system

Abstract

The system according to this embodiment aims to evaluate the performance of instructors in teaching and provide suggestions for improvement. [Solution] The system according to the embodiment comprises an acquisition unit, an evaluation unit, and a provision unit. The acquisition unit acquires information on the instructor's learning guidance for AI students set in a scenario. The evaluation unit evaluates the instructor's performance based on the learning guidance information acquired by the acquisition unit. The provision unit provides the instructor with suggestions for improvement in learning guidance based on the evaluation results from the evaluation unit.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , , , , ,

[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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the performance of a lecturer's learning guidance has not been sufficiently objectively evaluated and improvement points have not been provided, leaving room for improvement.

[0005] The system according to the embodiment aims to evaluate the performance of a lecturer's learning guidance and provide improvement points.​​​​​​The system according to this embodiment comprises an acquisition unit, an evaluation unit, and a provision unit. The acquisition unit acquires information on the instructor's learning guidance for AI students set in a scenario. The evaluation unit evaluates the instructor's performance based on the learning guidance information acquired by the acquisition unit. The provision unit provides the instructor with suggestions for improvement in learning guidance based on the evaluation results from the evaluation unit. [Effects of the Invention]

[0007] The system according to this embodiment can evaluate the performance of instructors in teaching and provide suggestions for improvement. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The training system according to an embodiment of the present invention is a system using an AI student designed for learners and educational institutions. This training system acquires information on the instructor's guidance of the AI ​​student set in a scenario, evaluates the instructor's performance based on that information, and provides the instructor with areas for improvement in the guidance based on the evaluation results. The training system supports a variety of scenarios from beginner to advanced levels and provides real-time feedback. In addition, the AI ​​student simulates emotions, enabling the instructor to learn appropriate responses. For example, the training system acquires information on the instructor's guidance of the AI ​​student set in a scenario. For example, it acquires information such as explanations, questions, and feedback given by the instructor during the lesson. This information is collected by the acquisition unit. Next, the training system evaluates the instructor's performance based on the acquired information. The evaluation unit analyzes the acquired information and evaluates the instructor's teaching methods and the student's reactions. For example, it evaluates whether the instructor's explanations were easy to understand and whether the answers to questions were appropriate. Furthermore, the training system provides the instructor with areas for improvement in the guidance based on the evaluation results. The provision unit suggests which areas the instructor should improve based on the evaluation results. For example, it provides specific areas for improvement such as improving the way explanations are given or reviewing the timing of questions. Furthermore, the acquisition unit modifies the AI ​​student's emotions in real time based on the acquired learning guidance information. The modification unit simulates the student's emotions in response to the instructor's guidance, enabling instructors to learn appropriate responses. For example, if the AI ​​student finds the instructor's explanation difficult, the system simulates emotional changes such as the AI ​​student showing a confused expression. In addition, the training system includes a reception unit that accepts scenario settings. The reception unit allows instructors to customize scenarios to suit their needs. For example, they can set up scenarios to strengthen specific skills. This allows the training system to enable instructors to improve their teaching methods while receiving real-time feedback. Moreover, through the emotional changes of the AI ​​student, instructors can gain a deeper understanding of student reactions and learn appropriate responses. This improves instructors' teaching skills and enhances the quality of education provided to learners.This allows the training system to improve instructors' teaching skills and enhance the quality of education provided to learners.

[0029] The training system according to the embodiment comprises an acquisition unit, an evaluation unit, and a provision unit. The acquisition unit acquires information on the instructor's learning guidance to the AI ​​student set in the scenario. The acquisition unit acquires information such as explanations, questions, and feedback given by the instructor during the lesson. The acquisition unit can collect learning guidance information by converting the instructor's statements into text data using speech recognition technology, for example. The acquisition unit can also collect learning guidance information by recording the instructor's movements and facial expressions using a video camera. Furthermore, the acquisition unit can also collect the instructor's biometric data (heart rate and skin electrical activity) using sensors to acquire learning guidance information. The evaluation unit evaluates the instructor's performance based on the learning guidance information acquired by the acquisition unit. The evaluation unit evaluates, for example, whether the instructor's explanations were easy to understand and whether the answers to questions were appropriate. The evaluation unit can analyze and evaluate the content of the instructor's statements using natural language processing technology, for example. The evaluation unit can also analyze and evaluate the instructor's movements and facial expressions using machine learning algorithms. Furthermore, the evaluation unit can analyze biometric data to evaluate the instructor's stress level and concentration level. The provisioning unit provides instructors with areas for improvement in their teaching based on the evaluation results from the evaluation unit. For example, the provisioning unit suggests which areas the instructor should improve based on the evaluation results. The provisioning unit can present specific areas for improvement using, for example, text messages. It can also present areas for improvement visually using video messages. Furthermore, it can present areas for improvement audibly using voice messages. As a result, the training system according to this embodiment can improve the teaching skills of instructors and enhance the quality of education provided to learners.

[0030] The acquisition unit acquires information on the instructor's teaching methods to the AI ​​student set in the scenario. For example, the acquisition unit acquires information such as explanations, questions, and feedback given by the instructor during the lesson. Specifically, it can collect information on teaching methods by converting the instructor's speech into text data using speech recognition technology. The speech recognition technology analyzes the instructor's speech in real time and performs noise reduction and optimization of the speech model to generate accurate text data. The acquisition unit can also collect information on teaching methods by recording the instructor's movements and facial expressions using a video camera. The video camera captures high-resolution video and records the instructor's gestures and changes in facial expressions in detail. This provides comprehensive information on teaching methods, including the instructor's nonverbal communication. Furthermore, the acquisition unit can also collect information on teaching methods by collecting the instructor's biometric data (heart rate and skin electrical activity) using sensors. Biometric data is an important indicator of the instructor's stress level and concentration level, and by analyzing this data, the instructor's psychological state can be understood. For example, by monitoring fluctuations in heart rate and changes in skin electrical activity in real time, it is possible to identify the situations in which the instructor is feeling stressed. This allows the data acquisition unit to comprehensively collect information on the instructor's speech, actions, and psychological state, providing fundamental data for improving the quality of instruction.

[0031] The evaluation unit assesses the instructor's performance based on the learning instruction information acquired by the acquisition unit. For example, the evaluation unit assesses whether the instructor's explanations were easy to understand and whether their answers to questions were appropriate. Specifically, it can analyze and evaluate the instructor's speech using natural language processing technology. Natural language processing technology grammatically and semantically analyzes the instructor's speech to evaluate the clarity and logic of their explanations. The evaluation unit can also analyze and evaluate the instructor's actions and facial expressions using machine learning algorithms. Machine learning algorithms recognize patterns in the instructor's gestures and facial expressions to infer their emotions and intentions. For example, if an instructor is smiling while explaining, it can be determined that they are providing positive feedback. Furthermore, the evaluation unit can analyze biometric data to assess the instructor's stress level and concentration. Algorithms that analyze heart rate variability and skin electrical activity patterns are used for biometric data analysis. This allows the evaluation unit to identify situations in which the instructor is stressed or focused. For example, a sudden increase in heart rate can be inferred as a possible indication that the instructor is nervous. This allows the evaluation department to comprehensively assess the instructor's speech content, actions, and psychological state, enabling a multifaceted analysis of the instructor's performance.

[0032] The service provider provides instructors with areas for improvement in their teaching methods based on evaluation results from the evaluation department. For example, the service provider can indicate which areas instructors should improve based on the evaluation results. Specifically, specific areas for improvement can be presented using text messages. These text messages include concise and specific advice to make them easy for instructors to understand. The service provider can also present areas for improvement visually using video messages. Video messages make it easier for instructors to understand by visually explaining areas for improvement with specific scenarios and examples. Furthermore, the service provider can present areas for improvement audibly using audio messages. Audio messages allow instructors to review areas for improvement even when they are on the go or working on other tasks. This allows the service provider to provide instructors with areas for improvement in various formats, enabling them to receive specific advice to improve their teaching skills. In addition, the service provider can collect feedback from instructors and continuously improve the accuracy and effectiveness of the advice provided. For example, feedback on how instructors felt about the advice provided and how they implemented it can be collected and reflected in future advice. This allows the service provider to offer effective support to improve instructors' teaching skills and enhance the quality of education for learners.

[0033] The acquisition unit includes a modification unit that instantly changes the AI ​​student's emotions based on the acquired learning guidance information. The modification unit simulates emotional changes, for example, if the AI ​​student finds the instructor's explanation difficult, it may show a confused expression. The modification unit can change the student's emotions in response to the instructor's guidance in real time, for example, using a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. The modification unit can also simulate emotional changes, for example, if the AI ​​student finds the instructor's explanation easy to understand, it may show a joyful expression. Furthermore, the modification unit can simulate the student's emotions in response to the instructor's guidance in detail, enabling instructors to learn appropriate responses. In this way, instructors can learn appropriate responses by changing the AI ​​student's emotions in real time.

[0034] The training system includes a reception area that accepts scenario settings. This reception area allows instructors to customize scenarios to their specific needs. For example, it can set up scenarios to enhance particular skills. The reception area can also suggest optimal scenarios based on the instructor's needs, using, for example, generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The reception area can also suggest similar scenarios based on scenarios previously set by the instructor. Furthermore, the reception area can customize scenarios in real time according to the instructor's needs, providing optimal training. This allows instructors to customize scenarios to their specific needs.

[0035] The evaluation unit analyzes the acquired information and evaluates the instructor's teaching methods and the students' responses. For example, the evaluation unit evaluates whether the instructor's explanations were easy to understand and whether the answers to questions were appropriate. The evaluation unit can, for example, use generative AI to analyze the acquired information and evaluate the instructor's teaching methods and the students' responses. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The evaluation unit can also evaluate, for example, how the students received the instructor's explanations. Furthermore, the evaluation unit can evaluate the instructor's teaching methods and the students' responses in detail and improve the quality of instruction. In this way, the quality of instruction is improved by evaluating the instructor's teaching methods and the students' responses.

[0036] The service provider will, based on the evaluation results, suggest areas where the instructor should improve. For example, the service provider can analyze the evaluation results using a generative AI and suggest specific areas for improvement. The generative AI could be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. The service provider can also suggest specific areas for improvement, such as improving the instructor's explanation style or reviewing the timing of questions. Furthermore, the service provider can improve the instructor's teaching methods in detail based on the evaluation results, thereby enhancing their teaching skills. In this way, by suggesting specific areas for improvement based on the evaluation results, the service provider enhances the instructor's teaching skills.

[0037] The data acquisition unit analyzes the instructor's past teaching history and selects the optimal data acquisition method. For example, the data acquisition unit acquires information in similar situations based on the instructor's past successful teaching methods. For example, the data acquisition unit acquires information using a different approach to avoid the instructor's past unsuccessful teaching methods. For example, the data acquisition unit optimizes data acquisition for specific time periods and situations based on the instructor's past teaching history. This allows the optimal data acquisition method to be selected by analyzing past teaching history. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input past teaching history data into a generative AI and have the generative AI select the optimal data acquisition method.

[0038] The data acquisition unit filters learning guidance information based on the instructor's current teaching style and areas of interest. For example, if an instructor teaches based on a specific educational theory, the data acquisition unit prioritizes acquiring information related to that theory. For example, if an instructor is interested in a particular subject, the data acquisition unit prioritizes acquiring information related to that subject. For example, the data acquisition unit prioritizes acquiring specific examples and practical information in line with the instructor's teaching style. By filtering information based on the instructor's teaching style and areas of interest, more relevant information can be acquired. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input data on the instructor's teaching style and areas of interest into a generative AI and have the generative AI perform the information filtering.

[0039] The data acquisition unit prioritizes acquiring highly relevant information when acquiring learning guidance information, taking into account the instructor's geographical location. For example, if the instructor is in an urban area, the data acquisition unit prioritizes acquiring educational examples from urban areas. For example, if the instructor is in a rural area, the data acquisition unit prioritizes acquiring educational examples from rural areas. For example, if the instructor is in a specific region, the data acquisition unit prioritizes acquiring information related to the culture and customs of that region. In this way, by considering geographical location information, highly relevant information can be acquired preferentially. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input the instructor's geographical location information into a generative AI and have the generative AI acquire highly relevant information.

[0040] The data acquisition unit analyzes the instructor's social media activities and acquires relevant information when acquiring learning guidance information. For example, the data acquisition unit acquires relevant information based on educational resources shared by the instructor on social media. For example, the data acquisition unit acquires relevant information based on posts from educational experts followed by the instructor on social media. For example, the data acquisition unit acquires relevant information based on topics in educational communities in which the instructor participates on social media. This allows for the efficient acquisition of relevant information by analyzing social media activities. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input the instructor's social media activity data into a generative AI and have the generative AI acquire the relevant information.

[0041] The evaluation unit improves the accuracy of its evaluations by considering the interrelationships of learning instruction. For example, the evaluation unit evaluates the relationship between the instructor's explanations and questions to assess overall teaching ability. For example, the evaluation unit evaluates the relationship between the instructor's feedback and the student's response to assess the effectiveness of the instruction. For example, the evaluation unit evaluates the relationship between the instructor's teaching method and the student's learning outcomes to assess the effectiveness of the instruction. By considering the interrelationships of learning instruction, the accuracy of the evaluation is improved. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input data on the interrelationships of learning instruction into a generative AI and have the generative AI perform the improvement of evaluation accuracy.

[0042] The evaluation unit conducts evaluations while considering the instructor's attribute information. For example, the evaluation unit considers the instructor's years of experience and sets appropriate evaluation criteria. For example, the evaluation unit considers the instructor's field of expertise and conducts evaluations specific to that field. For example, the evaluation unit considers the instructor's educational background and sets individual evaluation criteria. This makes it possible to conduct more individualized evaluations by considering the instructor's attribute information. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the evaluation unit can input instructor attribute information data into a generative AI and have the generative AI perform the evaluation.

[0043] The evaluation unit conducts evaluations while considering the geographical distribution of learning instruction. For example, the evaluation unit compares educational examples from urban and rural areas and sets evaluation criteria for each region. For example, the evaluation unit considers the culture and customs of a particular region and conducts evaluations appropriate to that region. For example, the evaluation unit considers geographical factors and conducts evaluations appropriate to the educational environment of each region. In this way, by considering geographical distribution, it becomes possible to conduct evaluations that are appropriate to the characteristics of each region. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or it may be performed without using a generative AI. For example, the evaluation unit can input geographical distribution data into a generative AI and have the generative AI perform the evaluation.

[0044] The evaluation unit improves the accuracy of its evaluations by referring to relevant literature during the evaluation process. The evaluation unit updates its evaluation criteria by, for example, referring to the latest educational research. The evaluation unit improves the accuracy of its evaluations by, for example, referring to relevant educational theories. The evaluation unit conducts consistent evaluations by, for example, referring to past evaluation data. As a result, the accuracy of the evaluation is improved by referring to relevant literature. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input relevant literature data into a generative AI and have the generative AI perform the evaluation.

[0045] The service provider adjusts the level of detail based on the importance of the learning instruction when providing improvement suggestions. For example, the service provider provides detailed improvement suggestions for high-importance instruction points. For example, the service provider provides concise improvement suggestions for low-importance instruction points. The service provider adjusts the level of detail of the improvement suggestions based on the overall importance of the learning instruction. This allows for more appropriate feedback to be provided by adjusting the level of detail based on the importance of the learning instruction. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input learning instruction importance data into a generative AI and have the generative AI perform the adjustment of the level of detail of the improvement suggestions.

[0046] The service provider applies different presentation algorithms depending on the category of instruction when providing suggestions for improvement. For example, for theoretical instruction, the service provider provides suggestions for improvement with specific examples. For practical instruction, the service provider provides step-by-step suggestions for improvement. For instruction on communication skills, the service provider provides suggestions for improving feedback methods. This allows the service provider to provide optimal suggestions for improvement according to the category of instruction. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input instruction category data into a generative AI and have the generative AI execute the application of the presentation algorithm.

[0047] The provisioning unit prioritizes improvement suggestions based on the submission timing of the learning instruction. For example, it prioritizes improvements for recent instruction. For example, it provides improvements for past instruction according to their importance. The provisioning unit adjusts the priority of improvements based on the submission timing. This allows for the provision of improvements at a more appropriate time by prioritizing based on the submission timing. Some or all of the above processing in the provisioning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the provisioning unit can input learning instruction submission timing data into a generative AI and have the generative AI perform the priority determination.

[0048] The service provider adjusts the order of improvement suggestions based on their relevance to the learning instruction. For example, the service provider prioritizes providing improvement suggestions for highly relevant instruction points. For example, it postpones providing improvement suggestions for less relevant instruction points. The service provider adjusts the order of improvement suggestions based on the overall relevance of the learning instruction. This allows for more effective feedback by adjusting the order based on relevance. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input learning instruction relevance data into a generative AI and have the generative AI perform the order adjustment.

[0049] The modification unit simulates the optimal emotional change when the AI ​​student's emotions change, by referring to the instructor's past teaching history. For example, the modification unit simulates the AI ​​student's emotional change based on the instructor's past successful teaching methods. For example, the modification unit simulates different emotional changes to avoid the instructor's past unsuccessful teaching methods. For example, the modification unit simulates the optimal emotional change in a specific situation from the instructor's past teaching history. This allows for the simulation of optimal emotional changes by referring to past teaching history. Some or all of the above processing in the modification unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the modification unit can input past teaching history data into a generative AI and have the generative AI perform an emotional change simulation.

[0050] The modification unit adjusts the emotional state of the AI ​​student, taking into account the instructor's geographical location. For example, if the instructor is in an urban area, the modification unit adjusts the emotional state based on urban educational practices. If the instructor is in a rural area, the modification unit adjusts the emotional state based on rural educational practices. If the instructor is in a specific region, the modification unit adjusts the emotional state based on the culture and customs of that region. This allows for more appropriate emotional adjustments by considering geographical location information. Some or all of the above processing in the modification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the modification unit can input the instructor's geographical location information into a generative AI and have the generative AI perform the emotional adjustments.

[0051] The modification unit analyzes the instructor's social media activity to simulate emotional changes in AI students. For example, the modification unit simulates relevant emotional changes based on educational resources shared by the instructor on social media. For example, the modification unit simulates relevant emotional changes based on posts from educational experts followed by the instructor on social media. For example, the modification unit simulates relevant emotional changes based on topics in educational communities the instructor participates in on social media. This allows for the simulation of more appropriate emotional changes by analyzing social media activity. Some or all of the above processing in the modification unit may be performed using, for example, generative AI, or without generative AI. For example, the modification unit can input the instructor's social media activity data into a generative AI and have the generative AI perform an emotional change simulation.

[0052] The reception desk, upon receiving a scenario setting request, selects the optimal reception method by referring to the instructor's past scenario setting history. For example, the reception desk automatically displays scenarios that the instructor has frequently set in the past as candidates. For example, the reception desk prioritizes suggesting input methods (voice, text, etc.) that the instructor has used in the past. For example, the reception desk predicts and suggests scenarios to be used during a specific time period based on the instructor's past scenario setting history. This allows the reception desk to select the optimal reception method by referring to the past scenario setting history. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or without a generative AI. For example, the reception desk can input past scenario setting history data into a generative AI and have the generative AI select the optimal reception method.

[0053] The reception unit automatically acquires the instructor's current location information when a scenario is set up, simplifying the input process. For example, when the instructor opens the app, the reception unit automatically acquires their current location and sets it as the starting point for the scenario setting. For example, when the instructor sets up a scenario, the reception unit suggests the most suitable candidate location, taking into account the distance from their current location. For example, if the instructor uses the app while on the move, the reception unit updates their current location in real time and reflects it in the scenario setting. This simplifies the input process by automatically acquiring the current location information. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the reception unit can input the current location data into a generative AI and have the generative AI perform the input simplification.

[0054] The reception unit, upon receiving the scenario settings, selects the optimal reception method by considering the instructor's device information. For example, if the instructor is using a smartphone, the reception unit provides a reception method adapted to the screen size. For example, if the instructor is using a tablet, the reception unit provides a reception method optimized for a larger screen. For example, if the instructor is using a desktop, the reception unit provides detailed input options. This allows the reception unit to select the optimal reception method by considering the device information. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the instructor's device information data into a generative AI and have the generative AI select the optimal reception method.

[0055] The reception desk, upon receiving a scenario setting request, refers to the instructor's calendar information and makes suggestions based on their schedule. For example, the reception desk automatically sets the departure and destination for the scenario setting by referring to the schedule registered in the instructor's calendar. For example, the reception desk suggests locations related to a specific event as candidate locations based on the instructor's calendar information. For example, the reception desk proposes the optimal scenario tailored to the schedule based on the instructor's calendar information. This makes it possible to set the optimal scenario based on the schedule by referring to the calendar information. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the instructor's calendar information data into a generative AI and have the generative AI execute the suggestions.

[0056] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0057] The training system can analyze an instructor's past teaching history and provide optimal feedback based on that history. For example, it can provide feedback in similar situations based on the instructor's past successful teaching methods. It can also provide feedback on different approaches to help instructors avoid past unsuccessful teaching methods. Furthermore, it can provide optimal feedback for specific times of day or situations based on the instructor's past teaching history. In this way, by utilizing past teaching history, more effective feedback can be provided.

[0058] The training system can provide highly relevant educational examples by considering the instructor's geographical location. For example, if the instructor is in an urban area, it can prioritize providing educational examples from urban areas. Similarly, if the instructor is in a rural area, it can prioritize providing educational examples from rural areas. Furthermore, if the instructor is in a specific region, it can provide educational examples related to the culture and customs of that region. In this way, by considering geographical location, it can provide more relevant educational examples.

[0059] The training system can analyze instructors' social media activity and provide relevant educational resources based on that activity. For example, it can provide relevant information based on educational resources that instructors have shared on social media. It can also provide relevant information based on posts from educational professionals that instructors follow on social media. Furthermore, it can provide relevant information based on topics in educational communities that instructors participate in on social media. In this way, by analyzing social media activity, relevant educational resources can be provided efficiently.

[0060] The training system can provide the optimal feedback method by taking into account the instructor's device information. For example, if the instructor is using a smartphone, it can provide feedback methods adapted to the screen size. If the instructor is using a tablet, it can provide feedback methods optimized for larger screens. Furthermore, if the instructor is using a desktop computer, it can provide detailed input options. In this way, by considering device information, the system can provide the most suitable feedback method.

[0061] The training system can provide optimal, schedule-based feedback by referencing the instructor's calendar information. For example, it can adjust the timing of feedback based on the instructor's schedule. It can also provide feedback related to specific events based on the instructor's calendar information. Furthermore, it can provide optimal, schedule-based feedback based on the instructor's calendar information. In short, by referring to calendar information, optimal, schedule-based feedback can be provided.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The acquisition unit acquires information about the instructor's teaching methods to the AI ​​student set in the scenario. For example, the acquisition unit acquires information such as explanations, questions, and feedback given by the instructor during the lesson. The acquisition unit can use speech recognition technology to convert the instructor's speech into text data and collect information on teaching methods. It can also use a video camera to record the instructor's movements and facial expressions and collect information on teaching methods. Furthermore, it can use sensors to collect the instructor's biometric data (heart rate and skin electrical activity) and acquire information on teaching methods. Step 2: The evaluation unit evaluates the instructor's performance based on the learning instruction information acquired by the acquisition unit. The evaluation unit assesses whether the instructor's explanations were easy to understand and whether their answers to questions were appropriate. The evaluation unit can analyze and evaluate the content of the instructor's speech using natural language processing technology. It can also analyze and evaluate the instructor's actions and facial expressions using machine learning algorithms. Furthermore, it can analyze biometric data to evaluate the instructor's stress level and concentration level. Step 3: The service provider provides instructors with areas for improvement in their teaching methods based on the evaluation results from the evaluation department. The service provider indicates which areas the instructors should improve based on the evaluation results. The service provider can provide specific areas for improvement using text messages. They can also provide areas for improvement visually using video messages. Furthermore, they can provide areas for improvement audibly using voice messages.

[0064] (Example of form 2) The training system according to an embodiment of the present invention is a system using an AI student designed for learners and educational institutions. This training system acquires information on the instructor's guidance of the AI ​​student set in a scenario, evaluates the instructor's performance based on that information, and provides the instructor with areas for improvement in the guidance based on the evaluation results. The training system supports a variety of scenarios from beginner to advanced levels and provides real-time feedback. In addition, the AI ​​student simulates emotions, enabling the instructor to learn appropriate responses. For example, the training system acquires information on the instructor's guidance of the AI ​​student set in a scenario. For example, it acquires information such as explanations, questions, and feedback given by the instructor during the lesson. This information is collected by the acquisition unit. Next, the training system evaluates the instructor's performance based on the acquired information. The evaluation unit analyzes the acquired information and evaluates the instructor's teaching methods and the student's reactions. For example, it evaluates whether the instructor's explanations were easy to understand and whether the answers to questions were appropriate. Furthermore, the training system provides the instructor with areas for improvement in the guidance based on the evaluation results. The provision unit suggests which areas the instructor should improve based on the evaluation results. For example, it provides specific areas for improvement such as improving the way explanations are given or reviewing the timing of questions. Furthermore, the acquisition unit modifies the AI ​​student's emotions in real time based on the acquired learning guidance information. The modification unit simulates the student's emotions in response to the instructor's guidance, allowing instructors to learn appropriate responses. For example, if the AI ​​student finds the instructor's explanation difficult, the system simulates emotional changes such as the AI ​​student showing a confused expression. In addition, the training system includes a reception unit that accepts scenario settings. The reception unit allows instructors to customize scenarios to suit their needs. For example, they can set up scenarios to strengthen specific skills. This allows the training system to enable instructors to improve their teaching methods while receiving real-time feedback. Moreover, through the emotional changes of the AI ​​student, instructors can gain a deeper understanding of student reactions and learn appropriate responses. This improves instructors' teaching skills and enhances the quality of education provided to learners.This allows the training system to improve instructors' teaching skills and enhance the quality of education provided to learners.

[0065] The training system according to the embodiment comprises an acquisition unit, an evaluation unit, and a provision unit. The acquisition unit acquires information on the instructor's learning guidance to the AI ​​student set in the scenario. The acquisition unit acquires information such as explanations, questions, and feedback given by the instructor during the lesson. The acquisition unit can collect learning guidance information by converting the instructor's statements into text data using speech recognition technology, for example. The acquisition unit can also collect learning guidance information by recording the instructor's movements and facial expressions using a video camera. Furthermore, the acquisition unit can also collect the instructor's biometric data (heart rate and skin electrical activity) using sensors to acquire learning guidance information. The evaluation unit evaluates the instructor's performance based on the learning guidance information acquired by the acquisition unit. The evaluation unit evaluates, for example, whether the instructor's explanations were easy to understand and whether the answers to questions were appropriate. The evaluation unit can analyze and evaluate the content of the instructor's statements using natural language processing technology, for example. The evaluation unit can also analyze and evaluate the instructor's movements and facial expressions using machine learning algorithms. Furthermore, the evaluation unit can analyze biometric data to evaluate the instructor's stress level and concentration level. The provisioning unit provides instructors with areas for improvement in their teaching based on the evaluation results from the evaluation unit. For example, the provisioning unit suggests which areas the instructor should improve based on the evaluation results. The provisioning unit can present specific areas for improvement using, for example, text messages. It can also present areas for improvement visually using video messages. Furthermore, it can present areas for improvement audibly using voice messages. As a result, the training system according to this embodiment can improve the teaching skills of instructors and enhance the quality of education provided to learners.

[0066] The acquisition unit acquires information on the instructor's teaching methods to the AI ​​student set in the scenario. For example, the acquisition unit acquires information such as explanations, questions, and feedback given by the instructor during the lesson. Specifically, it can collect information on teaching methods by converting the instructor's speech into text data using speech recognition technology. The speech recognition technology analyzes the instructor's speech in real time and performs noise reduction and optimization of the speech model to generate accurate text data. The acquisition unit can also collect information on teaching methods by recording the instructor's movements and facial expressions using a video camera. The video camera captures high-resolution video and records the instructor's gestures and changes in facial expressions in detail. This provides comprehensive information on teaching methods, including the instructor's nonverbal communication. Furthermore, the acquisition unit can also collect information on teaching methods by collecting the instructor's biometric data (heart rate and skin electrical activity) using sensors. Biometric data is an important indicator of the instructor's stress level and concentration level, and by analyzing this data, the instructor's psychological state can be understood. For example, by monitoring fluctuations in heart rate and changes in skin electrical activity in real time, it is possible to identify the situations in which the instructor is feeling stressed. This allows the data acquisition unit to comprehensively collect information on the instructor's speech, actions, and psychological state, providing fundamental data for improving the quality of instruction.

[0067] The evaluation unit assesses the instructor's performance based on the learning instruction information acquired by the acquisition unit. For example, the evaluation unit assesses whether the instructor's explanations were easy to understand and whether their answers to questions were appropriate. Specifically, it can analyze and evaluate the instructor's speech using natural language processing technology. Natural language processing technology grammatically and semantically analyzes the instructor's speech to evaluate the clarity and logic of their explanations. The evaluation unit can also analyze and evaluate the instructor's actions and facial expressions using machine learning algorithms. Machine learning algorithms recognize patterns in the instructor's gestures and facial expressions to infer their emotions and intentions. For example, if an instructor is smiling while explaining, it can be determined that they are providing positive feedback. Furthermore, the evaluation unit can analyze biometric data to assess the instructor's stress level and concentration. Algorithms that analyze heart rate variability and skin electrical activity patterns are used for biometric data analysis. This allows the evaluation unit to identify situations in which the instructor is stressed or focused. For example, a sudden increase in heart rate can be inferred as a possible indication that the instructor is nervous. This allows the evaluation department to comprehensively assess the instructor's speech content, actions, and psychological state, enabling a multifaceted analysis of the instructor's performance.

[0068] The service provider provides instructors with areas for improvement in their teaching methods based on evaluation results from the evaluation department. For example, the service provider can indicate which areas instructors should improve based on the evaluation results. Specifically, specific areas for improvement can be presented using text messages. These text messages include concise and specific advice to make them easy for instructors to understand. The service provider can also present areas for improvement visually using video messages. Video messages make it easier for instructors to understand by visually explaining areas for improvement with specific scenarios and examples. Furthermore, the service provider can present areas for improvement audibly using audio messages. Audio messages allow instructors to review areas for improvement even when they are on the go or working on other tasks. This allows the service provider to provide instructors with areas for improvement in various formats, enabling them to receive specific advice to improve their teaching skills. In addition, the service provider can collect feedback from instructors and continuously improve the accuracy and effectiveness of the advice provided. For example, feedback on how instructors felt about the advice provided and how they implemented it can be collected and reflected in future advice. This allows the service provider to offer effective support to improve instructors' teaching skills and enhance the quality of education for learners.

[0069] The acquisition unit includes a modification unit that instantly changes the AI ​​student's emotions based on the acquired learning guidance information. The modification unit simulates emotional changes, for example, if the AI ​​student finds the instructor's explanation difficult, it may show a confused expression. The modification unit can change the student's emotions in response to the instructor's guidance in real time, for example, using a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. The modification unit can also simulate emotional changes, for example, if the AI ​​student finds the instructor's explanation easy to understand, it may show a joyful expression. Furthermore, the modification unit can simulate the student's emotions in response to the instructor's guidance in detail, enabling instructors to learn appropriate responses. In this way, instructors can learn appropriate responses by changing the AI ​​student's emotions in real time.

[0070] The training system includes a reception area that accepts scenario settings. This reception area allows instructors to customize scenarios to their specific needs. For example, it can set up scenarios to enhance particular skills. The reception area can also suggest optimal scenarios based on the instructor's needs, using, for example, generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The reception area can also suggest similar scenarios based on scenarios previously set by the instructor. Furthermore, the reception area can customize scenarios in real time according to the instructor's needs, providing optimal training. This allows instructors to customize scenarios to their specific needs.

[0071] The evaluation unit analyzes the acquired information and evaluates the instructor's teaching methods and the students' responses. For example, the evaluation unit evaluates whether the instructor's explanations were easy to understand and whether the answers to questions were appropriate. The evaluation unit can, for example, use generative AI to analyze the acquired information and evaluate the instructor's teaching methods and the students' responses. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. The evaluation unit can also evaluate, for example, how the students received the instructor's explanations. Furthermore, the evaluation unit can evaluate the instructor's teaching methods and the students' responses in detail and improve the quality of instruction. In this way, the quality of instruction is improved by evaluating the instructor's teaching methods and the students' responses.

[0072] The service provider will, based on the evaluation results, suggest areas where the instructor should improve. For example, the service provider can analyze the evaluation results using a generative AI and suggest specific areas for improvement. The generative AI could be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. The service provider can also suggest specific areas for improvement, such as improving the instructor's explanation style or reviewing the timing of questions. Furthermore, the service provider can improve the instructor's teaching methods in detail based on the evaluation results, thereby enhancing their teaching skills. In this way, by suggesting specific areas for improvement based on the evaluation results, the service provider enhances the instructor's teaching skills.

[0073] The data acquisition unit estimates the instructor's emotions and adjusts the timing of acquiring learning guidance information based on those emotions. For example, if the instructor is relaxed, the data acquisition unit acquires information during the lesson, collecting data in a natural flow. For example, if the instructor is nervous, the data acquisition unit acquires information after the lesson ends, reducing the instructor's burden. For example, if the instructor is focused, the data acquisition unit acquires information immediately after important teaching points, collecting detailed data. By adjusting the timing of information acquisition according to the instructor's emotions, more appropriate data can be collected. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the data acquisition unit can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0074] The data acquisition unit analyzes the instructor's past teaching history and selects the optimal data acquisition method. For example, the data acquisition unit acquires information in similar situations based on the instructor's past successful teaching methods. For example, the data acquisition unit acquires information using a different approach to avoid the instructor's past unsuccessful teaching methods. For example, the data acquisition unit optimizes data acquisition for specific time periods and situations based on the instructor's past teaching history. This allows the optimal data acquisition method to be selected by analyzing past teaching history. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input past teaching history data into a generative AI and have the generative AI select the optimal data acquisition method.

[0075] The data acquisition unit filters learning guidance information based on the instructor's current teaching style and areas of interest. For example, if an instructor teaches based on a specific educational theory, the data acquisition unit prioritizes acquiring information related to that theory. For example, if an instructor is interested in a particular subject, the data acquisition unit prioritizes acquiring information related to that subject. For example, the data acquisition unit prioritizes acquiring specific examples and practical information in line with the instructor's teaching style. By filtering information based on the instructor's teaching style and areas of interest, more relevant information can be acquired. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input data on the instructor's teaching style and areas of interest into a generative AI and have the generative AI perform the information filtering.

[0076] The data acquisition unit estimates the instructor's emotions and determines the priority of learning guidance information to acquire based on those emotions. For example, if the instructor is stressed, the data acquisition unit prioritizes acquiring information of high importance. For example, if the instructor is relaxed, the data acquisition unit prioritizes acquiring detailed information. For example, if the instructor is focused, the data acquisition unit prioritizes acquiring information related to a specific topic. In this way, by prioritizing information based on the instructor's emotions, important information can be acquired preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the data acquisition unit can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0077] The data acquisition unit prioritizes acquiring highly relevant information when acquiring learning guidance information, taking into account the instructor's geographical location. For example, if the instructor is in an urban area, the data acquisition unit prioritizes acquiring educational examples from urban areas. For example, if the instructor is in a rural area, the data acquisition unit prioritizes acquiring educational examples from rural areas. For example, if the instructor is in a specific region, the data acquisition unit prioritizes acquiring information related to the culture and customs of that region. In this way, by considering geographical location information, highly relevant information can be acquired preferentially. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input the instructor's geographical location information into a generative AI and have the generative AI acquire highly relevant information.

[0078] The data acquisition unit analyzes the instructor's social media activities and acquires relevant information when acquiring learning guidance information. For example, the data acquisition unit acquires relevant information based on educational resources shared by the instructor on social media. For example, the data acquisition unit acquires relevant information based on posts from educational experts followed by the instructor on social media. For example, the data acquisition unit acquires relevant information based on topics in educational communities in which the instructor participates on social media. This allows for the efficient acquisition of relevant information by analyzing social media activities. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input the instructor's social media activity data into a generative AI and have the generative AI acquire the relevant information.

[0079] The evaluation unit estimates the instructor's emotions and adjusts the evaluation criteria based on those emotions. For example, if the instructor is nervous, the evaluation unit will relax the evaluation criteria to reduce stress. For example, if the instructor is relaxed, the evaluation unit will tighten the evaluation criteria and provide detailed feedback. For example, if the instructor is focused, the evaluation unit will set evaluation criteria that focus on specific teaching skills. This allows for more appropriate evaluation by adjusting the evaluation criteria based on the instructor'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. For example, the evaluation unit can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0080] The evaluation unit improves the accuracy of its evaluations by considering the interrelationships of learning instruction. For example, the evaluation unit evaluates the relationship between the instructor's explanations and questions to assess overall teaching ability. For example, the evaluation unit evaluates the relationship between the instructor's feedback and the student's response to assess the effectiveness of the instruction. For example, the evaluation unit evaluates the relationship between the instructor's teaching method and the student's learning outcomes to assess the effectiveness of the instruction. By considering the interrelationships of learning instruction, the accuracy of the evaluation is improved. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the evaluation unit can input data on the interrelationships of learning instruction into a generative AI and have the generative AI perform the improvement of evaluation accuracy.

[0081] The evaluation unit conducts evaluations while considering the instructor's attribute information. For example, the evaluation unit considers the instructor's years of experience and sets appropriate evaluation criteria. For example, the evaluation unit considers the instructor's field of expertise and conducts evaluations specific to that field. For example, the evaluation unit considers the instructor's educational background and sets individual evaluation criteria. This makes it possible to conduct more individualized evaluations by considering the instructor's attribute information. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the evaluation unit can input instructor attribute information data into a generative AI and have the generative AI perform the evaluation.

[0082] The evaluation unit estimates the instructor's emotions and adjusts the display order of evaluation results based on those emotions. For example, if the instructor is nervous, the evaluation unit displays positive evaluation results first to provide reassurance. For example, if the instructor is relaxed, the evaluation unit displays detailed evaluation results in a sequential manner. For example, if the instructor is focused, the evaluation unit displays important evaluation results first to provide efficient feedback. In this way, more effective feedback can be provided by adjusting the display order of evaluation results based on the instructor'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. For example, the evaluation unit can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0083] The evaluation unit conducts evaluations while considering the geographical distribution of learning instruction. For example, the evaluation unit compares educational examples from urban and rural areas and sets evaluation criteria for each region. For example, the evaluation unit considers the culture and customs of a particular region and conducts evaluations appropriate to that region. For example, the evaluation unit considers geographical factors and conducts evaluations appropriate to the educational environment of each region. In this way, by considering geographical distribution, it becomes possible to conduct evaluations that are appropriate to the characteristics of each region. Some or all of the above processing in the evaluation unit may be performed using, for example, a generative AI, or it may be performed without using a generative AI. For example, the evaluation unit can input geographical distribution data into a generative AI and have the generative AI perform the evaluation.

[0084] The evaluation unit improves the accuracy of its evaluations by referring to relevant literature during the evaluation process. The evaluation unit updates its evaluation criteria by, for example, referring to the latest educational research. The evaluation unit improves the accuracy of its evaluations by, for example, referring to relevant educational theories. The evaluation unit conducts consistent evaluations by, for example, referring to past evaluation data. As a result, the accuracy of the evaluation is improved by referring to relevant literature. Some or all of the above processes in the evaluation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the evaluation unit can input relevant literature data into a generative AI and have the generative AI perform the evaluation.

[0085] The service provider estimates the instructor's emotions and adjusts the way improvement suggestions are presented based on those emotions. For example, if the instructor is nervous, the service provider will present simple and easy-to-understand improvement suggestions. If the instructor is relaxed, the service provider will present detailed improvement suggestions. If the instructor is focused, the service provider will present specific improvement suggestions and provide practical advice. By adjusting the way improvement suggestions are presented based on the instructor's emotions, more effective feedback can be provided. 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. For example, the service provider can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0086] The service provider adjusts the level of detail based on the importance of the learning instruction when providing improvement suggestions. For example, the service provider provides detailed improvement suggestions for high-importance instruction points. For example, the service provider provides concise improvement suggestions for low-importance instruction points. The service provider adjusts the level of detail of the improvement suggestions based on the overall importance of the learning instruction. This allows for more appropriate feedback to be provided by adjusting the level of detail based on the importance of the learning instruction. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input learning instruction importance data into a generative AI and have the generative AI perform the adjustment of the level of detail of the improvement suggestions.

[0087] The service provider applies different presentation algorithms depending on the category of instruction when providing suggestions for improvement. For example, for theoretical instruction, the service provider provides suggestions for improvement with specific examples. For practical instruction, the service provider provides step-by-step suggestions for improvement. For instruction on communication skills, the service provider provides suggestions for improving feedback methods. This allows the service provider to provide optimal suggestions for improvement according to the category of instruction. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input instruction category data into a generative AI and have the generative AI execute the application of the presentation algorithm.

[0088] The service provider estimates the instructor's emotions and adjusts the length of the improvement suggestions based on those emotions. For example, if the instructor is nervous, the service provider will provide short, concise improvement suggestions. If the instructor is relaxed, the service provider will provide detailed improvement suggestions. If the instructor is focused, the service provider will provide specific improvement suggestions and practical advice. By adjusting the length of the improvement suggestions based on the instructor's emotions, more effective feedback can be provided. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the service provider can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0089] The provisioning unit prioritizes improvement suggestions based on the submission timing of the learning instruction. For example, it prioritizes improvements for recent instruction. For example, it provides improvements for past instruction according to their importance. The provisioning unit adjusts the priority of improvements based on the submission timing. This allows for the provision of improvements at a more appropriate time by prioritizing based on the submission timing. Some or all of the above processing in the provisioning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the provisioning unit can input learning instruction submission timing data into a generative AI and have the generative AI perform the priority determination.

[0090] The service provider adjusts the order of improvement suggestions based on their relevance to the learning instruction. For example, the service provider prioritizes providing improvement suggestions for highly relevant instruction points. For example, it postpones providing improvement suggestions for less relevant instruction points. The service provider adjusts the order of improvement suggestions based on the overall relevance of the learning instruction. This allows for more effective feedback by adjusting the order based on relevance. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input learning instruction relevance data into a generative AI and have the generative AI perform the order adjustment.

[0091] The modification unit estimates the instructor's emotions and adjusts the timing of the AI ​​student's emotional changes based on those emotions. For example, if the instructor is nervous, the modification unit delays the AI ​​student's emotional changes to reduce the instructor's burden. For example, if the instructor is relaxed, the modification unit speeds up the AI ​​student's emotional changes to provide real-time feedback. For example, if the instructor is focused, the modification unit performs the AI ​​student's emotional changes immediately after important teaching points. This allows for more appropriate feedback by adjusting the timing of emotional changes based on the instructor's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the modification unit can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0092] The modification unit selects the type of emotion based on the instructor's teaching style when the AI ​​student's emotions change. For example, if the instructor has a strict teaching style, the modification unit will show the AI ​​student as tense. If the instructor has a gentle teaching style, the modification unit will show the AI ​​student as relaxed. If the instructor has a humorous teaching style, the modification unit will show the AI ​​student as enjoying itself. By selecting the type of emotion based on the teaching style, more appropriate feedback can be provided. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the modification unit can input the instructor's teaching style data into the generative AI and have the generative AI perform the selection of the type of emotion.

[0093] The modification unit simulates the optimal emotional change when the AI ​​student's emotions change, by referring to the instructor's past teaching history. For example, the modification unit simulates the AI ​​student's emotional change based on the instructor's past successful teaching methods. For example, the modification unit simulates different emotional changes to avoid the instructor's past unsuccessful teaching methods. For example, the modification unit simulates the optimal emotional change in a specific situation from the instructor's past teaching history. This allows for the simulation of optimal emotional changes by referring to past teaching history. Some or all of the above processing in the modification unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the modification unit can input past teaching history data into a generative AI and have the generative AI perform an emotional change simulation.

[0094] The modification unit estimates the instructor's emotions and, based on those emotions, determines the priority of emotional changes for the AI ​​student. For example, if the instructor is nervous, the modification unit prioritizes high-priority emotional changes. If the instructor is relaxed, the modification unit prioritizes detailed emotional changes. If the instructor is focused, the modification unit prioritizes emotional changes related to a specific topic. This allows for more appropriate feedback by prioritizing emotional changes based on the instructor's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the modification unit can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0095] The modification unit adjusts the emotional state of the AI ​​student, taking into account the instructor's geographical location. For example, if the instructor is in an urban area, the modification unit adjusts the emotional state based on urban educational practices. If the instructor is in a rural area, the modification unit adjusts the emotional state based on rural educational practices. If the instructor is in a specific region, the modification unit adjusts the emotional state based on the culture and customs of that region. This allows for more appropriate emotional adjustments by considering geographical location information. Some or all of the above processing in the modification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the modification unit can input the instructor's geographical location information into a generative AI and have the generative AI perform the emotional adjustments.

[0096] The modification unit analyzes the instructor's social media activity to simulate emotional changes in AI students. For example, the modification unit simulates relevant emotional changes based on educational resources shared by the instructor on social media. For example, the modification unit simulates relevant emotional changes based on posts from educational experts followed by the instructor on social media. For example, the modification unit simulates relevant emotional changes based on topics in educational communities the instructor participates in on social media. This allows for the simulation of more appropriate emotional changes by analyzing social media activity. Some or all of the above processing in the modification unit may be performed using, for example, generative AI, or without generative AI. For example, the modification unit can input the instructor's social media activity data into a generative AI and have the generative AI perform an emotional change simulation.

[0097] The reception desk estimates the instructor's emotions and adjusts the scenario setting reception method based on those emotions. For example, if the instructor is nervous, the reception desk provides a simple interface and minimizes the input steps. If the instructor is relaxed, the reception desk provides detailed input options and suggests a customizable input method. If the instructor is in a hurry, the reception desk prioritizes voice input to allow for quick scenario setting. This allows for more appropriate scenario setting by adjusting the reception method based on the instructor's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. For example, the reception desk can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0098] The reception desk, upon receiving a scenario setting request, selects the optimal reception method by referring to the instructor's past scenario setting history. For example, the reception desk automatically displays scenarios that the instructor has frequently set in the past as candidates. For example, the reception desk prioritizes suggesting input methods (voice, text, etc.) that the instructor has used in the past. For example, the reception desk predicts and suggests scenarios to be used during a specific time period based on the instructor's past scenario setting history. This allows the reception desk to select the optimal reception method by referring to the past scenario setting history. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or without a generative AI. For example, the reception desk can input past scenario setting history data into a generative AI and have the generative AI select the optimal reception method.

[0099] The reception unit automatically acquires the instructor's current location information when a scenario is set up, simplifying the input process. For example, when the instructor opens the app, the reception unit automatically acquires their current location and sets it as the starting point for the scenario setting. For example, when the instructor sets up a scenario, the reception unit suggests the most suitable candidate location, taking into account the distance from their current location. For example, if the instructor uses the app while on the move, the reception unit updates their current location in real time and reflects it in the scenario setting. This simplifies the input process by automatically acquiring the current location information. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the reception unit can input the current location data into a generative AI and have the generative AI perform the input simplification.

[0100] The reception desk estimates the instructor's emotions and adjusts the input interface design based on those emotions. For example, if the instructor is nervous, the reception desk provides an interface with calming colors to reduce visual stress. For example, if the instructor is enjoying themselves, the reception desk provides an interface with bright colors to make the input process more enjoyable. For example, if the instructor is tired, the reception desk provides a simple and highly visible interface to facilitate the input process. In this way, a more comfortable input environment can be provided by adjusting the interface design based on the instructor'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. For example, the reception desk can input the instructor's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0101] The reception unit, upon receiving the scenario settings, selects the optimal reception method by considering the instructor's device information. For example, if the instructor is using a smartphone, the reception unit provides a reception method adapted to the screen size. For example, if the instructor is using a tablet, the reception unit provides a reception method optimized for a larger screen. For example, if the instructor is using a desktop, the reception unit provides detailed input options. This allows the reception unit to select the optimal reception method by considering the device information. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the instructor's device information data into a generative AI and have the generative AI select the optimal reception method.

[0102] The reception desk, upon receiving a scenario setting request, refers to the instructor's calendar information and makes suggestions based on their schedule. For example, the reception desk automatically sets the departure and destination for the scenario setting by referring to the schedule registered in the instructor's calendar. For example, the reception desk suggests locations related to a specific event as candidate locations based on the instructor's calendar information. For example, the reception desk proposes the optimal scenario tailored to the schedule based on the instructor's calendar information. This makes it possible to set the optimal scenario based on the schedule by referring to the calendar information. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the instructor's calendar information data into a generative AI and have the generative AI execute the suggestions.

[0103] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0104] The training system aims to improve instructors' teaching skills by estimating their emotions and adjusting the content of feedback accordingly. For example, if an instructor is nervous, the feedback can be focused on positive content to provide reassurance. If the instructor is relaxed, detailed feedback can be provided, suggesting specific areas for improvement. Furthermore, if the instructor is focused, feedback can be provided that focuses on key teaching points, promoting efficient improvement in teaching. By providing feedback tailored to the instructor's emotions, it is expected that more effective improvement in teaching skills can be achieved.

[0105] The training system can analyze an instructor's past teaching history and provide optimal feedback based on that history. For example, it can provide feedback in similar situations based on the instructor's past successful teaching methods. It can also provide feedback on different approaches to help instructors avoid past unsuccessful teaching methods. Furthermore, it can provide optimal feedback for specific times of day or situations based on the instructor's past teaching history. In this way, by utilizing past teaching history, more effective feedback can be provided.

[0106] The training system can estimate the instructor's emotions and adjust the AI ​​student's emotional changes based on those emotions. For example, if the instructor is nervous, the AI ​​student's emotional changes can be delayed to reduce the instructor's burden. Conversely, if the instructor is relaxed, the AI ​​student's emotional changes can be accelerated to provide real-time feedback. Furthermore, if the instructor is focused, the AI ​​student's emotional changes can be triggered immediately after important teaching points. This allows for more appropriate feedback by adjusting the timing of emotional changes based on the instructor's emotions.

[0107] The training system can provide highly relevant educational examples by considering the instructor's geographical location. For example, if the instructor is in an urban area, it can prioritize providing educational examples from urban areas. Similarly, if the instructor is in a rural area, it can prioritize providing educational examples from rural areas. Furthermore, if the instructor is in a specific region, it can provide educational examples related to the culture and customs of that region. In this way, by considering geographical location, it can provide more relevant educational examples.

[0108] The training system can estimate the instructor's emotions and adjust the evaluation criteria based on those emotions. For example, if the instructor is nervous, the evaluation criteria can be relaxed to reduce stress. Conversely, if the instructor is relaxed, the evaluation criteria can be made stricter to provide more detailed feedback. Furthermore, if the instructor is focused, evaluation criteria can be set to focus on specific teaching skills. This allows for more appropriate evaluations by adjusting the evaluation criteria based on the instructor's emotions.

[0109] The training system can analyze instructors' social media activity and provide relevant educational resources based on that activity. For example, it can provide relevant information based on educational resources that instructors have shared on social media. It can also provide relevant information based on posts from educational professionals that instructors follow on social media. Furthermore, it can provide relevant information based on topics in educational communities that instructors participate in on social media. In this way, by analyzing social media activity, relevant educational resources can be provided efficiently.

[0110] The training system can estimate the instructor's emotions and adjust how improvement points are presented based on those emotions. For example, if the instructor is nervous, it can present simple and easy-to-understand improvement points. If the instructor is relaxed, it can present detailed improvement points. Furthermore, if the instructor is focused, it can present specific improvement points and provide practical advice. In this way, by adjusting how improvement points are presented based on the instructor's emotions, more effective feedback can be provided.

[0111] The training system can provide the optimal feedback method by taking into account the instructor's device information. For example, if the instructor is using a smartphone, it can provide feedback methods adapted to the screen size. If the instructor is using a tablet, it can provide feedback methods optimized for larger screens. Furthermore, if the instructor is using a desktop computer, it can provide detailed input options. In this way, by considering device information, the system can provide the most suitable feedback method.

[0112] The training system can estimate the instructor's emotions and adjust the display order of evaluation results based on those emotions. For example, if the instructor is nervous, positive evaluation results can be displayed first to provide reassurance. If the instructor is relaxed, detailed evaluation results can be displayed in a more sequential manner. Furthermore, if the instructor is focused, important evaluation results can be displayed first to provide efficient feedback. In this way, by adjusting the display order of evaluation results based on the instructor's emotions, more effective feedback can be provided.

[0113] The training system can provide optimal, schedule-based feedback by referencing the instructor's calendar information. For example, it can adjust the timing of feedback based on the instructor's schedule. It can also provide feedback related to specific events based on the instructor's calendar information. Furthermore, it can provide optimal, schedule-based feedback based on the instructor's calendar information. In short, by referring to calendar information, optimal, schedule-based feedback can be provided.

[0114] The following briefly describes the processing flow for example form 2.

[0115] Step 1: The acquisition unit acquires information about the instructor's teaching methods to the AI ​​student set in the scenario. For example, the acquisition unit acquires information such as explanations, questions, and feedback given by the instructor during the lesson. The acquisition unit can use speech recognition technology to convert the instructor's speech into text data and collect information on teaching methods. It can also use a video camera to record the instructor's movements and facial expressions and collect information on teaching methods. Furthermore, it can use sensors to collect the instructor's biometric data (heart rate and skin electrical activity) and acquire information on teaching methods. Step 2: The evaluation unit evaluates the instructor's performance based on the learning instruction information acquired by the acquisition unit. The evaluation unit assesses whether the instructor's explanations were easy to understand and whether their answers to questions were appropriate. The evaluation unit can analyze and evaluate the content of the instructor's speech using natural language processing technology. It can also analyze and evaluate the instructor's actions and facial expressions using machine learning algorithms. Furthermore, it can analyze biometric data to evaluate the instructor's stress level and concentration level. Step 3: The service provider provides instructors with areas for improvement in their teaching methods based on the evaluation results from the evaluation department. The service provider indicates which areas the instructors should improve based on the evaluation results. The service provider can provide specific areas for improvement using text messages. They can also provide areas for improvement visually using video messages. Furthermore, they can provide areas for improvement audibly using voice messages.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] For example, the acquisition unit uses the camera 42 and microphone 38B of the smart device 14 to acquire information such as the instructor's explanations, questions, and feedback. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, which analyzes the acquired information and evaluates the instructor's teaching methods and the students' reactions. The provision unit is implemented, for example, by the control unit 46A of the smart device 14, which presents specific areas for improvement to the instructor based on the evaluation results. The modification unit is implemented, for example, by the control unit 46A of the smart device 14, which changes the AI ​​student's emotions towards the instructor's instruction in real time. The reception unit is implemented, for example, by the control unit 46A of the smart device 14, which allows the instructor to customize the scenario. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0120] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] For example, the acquisition unit uses the camera 42 and microphone 238 of the smart glasses 214 to acquire information such as the instructor's explanations, questions, and feedback. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, which analyzes the acquired information and evaluates the instructor's teaching methods and the student's reactions. The provision unit is implemented, for example, by the control unit 46A of the smart glasses 214, which presents the instructor with specific areas for improvement based on the evaluation results. The modification unit is implemented, for example, by the control unit 46A of the smart glasses 214, which changes the AI ​​student's emotions towards the instructor's instruction in real time. The reception unit is implemented, for example, by the control unit 46A of the smart glasses 214, which allows the instructor to customize the scenario. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0136] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] For example, the acquisition unit uses the camera 42 and microphone 238 of the headset terminal 314 to acquire information such as the instructor's explanations, questions, and feedback. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, which analyzes the acquired information and evaluates the instructor's teaching methods and the students' reactions. The provision unit is implemented, for example, by the control unit 46A of the headset terminal 314, which presents specific areas for improvement to the instructor based on the evaluation results. The modification unit is implemented, for example, by the control unit 46A of the headset terminal 314, which changes the AI ​​student's emotions towards the instructor's instruction in real time. The reception unit is implemented, for example, by the control unit 46A of the headset terminal 314, which allows the instructor to customize the scenario. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0152] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] For example, the acquisition unit uses the camera 42 and microphone 238 of the robot 414 to acquire information such as the instructor's explanations, questions, and feedback. The evaluation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, which analyzes the acquired information and evaluates the instructor's teaching methods and the students' reactions. The provision unit is implemented, for example, by the control unit 46A of the robot 414, which presents specific areas for improvement to the instructor based on the evaluation results. The modification unit is implemented, for example, by the control unit 46A of the robot 414, which changes the AI ​​student's emotions towards the instructor's instruction in real time. The reception unit is implemented, for example, by the control unit 46A of the robot 414, which allows the instructor to customize the scenario. The correspondence between each unit and the devices and control units is not limited to the examples described above, and various modifications are possible.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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."

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] (Note 1) An acquisition unit that acquires information on the instructor's learning guidance for the AI ​​student set in the scenario, An evaluation unit that evaluates the instructor's performance based on the learning guidance information acquired by the acquisition unit, The system includes a provisioning unit that provides the instructor with suggestions for improvement in the learning instruction based on the evaluation results from the evaluation unit. A system characterized by the following features. (Note 2) The acquisition unit is, It includes a modification function that instantly changes the emotions of the AI ​​student based on acquired learning guidance information. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a reception desk for accepting scenario settings. The system described in Appendix 1, characterized by the features described herein. (Note 4) The evaluation unit described above, The acquired information is analyzed to evaluate the instructor's teaching methods and the students' responses. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, Based on the evaluation results, the instructor will indicate which areas need improvement. The system described in Appendix 1, characterized by the features described herein. (Note 6) The acquisition unit is, The system estimates the instructor's emotions and adjusts the timing of acquiring learning guidance information based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, Analyze the instructor's past teaching history and select the most suitable method of acquisition. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, When acquiring information on teaching methods, filtering is performed based on the instructor's current teaching style and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, The system estimates the instructor's emotions and prioritizes the learning guidance information to be acquired based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, When acquiring information for learning guidance, the system prioritizes acquiring highly relevant information by considering the geographical location of the instructors. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, When acquiring information on teaching methods, we analyze the instructors' social media activity and obtain relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The evaluation unit described above, The system estimates the instructor's emotions and adjusts the evaluation criteria based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The evaluation unit described above, When evaluating, consider the interrelationships of learning instruction to improve the accuracy of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 14) The evaluation unit described above, During the evaluation process, the instructor's attribute information will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 15) The evaluation unit described above, The system estimates the instructor's emotions and adjusts the display order of evaluation results based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The evaluation unit described above, During evaluation, the geographical distribution of instructional materials should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 17) The evaluation unit described above, During the evaluation process, we refer to relevant literature to improve the accuracy of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned supply unit is, We estimate the instructor's emotions and adjust the way we present areas for improvement based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, When providing suggestions for improvement, adjust the level of detail based on the importance of the learning instruction. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When providing suggestions for improvement, different presentation algorithms are applied depending on the category of learning instruction. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, The system estimates the instructor's emotions and adjusts the length of the improvement suggestions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, When providing suggestions for improvement, prioritize them based on the submission deadline for learning guidance. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing suggestions for improvement, adjust the order based on their relevance to the learning instruction. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned modified part is, The system estimates the instructor's emotions and adjusts the timing of the AI ​​student's emotional changes based on those emotions. The system described in Appendix 2, characterized by the features described herein. (Note 25) The aforementioned modified part is, When the AI ​​student's emotions change, the system selects the type of emotion based on the instructor's teaching style. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned modified part is, When an AI student's emotions change, the system simulates the optimal emotional response by referencing the instructor's past teaching history. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned modified part is, The system estimates the instructor's emotions and uses those emotions to prioritize the emotional changes of the AI ​​student. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned modified part is, When an AI student's emotions change, the instructor's geographical location information is taken into consideration when adjusting the emotional response. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned modified part is, When an AI student's emotions change, the system analyzes the instructor's social media activity to simulate those changes. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned reception unit is We estimate the instructor's emotions and adjust the scenario setting acceptance method based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned reception unit is When receiving a scenario request, the system will refer to the instructor's past scenario setting history to select the most suitable method of acceptance. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned reception unit is When a scenario is submitted, the system automatically retrieves the instructor's current location information to simplify input. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned reception unit is The system estimates the instructor's emotions and adjusts the input interface design based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned reception unit is When receiving scenario settings, the system selects the most suitable registration method, taking into account the instructor's device information. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned reception unit is When receiving a scenario request, the instructor's calendar information will be referenced to provide a proposal based on their schedule. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0188] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An acquisition unit that acquires information on the instructor's learning guidance for the AI ​​student set in the scenario, An evaluation unit that evaluates the instructor's performance based on the learning guidance information acquired by the acquisition unit, The system includes a provisioning unit that provides the instructor with suggestions for improvement in the learning instruction based on the evaluation results from the evaluation unit. A system characterized by the following features.

2. The acquisition unit is, It includes a modification unit that instantly changes the emotions of the AI ​​student based on acquired learning guidance information. The system according to feature 1.

3. It has a reception desk for accepting scenario settings. The system according to feature 1.

4. The evaluation unit described above, The acquired information is analyzed to evaluate the instructor's teaching methods and the students' responses. The system according to feature 1.

5. The aforementioned supply unit is, Based on the evaluation results, the instructor will indicate which areas need improvement. The system according to feature 1.

6. The acquisition unit is, The system estimates the instructor's emotions and adjusts the timing of acquiring learning guidance information based on those emotions. The system according to feature 1.

7. The acquisition unit is, Analyze the instructor's past teaching history and select the most suitable method of acquisition. The system according to feature 1.

8. The acquisition unit is, When acquiring information on teaching methods, filtering is performed based on the instructor's current teaching style and areas of interest. The system according to feature 1.

9. The acquisition unit is, The system estimates the instructor's emotions and prioritizes the learning guidance information to be acquired based on those emotions. The system according to feature 1.

Images