relevant hypotheses can be prioritized by considering the student's learning history. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the verification unit can input the student's learning history data into a generative AI, which can then propose the most suitable hypothesis.

[0081] The verification unit optimizes the verification method by referring to the student's project participation history during verification. For example, the verification unit can refer to data from projects the student has participated in in the past and propose the optimal verification method. For example, the verification unit can analyze the student's project participation history and reuse successful methods. For example, the verification unit can suggest improvements to avoid failed methods based on the student's project participation history. In this way, the optimal verification method can be selected by referring to the student's project participation history. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the verification unit can input the student's project participation history data into a generative AI, and the generative AI can propose the optimal verification method.

[0082] The development department estimates students' emotions and adjusts the pace of the development process based on the estimated emotions. For example, if a student is stressed, the development department can slow down the pace of the development process and provide additional materials to deepen understanding. For example, if a student is relaxed, the development department can speed up the pace of the development process to move to the next step sooner. For example, if a student is excited, the development department can adjust the pace of the development process and suggest a break to maintain concentration. This enhances learning effectiveness by adjusting the pace of the development process according to students' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the development department may be performed using a generative AI, or not. For example, the development department can input student emotion data into a generative AI, and the generative AI can generate emotion estimation results.

[0083] The development department selects the optimal development method by referring to past development data. For example, the development department can propose the optimal development method for a similar project based on past successful development data. For example, the development department can analyze past failed development data and propose improvements to avoid the same mistakes. For example, the development department can select a development method appropriate to the students' level of expertise by referring to past development data. In this way, the optimal development method can be selected by utilizing past data. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input past development data into a generative AI, and the generative AI can propose the optimal development method.

[0084] The development department customizes development methods according to the students' level of expertise during development. For example, the development department can provide beginner students with basic development methods and add step-by-step guides. For example, the development department can provide intermediate students with more complex development methods and hints to encourage independent learning. For example, the development department can provide advanced students with the latest development methods and resources to promote self-learning. This enhances learning effectiveness by providing development methods tailored to the students' level of expertise. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not. For example, the development department can input the students' level of expertise into a generative AI, which can then suggest the optimal development method.

[0085] The development department estimates students' emotions and adjusts the presentation method of the development results based on the estimated emotions. For example, if a student is stressed, the development department can present development results in a simple and visually easy-to-understand manner. If a student is relaxed, the development department can present development results that include detailed data and graphs. If a student is excited, the development department can present development results in an interactive format to maintain interest. This deepens understanding by adjusting the presentation method of development results according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the development department may be performed using or without a generative AI. For example, the development department can input student emotion data into a generative AI, which can then generate emotion estimation results.

[0086] The development department prioritizes the application of relevant development methods during development, taking into account the students' learning history. For example, the development department can prioritize development methods related to what the students have learned in the past. For example, the development department can analyze the students' learning history and prioritize the application of development methods in areas where the students have a low level of understanding. For example, the development department can prioritize the application of development methods that the students are likely to be interested in, based on their learning history. In this way, relevant development methods can be prioritized by considering the students' learning history. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input student learning history data into a generative AI, which can then propose the optimal development method.

[0087] The development department optimizes development methods by referring to students' project participation history during development. For example, the development department can refer to data from projects students have previously participated in and propose the optimal development method. For example, the development department can analyze students' project participation history and reuse successful methods. For example, the development department can suggest improvements to avoid failed methods based on students' project participation history. In this way, the optimal development method can be selected by referring to students' project participation history. Some or all of the above processes in the development department may be performed using, for example, generative AI, or not using generative AI. For example, the development department can input student project participation history data into generative AI, and the generative AI can propose the optimal development method.

[0088] The testing unit estimates the student's emotions and adjusts the pace of the testing process based on the estimated emotions. For example, if a student is stressed, the testing unit can slow down the pace of the testing process and provide additional materials to deepen understanding. For example, if a student is relaxed, the testing unit can speed up the pace of the testing process to allow them to move to the next step sooner. For example, if a student is excited, the testing unit can adjust the pace of the testing process and suggest a break to maintain concentration. This enhances learning effectiveness by adjusting the pace of the testing process according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the testing unit may be performed using a generative AI, or not. For example, the testing unit can input student emotion data into a generative AI, which can then generate an emotion estimation result.

[0089] The testing department selects the optimal testing method by referring to past test data. For example, the testing department can propose the most suitable testing method for a similar project based on past successful test data. For example, the testing department can analyze past failed test data and propose improvements to avoid the same mistakes. For example, the testing department can select a testing method appropriate to the students' level of expertise by referring to past test data. In this way, the optimal testing method can be selected by utilizing past data. Some or all of the above processes in the testing department may be performed using, for example, generative AI, or not using generative AI. For example, the testing department can input past test data into a generative AI, and the generative AI can propose the optimal testing method.

[0090] The testing department customizes the testing methodology according to the students' level of expertise during testing. For example, it can provide beginner students with basic testing methodology and add step-by-step guidance. For intermediate students, it can provide more complex testing methodology and hints to encourage independent learning. For advanced students, it can provide the latest testing methodology and resources to facilitate self-study. This enhances learning effectiveness by providing testing methodology tailored to the students' level of expertise. Some or all of the above processes in the testing department may be performed using, for example, generative AI, or not. For example, the testing department can input the students' level of expertise into a generative AI, which can then suggest the most suitable testing methodology.

[0091] The testing unit estimates the student's emotions and adjusts the presentation of test results based on the estimated emotions. For example, if a student is stressed, the testing unit can present simple and visually easy-to-understand test results. If a student is relaxed, the testing unit can present test results with detailed data and graphs. If a student is excited, the testing unit can present test results in an interactive format to maintain interest. This deepens understanding by adjusting the presentation of test results according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the testing unit may be performed using or without a generative AI. For example, the testing unit can input student emotion data into a generative AI, which can then generate an emotion estimation result.

[0092] The testing unit prioritizes the application of relevant testing methods during testing, taking into account the student's learning history. For example, the testing unit can prioritize the application of testing methods related to content the student has previously learned. For example, the testing unit can analyze the student's learning history and prioritize the application of testing methods in areas where the student's understanding is weak. For example, the testing unit can prioritize the application of testing methods that the student is likely to be interested in, based on the student's learning history. In this way, relevant testing methods can be prioritized by considering the student's learning history. Some or all of the above processing in the testing unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the testing unit can input student learning history data into a generative AI, which can then suggest the optimal testing method.

[0093] The testing unit optimizes testing methods by referring to students' project participation history during testing. For example, the testing unit can refer to data from projects students have previously participated in and propose the optimal testing method. For example, the testing unit can analyze students' project participation history and reuse successful methods. For example, the testing unit can suggest improvements to avoid failed methods based on students' project participation history. This allows for the selection of the optimal testing method by referring to students' project participation history. Some or all of the above processes in the testing unit may be performed using, for example, generative AI, or without generative AI. For example, the testing unit can input student project participation history data into a generative AI, which can then propose the optimal testing method.

[0094] The feedback unit estimates the student's emotions and adjusts the content of the feedback based on the estimated emotions. For example, if the student is stressed, the feedback unit can prioritize positive feedback and gently convey areas for improvement. For example, if the student is relaxed, the feedback unit can provide detailed feedback and specific advice for taking the next step. For example, if the student is excited, the feedback unit can make the content of the feedback concise and increase motivation for the next challenge. This enhances learning effectiveness by adjusting the content of feedback according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the feedback unit may be performed using a generative AI, or not using a generative AI. For example, the feedback unit can input student emotion data into a generative AI, and the generative AI can generate an emotion estimation result.

[0095] The feedback unit provides optimal feedback by referring to the student's past performance data during the feedback process. For example, the feedback unit can analyze the student's past performance data and provide feedback that allows the student to feel a sense of growth. For example, the feedback unit can identify the student's past weaknesses and provide specific advice for improvement. For example, the feedback unit can provide motivational feedback based on the student's past successes. In this way, optimal feedback can be provided by referring to the student's past performance data. Some or all of the above processes in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input the student's past performance data into a generative AI, and the generative AI can suggest optimal feedback.

[0096] The feedback unit estimates the student's emotions and adjusts the timing of feedback based on the estimated emotions. For example, if the student is stressed, the feedback unit can delay the timing of feedback so that the student can receive it calmly. For example, if the student is relaxed, the feedback unit can advance the timing of feedback so that the student can move on to the next step sooner. For example, if the student is excited, the feedback unit can adjust the timing of feedback and suggest a break to maintain concentration. This enhances learning effectiveness by adjusting the timing of feedback according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the feedback unit may be performed using a generative AI, for example, or not using a generative AI. For example, the feedback unit can input student emotion data into a generative AI, and the generative AI can generate an emotion estimation result.

[0097] The feedback unit, when providing feedback, prioritizes relevant feedback by considering the student's learning history. For example, the feedback unit can analyze the student's learning history and provide feedback related to what they have learned in the past. For example, the feedback unit can prioritize providing feedback on areas where the student's understanding is weak, based on their learning history. For example, the feedback unit can refer to the student's learning history and provide feedback on topics that might interest them. This allows the feedback unit to prioritize providing relevant feedback by considering the student's learning history. Some or all of the above processing in the feedback unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the feedback unit can input student learning history data into a generative AI, which can then suggest the most appropriate feedback.

[0098] The integration unit estimates students' emotions and adjusts the functionality of the project management tool based on the estimated emotions. For example, if a student is stressed, the integration unit can provide a simple interface and simplify operation. For example, if a student is relaxed, the integration unit can provide detailed functions and increase the flexibility of project management. For example, if a student is excited, the integration unit can add interactive functions to make project management more enjoyable. This makes project management more efficient by adjusting the functionality of the project management tool according to students' emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the integration unit may be performed using a generative AI, for example, or not using a generative AI. For example, the integration unit can input student emotion data into a generative AI, and the generative AI can generate emotion estimation results.

[0099] The integration unit selects the optimal integration method by referring to the student's past project data during integration. The integration unit can, for example, analyze the student's past project data and reuse successful integration methods. The integration unit can, for example, suggest improvements to avoid failed integration methods based on the student's past project data. The integration unit can, for example, refer to the student's past project data and select the optimal integration method. This allows the optimal integration method to be selected by referring to the student's past project data. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input the student's past project data into a generative AI, and the generative AI can suggest the optimal integration method.

[0100] The integration unit estimates students' emotions and adjusts the display of project management tools based on the estimated emotions. For example, if a student is stressed, the integration unit can provide a simple and visually easy-to-understand display. For example, if a student is relaxed, the integration unit can provide a display that includes detailed data and graphs. For example, if a student is excited, the integration unit can provide an interactive display to keep them engaged. This streamlines project management by adjusting the display of project management tools according to students' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the integration unit may be performed using or without a generative AI. For example, the integration unit can input student emotion data into a generative AI, which can then generate emotion estimation results.

[0101] The integration unit, during integration, prioritizes the application of relevant integration methods, taking into account the student's learning history. For example, the integration unit can analyze the student's learning history and prioritize the application of integration methods related to what the student has learned in the past. For example, based on the student's learning history, the integration unit can prioritize the application of integration methods in areas where the student has a low level of understanding. For example, the integration unit can refer to the student's learning history and prioritize the application of integration methods that the student might be interested in. In this way, relevant integration methods can be prioritized by considering the student's learning history. Some or all of the above processing in the integration unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the integration unit can input student learning history data into a generative AI, which can then propose the optimal integration method.

[0102] The customization unit estimates the student's emotions and adjusts the learning plan based on the estimated emotions. For example, if a student is stressed, the customization unit can simplify the learning plan to reduce the burden. If a student is relaxed, the customization unit can make the learning plan more detailed to promote deeper understanding. If a student is excited, the customization unit can make the learning plan more interactive to keep them interested. This enhances learning effectiveness by adjusting the learning plan according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the customization unit may be performed using a generative AI or not. For example, the customization unit can input student emotion data into a generative AI, which can then generate an emotion estimation result.

[0103] The customization unit provides an optimal learning plan by referring to the student's past learning data during the customization process. For example, the customization unit can analyze the student's past learning data and provide a learning plan that allows the student to feel a sense of growth. For example, the customization unit can identify the student's past weaknesses and provide a specific learning plan for improvement. For example, the customization unit can provide a learning plan that increases motivation based on the student's past successes. In this way, the optimal learning plan can be provided by referring to the student's past learning data. Some or all of the above processing in the customization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the customization unit can input the student's past learning data into a generative AI, and the generative AI can propose an optimal learning plan.

[0104] The customization unit estimates the student's emotions and adjusts the pace of the learning plan based on the estimated emotions. For example, if the student is stressed, the customization unit can slow down the pace of the learning plan and provide additional materials to deepen understanding. For example, if the student is relaxed, the customization unit can speed up the pace of the learning plan to allow them to move to the next step sooner. For example, if the student is excited, the customization unit can adjust the pace of the learning plan and suggest a break to maintain concentration. This enhances learning effectiveness by adjusting the pace of the learning plan according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the customization unit may be performed using a generative AI, or not using a generative AI. For example, the customization unit can input student emotion data into a generative AI, and the generative AI can generate an emotion estimation result.

[0105] The customization unit prioritizes providing relevant learning plans by considering the student's learning history during the customization process. For example, the customization unit can analyze the student's learning history and prioritize providing learning plans related to what they have learned in the past. For example, based on the student's learning history, the customization unit can prioritize providing learning plans in areas where the student has a low level of understanding. For example, the customization unit can refer to the student's learning history and prioritize providing learning plans that are likely to interest them. In this way, relevant learning plans can be prioritized by considering the student's learning history. Some or all of the above processing in the customization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the customization unit can input the student's learning history data into a generative AI, which can then propose an optimal learning plan.

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

[0107] The verification unit can estimate students' emotions and adjust the pace of hypothesis testing based on those estimates. For example, if a student is stressed, the pace of hypothesis testing can be slowed down, and additional materials can be provided to deepen understanding. If a student is relaxed, the pace of hypothesis testing can be sped up, allowing them to move to the next step sooner. If a student is excited, the pace of hypothesis testing can be adjusted, and a break can be suggested to maintain concentration. In this way, the learning effect can be enhanced by adjusting the pace of hypothesis testing according to students' emotions.

[0108] The development department can estimate students' emotions and adjust the pace of the development process based on those estimates. For example, if a student is stressed, the pace of the development process can be slowed down, and additional materials can be provided to deepen their understanding. If a student is relaxed, the pace of the development process can be sped up, allowing them to move to the next step sooner. If a student is excited, the pace of the development process can be adjusted, and a break can be suggested to maintain their concentration. In this way, the learning effect can be enhanced by adjusting the pace of the development process according to the students' emotions.

[0109] The testing department can estimate students' emotions and adjust the pace of the testing process based on those estimates. For example, if a student is stressed, the pace of the testing process can be slowed down, and additional materials can be provided to deepen their understanding. If a student is relaxed, the pace of the testing process can be sped up, allowing them to move on to the next step sooner. If a student is excited, the pace of the testing process can be adjusted, and breaks can be suggested to help them maintain their concentration. By adjusting the pace of the testing process according to students' emotions, the learning effect can be enhanced.

[0110] The feedback system can estimate a student's emotions and adjust the content of the feedback based on those emotions. For example, if a student is stressed, it can prioritize positive feedback and gently communicate areas for improvement. If a student is relaxed, it can provide detailed feedback and specific advice for taking the next step. If a student is excited, it can make the feedback concise and increase their motivation for the next challenge. In this way, adjusting the content of feedback according to the student's emotions can enhance learning effectiveness.

[0111] The integration system can estimate students' emotions and adjust the functionality of project management tools based on those estimates. For example, if a student is stressed, a simple interface can be provided to simplify operation. If a student is relaxed, detailed features can be provided to increase the flexibility of project management. If a student is excited, interactive features can be added to make project management more enjoyable. In this way, project management becomes more efficient by adjusting the functionality of project management tools according to students' emotions.

[0112] The verification unit can select the optimal verification method by referring to past verification data. For example, it can propose the most suitable verification method for similar projects based on past successful verification data. It can also analyze past failed verification data and propose improvements to avoid the same mistakes. It can select verification methods that match the students' level of expertise. In this way, the optimal verification method can be selected by utilizing past data.

[0113] The development department can select the optimal development method by referring to past development data. For example, based on past successful development data, they can propose the most suitable development method for similar projects. They can also analyze past failed development data and propose improvements to avoid the same mistakes. They can select development methods that match the students' level of expertise. In this way, the optimal development method can be selected by utilizing past data.

[0114] The testing department can select the optimal testing method by referring to past test data. For example, based on past successful test data, they can propose the most suitable testing method for similar projects. They can analyze past failed test data and propose improvements to avoid the same mistakes. They can select testing methods appropriate to the students' level of expertise. In this way, the optimal testing method can be selected by utilizing past data.

[0115] The feedback department can provide optimal feedback by referring to students' past performance data. For example, it can analyze students' past performance data and provide feedback that allows them to feel their growth. It can identify students' past weaknesses and provide specific advice for improvement. It can provide motivational feedback based on students' past successes. In this way, by referring to students' past performance data, it can provide optimal feedback.

[0116] The customization function can provide an optimal learning plan by referencing the student's past learning data during the customization process. For example, it can analyze the student's past learning data and provide a learning plan that allows them to feel a sense of growth. It can identify the student's past weaknesses and provide a specific learning plan for improvement. It can provide a learning plan that increases motivation based on the student's past successes. In this way, by referring to the student's past learning data, the optimal learning plan can be provided.

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

[0118] Step 1: The verification section involves students participating in AI projects and testing hypotheses. For example, students can verify their hypotheses through experiments and data analysis. They can use experimental and data analysis techniques to test their hypotheses. Step 2: The development department develops an AI model based on the hypotheses verified by the verification department. For example, they can develop an AI model using machine learning algorithms, deep learning techniques, and natural language processing techniques. Step 3: The testing department tests the AI ​​model developed by the development department. For example, they can create test cases to evaluate the performance of the AI ​​model, use test datasets to evaluate accuracy, and apply test methods to evaluate generalization performance.

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

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

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

[0122] Each of the multiple elements described above, including the verification unit, development unit, testing unit, feedback unit, integration unit, and customization unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the verification unit is implemented by the control unit 46A of the smart device 14 and verifies the hypotheses formulated by students through experiments and data analysis. The development unit is implemented by the specific processing unit 290 of the data processing unit 12 and develops an AI model using machine learning algorithms. The testing unit is implemented by the control unit 46A of the smart device 14 and evaluates the performance of the AI ​​model. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and evaluates the students' progress in real time and provides feedback. The integration unit is implemented by the control unit 46A of the smart device 14 and manages the progress of the project. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates a learning plan tailored to the students' learning style and progress. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0138] Each of the multiple elements described above, including the verification unit, development unit, testing unit, feedback unit, integration unit, and customization unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the verification unit is implemented by the control unit 46A of the smart glasses 214 and verifies the hypotheses formulated by students through experiments and data analysis. The development unit is implemented by the specific processing unit 290 of the data processing unit 12 and develops an AI model using machine learning algorithms. The testing unit is implemented by the control unit 46A of the smart glasses 214 and evaluates the performance of the AI ​​model. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and evaluates the students' progress in real time and provides feedback. The integration unit is implemented by the control unit 46A of the smart glasses 214 and manages the progress of the project. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates a learning plan tailored to the students' learning style and progress. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0154] Each of the multiple elements described above, including the verification unit, development unit, testing unit, feedback unit, integration unit, and customization unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the verification unit is implemented by the control unit 46A of the headset terminal 314 and verifies the hypotheses formulated by students through experiments and data analysis. The development unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and develops an AI model using machine learning algorithms. The testing unit is implemented by, for example, the control unit 46A of the headset terminal 314 and evaluates the performance of the AI ​​model. The feedback unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and evaluates the students' progress in real time and provides feedback. The integration unit is implemented by, for example, the control unit 46A of the headset terminal 314 and manages the progress of the project. The customization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and creates a learning plan tailored to the students' learning style and progress. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0171] Each of the multiple elements described above, including the verification unit, development unit, test unit, feedback unit, integration unit, and customization unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the verification unit is implemented by the control unit 46A of the robot 414 and verifies the hypotheses formulated by students through experiments and data analysis. The development unit is implemented by the specific processing unit 290 of the data processing unit 12 and develops an AI model using machine learning algorithms. The test unit is implemented by the control unit 46A of the robot 414 and evaluates the performance of the AI ​​model. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12 and evaluates the students' progress in real time and provides feedback. The integration unit is implemented by the control unit 46A of the robot 414 and manages the progress of the project. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates a learning plan tailored to the students' learning style and progress. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

[0181] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

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

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

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

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

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

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

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

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

[0190] (Note 1) Students participate in AI projects, with a verification team that tests hypotheses, The development unit develops an AI model based on the hypothesis verified by the verification unit, A testing unit that tests the AI ​​models developed by the aforementioned development unit, Equipped with A system characterized by the following features. (Note 2) Equipped with a feedback unit that provides real-time feedback. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features an integration unit that integrates project management tools. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a customization section for tailoring individual learning plans. The system described in Appendix 1, characterized by the features described herein. (Note 5) The verification unit, Test the hypothesis The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned development department, Develop an AI model The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned test unit is Test the AI ​​model The system described in Appendix 1, characterized by the features described herein. (Note 8) The verification unit, The system estimates students' emotions and adjusts the pace of hypothesis testing based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The verification unit, Refer to past validation data and select the optimal validation method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The verification unit, During validation, the validation methodology will be customized according to the students' level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 11) The verification unit, We estimate students' emotions and adjust the presentation method of the verification results based on the estimated students' emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The verification unit, During validation, we prioritize testing relevant hypotheses by considering students' learning histories. The system described in Appendix 1, characterized by the features described herein. (Note 13) The verification unit, During verification, the verification method is optimized by referring to the students' project participation history. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned development department, Estimate students' emotions and adjust the pace of the development process based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned development department, Refer to past development data to select the optimal development method. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned development department, During development, the development methodology is customized according to the students' level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned development department, We estimate students' emotions and adjust the presentation method of development results based on the estimated student emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned development department, During development, we prioritize the application of development methods relevant to students' learning history. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned development department, During development, optimize development methods by referring to students' project participation history. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned test unit is The system estimates the students' emotions and adjusts the pace of the test process based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned test unit is Refer to past test data and select the optimal testing method. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned test unit is During testing, customize the testing methodology according to the students' level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned test unit is The system estimates students' emotions and adjusts how test results are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned test unit is During testing, the relevant testing methodology should be prioritized, taking into account the student's learning history. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned test unit is During testing, optimize the testing methodology by referring to the students' project participation history. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned feedback unit is The system estimates the student's emotions and adjusts the content of the feedback based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned feedback unit is When providing feedback, we refer to the student's past performance data to provide the most appropriate feedback. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned feedback unit is The system estimates the student's emotions and adjusts the timing of feedback based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned feedback unit is When providing feedback, we prioritize providing relevant feedback by considering the student's learning history. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned integration unit is It estimates students' emotions and adjusts the functionality of project management tools based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned integration unit is During integration, the optimal integration method will be selected by referring to students' past project data. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned integration unit is It estimates students' emotions and adjusts how project management tools are displayed based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned integration unit is During integration, the relevant integration method will be prioritized, taking into account the students' learning history. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned customization unit is The system estimates students' emotions and adjusts the learning plan based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 35) The aforementioned customization unit is During customization, the system provides an optimal learning plan by referencing the student's past learning data. The system described in Appendix 4, characterized by the features described herein. (Note 36) The aforementioned customization unit is The system estimates students' emotions and adjusts the pace of the learning plan based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 37) The aforementioned customization unit is During customization, the system prioritizes providing relevant learning plans by considering the student's learning history. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

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

Claims

1. Students participate in the AI ​​project, with a verification team that tests hypotheses, A development unit develops an AI model based on the hypothesis verified by the verification unit, A testing unit for testing the AI ​​model developed by the aforementioned development unit, Equipped with A system characterized by the following features.

2. Equipped with a feedback unit that provides real-time feedback. The system according to feature 1.

3. It features an integration unit that integrates project management tools. The system according to feature 1.

4. It includes a customization section for tailoring individual learning plans. The system according to feature 1.

5. The verification unit, Test the hypothesis The system according to feature 1.

6. The aforementioned development department, Developing AI models The system according to feature 1.

7. The aforementioned test unit is Test the AI ​​model The system according to feature 1.

8. The verification unit, The system estimates students' emotions and adjusts the pace of hypothesis testing based on those estimated emotions. The system according to feature 1.

Images