system

Abstract

The system according to this embodiment aims to enable children to acquire knowledge in STEM fields while maintaining their interest. [Solution] The system according to the embodiment comprises a lecture generation unit, an output unit, a reception unit, an answer generation unit, and a provision unit. The lecture generation unit generates audio of lectures on STEM fields using AI. The output unit outputs the audio generated by the lecture generation unit through a speaker attached to a stuffed animal. The reception unit receives audio of questions from lecture participants through a microphone attached to the stuffed animal. The answer generation unit generates answers based on the questions received by the reception unit. The provision unit provides the answers generated by the answer generation unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, in educational programs related to the STEM field, there was a problem that it was difficult for children to maintain their interest.

[0005] The system according to the embodiment aims to enable children to acquire knowledge in the STEM field while maintaining their interest.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a lecture generation unit, an output unit, a reception unit, an answer generation unit, and a provision unit. The lecture generation unit generates audio of lectures on STEM fields using AI. The output unit outputs the audio generated by the lecture generation unit through a speaker attached to a stuffed animal. The reception unit receives audio of questions from lecture participants using a microphone attached to the stuffed animal. The answer generation unit generates answers based on the questions received by the reception unit. The provision unit provides the answers generated by the answer generation unit. [Effects of the Invention]

[0007] The system according to this embodiment allows children to acquire knowledge in STEM fields while maintaining their interest. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An embodiment of the present invention provides an educational program in the fields of science, technology, engineering, and mathematics (STEM) using a stuffed animal that directly or readily incorporates a generative AI. This STEM education system consists of the following steps: First, a lecture generation unit uses AI to generate audio lectures on STEM fields. Next, the generated audio is output from a speaker attached to the stuffed animal. When a student asks a question, a microphone attached to the stuffed animal receives the audio of the question. The reception unit generates an answer based on the received question, and the delivery unit provides the answer. For example, if a child asks, "Why is the sky blue?", the reception unit receives the question, and the answer generation unit uses generative AI to generate an answer. The generated answer is output from the stuffed animal through the delivery unit. Furthermore, the answer generation unit can also estimate the student's emotions and generate an answer based on the estimated emotions. It can also analyze the student's question history and generate an answer based on the analysis results. This system can also generate answers based on the student's current learning situation and areas of interest. For example, if a child is interested in mathematics, it can provide more detailed answers to questions related to mathematics. Furthermore, the stuffed animals can be controlled to conduct experiments, allowing children to learn by actually watching the experiments. The reception unit can also analyze the audio of received questions and determine the learner's level of understanding based on the analysis results. The lecture generation unit can adjust the difficulty level of the lecture based on the learner's level of understanding. For example, it can provide simple explanations for content the child is learning for the first time and more advanced explanations for content they already understand. In this way, by using stuffed animals with directly or readily available generating AI, children can learn about STEM fields in a fun way. For example, by having the stuffed animals explain scientific principles and mathematical formulas and conduct experiments, children can learn through hands-on experience. This can foster children's interest in STEM fields and increase their motivation to learn in the future. Thus, STEM education systems can make learning science, technology, engineering, and mathematics fun for children.Stuffed animals are robots that resemble humans or animals, but are not limited to such examples.

[0029] The STEM education system according to this embodiment comprises a lecture generation unit, an output unit, a reception unit, an answer generation unit, and a provision unit. The lecture generation unit generates audio of lectures on STEM fields using AI. The lecture generation unit generates the audio of the lecture using, for example, speech synthesis technology. The lecture generation unit can also generate the content of the lecture using natural language processing technology. For example, the lecture generation unit inputs knowledge in the STEM field into an AI model and generates the audio of the lecture. The output unit outputs the audio generated by the lecture generation unit from a speaker attached to a stuffed animal. The output unit outputs the audio using, for example, a speaker. The output unit can also adjust the tone and speed of the audio. For example, the output unit adjusts the tone and speed of the audio using AI to provide audio suitable for the student. The reception unit receives audio of questions raised by students of the lecture using a microphone attached to the stuffed animal. The reception unit receives audio using, for example, a microphone. The reception unit can also analyze the content of the questions using speech recognition technology. For example, the reception unit uses AI to convert speech to text and analyze the content of the question. The answer generation unit generates an answer based on the question received by the reception unit. The answer generation unit generates an answer to the question using, for example, a generation AI. The answer generation unit can also estimate the student's emotions and generate an answer based on the estimated emotions. For example, the answer generation unit uses AI to analyze the student's emotions and generate an appropriate answer. The delivery unit provides the answer generated by the answer generation unit. The delivery unit provides the answer using, for example, a speaker. The delivery unit can also provide the answer in text format. For example, the delivery unit uses AI to generate text and displays it on the screen. As a result, the STEM education system according to this embodiment can automatically generate lectures on STEM fields and provide appropriate answers to students' questions.

[0030] The lecture generation unit generates audio for lectures in STEM fields using AI. Specifically, it generates lecture audio using speech synthesis technology. Speech synthesis technology includes Text-to-Speech (TTS) technology, which converts text into speech, enabling the generation of speech with natural pronunciation and intonation. Furthermore, the lecture generation unit can also generate lecture content using natural language processing technology. Natural language processing technology includes text generation, summarization, and translation, making it possible to automatically create lecture content. For example, the lecture generation unit inputs knowledge in STEM fields into an AI model and generates lecture audio. This AI model has been trained on a large dataset of STEM fields and possesses specialized knowledge. Specifically, when a prompt such as "Generate a lecture explaining the basic principles of physics" is input to the AI ​​model, the AI ​​searches for relevant information and generates lecture text containing appropriate content. This text is then converted into speech using speech synthesis technology. As a result, the lecture generation unit can automatically generate lectures with specialized knowledge and provide them to students.

[0031] The output unit outputs the audio generated by the lecture generation unit through a speaker attached to the stuffed animal. Specifically, it outputs audio using a speaker. The speaker is designed to achieve high-quality audio output, providing clear and easy-to-understand sound. The output unit can also adjust the tone and speed of the audio. For example, the output unit uses AI to adjust the tone and speed of the audio, providing audio suitable for the learner. The AI ​​analyzes the learner's reactions and level of understanding in real time and optimizes the tone and speed of the audio based on that. For example, if a learner is confused by difficult content, the AI ​​will slow down the audio speed and soften the tone to help them understand. The output unit can also adjust the volume of the audio, providing the optimal volume according to ambient noise and the learner's position. In this way, the output unit can provide the learner with the optimal audio environment and maximize the effectiveness of the lecture.

[0032] The reception desk uses a microphone attached to a stuffed animal to receive audio questions from lecture participants. Specifically, it uses a microphone to receive audio. The microphone is highly sensitive and can clearly pick up the participants' voices. The reception desk can also analyze the content of questions using speech recognition technology. This speech recognition technology includes ASR (Automatic Speech Recognition) technology, which converts speech to text, allowing for accurate transcription of participants' questions. For example, the reception desk uses AI to convert speech to text and analyze the content of the questions. The AI ​​understands the intent and content of the questions and provides information to generate appropriate answers. Furthermore, the reception desk can use noise cancellation technology to remove background noise and make the audio of the questions clearer. This allows the reception desk to accurately receive and analyze participants' questions.

[0033] The answer generation unit generates answers based on questions received by the reception unit. Specifically, it uses a generation AI to generate answers to questions. The generation AI has learned from a large dataset and has the ability to generate appropriate answers to a variety of questions. For example, if a student asks, "Please explain Newton's laws of motion," the generation AI will search for relevant information and generate an appropriate answer. The answer generation unit can also estimate the student's emotions and generate answers based on those estimated emotions. For example, the answer generation unit uses AI to analyze the student's emotions and generate an appropriate answer. The AI ​​analyzes the student's tone of voice and facial expressions, and if the student is confused, it will provide a more polite and easy-to-understand answer. In this way, the answer generation unit can provide appropriate and emotionally sensitive answers to students' questions.

[0034] The information provider unit provides the answers generated by the answer generation unit. Specifically, it provides answers via audio using a speaker. The speaker delivers high-quality audio output, providing learners with clear and easy-to-understand answers. The information provider unit can also provide answers in text format. For example, the information provider unit can use AI to generate text and display it on the screen. This allows learners to confirm answers not only aurally but also visually. Furthermore, the information provider unit can record the content of the answers for later reference. For example, if a learner wants to review past questions and answers, the information provider unit can search for and provide that information. This allows the information provider unit to provide learners with answers in various formats, thereby enhancing the learning effect.

[0035] The answer generation unit can generate answers to questions using a generation AI. For example, the answer generation unit generates answers to questions using a generation AI. For example, the answer generation unit inputs the content of the question into an AI model and generates an appropriate answer. The answer generation unit can also generate detailed answers to questions using a generation AI. For example, the answer generation unit analyzes background information of the question using AI and generates a detailed answer. As a result, the accuracy of the answers to questions is improved by using a generation AI.

[0036] The answer generation unit can analyze the learner's question history and generate answers based on the analysis results. The answer generation unit can analyze the learner's question history using, for example, data mining techniques. For example, the answer generation unit can analyze past question content to identify the learner's areas of interest. The answer generation unit can also analyze the learner's question history using machine learning algorithms. For example, the answer generation unit can use AI to cluster the question history and identify related questions. Furthermore, the answer generation unit can analyze patterns in the question history and generate optimal answers. For example, the answer generation unit can learn past question-and-answer pairs and generate appropriate answers for new questions. This allows for the provision of more appropriate answers based on the learner's past question history. Some or all of the above processing in the answer generation unit may be performed using, for example, AI, or not using AI. For example, the answer generation unit can input the learner's question history data into a generation AI and have the generation AI perform the analysis of the question history and the generation of answers.

[0037] The reception unit can generate responses based on the student's current learning status or areas of interest. For example, the reception unit can analyze test results to evaluate learning progress. For example, the reception unit can use AI to analyze test results and evaluate the student's level of understanding. The reception unit can also analyze learning history to identify the student's areas of interest. For example, the reception unit can analyze past learning history to identify areas of interest for the student. Furthermore, the reception unit can analyze survey results to identify the student's areas of interest. For example, the reception unit can use AI to analyze survey results and identify the student's areas of interest. This allows the reception unit to provide appropriate responses tailored to the student's learning status and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the student's learning history data into a generating AI and have the generating AI perform the evaluation of the learning status and generate responses.

[0038] The system further includes a control unit that controls the stuffed animal to conduct experiments. The control unit can control the stuffed animal to perform experiments. For example, the control unit can program the experimental procedure and have the stuffed animal execute it. For example, the control unit can use AI to analyze the experimental procedure and give instructions to the stuffed animal. The control unit can also monitor the progress of the experiment and make adjustments as needed. For example, the control unit can use sensors to monitor the progress of the experiment and respond if an anomaly occurs. Furthermore, the control unit can analyze the results of the experiment and provide feedback. For example, the control unit can use AI to analyze the results of the experiment and provide feedback to the learner. This allows learners to learn by actually observing the experiment as the stuffed animal conducts it. Some or all of the above-described processes in the control unit may be performed using AI, for example, or without AI. For example, the control unit can input experimental procedure data into a generating AI and have the generating AI execute the control of the experiment.

[0039] The reception unit further includes a judgment unit that analyzes the audio of received questions and determines the learner's level of understanding based on the analysis results. The judgment unit analyzes the content of questions using, for example, speech recognition technology. For example, the judgment unit converts audio to text using AI and analyzes the content of the questions. The judgment unit can also evaluate the learner's level of understanding based on the content of the questions. For example, the judgment unit uses AI to evaluate the difficulty level of the questions and determines the learner's level of understanding. Furthermore, the judgment unit can analyze the frequency and type of questions and evaluate the learner's learning progress. For example, the judgment unit uses AI to analyze the patterns of questions and evaluate the level of understanding. The lecture generation unit can adjust the difficulty level of the lectures based on the learners' level of understanding. For example, the lecture generation unit uses AI to generate lecture content and adjusts the difficulty level according to the learners' level of understanding. For example, the lecture generation unit provides simple explanations for beginners while providing advanced explanations for learners who already understand the material. This makes it possible to provide lectures of appropriate difficulty level according to the learners' level of understanding. Some or all of the above-described processes in the judgment unit and the lecture generation unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the student's question data into the generation AI and have the generation AI perform a judgment on the level of learning.

[0040] The lecture generation unit can analyze a student's past learning history and select the most suitable lecture content. For example, the lecture generation unit can analyze a student's learning history using data mining techniques. For instance, it can analyze past learning content and evaluate the student's level of understanding. The lecture generation unit can also analyze a student's learning history using machine learning algorithms. For example, it can use AI to cluster the learning history and identify relevant lecture content. Furthermore, the lecture generation unit can analyze patterns in the learning history and select the most suitable lecture content. For example, it can compare past learning content with the current learning status and select the next topic to learn. This allows the system to provide optimal lecture content based on the student's past learning history. Some or all of the above-described processes in the lecture generation unit may be performed using AI, or not. For example, the lecture generation unit can input student learning history data into a generation AI and have the generation AI perform the analysis of the learning history and the selection of lecture content.

[0041] The lecture generation unit can apply different lecture styles depending on the age and comprehension level of the students. For example, the lecture generation unit can conduct lectures using age-appropriate materials. For instance, for preschoolers, the lecture generation unit can apply a lecture style that uses simple language and many illustrations. For elementary school students, the lecture generation unit can also apply a lecture style that incorporates many concrete examples. Furthermore, for middle and high school students, the lecture generation unit can apply a lecture style that emphasizes theoretical explanations. For example, the lecture generation unit can use AI to analyze the age and comprehension level of the students and select an appropriate lecture style. This allows the unit to provide a lecture style that is appropriate for the age and comprehension level of the students. Some or all of the above processing in the lecture generation unit may be performed using AI, for example, or without AI. For example, the lecture generation unit can input student age and comprehension data into a generating AI and have the generating AI select the lecture style.

[0042] The lecture generation unit can incorporate highly relevant case studies based on the learner's geographical location. For example, the lecture generation unit can identify the learner's location using geographical data. For example, the lecture generation unit can analyze GPS data to obtain the learner's location. The lecture generation unit can also select relevant case studies based on location information. For example, the lecture generation unit can incorporate scientific case studies related to the climate of the area where the learner lives. Furthermore, the lecture generation unit can incorporate technological case studies related to the history of the area where the learner lives. For example, the lecture generation unit can generate lecture content considering the historical background of the region. This allows the lecture generation unit to provide highly relevant case studies based on the learner's geographical location. Some or all of the above processing in the lecture generation unit may be performed using AI, for example, or without AI. For example, the lecture generation unit can input the learner's location data into a generation AI and have the generation AI select relevant case studies.

[0043] The lecture generation unit can analyze students' social media activity and incorporate relevant topics into the lectures. For example, the lecture generation unit can analyze students' social media activity using data mining techniques. For instance, it can analyze information about content shared and accounts followed by students. The lecture generation unit can also analyze social media activity using machine learning algorithms. For example, it can use AI to cluster social media posts and identify relevant topics. Furthermore, the lecture generation unit can analyze patterns in social media activity and generate optimal lecture content. For example, it can incorporate scientific examples related to topics of interest to students into the lectures. This allows for the provision of highly relevant lecture content based on students' social media activity. Some or all of the above processing in the lecture generation unit may be performed using AI, or not. For example, the lecture generation unit can input students' social media data into a generating AI and have the generating AI select relevant topics.

[0044] The output unit can optimize the frequency of the audio based on the learner's auditory characteristics. For example, the output unit can conduct an audiometry test to evaluate the learner's auditory characteristics. For example, the output unit can use AI to analyze the results of the audiometry test and evaluate the learner's auditory characteristics. The output unit can also adjust the frequency of the audio based on the auditory characteristics. For example, the output unit can use AI to optimize the frequency of the audio and provide audio suitable for the learner. Furthermore, the output unit can provide audio tailored to the learner's auditory characteristics by emphasizing specific frequency bands. For example, the output unit can provide audio with emphasized bass frequencies to learners who have difficulty hearing high frequencies. This allows for the provision of optimal audio tailored to the learner's auditory characteristics. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audiometry test data into a generating AI and have the generating AI perform the optimization of the audio frequency.

[0045] The output unit can detect the learner's ambient sounds and automatically adjust the audio volume. For example, the output unit uses a microphone to detect ambient sounds. For example, the output unit uses AI to analyze ambient sounds and evaluate the noise level around the learner. The output unit can also adjust the audio volume based on ambient sounds. For example, the output unit uses AI to automatically adjust the audio volume, providing a suitable volume for the learner. Furthermore, the output unit can adjust the audio volume in real time in response to changes in ambient sounds. For example, the output unit increases the volume when the surroundings are noisy and decreases it when it is quiet. This allows for the provision of an appropriate audio volume according to the learner's ambient sounds. Some or all of the above processing in the output unit may be performed using AI, or without AI. For example, the output unit can input ambient sound data into a generating AI and have the generating AI perform the audio volume adjustment.

[0046] The output unit can select the optimal audio format considering the learner's device information. For example, the output unit collects device information to identify the type of device. For example, the output unit uses AI to analyze the device information and identify the device the learner is using. The output unit can also select the optimal audio format based on the device information. For example, the output unit uses AI to select an audio format suitable for the device and provides it to the learner. Furthermore, the output unit can adjust the audio quality according to the characteristics of the device. For example, the output unit selects the optimal audio format for a smartphone and adjusts the audio quality. This allows the output unit to provide the optimal audio format based on the learner's device information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input device information data into a generating AI and have the generating AI perform the audio format selection.

[0047] The output unit can provide multilingual audio based on the learner's language settings. For example, the output unit collects device information to obtain the device's language settings. For example, the output unit uses AI to analyze the device's language settings and identify the language the learner is using. The output unit can also provide multilingual audio based on the language settings. For example, the output unit uses AI to generate audio in multiple languages ​​and provide it to the learner. Furthermore, the output unit can accommodate learners who use multiple languages ​​by providing a language switching function. For example, if the learner selects a specific language, the output unit provides audio in that language. This allows for the provision of multilingual audio according to the learner's language settings. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input language setting data into a generating AI and have the generating AI generate multilingual audio.

[0048] The reception department can select the optimal reception method when receiving a question by referring to the participant's past question history. The reception department can analyze the participant's question history using, for example, data mining techniques. For example, the reception department can analyze the content of past questions to identify the participant's areas of interest. The reception department can also analyze the participant's question history using machine learning algorithms. For example, the reception department can use AI to cluster the question history and identify related questions. Furthermore, the reception department can analyze patterns in the question history to select the optimal reception method. For example, the reception department can learn from past question-and-answer pairs and select an appropriate reception method for new questions. This allows the reception department to provide the optimal question reception method based on the participant's past question history. Some or all of the above processing in the reception department may be performed using, for example, AI, or not using AI. For example, the reception department can input the participant's question history data into a generating AI and have the generating AI perform the selection of the question reception method.

[0049] The reception desk can analyze the pronunciation characteristics of participants when questions are received, thereby improving the accuracy of speech recognition. For example, the reception desk can analyze the pronunciation characteristics of participants using speech analysis technology. For example, the reception desk can analyze the tone and speed of the voice to identify the participant's pronunciation characteristics. The reception desk can also analyze pronunciation characteristics using machine learning algorithms. For example, the reception desk can use AI to cluster pronunciation characteristics and improve the accuracy of speech recognition. Furthermore, the reception desk can adjust the parameters of speech recognition based on pronunciation characteristics. For example, the reception desk can adjust the parameters of speech recognition for participants with a specific accent. This improves the accuracy of speech recognition based on the participant's pronunciation characteristics. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the participant's pronunciation data into a generating AI and have the generating AI perform the speech recognition accuracy improvement.

[0050] The reception desk can prioritize accepting questions that are highly relevant to the participant, taking into account the participant's geographical location. For example, the reception desk can identify the participant's location using geographical data. For example, the reception desk can analyze GPS data to obtain the participant's location. The reception desk can also select relevant questions based on location information. For example, the reception desk can prioritize accepting questions related to the area where the participant lives. Furthermore, if the participant is traveling, the reception desk can prioritize accepting questions related to that area. For example, if the participant is in a specific location, the reception desk can prioritize accepting questions related to that location. This allows the reception desk to prioritize accepting highly relevant questions based on the participant's geographical location. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input location data into a generating AI and have the generating AI select relevant questions.

[0051] The reception desk can analyze participants' social media activity when receiving questions and accept relevant questions. For example, the reception desk can analyze participants' social media activity using data mining techniques. For example, the reception desk can analyze information on what participants have shared and the accounts they follow. The reception desk can also analyze social media activity using machine learning algorithms. For example, the reception desk can use AI to cluster social media posts and identify relevant questions. Furthermore, the reception desk can analyze patterns in social media activity and accept the most relevant questions. For example, the reception desk can accept questions related to topics that participants are interested in. This allows the reception desk to accept highly relevant questions based on participants' social media activity. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input social media data into a generating AI and have the generating AI select relevant questions.

[0052] The answer generation unit can analyze the learner's past question history and select the optimal answer when generating an answer. For example, the answer generation unit can analyze the learner's question history using data mining techniques. For example, the answer generation unit can analyze the content of past questions and identify the learner's areas of interest. The answer generation unit can also analyze the learner's question history using machine learning algorithms. For example, the answer generation unit can use AI to cluster the question history and identify related answers. Furthermore, the answer generation unit can analyze patterns in the question history and select the optimal answer. For example, the answer generation unit can learn from past question-and-answer pairs and select an appropriate answer for a new question. This allows the answer generation unit to provide the optimal answer based on the learner's past question history. Some or all of the above processing in the answer generation unit may be performed using AI, for example, or without AI. For example, the answer generation unit can input the learner's question history data into a generation AI and have the generation AI perform the answer selection.

[0053] The answer generation unit can apply different answer styles depending on the learner's age and level of understanding when generating answers. For example, the answer generation unit can generate answers using age-appropriate answer methods. For example, for preschoolers, the answer generation unit can apply an answer style that uses simple words and illustrations extensively. For elementary school students, the answer generation unit can also apply an answer style that incorporates many concrete examples. Furthermore, for junior and senior high school students, the answer generation unit can apply an answer style that emphasizes theoretical explanations. For example, the answer generation unit can use AI to analyze the learner's age and level of understanding and select an appropriate answer style. This makes it possible to provide an appropriate answer style according to the learner's age and level of understanding. Some or all of the above processing in the answer generation unit may be performed using AI, for example, or without AI. For example, the answer generation unit can input the learner's age and level of understanding data into a generation AI and have the generation AI select the answer style.

[0054] The answer generation unit can incorporate highly relevant examples by considering the learner's geographical location information when generating answers. For example, the answer generation unit can identify the learner's location information using geographical data. For example, the answer generation unit can analyze GPS data to obtain the learner's location information. The answer generation unit can also select relevant examples based on location information. For example, the answer generation unit can incorporate scientific examples related to the climate of the area where the learner lives into the answer. Furthermore, the answer generation unit can incorporate technological examples related to the history of the area where the learner lives into the answer. For example, the answer generation unit generates answer content considering the historical background of the region. This makes it possible to provide highly relevant examples based on the learner's geographical location information. Some or all of the above processing in the answer generation unit may be performed using AI, for example, or without AI. For example, the answer generation unit can input the learner's location information data into a generation AI and have the generation AI perform the selection of relevant examples.

[0055] The response generation unit can analyze the participant's social media activity and incorporate relevant topics into the response during the response generation process. For example, the response generation unit can analyze the participant's social media activity using data mining techniques. For instance, it can analyze information about content shared and accounts followed by the participant. The response generation unit can also analyze social media activity using machine learning algorithms. For example, it can use AI to cluster social media posts and identify relevant topics. Furthermore, the response generation unit can analyze patterns in social media activity and generate optimal responses. For example, it can incorporate scientific examples related to topics of interest to the participant into the response. This allows for the provision of highly relevant responses based on the participant's social media activity. Some or all of the above-described processes in the response generation unit may be performed using AI, or not. For example, the response generation unit can input social media data into a generating AI and have the generating AI select relevant topics.

[0056] The service provider can select the optimal delivery method by referring to the learner's past learning history when providing answers. The service provider can analyze the learner's learning history using, for example, data mining techniques. For example, the service provider can analyze past learning content and evaluate the learner's level of understanding. The service provider can also analyze the learner's learning history using machine learning algorithms. For example, the service provider can use AI to cluster the learning history and identify relevant delivery methods. Furthermore, the service provider can analyze patterns in the learning history and select the optimal delivery method. For example, the service provider can compare past learning content with the current learning status and select the optimal delivery method. This enables the service provider to provide the optimal answer delivery method based on the learner's past learning history. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the learner's learning history data into a generating AI and have the generating AI select the delivery method.

[0057] The service provider can detect the learner's ambient noise when providing answers and automatically adjust the audio volume. For example, the service provider uses a microphone to detect ambient noise. For example, the service provider uses AI to analyze ambient noise and evaluate the noise level around the learner. The service provider can also adjust the audio volume based on ambient noise. For example, the service provider uses AI to automatically adjust the audio volume and provide a suitable volume for the learner. Furthermore, the service provider can adjust the audio volume in real time in response to changes in ambient noise. For example, the service provider increases the volume when the surroundings are noisy and decreases it when it is quiet. This allows the service provider to provide an appropriate audio volume according to the learner's ambient noise. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input ambient noise data into a generating AI and have the generating AI perform the audio volume adjustment.

[0058] The service provider can select the optimal audio format when providing answers, taking into account the participant's device information. For example, the service provider collects device information to identify the type of device. For example, the service provider uses AI to analyze the device information and identify the device the participant is using. The service provider can also select the optimal audio format based on the device information. For example, the service provider uses AI to select an audio format suitable for the device and provides it to the participant. Furthermore, the service provider can adjust the audio quality according to the characteristics of the device. For example, the service provider selects the optimal audio format for a smartphone and adjusts the audio quality. This allows the service provider to provide the optimal audio format based on the participant's device information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input device information data into a generating AI and have the generating AI perform the audio format selection.

[0059] The service provider can provide multilingual audio based on the learner's language settings when providing answers. For example, the service provider collects device information to obtain the device's language settings. For example, the service provider uses AI to analyze the device's language settings and identify the language the learner is using. The service provider can also provide multilingual audio based on language settings. For example, the service provider uses AI to generate audio in multiple languages ​​and provide it to the learner. Furthermore, the service provider can accommodate learners who use multiple languages ​​by providing a language switching function. For example, if the learner selects a specific language, the service provider provides audio in that language. This allows the service provider to provide multilingual audio according to the learner's language settings. Some or all of the above processing in the service provider may be performed using AI, or not using AI. For example, the service provider can input language setting data into a generating AI and have the generating AI generate multilingual audio.

[0060] The control unit can select the optimal control method during experiment control by referring to the participant's past experiment history. The control unit can analyze the participant's experiment history using, for example, data mining techniques. For example, the control unit can analyze past experiment content and evaluate the participant's level of understanding. The control unit can also analyze the participant's experiment history using machine learning algorithms. For example, the control unit can use AI to cluster the experiment history and identify related control methods. Furthermore, the control unit can analyze patterns in the experiment history and select the optimal control method. For example, the control unit can learn past experiment and result pairs and select an appropriate control method for a new experiment. This makes it possible to provide an optimal experiment control method based on the participant's past experiment history. Some or all of the above processing in the control unit may be performed using, for example, AI, or not using AI. For example, the control unit can input the participant's experiment history data into a generating AI and have the generating AI perform the selection of a control method.

[0061] The control unit can apply different experimental styles to the participants' ages and levels of understanding during experiment control. For example, the control unit can control experiments using age-appropriate experimental methods. For instance, it can apply a simple experiment style to young children. It can also apply an experimental style incorporating many concrete examples to elementary school students. Furthermore, it can apply an experimental style emphasizing theoretical explanations to middle and high school students. For example, the control unit can use AI to analyze the participants' ages and levels of understanding and select an appropriate experimental style. This allows for the provision of an appropriate experimental style tailored to the participants' ages and levels of understanding. Some or all of the above-described processes in the control unit may be performed using AI, or not. For example, the control unit can input participant age and understanding data into a generating AI and have the generating AI select the experimental style.

[0062] The control unit can prioritize highly relevant experiments by considering the geographical location of the participant during experiment control. For example, the control unit can identify the participant's location using geographical data. For example, the control unit can analyze GPS data to obtain the participant's location. The control unit can also select relevant experiments based on location information. For example, the control unit can prioritize experiments related to the climate of the region where the participant lives. Furthermore, the control unit can also prioritize experiments related to the history of the region where the participant lives. For example, the control unit can select experiment content considering the historical background of the region. This allows the control unit to provide highly relevant experiments based on the participant's geographical location. Some or all of the above processing in the control unit may be performed using AI, for example, or without AI. For example, the control unit can input the participant's location data into a generating AI and have the generating AI select relevant experiments.

[0063] The control unit can analyze the social media activity of participants and conduct relevant experiments during experiment control. For example, the control unit can analyze participants' social media activity using data mining techniques. For example, the control unit can analyze information on what participants have shared and the accounts they follow. The control unit can also analyze social media activity using machine learning algorithms. For example, the control unit can use AI to cluster social media posts and identify relevant experiments. Furthermore, the control unit can analyze patterns in social media activity and select the most suitable experiment. For example, the control unit can conduct experiments related to topics that participants are interested in. This allows the control unit to provide highly relevant experiments based on participants' social media activity. Some or all of the above processing in the control unit may be performed using AI, or not using AI. For example, the control unit can input social media data into a generating AI and have the generating AI select relevant experiments.

[0064] The assessment unit can select the optimal assessment method by referring to the learner's past learning history when determining their learning level. The assessment unit can analyze the learner's learning history using, for example, data mining techniques. For example, the assessment unit can analyze past learning content and evaluate the learner's level of understanding. The assessment unit can also analyze the learner's learning history using machine learning algorithms. For example, the assessment unit can cluster the learning history using AI and identify relevant assessment methods. Furthermore, the assessment unit can analyze patterns in the learning history and select the optimal assessment method. For example, the assessment unit can compare past learning content with the current learning status and select the optimal assessment method. This makes it possible to provide an optimal learning level assessment method based on the learner's past learning history. Some or all of the above processing in the assessment unit may be performed using, for example, AI, or without AI. For example, the assessment unit can input the learner's learning history data into a generating AI and have the generating AI perform the selection of the assessment method.

[0065] The assessment unit can apply different assessment criteria depending on the learner's age and level of understanding when determining their learning progress. For example, the assessment unit can use age-specific assessment criteria to determine the learning progress. For example, for preschoolers, the assessment unit can apply assessment criteria that make extensive use of simple language and illustrations. For elementary school students, the assessment unit can also apply assessment criteria that incorporate many concrete examples. Furthermore, for middle and high school students, the assessment unit can apply assessment criteria that emphasize theoretical explanations. For example, the assessment unit can use AI to analyze the learner's age and level of understanding and select appropriate assessment criteria. This allows the assessment unit to provide appropriate learning progress criteria according to the learner's age and level of understanding. Some or all of the above-described processes in the assessment unit may be performed using AI, or not using AI. For example, the assessment unit can input the learner's age and level of understanding data into a generating AI and have the generating AI select the assessment criteria.

[0066] The assessment unit can make highly relevant assessments by considering the learner's geographical location information when determining their learning level. For example, the assessment unit can identify the learner's location information using geographical data. For example, the assessment unit can analyze GPS data to obtain the learner's location information. The assessment unit can also make relevant assessments based on location information. For example, the assessment unit can determine the learning level related to the climate of the area where the learner lives. Furthermore, the assessment unit can also determine the learning level related to the history of the area where the learner lives. For example, the assessment unit can determine the learning level by considering the historical background of the area. This makes it possible to provide highly relevant learning level assessments based on the learner's geographical location information. Some or all of the above processing in the assessment unit may be performed using AI, for example, or without using AI. For example, the assessment unit can input the learner's location information data into a generating AI and have the generating AI perform the relevant assessment.

[0067] The assessment unit can analyze the learner's social media activity and make relevant judgments when determining their learning level. For example, the assessment unit can analyze the learner's social media activity using data mining techniques. For example, the assessment unit can analyze information on what the learner has shared and the accounts they follow. The assessment unit can also analyze social media activity using machine learning algorithms. For example, the assessment unit can use AI to cluster social media posts and identify relevant judgments. Furthermore, the assessment unit can analyze patterns in social media activity and make optimal judgments. For example, the assessment unit can determine the learning level related to topics the learner is interested in. This allows for the provision of highly relevant learning level judgments based on the learner's social media activity. Some or all of the above processing in the assessment unit may be performed using AI, for example, or without AI. For example, the assessment unit can input social media data into a generating AI and have the generating AI perform relevant judgments.

[0068] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0069] STEM education systems can further estimate students' learning styles and customize lecture content based on those estimates. For example, visual learners can be provided with lectures that make extensive use of diagrams and graphs. Auditory learners can be provided with lectures that make extensive use of audio and music. Furthermore, practical learners can be provided with lectures that incorporate many experiments and hands-on activities. This allows for the provision of optimal lecture content tailored to each student's learning style. Learning styles can be estimated, for example, by analyzing questionnaires and past learning history. This maximizes the learning effectiveness for each student.

[0070] STEM education systems can further monitor students' learning progress in real time and adjust lecture content accordingly. For example, if a student is struggling with a particular topic, additional explanations or practice problems related to that topic can be provided. Conversely, if a student is progressing well, they can move on to the next topic. Furthermore, student progress data can be accumulated to create long-term learning plans. This maximizes the effectiveness of student learning. Progress monitoring can be done, for example, by analyzing quiz or test results in real time.

[0071] STEM education systems can further analyze students' learning history and suggest optimal learning paths. For example, they can suggest topics to study next based on past learning content and performance. They can also suggest relevant topics based on students' interests and concerns. Furthermore, they can create long-term learning plans according to students' learning goals. This maximizes the effectiveness of students' learning. Learning path suggestions can be made using, for example, data mining techniques and machine learning algorithms.

[0072] STEM education systems can further analyze students' learning history and provide optimal learning resources. For example, they can suggest relevant textbooks and reference books based on past learning content and performance. They can also suggest relevant videos and articles based on students' interests. Furthermore, they can provide optimal learning resources according to students' learning goals. This maximizes the effectiveness of students' learning. Learning resource suggestions can be made using, for example, data mining techniques and machine learning algorithms.

[0073] STEM education systems can further analyze students' learning history and suggest optimal learning methods. For example, they can suggest effective learning methods based on past learning content and performance. They can also suggest relevant learning methods based on students' interests and concerns. Furthermore, they can suggest optimal learning methods according to students' learning goals. This maximizes the effectiveness of students' learning. Learning method suggestions can be made using, for example, data mining techniques and machine learning algorithms.

[0074] STEM education systems can further analyze students' learning history and set optimal learning goals. For example, realistic learning goals can be set based on past learning content and performance. Relevant learning goals can also be set based on students' interests and concerns. Furthermore, long-term learning plans can be created according to students' learning goals, thereby maximizing the effectiveness of their learning. Setting learning goals can be done, for example, using data mining techniques or machine learning algorithms.

[0075] The following briefly describes the processing flow for example form 1.

[0076] Step 1: The lecture generation unit generates audio for lectures on STEM fields using AI. For example, it generates lecture content using speech synthesis technology and natural language processing technology, inputs knowledge of STEM fields into the AI ​​model, and generates the lecture audio. Step 2: The output unit outputs the audio generated by the lecture generation unit through a speaker attached to the stuffed animal. For example, it outputs audio using a speaker and adjusts the tone and speed of the audio to provide audio suitable for the learner. Step 3: The reception desk receives audio questions from lecture participants using microphones attached to stuffed animals. For example, the microphone is used to receive the audio, and speech recognition technology is used to analyze the content of the questions. Step 4: The response generation unit generates answers based on the questions received by the reception unit. For example, it uses a generation AI to generate answers to questions and estimates the participant's emotions to generate appropriate answers. Step 5: The providing unit provides the answer generated by the answer generation unit. For example, the answer can be provided via voice using a speaker and displayed on the screen in text format.

[0077] (Example of form 2) An embodiment of the present invention provides an educational program in the fields of science, technology, engineering, and mathematics (STEM) using a stuffed animal that directly or readily incorporates a generative AI. This STEM education system consists of the following steps: First, a lecture generation unit uses AI to generate audio lectures on STEM fields. Next, the generated audio is output from a speaker attached to the stuffed animal. When a student asks a question, a microphone attached to the stuffed animal receives the audio of the question. The reception unit generates an answer based on the received question, and the delivery unit provides the answer. For example, if a child asks, "Why is the sky blue?", the reception unit receives the question, and the answer generation unit uses generative AI to generate an answer. The generated answer is output from the stuffed animal through the delivery unit. Furthermore, the answer generation unit can also estimate the student's emotions and generate an answer based on the estimated emotions. It can also analyze the student's question history and generate an answer based on the analysis results. This system can also generate answers based on the student's current learning situation and areas of interest. For example, if a child is interested in mathematics, it can provide more detailed answers to questions related to mathematics. Furthermore, the stuffed animals can be controlled to conduct experiments, allowing children to learn by actually watching the experiments. The reception unit can also analyze the audio of received questions and determine the learner's level of understanding based on the analysis results. The lecture generation unit can adjust the difficulty level of the lecture based on the learner's level of understanding. For example, it can provide simple explanations for content the child is learning for the first time and more advanced explanations for content they already understand. In this way, by using stuffed animals with directly or readily available generating AI, children can learn about STEM fields in a fun way. For example, by having the stuffed animals explain scientific principles and mathematical formulas and conduct experiments, children can learn through hands-on experience. This can foster children's interest in STEM fields and increase their motivation to learn in the future. Thus, STEM education systems can make learning science, technology, engineering, and mathematics fun for children.Stuffed animals are robots that resemble humans or animals, but are not limited to such examples.

[0078] The STEM education system according to this embodiment comprises a lecture generation unit, an output unit, a reception unit, an answer generation unit, and a provision unit. The lecture generation unit generates audio of lectures on STEM fields using AI. The lecture generation unit generates the audio of the lecture using, for example, speech synthesis technology. The lecture generation unit can also generate the content of the lecture using natural language processing technology. For example, the lecture generation unit inputs knowledge in the STEM field into an AI model and generates the audio of the lecture. The output unit outputs the audio generated by the lecture generation unit from a speaker attached to a stuffed animal. The output unit outputs the audio using, for example, a speaker. The output unit can also adjust the tone and speed of the audio. For example, the output unit adjusts the tone and speed of the audio using AI to provide audio suitable for the student. The reception unit receives audio of questions raised by students of the lecture using a microphone attached to the stuffed animal. The reception unit receives audio using, for example, a microphone. The reception unit can also analyze the content of the questions using speech recognition technology. For example, the reception unit uses AI to convert speech to text and analyze the content of the question. The answer generation unit generates an answer based on the question received by the reception unit. The answer generation unit generates an answer to the question using, for example, a generation AI. The answer generation unit can also estimate the student's emotions and generate an answer based on the estimated emotions. For example, the answer generation unit uses AI to analyze the student's emotions and generate an appropriate answer. The delivery unit provides the answer generated by the answer generation unit. The delivery unit provides the answer using, for example, a speaker. The delivery unit can also provide the answer in text format. For example, the delivery unit uses AI to generate text and displays it on the screen. As a result, the STEM education system according to this embodiment can automatically generate lectures on STEM fields and provide appropriate answers to students' questions.

[0079] The lecture generation unit generates audio for lectures in STEM fields using AI. Specifically, it generates lecture audio using speech synthesis technology. Speech synthesis technology includes Text-to-Speech (TTS) technology, which converts text into speech, enabling the generation of speech with natural pronunciation and intonation. Furthermore, the lecture generation unit can also generate lecture content using natural language processing technology. Natural language processing technology includes text generation, summarization, and translation, making it possible to automatically create lecture content. For example, the lecture generation unit inputs knowledge in STEM fields into an AI model and generates lecture audio. This AI model has been trained on a large dataset of STEM fields and possesses specialized knowledge. Specifically, when a prompt such as "Generate a lecture explaining the basic principles of physics" is input to the AI ​​model, the AI ​​searches for relevant information and generates lecture text containing appropriate content. This text is then converted into speech using speech synthesis technology. As a result, the lecture generation unit can automatically generate lectures with specialized knowledge and provide them to students.

[0080] The output unit outputs the audio generated by the lecture generation unit through a speaker attached to the stuffed animal. Specifically, it outputs audio using a speaker. The speaker is designed to achieve high-quality audio output, providing clear and easy-to-understand sound. The output unit can also adjust the tone and speed of the audio. For example, the output unit uses AI to adjust the tone and speed of the audio, providing audio suitable for the learner. The AI ​​analyzes the learner's reactions and level of understanding in real time and optimizes the tone and speed of the audio based on that. For example, if a learner is confused by difficult content, the AI ​​will slow down the audio speed and soften the tone to help them understand. The output unit can also adjust the volume of the audio, providing the optimal volume according to ambient noise and the learner's position. In this way, the output unit can provide the learner with the optimal audio environment and maximize the effectiveness of the lecture.

[0081] The reception desk uses a microphone attached to a stuffed animal to receive audio questions from lecture participants. Specifically, it uses a microphone to receive audio. The microphone is highly sensitive and can clearly pick up the participants' voices. The reception desk can also analyze the content of questions using speech recognition technology. This speech recognition technology includes ASR (Automatic Speech Recognition) technology, which converts speech to text, allowing for accurate transcription of participants' questions. For example, the reception desk uses AI to convert speech to text and analyze the content of the questions. The AI ​​understands the intent and content of the questions and provides information to generate appropriate answers. Furthermore, the reception desk can use noise cancellation technology to remove background noise and make the audio of the questions clearer. This allows the reception desk to accurately receive and analyze participants' questions.

[0082] The answer generation unit generates answers based on questions received by the reception unit. Specifically, it uses a generation AI to generate answers to questions. The generation AI has learned from a large dataset and has the ability to generate appropriate answers to a variety of questions. For example, if a student asks, "Please explain Newton's laws of motion," the generation AI will search for relevant information and generate an appropriate answer. The answer generation unit can also estimate the student's emotions and generate answers based on those estimated emotions. For example, the answer generation unit uses AI to analyze the student's emotions and generate an appropriate answer. The AI ​​analyzes the student's tone of voice and facial expressions, and if the student is confused, it will provide a more polite and easy-to-understand answer. In this way, the answer generation unit can provide appropriate and emotionally sensitive answers to students' questions.

[0083] The information provider unit provides the answers generated by the answer generation unit. Specifically, it provides answers via audio using a speaker. The speaker delivers high-quality audio output, providing learners with clear and easy-to-understand answers. The information provider unit can also provide answers in text format. For example, the information provider unit can use AI to generate text and display it on the screen. This allows learners to confirm answers not only aurally but also visually. Furthermore, the information provider unit can record the content of the answers for later reference. For example, if a learner wants to review past questions and answers, the information provider unit can search for and provide that information. This allows the information provider unit to provide learners with answers in various formats, thereby enhancing the learning effect.

[0084] The answer generation unit can generate answers to questions using a generation AI. For example, the answer generation unit generates answers to questions using a generation AI. For example, the answer generation unit inputs the content of the question into an AI model and generates an appropriate answer. The answer generation unit can also generate detailed answers to questions using a generation AI. For example, the answer generation unit analyzes background information of the question using AI and generates a detailed answer. As a result, the accuracy of the answers to questions is improved by using a generation AI.

[0085] The response generation unit can estimate the learner's emotions and generate responses based on the estimated emotions. The response generation unit can estimate the learner's emotions using, for example, speech analysis technology. For example, the response generation unit can analyze the tone and speed of the voice to estimate the learner's emotions. The response generation unit can also estimate the learner's emotions using facial recognition technology. For example, the response generation unit can analyze the learner's facial expressions using a camera to estimate their emotions. Furthermore, the response generation unit can also estimate the learner's emotions using text analysis technology. For example, the response generation unit can analyze the content of the learner's question to estimate their emotions. This makes it possible to provide appropriate responses that correspond to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the response generation unit may be performed using, for example, AI, or without AI. For example, the response generation unit can input image data of the student captured by the camera into the generation AI, and have the generation AI perform the estimation of the student's emotions.

[0086] The answer generation unit can analyze the learner's question history and generate answers based on the analysis results. The answer generation unit can analyze the learner's question history using, for example, data mining techniques. For example, the answer generation unit can analyze past question content to identify the learner's areas of interest. The answer generation unit can also analyze the learner's question history using machine learning algorithms. For example, the answer generation unit can use AI to cluster the question history and identify related questions. Furthermore, the answer generation unit can analyze patterns in the question history and generate optimal answers. For example, the answer generation unit can learn past question-and-answer pairs and generate appropriate answers for new questions. This allows for the provision of more appropriate answers based on the learner's past question history. Some or all of the above processing in the answer generation unit may be performed using, for example, AI, or not using AI. For example, the answer generation unit can input the learner's question history data into a generation AI and have the generation AI perform the analysis of the question history and the generation of answers.

[0087] The reception unit can generate responses based on the student's current learning status or areas of interest. For example, the reception unit can analyze test results to evaluate learning progress. For example, the reception unit can use AI to analyze test results and evaluate the student's level of understanding. The reception unit can also analyze learning history to identify the student's areas of interest. For example, the reception unit can analyze past learning history to identify areas of interest for the student. Furthermore, the reception unit can analyze survey results to identify the student's areas of interest. For example, the reception unit can use AI to analyze survey results and identify the student's areas of interest. This allows the reception unit to provide appropriate responses tailored to the student's learning status and areas of interest. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the student's learning history data into a generating AI and have the generating AI perform the evaluation of the learning status and generate responses.

[0088] The system further includes a control unit that controls the stuffed animal to conduct experiments. The control unit can control the stuffed animal to perform experiments. For example, the control unit can program the experimental procedure and have the stuffed animal execute it. For example, the control unit can use AI to analyze the experimental procedure and give instructions to the stuffed animal. The control unit can also monitor the progress of the experiment and make adjustments as needed. For example, the control unit can use sensors to monitor the progress of the experiment and respond if an anomaly occurs. Furthermore, the control unit can analyze the results of the experiment and provide feedback. For example, the control unit can use AI to analyze the results of the experiment and provide feedback to the learner. This allows learners to learn by actually observing the experiment as the stuffed animal conducts it. Some or all of the above-described processes in the control unit may be performed using AI, for example, or without AI. For example, the control unit can input experimental procedure data into a generating AI and have the generating AI execute the control of the experiment.

[0089] The reception unit further includes a judgment unit that analyzes the audio of received questions and determines the learner's level of understanding based on the analysis results. The judgment unit analyzes the content of questions using, for example, speech recognition technology. For example, the judgment unit converts audio to text using AI and analyzes the content of the questions. The judgment unit can also evaluate the learner's level of understanding based on the content of the questions. For example, the judgment unit uses AI to evaluate the difficulty level of the questions and determines the learner's level of understanding. Furthermore, the judgment unit can analyze the frequency and type of questions and evaluate the learner's learning progress. For example, the judgment unit uses AI to analyze the patterns of questions and evaluate the level of understanding. The lecture generation unit can adjust the difficulty level of the lectures based on the learners' level of understanding. For example, the lecture generation unit uses AI to generate lecture content and adjusts the difficulty level according to the learners' level of understanding. For example, the lecture generation unit provides simple explanations for beginners while providing advanced explanations for learners who already understand the material. This makes it possible to provide lectures of appropriate difficulty level according to the learners' level of understanding. Some or all of the above-described processes in the judgment unit and the lecture generation unit may be performed using AI, for example, or without AI. For example, the judgment unit can input the student's question data into the generation AI and have the generation AI perform a judgment on the level of learning.

[0090] The lecture generation unit can estimate the emotions of the students and adjust the content and tone of the lecture based on the estimated emotions. For example, the lecture generation unit can estimate the emotions of the students using speech analysis technology. For example, the lecture generation unit can analyze the tone and speed of the speech to estimate the emotions of the students. The lecture generation unit can also estimate the emotions of the students using facial recognition technology. For example, the lecture generation unit can analyze the facial expressions of the students using a camera to estimate their emotions. Furthermore, the lecture generation unit can also estimate the emotions of the students using text analysis technology. For example, the lecture generation unit can analyze the content of the students' questions to estimate their emotions. This makes it possible to provide appropriate lecture content and tone according to the emotions of the students. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the lecture generation unit may be performed using AI, for example, or without using AI. For example, the lecture generation unit can input image data of students captured by a camera into a generation AI, which can then perform the estimation of the students' emotions.

[0091] The lecture generation unit can analyze a student's past learning history and select the most suitable lecture content. For example, the lecture generation unit can analyze a student's learning history using data mining techniques. For instance, it can analyze past learning content and evaluate the student's level of understanding. The lecture generation unit can also analyze a student's learning history using machine learning algorithms. For example, it can use AI to cluster the learning history and identify relevant lecture content. Furthermore, the lecture generation unit can analyze patterns in the learning history and select the most suitable lecture content. For example, it can compare past learning content with the current learning status and select the next topic to learn. This allows the system to provide optimal lecture content based on the student's past learning history. Some or all of the above-described processes in the lecture generation unit may be performed using AI, or not. For example, the lecture generation unit can input student learning history data into a generation AI and have the generation AI perform the analysis of the learning history and the selection of lecture content.

[0092] The lecture generation unit can apply different lecture styles depending on the age and comprehension level of the students. For example, the lecture generation unit can conduct lectures using age-appropriate materials. For instance, for preschoolers, the lecture generation unit can apply a lecture style that uses simple language and many illustrations. For elementary school students, the lecture generation unit can also apply a lecture style that incorporates many concrete examples. Furthermore, for middle and high school students, the lecture generation unit can apply a lecture style that emphasizes theoretical explanations. For example, the lecture generation unit can use AI to analyze the age and comprehension level of the students and select an appropriate lecture style. This allows the unit to provide a lecture style that is appropriate for the age and comprehension level of the students. Some or all of the above processing in the lecture generation unit may be performed using AI, for example, or without AI. For example, the lecture generation unit can input student age and comprehension data into a generating AI and have the generating AI select the lecture style.

[0093] The lecture generation unit can estimate the emotions of the learners and adjust the length of the lecture based on the estimated emotions. The lecture generation unit can estimate the emotions of the learners using, for example, speech analysis technology. For example, the lecture generation unit can analyze the tone and speed of the voice to estimate the emotions of the learners. The lecture generation unit can also estimate the emotions of the learners using facial recognition technology. For example, the lecture generation unit can analyze the facial expressions of the learners using a camera to estimate their emotions. Furthermore, the lecture generation unit can also estimate the emotions of the learners using text analysis technology. For example, the lecture generation unit can analyze the content of the learners' questions to estimate their emotions. This makes it possible to provide an appropriate lecture length according to the learners' emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The 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 lecture generation unit may be performed using, for example, AI, or not using AI. For example, the lecture generation unit can input image data of students captured by a camera into a generation AI, which can then perform the estimation of the students' emotions.

[0094] The lecture generation unit can incorporate highly relevant case studies based on the learner's geographical location. For example, the lecture generation unit can identify the learner's location using geographical data. For example, the lecture generation unit can analyze GPS data to obtain the learner's location. The lecture generation unit can also select relevant case studies based on location information. For example, the lecture generation unit can incorporate scientific case studies related to the climate of the area where the learner lives. Furthermore, the lecture generation unit can incorporate technological case studies related to the history of the area where the learner lives. For example, the lecture generation unit can generate lecture content considering the historical background of the region. This allows the lecture generation unit to provide highly relevant case studies based on the learner's geographical location. Some or all of the above processing in the lecture generation unit may be performed using AI, for example, or without AI. For example, the lecture generation unit can input the learner's location data into a generation AI and have the generation AI select relevant case studies.

[0095] The lecture generation unit can analyze students' social media activity and incorporate relevant topics into the lectures. For example, the lecture generation unit can analyze students' social media activity using data mining techniques. For instance, it can analyze information about content shared and accounts followed by students. The lecture generation unit can also analyze social media activity using machine learning algorithms. For example, it can use AI to cluster social media posts and identify relevant topics. Furthermore, the lecture generation unit can analyze patterns in social media activity and generate optimal lecture content. For example, it can incorporate scientific examples related to topics of interest to students into the lectures. This allows for the provision of highly relevant lecture content based on students' social media activity. Some or all of the above processing in the lecture generation unit may be performed using AI, or not. For example, the lecture generation unit can input students' social media data into a generating AI and have the generating AI select relevant topics.

[0096] The output unit can estimate the learner's emotions and adjust the tone and speed of the voice based on the estimated emotions. The output unit can estimate the learner's emotions using, for example, speech analysis technology. For example, the output unit can analyze the tone and speed of the voice and estimate the learner's emotions. The output unit can also estimate the learner's emotions using facial recognition technology. For example, the output unit can analyze the learner's facial expressions using a camera and estimate their emotions. Furthermore, the output unit can also estimate the learner's emotions using text analysis technology. For example, the output unit can analyze the content of the learner's questions and estimate their emotions. This makes it possible to provide an appropriate tone and speed of voice according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can input image data of the student captured by the camera into a generating AI, which can then perform the estimation of the student's emotions.

[0097] The output unit can optimize the frequency of the audio based on the learner's auditory characteristics. For example, the output unit can conduct an audiometry test to evaluate the learner's auditory characteristics. For example, the output unit can use AI to analyze the results of the audiometry test and evaluate the learner's auditory characteristics. The output unit can also adjust the frequency of the audio based on the auditory characteristics. For example, the output unit can use AI to optimize the frequency of the audio and provide audio suitable for the learner. Furthermore, the output unit can provide audio tailored to the learner's auditory characteristics by emphasizing specific frequency bands. For example, the output unit can provide audio with emphasized bass frequencies to learners who have difficulty hearing high frequencies. This allows for the provision of optimal audio tailored to the learner's auditory characteristics. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input audiometry test data into a generating AI and have the generating AI perform the optimization of the audio frequency.

[0098] The output unit can detect the learner's ambient sounds and automatically adjust the audio volume. For example, the output unit uses a microphone to detect ambient sounds. For example, the output unit uses AI to analyze ambient sounds and evaluate the noise level around the learner. The output unit can also adjust the audio volume based on ambient sounds. For example, the output unit uses AI to automatically adjust the audio volume, providing a suitable volume for the learner. Furthermore, the output unit can adjust the audio volume in real time in response to changes in ambient sounds. For example, the output unit increases the volume when the surroundings are noisy and decreases it when it is quiet. This allows for the provision of an appropriate audio volume according to the learner's ambient sounds. Some or all of the above processing in the output unit may be performed using AI, or without AI. For example, the output unit can input ambient sound data into a generating AI and have the generating AI perform the audio volume adjustment.

[0099] The output unit can estimate the learner's emotions and adjust the intonation of the speech based on the estimated emotions. The output unit can estimate the learner's emotions using, for example, speech analysis technology. For example, the output unit can analyze the tone and speed of the speech to estimate the learner's emotions. The output unit can also estimate the learner's emotions using facial recognition technology. For example, the output unit can analyze the learner's facial expressions using a camera to estimate their emotions. Furthermore, the output unit can also estimate the learner's emotions using text analysis technology. For example, the output unit can analyze the content of the learner's questions to estimate their emotions. This makes it possible to provide appropriate speech intonation according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can input image data of the student captured by the camera into a generating AI, which can then perform the estimation of the student's emotions.

[0100] The output unit can select the optimal audio format considering the learner's device information. For example, the output unit collects device information to identify the type of device. For example, the output unit uses AI to analyze the device information and identify the device the learner is using. The output unit can also select the optimal audio format based on the device information. For example, the output unit uses AI to select an audio format suitable for the device and provides it to the learner. Furthermore, the output unit can adjust the audio quality according to the characteristics of the device. For example, the output unit selects the optimal audio format for a smartphone and adjusts the audio quality. This allows the output unit to provide the optimal audio format based on the learner's device information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input device information data into a generating AI and have the generating AI perform the audio format selection.

[0101] The output unit can provide multilingual audio based on the learner's language settings. For example, the output unit collects device information to obtain the device's language settings. For example, the output unit uses AI to analyze the device's language settings and identify the language the learner is using. The output unit can also provide multilingual audio based on the language settings. For example, the output unit uses AI to generate audio in multiple languages ​​and provide it to the learner. Furthermore, the output unit can accommodate learners who use multiple languages ​​by providing a language switching function. For example, if the learner selects a specific language, the output unit provides audio in that language. This allows for the provision of multilingual audio according to the learner's language settings. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input language setting data into a generating AI and have the generating AI generate multilingual audio.

[0102] The reception desk can estimate the emotions of participants and adjust the question reception method based on the estimated emotions. The reception desk can estimate the emotions of participants using, for example, voice analysis technology. For example, the reception desk can estimate the emotions of participants by analyzing the tone and speed of their voice. The reception desk can also estimate the emotions of participants using facial recognition technology. For example, the reception desk can estimate the emotions by analyzing the facial expressions of participants using a camera. Furthermore, the reception desk can also estimate the emotions of participants using text analysis technology. For example, the reception desk can estimate the emotions by analyzing the content of the participants' questions. This makes it possible to provide an appropriate question reception method according to the emotions of the participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can input image data of participants captured by a camera into a generative AI and have the AI ​​perform an estimation of the participants' emotions.

[0103] The reception department can select the optimal reception method when receiving a question by referring to the participant's past question history. The reception department can analyze the participant's question history using, for example, data mining techniques. For example, the reception department can analyze the content of past questions to identify the participant's areas of interest. The reception department can also analyze the participant's question history using machine learning algorithms. For example, the reception department can use AI to cluster the question history and identify related questions. Furthermore, the reception department can analyze patterns in the question history to select the optimal reception method. For example, the reception department can learn from past question-and-answer pairs and select an appropriate reception method for new questions. This allows the reception department to provide the optimal question reception method based on the participant's past question history. Some or all of the above processing in the reception department may be performed using, for example, AI, or not using AI. For example, the reception department can input the participant's question history data into a generating AI and have the generating AI perform the selection of the question reception method.

[0104] The reception desk can analyze the pronunciation characteristics of participants when questions are received, thereby improving the accuracy of speech recognition. For example, the reception desk can analyze the pronunciation characteristics of participants using speech analysis technology. For example, the reception desk can analyze the tone and speed of the voice to identify the participant's pronunciation characteristics. The reception desk can also analyze pronunciation characteristics using machine learning algorithms. For example, the reception desk can use AI to cluster pronunciation characteristics and improve the accuracy of speech recognition. Furthermore, the reception desk can adjust the parameters of speech recognition based on pronunciation characteristics. For example, the reception desk can adjust the parameters of speech recognition for participants with a specific accent. This improves the accuracy of speech recognition based on the participant's pronunciation characteristics. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the participant's pronunciation data into a generating AI and have the generating AI perform the speech recognition accuracy improvement.

[0105] The reception desk can estimate the emotions of the participants and determine the priority of questions based on the estimated emotions. The reception desk can estimate the emotions of the participants using, for example, voice analysis technology. For example, the reception desk can estimate the emotions of the participants by analyzing the tone and speed of their voice. The reception desk can also estimate the emotions of the participants using facial recognition technology. For example, the reception desk can estimate the emotions by analyzing the emotions of the participants using a camera. Furthermore, the reception desk can also estimate the emotions of the participants using text analysis technology. For example, the reception desk can estimate the emotions by analyzing the content of the participants' questions. This makes it possible to provide appropriate question prioritization according to the emotions of the participants. Emotion estimation is achieved using an emotion estimation function, for example, 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 reception desk may be performed using, for example, AI, or not using AI. For example, the reception desk can input image data of participants captured by a camera into a generative AI and have the AI ​​perform an estimation of the participants' emotions.

[0106] The reception desk can prioritize accepting questions that are highly relevant to the participant, taking into account the participant's geographical location. For example, the reception desk can identify the participant's location using geographical data. For example, the reception desk can analyze GPS data to obtain the participant's location. The reception desk can also select relevant questions based on location information. For example, the reception desk can prioritize accepting questions related to the area where the participant lives. Furthermore, if the participant is traveling, the reception desk can prioritize accepting questions related to that area. For example, if the participant is in a specific location, the reception desk can prioritize accepting questions related to that location. This allows the reception desk to prioritize accepting highly relevant questions based on the participant's geographical location. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input location data into a generating AI and have the generating AI select relevant questions.

[0107] The reception desk can analyze participants' social media activity when receiving questions and accept relevant questions. For example, the reception desk can analyze participants' social media activity using data mining techniques. For example, the reception desk can analyze information on what participants have shared and the accounts they follow. The reception desk can also analyze social media activity using machine learning algorithms. For example, the reception desk can use AI to cluster social media posts and identify relevant questions. Furthermore, the reception desk can analyze patterns in social media activity and accept the most relevant questions. For example, the reception desk can accept questions related to topics that participants are interested in. This allows the reception desk to accept highly relevant questions based on participants' social media activity. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input social media data into a generating AI and have the generating AI select relevant questions.

[0108] The response generation unit can estimate the learner's emotions and adjust the content and tone of the response based on the estimated emotions. For example, the response generation unit can estimate the learner's emotions using speech analysis technology. For example, the response generation unit can analyze the tone and speed of the voice to estimate the learner's emotions. The response generation unit can also estimate the learner's emotions using facial recognition technology. For example, the response generation unit can analyze the learner's facial expressions using a camera to estimate their emotions. Furthermore, the response generation unit can also estimate the learner's emotions using text analysis technology. For example, the response generation unit can analyze the content of the learner's question to estimate their emotions. This makes it possible to provide appropriate response content and tone according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the response generation unit may be performed using AI, for example, or without using AI. For example, the response generation unit can input image data of the student captured by the camera into the generation AI, and have the generation AI perform the estimation of the student's emotions.

[0109] The answer generation unit can analyze the learner's past question history and select the optimal answer when generating an answer. For example, the answer generation unit can analyze the learner's question history using data mining techniques. For example, the answer generation unit can analyze the content of past questions and identify the learner's areas of interest. The answer generation unit can also analyze the learner's question history using machine learning algorithms. For example, the answer generation unit can use AI to cluster the question history and identify related answers. Furthermore, the answer generation unit can analyze patterns in the question history and select the optimal answer. For example, the answer generation unit can learn from past question-and-answer pairs and select an appropriate answer for a new question. This allows the answer generation unit to provide the optimal answer based on the learner's past question history. Some or all of the above processing in the answer generation unit may be performed using AI, for example, or without AI. For example, the answer generation unit can input the learner's question history data into a generation AI and have the generation AI perform the answer selection.

[0110] The answer generation unit can apply different answer styles depending on the learner's age and level of understanding when generating answers. For example, the answer generation unit can generate answers using age-appropriate answer methods. For example, for preschoolers, the answer generation unit can apply an answer style that uses simple words and illustrations extensively. For elementary school students, the answer generation unit can also apply an answer style that incorporates many concrete examples. Furthermore, for junior and senior high school students, the answer generation unit can apply an answer style that emphasizes theoretical explanations. For example, the answer generation unit can use AI to analyze the learner's age and level of understanding and select an appropriate answer style. This makes it possible to provide an appropriate answer style according to the learner's age and level of understanding. Some or all of the above processing in the answer generation unit may be performed using AI, for example, or without AI. For example, the answer generation unit can input the learner's age and level of understanding data into a generation AI and have the generation AI select the answer style.

[0111] The response generation unit can estimate the learner's emotions and adjust the length of the response based on the estimated emotions. The response generation unit can estimate the learner's emotions using, for example, speech analysis technology. For example, the response generation unit can analyze the tone and speed of the voice to estimate the learner's emotions. The response generation unit can also estimate the learner's emotions using facial recognition technology. For example, the response generation unit can analyze the learner's facial expressions using a camera to estimate their emotions. Furthermore, the response generation unit can also estimate the learner's emotions using text analysis technology. For example, the response generation unit can analyze the content of the learner's question to estimate their emotions. This makes it possible to provide an appropriate response length according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response generation unit may be performed using, for example, AI, or not using AI. For example, the response generation unit can input image data of the student captured by the camera into the generation AI, and have the generation AI perform the estimation of the student's emotions.

[0112] The answer generation unit can incorporate highly relevant examples by considering the learner's geographical location information when generating answers. For example, the answer generation unit can identify the learner's location information using geographical data. For example, the answer generation unit can analyze GPS data to obtain the learner's location information. The answer generation unit can also select relevant examples based on location information. For example, the answer generation unit can incorporate scientific examples related to the climate of the area where the learner lives into the answer. Furthermore, the answer generation unit can incorporate technological examples related to the history of the area where the learner lives into the answer. For example, the answer generation unit generates answer content considering the historical background of the region. This makes it possible to provide highly relevant examples based on the learner's geographical location information. Some or all of the above processing in the answer generation unit may be performed using AI, for example, or without AI. For example, the answer generation unit can input the learner's location information data into a generation AI and have the generation AI perform the selection of relevant examples.

[0113] The response generation unit can analyze the participant's social media activity and incorporate relevant topics into the response during the response generation process. For example, the response generation unit can analyze the participant's social media activity using data mining techniques. For instance, it can analyze information about content shared and accounts followed by the participant. The response generation unit can also analyze social media activity using machine learning algorithms. For example, it can use AI to cluster social media posts and identify relevant topics. Furthermore, the response generation unit can analyze patterns in social media activity and generate optimal responses. For example, it can incorporate scientific examples related to topics of interest to the participant into the response. This allows for the provision of highly relevant responses based on the participant's social media activity. Some or all of the above-described processes in the response generation unit may be performed using AI, or not. For example, the response generation unit can input social media data into a generating AI and have the generating AI select relevant topics.

[0114] The service provider can estimate the learner's emotions and adjust the method of providing answers based on the estimated emotions. For example, the service provider can estimate the learner's emotions using voice analysis technology. For example, the service provider can analyze the tone and speed of the voice to estimate the learner's emotions. The service provider can also estimate the learner's emotions using facial recognition technology. For example, the service provider can analyze the learner's facial expressions using a camera to estimate their emotions. Furthermore, the service provider can also estimate the learner's emotions using text analysis technology. For example, the service provider can analyze the content of the learner's questions to estimate their emotions. This allows the service provider to provide appropriate answers according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input image data of participants captured by a camera into a generating AI and have the AI ​​perform an estimation of the participants' emotions.

[0115] The service provider can select the optimal delivery method by referring to the learner's past learning history when providing answers. The service provider can analyze the learner's learning history using, for example, data mining techniques. For example, the service provider can analyze past learning content and evaluate the learner's level of understanding. The service provider can also analyze the learner's learning history using machine learning algorithms. For example, the service provider can use AI to cluster the learning history and identify relevant delivery methods. Furthermore, the service provider can analyze patterns in the learning history and select the optimal delivery method. For example, the service provider can compare past learning content with the current learning status and select the optimal delivery method. This enables the service provider to provide the optimal answer delivery method based on the learner's past learning history. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the learner's learning history data into a generating AI and have the generating AI select the delivery method.

[0116] The service provider can detect the learner's ambient noise when providing answers and automatically adjust the audio volume. For example, the service provider uses a microphone to detect ambient noise. For example, the service provider uses AI to analyze ambient noise and evaluate the noise level around the learner. The service provider can also adjust the audio volume based on ambient noise. For example, the service provider uses AI to automatically adjust the audio volume and provide a suitable volume for the learner. Furthermore, the service provider can adjust the audio volume in real time in response to changes in ambient noise. For example, the service provider increases the volume when the surroundings are noisy and decreases it when it is quiet. This allows the service provider to provide an appropriate audio volume according to the learner's ambient noise. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input ambient noise data into a generating AI and have the generating AI perform the audio volume adjustment.

[0117] The service provider can estimate the learner's emotions and adjust the order in which answers are provided based on the estimated emotions. For example, the service provider can estimate the learner's emotions using voice analysis technology. For example, the service provider can analyze the tone and speed of the voice to estimate the learner's emotions. The service provider can also estimate the learner's emotions using facial recognition technology. For example, the service provider can analyze the learner's facial expressions using a camera to estimate their emotions. Furthermore, the service provider can also estimate the learner's emotions using text analysis technology. For example, the service provider can analyze the content of the learner's questions to estimate their emotions. This allows the service provider to provide an appropriate order of answers according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input image data of participants captured by a camera into a generating AI and have the AI ​​perform an estimation of the participants' emotions.

[0118] The service provider can select the optimal audio format when providing answers, taking into account the participant's device information. For example, the service provider collects device information to identify the type of device. For example, the service provider uses AI to analyze the device information and identify the device the participant is using. The service provider can also select the optimal audio format based on the device information. For example, the service provider uses AI to select an audio format suitable for the device and provides it to the participant. Furthermore, the service provider can adjust the audio quality according to the characteristics of the device. For example, the service provider selects the optimal audio format for a smartphone and adjusts the audio quality. This allows the service provider to provide the optimal audio format based on the participant's device information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input device information data into a generating AI and have the generating AI perform the audio format selection.

[0119] The service provider can provide multilingual audio based on the learner's language settings when providing answers. For example, the service provider collects device information to obtain the device's language settings. For example, the service provider uses AI to analyze the device's language settings and identify the language the learner is using. The service provider can also provide multilingual audio based on language settings. For example, the service provider uses AI to generate audio in multiple languages ​​and provide it to the learner. Furthermore, the service provider can accommodate learners who use multiple languages ​​by providing a language switching function. For example, if the learner selects a specific language, the service provider provides audio in that language. This allows the service provider to provide multilingual audio according to the learner's language settings. Some or all of the above processing in the service provider may be performed using AI, or not using AI. For example, the service provider can input language setting data into a generating AI and have the generating AI generate multilingual audio.

[0120] The control unit can estimate the participant's emotions and adjust the experiment's progress based on the estimated emotions. For example, the control unit can estimate the participant's emotions using speech analysis technology. For example, the control unit can analyze the tone and speed of the speech to estimate the participant's emotions. The control unit can also estimate the participant's emotions using facial recognition technology. For example, the control unit can analyze the participant's facial expressions using a camera to estimate their emotions. Furthermore, the control unit can also estimate the participant's emotions using text analysis technology. For example, the control unit can analyze the content of the participant's questions to estimate their emotions. This allows for the provision of an appropriate experiment progress method that corresponds to the participant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the control unit may be performed using AI, for example, or without AI. For example, the control unit can input image data of the student captured by the camera into the generating AI and have the generating AI perform the estimation of the student's emotions.

[0121] The control unit can select the optimal control method during experiment control by referring to the participant's past experiment history. The control unit can analyze the participant's experiment history using, for example, data mining techniques. For example, the control unit can analyze past experiment content and evaluate the participant's level of understanding. The control unit can also analyze the participant's experiment history using machine learning algorithms. For example, the control unit can use AI to cluster the experiment history and identify related control methods. Furthermore, the control unit can analyze patterns in the experiment history and select the optimal control method. For example, the control unit can learn past experiment and result pairs and select an appropriate control method for a new experiment. This makes it possible to provide an optimal experiment control method based on the participant's past experiment history. Some or all of the above processing in the control unit may be performed using, for example, AI, or not using AI. For example, the control unit can input the participant's experiment history data into a generating AI and have the generating AI perform the selection of a control method.

[0122] The control unit can apply different experimental styles to the participants' ages and levels of understanding during experiment control. For example, the control unit can control experiments using age-appropriate experimental methods. For instance, it can apply a simple experiment style to young children. It can also apply an experimental style incorporating many concrete examples to elementary school students. Furthermore, it can apply an experimental style emphasizing theoretical explanations to middle and high school students. For example, the control unit can use AI to analyze the participants' ages and levels of understanding and select an appropriate experimental style. This allows for the provision of an appropriate experimental style tailored to the participants' ages and levels of understanding. Some or all of the above-described processes in the control unit may be performed using AI, or not. For example, the control unit can input participant age and understanding data into a generating AI and have the generating AI select the experimental style.

[0123] The control unit can estimate the emotions of the participants and determine the priority of experiments based on the estimated emotions. For example, the control unit can estimate the emotions of the participants using speech analysis technology. For example, the control unit can analyze the tone and speed of the speech to estimate the emotions of the participants. The control unit can also estimate the emotions of the participants using facial recognition technology. For example, the control unit can analyze the facial expressions of the participants using a camera to estimate their emotions. Furthermore, the control unit can also estimate the emotions of the participants using text analysis technology. For example, the control unit can analyze the content of the participants' questions to estimate their emotions. This makes it possible to provide appropriate experiment priorities according to the emotions of the participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the control unit may be performed using AI, for example, or without AI. For example, the control unit can input image data of the participants captured by a camera into the generative AI and have the generative AI perform the estimation of the participants' emotions.

[0124] The control unit can prioritize highly relevant experiments by considering the geographical location of the participant during experiment control. For example, the control unit can identify the participant's location using geographical data. For example, the control unit can analyze GPS data to obtain the participant's location. The control unit can also select relevant experiments based on location information. For example, the control unit can prioritize experiments related to the climate of the region where the participant lives. Furthermore, the control unit can also prioritize experiments related to the history of the region where the participant lives. For example, the control unit can select experiment content considering the historical background of the region. This allows the control unit to provide highly relevant experiments based on the participant's geographical location. Some or all of the above processing in the control unit may be performed using AI, for example, or without AI. For example, the control unit can input the participant's location data into a generating AI and have the generating AI select relevant experiments.

[0125] The control unit can analyze the social media activity of participants and conduct relevant experiments during experiment control. For example, the control unit can analyze participants' social media activity using data mining techniques. For example, the control unit can analyze information on what participants have shared and the accounts they follow. The control unit can also analyze social media activity using machine learning algorithms. For example, the control unit can use AI to cluster social media posts and identify relevant experiments. Furthermore, the control unit can analyze patterns in social media activity and select the most suitable experiment. For example, the control unit can conduct experiments related to topics that participants are interested in. This allows the control unit to provide highly relevant experiments based on participants' social media activity. Some or all of the above processing in the control unit may be performed using AI, or not using AI. For example, the control unit can input social media data into a generating AI and have the generating AI select relevant experiments.

[0126] The assessment unit can estimate the learner's emotions and adjust the learning level determination method based on the estimated emotions. For example, the assessment unit can estimate the learner's emotions using speech analysis technology. For example, the assessment unit can analyze the tone and speed of the voice to estimate the learner's emotions. The assessment unit can also estimate the learner's emotions using facial recognition technology. For example, the assessment unit can analyze the learner's facial expressions using a camera to estimate their emotions. Furthermore, the assessment unit can also estimate the learner's emotions using text analysis technology. For example, the assessment unit can analyze the content of the learner's questions to estimate their emotions. This makes it possible to provide an appropriate learning level determination method that corresponds to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the assessment unit may be performed using AI, for example, or without using AI. For example, the judgment unit can input image data of the student captured by the camera into the generating AI, and have the generating AI perform the estimation of the student's emotions.

[0127] The assessment unit can select the optimal assessment method by referring to the learner's past learning history when determining their learning level. The assessment unit can analyze the learner's learning history using, for example, data mining techniques. For example, the assessment unit can analyze past learning content and evaluate the learner's level of understanding. The assessment unit can also analyze the learner's learning history using machine learning algorithms. For example, the assessment unit can cluster the learning history using AI and identify relevant assessment methods. Furthermore, the assessment unit can analyze patterns in the learning history and select the optimal assessment method. For example, the assessment unit can compare past learning content with the current learning status and select the optimal assessment method. This makes it possible to provide an optimal learning level assessment method based on the learner's past learning history. Some or all of the above processing in the assessment unit may be performed using, for example, AI, or without AI. For example, the assessment unit can input the learner's learning history data into a generating AI and have the generating AI perform the selection of the assessment method.

[0128] The assessment unit can apply different assessment criteria depending on the learner's age and level of understanding when determining their learning progress. For example, the assessment unit can use age-specific assessment criteria to determine the learning progress. For example, for preschoolers, the assessment unit can apply assessment criteria that make extensive use of simple language and illustrations. For elementary school students, the assessment unit can also apply assessment criteria that incorporate many concrete examples. Furthermore, for middle and high school students, the assessment unit can apply assessment criteria that emphasize theoretical explanations. For example, the assessment unit can use AI to analyze the learner's age and level of understanding and select appropriate assessment criteria. This allows the assessment unit to provide appropriate learning progress criteria according to the learner's age and level of understanding. Some or all of the above-described processes in the assessment unit may be performed using AI, or not using AI. For example, the assessment unit can input the learner's age and level of understanding data into a generating AI and have the generating AI select the assessment criteria.

[0129] The assessment unit can estimate the learner's emotions and determine the priority of learning levels based on the estimated emotions. The assessment unit can estimate the learner's emotions using, for example, speech analysis technology. For example, the assessment unit can analyze the tone and speed of the voice to estimate the learner's emotions. The assessment unit can also estimate the learner's emotions using facial recognition technology. For example, the assessment unit can analyze the learner's facial expressions using a camera to estimate their emotions. Furthermore, the assessment unit can also estimate the learner's emotions using text analysis technology. For example, the assessment unit can analyze the content of the learner's questions to estimate their emotions. This makes it possible to provide an appropriate priority of learning levels according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The 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 assessment unit may be performed using, for example, AI, or not using AI. For example, the judgment unit can input image data of the student captured by the camera into the generating AI, and have the generating AI perform the estimation of the student's emotions.

[0130] The assessment unit can make highly relevant assessments by considering the learner's geographical location information when determining their learning level. For example, the assessment unit can identify the learner's location information using geographical data. For example, the assessment unit can analyze GPS data to obtain the learner's location information. The assessment unit can also make relevant assessments based on location information. For example, the assessment unit can determine the learning level related to the climate of the area where the learner lives. Furthermore, the assessment unit can also determine the learning level related to the history of the area where the learner lives. For example, the assessment unit can determine the learning level by considering the historical background of the area. This makes it possible to provide highly relevant learning level assessments based on the learner's geographical location information. Some or all of the above processing in the assessment unit may be performed using AI, for example, or without using AI. For example, the assessment unit can input the learner's location information data into a generating AI and have the generating AI perform the relevant assessment.

[0131] The assessment unit can analyze the learner's social media activity and make relevant judgments when determining their learning level. For example, the assessment unit can analyze the learner's social media activity using data mining techniques. For example, the assessment unit can analyze information on what the learner has shared and the accounts they follow. The assessment unit can also analyze social media activity using machine learning algorithms. For example, the assessment unit can use AI to cluster social media posts and identify relevant judgments. Furthermore, the assessment unit can analyze patterns in social media activity and make optimal judgments. For example, the assessment unit can determine the learning level related to topics the learner is interested in. This allows for the provision of highly relevant learning level judgments based on the learner's social media activity. Some or all of the above processing in the assessment unit may be performed using AI, for example, or without AI. For example, the assessment unit can input social media data into a generating AI and have the generating AI perform relevant judgments.

[0132] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0133] STEM education systems can further estimate students' learning styles and customize lecture content based on those estimates. For example, visual learners can be provided with lectures that make extensive use of diagrams and graphs. Auditory learners can be provided with lectures that make extensive use of audio and music. Furthermore, practical learners can be provided with lectures that incorporate many experiments and hands-on activities. This allows for the provision of optimal lecture content tailored to each student's learning style. Learning styles can be estimated, for example, by analyzing questionnaires and past learning history. This maximizes the learning effectiveness for each student.

[0134] STEM education systems can further monitor students' learning progress in real time and adjust lecture content accordingly. For example, if a student is struggling with a particular topic, additional explanations or practice problems related to that topic can be provided. Conversely, if a student is progressing well, they can move on to the next topic. Furthermore, student progress data can be accumulated to create long-term learning plans. This maximizes the effectiveness of student learning. Progress monitoring can be done, for example, by analyzing quiz or test results in real time.

[0135] STEM education systems can further estimate learners' emotions and provide feedback based on those estimated emotions. For example, if a learner is excited, they can be offered praise and encouragement. If a learner is depressed, they can be offered comfort and encouragement. Furthermore, if a learner is focused, they can be encouraged to continue learning. This allows for the provision of appropriate feedback tailored to the learner's emotions. Emotion estimation can be performed using, for example, voice analysis or facial recognition technology.

[0136] STEM education systems can further analyze students' learning history and suggest optimal learning paths. For example, they can suggest topics to study next based on past learning content and performance. They can also suggest relevant topics based on students' interests and concerns. Furthermore, they can create long-term learning plans according to students' learning goals. This maximizes the effectiveness of students' learning. Learning path suggestions can be made using, for example, data mining techniques and machine learning algorithms.

[0137] STEM education systems can further estimate learners' emotions and adjust the learning environment based on those estimates. For example, if a learner is feeling stressed, relaxing music can be played. If a learner is concentrating, a quiet environment can be provided. Furthermore, if a learner is tired, a break can be encouraged. This allows for the provision of an optimal learning environment tailored to the learner's emotions. Emotion estimation can be performed using, for example, voice analysis or facial recognition technology.

[0138] STEM education systems can further analyze students' learning history and provide optimal learning resources. For example, they can suggest relevant textbooks and reference books based on past learning content and performance. They can also suggest relevant videos and articles based on students' interests. Furthermore, they can provide optimal learning resources according to students' learning goals. This maximizes the effectiveness of students' learning. Learning resource suggestions can be made using, for example, data mining techniques and machine learning algorithms.

[0139] The STEM education system can further estimate the learner's emotions and adjust the pace of learning based on those emotions. For example, if a learner is excited, the pace of learning can be increased. If a learner is tired, the pace of learning can be slowed down. Furthermore, if a learner is focused, learning can continue at the same pace. This allows for the provision of an optimal learning pace tailored to the learner's emotions. Emotion estimation can be performed using, for example, voice analysis or facial recognition technology.

[0140] STEM education systems can further analyze students' learning history and suggest optimal learning methods. For example, they can suggest effective learning methods based on past learning content and performance. They can also suggest relevant learning methods based on students' interests and concerns. Furthermore, they can suggest optimal learning methods according to students' learning goals. This maximizes the effectiveness of students' learning. Learning method suggestions can be made using, for example, data mining techniques and machine learning algorithms.

[0141] STEM education systems can further estimate learners' emotions and improve their learning motivation based on those estimated emotions. For example, if a learner is excited, they can be offered words of praise and encouragement. If a learner is depressed, they can be offered words of comfort and encouragement. Furthermore, if a learner is focused, they can be encouraged to continue learning. This allows for the provision of optimal motivational strategies tailored to the learner's emotions. Emotion estimation can be performed using, for example, voice analysis or facial recognition technology.

[0142] STEM education systems can further analyze students' learning history and set optimal learning goals. For example, realistic learning goals can be set based on past learning content and performance. Relevant learning goals can also be set based on students' interests and concerns. Furthermore, long-term learning plans can be created according to students' learning goals, thereby maximizing the effectiveness of their learning. Setting learning goals can be done, for example, using data mining techniques or machine learning algorithms.

[0143] The following briefly describes the processing flow for example form 2.

[0144] Step 1: The lecture generation unit generates audio for lectures on STEM fields using AI. For example, it generates lecture content using speech synthesis technology and natural language processing technology, inputs knowledge of STEM fields into the AI ​​model, and generates the lecture audio. Step 2: The output unit outputs the audio generated by the lecture generation unit through a speaker attached to the stuffed animal. For example, it outputs audio using a speaker and adjusts the tone and speed of the audio to provide audio suitable for the learner. Step 3: The reception desk receives audio questions from lecture participants using microphones attached to stuffed animals. For example, the microphone is used to receive the audio, and speech recognition technology is used to analyze the content of the questions. Step 4: The response generation unit generates answers based on the questions received by the reception unit. For example, it uses a generation AI to generate answers to questions and estimates the participant's emotions to generate appropriate answers. Step 5: The providing unit provides the answer generated by the answer generation unit. For example, the answer can be provided via voice using a speaker and displayed on the screen in text format.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] For example, the lecture generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the output unit is implemented by the control unit 46A of the smart device 14. For example, the reception unit is implemented by the microphone 38B and control unit 46A of the smart device 14. For example, the answer generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the provision unit is implemented by the speaker 40B and control unit 46A of the smart device 14. For example, the control unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the judgment unit is implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0149] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] For example, the lecture generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the output unit is implemented by the control unit 46A of the smart glasses 214. For example, the reception unit is implemented by the microphone 238 and control unit 46A of the smart glasses 214. For example, the answer generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the delivery unit is implemented by the speaker 240 and control unit 46A of the smart glasses 214. For example, the control unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the judgment unit is implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0165] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] For example, the lecture generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the output unit is implemented by the control unit 46A of the headset terminal 314. For example, the reception unit is implemented by the microphone 238 and control unit 46A of the headset terminal 314. For example, the answer generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the provision unit is implemented by the speaker 240 and control unit 46A of the headset terminal 314. For example, the control unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the judgment unit is implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0181] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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).

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.).

[0194] 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.

[0195] 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.

[0196] 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.

[0197] For example, the lecture generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the output unit is implemented by the control unit 46A of the stuffed animal 414. For example, the reception unit is implemented by the microphone 238 and control unit 46A of the stuffed animal 414. For example, the answer generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the delivery unit is implemented by the speaker 240 and control unit 46A of the stuffed animal 414. For example, the control unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the judgment unit is implemented by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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."

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] (Note 1) A lecture generation unit that uses AI to generate audio for lectures on STEM fields, An output unit that outputs the audio generated by the lecture generation unit from a speaker attached to the stuffed animal, A microphone attached to the stuffed animal serves as a reception unit that receives audio of questions from the lecture participants, An answer generation unit that generates an answer based on a question received by the reception unit, The system includes a providing unit that provides the answers generated by the answer generation unit. A system characterized by the following features. (Note 2) The aforementioned response generation unit, Generative AI generates answers to questions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned response generation unit, It estimates the emotions of the participants and generates responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned response generation unit, Analyze the learner's question history and generate answers based on the analysis results. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is The system generates responses based on the participant's current learning status or areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 6) It also includes a control unit that controls the stuffed animal to perform experiments. The system described in Appendix 1, characterized by the features described herein. (Note 7) The system further includes a judgment unit that analyzes the audio of questions received by the reception department and determines the learner's level of understanding based on the analysis results. The aforementioned lecture generation unit, The difficulty level of the lectures will be adjusted based on the students' learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned lecture generation unit, The system estimates the emotions of the participants and adjusts the content and tone of the lecture based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned lecture generation unit, We analyze the student's past learning history and select the most suitable lecture content. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned lecture generation unit, Apply different teaching styles depending on the age and level of understanding of the students. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned lecture generation unit, The system estimates the emotions of the participants and adjusts the length of the lecture based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned lecture generation unit, Incorporate highly relevant case studies based on the geographical location of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned lecture generation unit, Analyze students' social media activity and incorporate relevant topics into the lectures. The system described in Appendix 1, characterized by the features described herein. (Note 14) The output unit is, It estimates the learner's emotions and adjusts the tone and speed of the voice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The output unit is, Optimize the audio frequency based on the learner's auditory characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 16) The output unit is, The system detects ambient noise from the learner and automatically adjusts the audio volume. The system described in Appendix 1, characterized by the features described herein. (Note 17) The output unit is, It estimates the learner's emotions and adjusts the intonation of the voice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The output unit is, The optimal audio format is selected considering the participant's device information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The output unit is, Provides multilingual audio based on the learner's language settings. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned reception unit is We estimate the emotions of the participants and adjust the question-taking method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned reception unit is When receiving questions, the system will refer to the participant's past question history to select the most appropriate method of receiving questions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned reception unit is When questions are submitted, the system analyzes the pronunciation characteristics of the participants to improve the accuracy of speech recognition. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned reception unit is The system estimates the participants' emotions and prioritizes questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned reception unit is When accepting questions, priority will be given to questions that are highly relevant based on the participant's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned reception unit is When accepting questions, we analyze the participants' social media activity and accept related questions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned response generation unit, The system estimates the emotions of the participants and adjusts the content and tone of their responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned response generation unit, When generating answers, the system analyzes the participant's past question history and selects the most appropriate answer. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned response generation unit, When generating answers, different answer styles are applied depending on the age and level of understanding of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned response generation unit, The system estimates the participant's emotions and adjusts the length of their responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned response generation unit, When generating responses, relevant examples are incorporated based on the participant's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned response generation unit, When generating responses, analyze participants' social media activity and incorporate relevant topics into the answers. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned supply unit is, The system estimates the participants' emotions and adjusts the way responses are provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned supply unit is, When providing answers, the system will select the most suitable method of delivery by referring to the participant's past learning history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned supply unit is, When providing answers, the system detects the participant's ambient noise and automatically adjusts the audio volume. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned supply unit is, The system estimates the participants' emotions and adjusts the order in which responses are provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned supply unit is, When providing responses, the system selects the optimal audio format considering the participant's device information. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned supply unit is, When providing answers, multilingual audio will be provided based on the participant's language settings. The system described in Appendix 1, characterized by the features described herein. (Note 38) The control unit, We estimate the participants' emotions and adjust the experiment's progression based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 39) The control unit, During experimental control, the optimal control method is selected by referring to the participant's past experimental history. The system described in Appendix 2, characterized by the features described herein. (Note 40) The control unit, During experimental control, different experimental styles are applied depending on the age and level of understanding of the participants. The system described in Appendix 2, characterized by the features described herein. (Note 41) The control unit, Estimate the emotions of the learners and determine the priority order of experiments based on the estimated emotions The system according to Appendix 2, characterized in that it does the above (Appendix 42) The control unit During experiment control, preferentially conduct experiments with high relevance based on the geographical location information of the learners The system according to Appendix 2, characterized in that it does the above (Appendix 43) The control unit During experiment control, analyze the social media activities of the learners and conduct relevant experiments The system according to Appendix 2, characterized in that it does the above (Appendix 44) The determination unit Estimate the emotions of the learners and adjust the method for determining the learning degree based on the estimated emotions The system according to Appendix 3, characterized in that it does the above (Appendix 45) The determination unit During learning degree determination, select the optimal determination method by referring to the past learning history of the learners The system according to Appendix 3, characterized in that it does the above (Appendix 46) The determination unit During learning degree determination, apply different determination criteria according to the age and comprehension level of the learners The system according to Appendix 3, characterized in that it does the above (Appendix 47) The determination unit Estimate the emotions of the learners and determine the priority order of the learning degree based on the estimated emotions The system according to Appendix 3, characterized in that it does the above (Appendix 48) The determination unit During learning degree determination, conduct a determination with high relevance based on the geographical location information of the learners The system according to Appendix 3, characterized in that it does the above (Appendix 49) The determination unit During learning degree determination, analyze the social media activities of the learners and conduct relevant determinations The system according to appended note 3, characterized by the above.

Explanation of symbols

[0217] 10, 210, 310, 410 Data processing systems 12 Data processing devices 14 Smart devices 214 Smart glasses 314 Headset-type terminals 414 Robots

Claims

1. A lecture generation unit that uses AI to generate audio for lectures on the STEM field, An output unit that outputs the audio generated by the lecture generation unit from a speaker attached to the stuffed animal, A microphone attached to the stuffed animal serves as a reception unit that receives audio of questions from the lecture participants, An answer generation unit that generates an answer based on a question received by the reception unit, The system includes a providing unit that provides the answers generated by the answer generation unit. A system characterized by the following features.

2. The aforementioned response generation unit, Generative AI generates answers to questions. The system according to feature 1.

3. The aforementioned response generation unit, It estimates the emotions of the participants and generates responses based on those estimated emotions. The system according to feature 1.

4. The aforementioned response generation unit, Analyze the learner's question history and generate answers based on the analysis results. The system according to feature 1.

5. The aforementioned reception unit is The system generates responses based on the participant's current learning status or areas of interest. The system according to feature 1.

6. It also includes a control unit that controls the stuffed animal to perform experiments. The system according to feature 1.

7. The system further includes a determination unit that analyzes the audio of questions received by the reception unit and determines the learner's level of understanding based on the analysis results. The aforementioned lecture generation unit, The difficulty level of the lectures will be adjusted based on the students' learning progress. The system according to feature 1.

8. The aforementioned lecture generation unit, The system estimates the emotions of the participants and adjusts the content and tone of the lecture based on those estimated emotions. The system according to feature 1.

9. The aforementioned lecture generation unit, We analyze the student's past learning history and select the most suitable lecture content. The system according to feature 1.

Images