system

Abstract

The system according to the embodiment aims to promote learners' independent learning and reduce teachers' burden of lesson preparation. [Solution] A system according to an embodiment includes a receiving unit, a generating unit, a presenting unit, and an analyzing unit. The receiving unit receives an original question input by a teacher. The generating unit generates an "intentionally incorrect answer" for the question input by the receiving unit. The presenting unit presents the incorrect answer generated by the generating unit to the learner. The analyzing unit analyzes the learner's response data to the incorrect answer presented by the presenting unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has limited means for encouraging learners to take an active role in their learning, and has placed a heavy burden on teachers in preparing lessons.

[0005] The system according to the embodiment aims to promote learners' independent learning and reduce teachers' burden of lesson preparation. [Means for solving the problem]

[0006] The system according to this embodiment comprises a reception unit, a generation unit, a presentation unit, and an analysis unit. The reception unit receives original questions from the teacher. The generation unit generates "intentionally incorrect answers" to the questions entered by the reception unit. The presentation unit presents the incorrect answers generated by the generation unit to the learners. The analysis unit analyzes the learners' response data to the incorrect answers presented by the presentation unit. [Effects of the Invention]

[0007] The system according to the embodiment can promote learners' independent learning and reduce the burden on teachers in preparing lessons. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An educational support system according to an embodiment of the present invention uses a generative AI to present "intentionally incorrect answers" to students, thereby increasing their motivation and promoting active, independent learning. In this educational support system, a teacher inputs an original problem into the generative AI, which then generates an "intentionally incorrect answer" for that problem. The generated incorrect answer is then presented to the student. The student then realizes that the answer is incorrect and thinks to arrive at the correct answer. This process encourages the student to utilize their own knowledge and learn independently. Furthermore, the generative AI analyzes the student's response and evaluates how the student responded to the incorrect answer. Based on this evaluation, the quality of the incorrect answer presented in the next lesson can be improved. This system reduces the teacher's lesson preparation burden and provides high-quality education. The use of generative AI allows the system to present original answers to problems, thereby increasing students' motivation and promoting active, independent learning. For example, when a teacher inputs a math problem into the generative AI, the generative AI intentionally generates an incorrect answer for that problem. Next, the generated incorrect answer is presented to the learner, who then realizes that the answer is incorrect and thinks about it to arrive at the correct answer. In this process, the learner utilizes their own knowledge and is encouraged to learn independently. Furthermore, the generating AI analyzes the learner's response and evaluates how the learner reacted to the incorrect answer. Based on this evaluation, the quality of the incorrect answer presented in the next lesson can be improved. This system reduces the burden on teachers of lesson preparation and provides high-quality education. In this way, the educational support system can increase learners' motivation to learn and promote active, "independent learning."

[0029] An educational support system according to an embodiment includes a receiving unit, a generating unit, a presenting unit, and an analyzing unit. The receiving unit receives original questions from a teacher. Examples of original questions input by the teacher include, but are not limited to, mathematics questions, physics questions, and language questions. The receiving unit can receive questions via, for example, text input, voice input, image input, or other methods. The generating unit uses a generation AI to generate an "intentionally incorrect answer" for the question input by the receiving unit. The generation AI generates an intentionally incorrect answer, for example, using a specific machine learning model or natural language generation technology. For example, the generating AI receives a prompt such as "Please generate an incorrect answer for this question," and generates the incorrect answer. The presenting unit presents the incorrect answer generated by the generating unit to a learner. The presenting unit can present the incorrect answer via, for example, text display, audio presentation, or visual presentation. For example, the presenting unit displays the generated incorrect answer on a screen and presents it to the learner. The presenting unit can also present the incorrect answer via audio using speech synthesis technology. The analysis unit analyzes the learner's reaction data to the incorrect answers presented by the presentation unit. The analysis unit collects and analyzes the learner's reaction data, such as the time it takes to answer, the correct answer rate, and emotional data. The analysis unit evaluates, for example, how the learner reacted to the incorrect answers and, based on the evaluation results, improves the quality of the incorrect answers presented in the next lesson. In this way, the education support system according to the embodiment can increase the learner's motivation to learn and promote active, "proactive learning."

[0030] The generation unit can generate an "intentionally incorrect answer" to the original problem using the generation AI. For example, the generation unit causes the generation AI to intentionally generate an incorrect answer to the original problem. The generation AI generates the incorrect answer using, for example, a specific machine learning model or natural language generation technology. For example, the generation unit generates an incorrect answer when the generation AI receives a prompt such as, "Please generate an incorrect answer to this problem." The generation AI can generate an incorrect answer, for example, for a math problem, that includes a calculation error. The generation AI can also generate an incorrect answer for a history problem that includes a chronological error. Furthermore, the generation AI can generate an incorrect answer for a science problem that includes a conceptual misunderstanding. This improves the accuracy of generating incorrect answers to the original problem by using the generation AI. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can supervise the process by which the generation AI generates an incorrect answer to the original problem and evaluate the quality of the generated answer.

[0031] The analysis unit can acquire the learner's response data and reflect it in generating an incorrect answer to be presented in the next lesson. The analysis unit, for example, collects the learner's response data and reflects it in generating an incorrect answer to be presented in the next lesson. The learner's response data includes, but is not limited to, response time, correct answer rate, and emotional data. The analysis unit, for example, evaluates how the learner responded to an incorrect answer and improves the quality of the incorrect answer to be presented in the next lesson based on the evaluation results. The analysis unit, for example, analyzes the learner's response data and evaluates how the learner responded to an incorrect answer. This allows the learner's response data to be collected and the quality of the incorrect answer to be presented in the next lesson to be improved. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI or without a generation AI. For example, the analysis unit can supervise the process in which the generation AI analyzes the learner's response data and improves the quality of the incorrect answer to be presented in the next lesson based on the results.

[0032] The reception unit can analyze the teacher's past question input history and select an appropriate input method. The reception unit, for example, analyzes the teacher's past question input history and selects the optimal input method. The past question input history includes, for example, the type, frequency, and difficulty of the entered questions. The reception unit, for example, preferentially suggests input methods (such as voice input or text input) that the teacher has frequently used in the past. The reception unit can also suggest the optimal input method for a specific time period based on the teacher's past input history. Furthermore, the reception unit can analyze the patterns of questions that the teacher has previously entered and suggest an efficient input method. In this way, the optimal input method can be suggested by analyzing the teacher's past question input history. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can supervise a process in which the generation AI analyzes the teacher's past question input history and suggests the optimal input method based on the results.

[0033] The reception unit can perform filtering processing based on the teacher's current lesson plan or curriculum when inputting questions. For example, the reception unit filters questions based on the teacher's current lesson plan or curriculum when inputting questions. Lesson plans and curricula include, for example, annual plans and unit goals. The reception unit, for example, displays only relevant questions as input candidates based on the teacher's lesson plan. The reception unit can also automatically filter questions of appropriate difficulty based on the teacher's curriculum. Furthermore, the reception unit can also suggest inputting questions at the optimal timing depending on the teacher's lesson progress. This enables efficient lesson preparation by filtering questions based on the teacher's lesson plan or curriculum. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can supervise a process in which the generation AI analyzes the teacher's lesson plan or curriculum and filters questions based on the results.

[0034] When inputting questions, the reception unit can prioritize inputting highly relevant questions based on the geographical location information of the teacher. For example, when inputting questions, the reception unit prioritizes inputting highly relevant questions taking into account the geographical location information of the teacher. Geographical location information includes, for example, GPS data, questions specific to a region, etc. For example, if a teacher is teaching in a specific region, the reception unit prioritizes inputting questions related to that region. In addition, if a teacher is traveling, the reception unit can automatically suggest questions related to the teacher's current location. Furthermore, if a teacher is teaching in a specific school, the reception unit can prioritize inputting questions related to the school's curriculum. In this way, highly relevant questions can be prioritized by taking the geographical location information of the teacher into consideration. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can supervise a process in which the generation AI analyzes the teacher's geographical location information and prioritizes inputting highly relevant questions based on the results.

[0035] The reception unit can analyze the teacher's social media activity data and input related questions when a question is entered. For example, the reception unit can analyze the teacher's social media activity and input related questions when a question is entered. Social media activity data includes, for example, the content of posts, the number of likes, and the number of followers. For example, the reception unit can suggest related questions based on educational resources shared by the teacher on social media. The reception unit can also analyze posts by educational experts the teacher follows on social media and input related questions. Furthermore, the reception unit can suggest related questions based on topics in educational communities in which the teacher participates on social media. This allows for efficient input of related questions by analyzing the teacher's social media activity. Some or all of the above-described processing in the reception unit can be performed using, or without, a generation AI. For example, the reception unit can supervise a process in which the generation AI analyzes the teacher's social media activity data and inputs related questions based on the results.

[0036] When generating an incorrect answer, the generation unit can adjust the specificity of the generated answer based on the difficulty of the question. For example, when generating an incorrect answer, the generation unit adjusts the level of detail of the generated answer based on the difficulty of the question. The difficulty of the question includes, for example, the correct answer rate and the answer time. For example, for an easy question, the generation unit generates a simple incorrect answer. For a difficult question, the generation unit can also generate an incorrect answer with detailed explanation. Furthermore, for a medium-difficulty question, the generation unit can generate an incorrect answer with moderate detail. This allows the learner to deepen their understanding by adjusting the level of detail of the incorrect answer depending on the difficulty of the question. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can supervise a process in which the generation AI analyzes the difficulty of the question and adjusts the level of detail of the incorrect answer based on the result.

[0037] The generation unit can use different generation algorithms depending on the problem category when generating an incorrect answer. For example, the generation unit applies different generation algorithms depending on the problem category when generating an incorrect answer. Problem categories include, for example, mathematics, physics, and language. For example, the generation unit generates an incorrect answer including a calculation error for a mathematics problem. Furthermore, the generation unit can generate an incorrect answer including a chronological error for a history problem. Furthermore, the generation unit can generate an incorrect answer including a conceptual misunderstanding for a science problem. In this way, by applying a generation algorithm depending on the problem category, a more appropriate incorrect answer can be generated. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can supervise a process in which the generation AI analyzes the problem category and applies different generation algorithms based on the results.

[0038] When generating incorrect answers, the generation unit can determine the order of generation based on the time when the question was submitted. For example, when generating incorrect answers, the generation unit determines the priority of generation based on the time when the question was submitted. The time when the question was submitted includes, for example, during the semester or before an exam. For example, the generation unit quickly generates incorrect answers for questions with an approaching deadline. The generation unit can also generate detailed incorrect answers for questions with a long submission deadline. Furthermore, the generation unit can generate incorrect answers with moderate detail for questions with a medium submission deadline. This enables efficient problem solving by determining the priority of generation based on the time when the question was submitted. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can supervise a process in which the generation AI analyzes the time when the question was submitted and determines the priority of generation based on the results.

[0039] The generation unit can set the order of generation based on the relevance of questions when generating incorrect answers. For example, the generation unit can adjust the order of generation based on the relevance of questions when generating incorrect answers. The relevance of questions includes, for example, the relevance to previous and subsequent questions and the relevance to the learning content. For example, the generation unit can prioritize generating incorrect answers related to questions that the learner has previously answered incorrectly. The generation unit can also prioritize generating incorrect answers related to a topic the learner is currently studying. Furthermore, the generation unit can prioritize generating incorrect answers related to a topic in which the learner is interested. This enables efficient problem solving by adjusting the order of generation based on the relevance of questions. Some or all of the above-described processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can supervise a process in which the generation AI analyzes the relevance of questions and adjusts the order of generation based on the results.

[0040] The presentation unit can select an appropriate presentation method by referring to the learner's past response history when presenting an incorrect answer. For example, when presenting an incorrect answer, the presentation unit can select an optimal presentation method by referring to the learner's past response history. The past response history includes, for example, past answer data, reaction time, and correct answer rate. For example, the presentation unit preferentially uses a presentation method that the learner previously preferred. The presentation unit can also select the most effective presentation method from the learner's past response history. Furthermore, the presentation unit can avoid presentation methods that the learner previously found difficult. In this way, the optimal presentation method can be selected by referring to the learner's past response history. Some or all of the above-described processing in the presentation unit can be performed, for example, using a generation AI or without using a generation AI. For example, the presentation unit can supervise a process in which the generation AI analyzes the learner's past response history and selects an optimal presentation method based on the results.

[0041] The presentation unit can customize the presentation method based on the learner's current learning situation when presenting an incorrect answer. For example, when presenting an incorrect answer, the presentation unit customizes the presentation means based on the learner's current learning situation. The current learning situation includes, for example, progress, level of understanding, learning pace, etc. The presentation unit, for example, presents an incorrect answer related to the topic the learner is currently studying. The presentation unit can also present an incorrect answer at an appropriate time depending on the learner's progress. Furthermore, the presentation unit can present an incorrect answer with a detailed explanation depending on the learner's level of understanding. This allows the learner to deepen their understanding by customizing the presentation means based on the learner's current learning situation. Some or all of the above-mentioned processing in the presentation unit may be performed using, or without, a generation AI. For example, the presentation unit can supervise a process in which the generation AI analyzes the learner's current learning situation and customizes the presentation means based on the results.

[0042] The presentation unit can select an appropriate presentation method by taking into account the learner's geographical location information when presenting an incorrect answer. For example, the presentation unit selects the optimal presentation method by taking into account the learner's geographical location information when presenting an incorrect answer. Geographical location information includes, for example, GPS data, questions specific to a region, etc. For example, if the learner is studying in a specific region, the presentation unit can present an incorrect answer related to that region. Furthermore, if the learner is traveling, the presentation unit can present an incorrect answer related to the learner's current location. Furthermore, if the learner is studying at a specific school, the presentation unit can present an incorrect answer related to the school's curriculum. In this way, the optimal presentation method can be selected by taking into account the learner's geographical location information. Some or all of the above-described processing in the presentation unit may be performed using, or without, a generation AI. For example, the presentation unit can supervise a process in which the generation AI analyzes the learner's geographical location information and selects the optimal presentation method based on the results.

[0043] When presenting an incorrect answer, the suggestion unit can analyze the learner's social media activity data to suggest a presentation method. For example, when presenting an incorrect answer, the suggestion unit analyzes the learner's social media activity and suggests a related incorrect answer. Social media activity data includes, for example, the content of posts, the number of likes, the number of followers, etc. The suggestion unit can suggest a related incorrect answer based on, for example, learning resources shared by the learner on social media. The suggestion unit can also analyze posts from educational experts the learner follows on social media and suggest a related incorrect answer. Furthermore, the suggestion unit can suggest a related incorrect answer based on topics in educational communities in which the learner participates on social media. In this way, the optimal presentation method can be suggested by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can supervise a process in which the generation AI analyzes the learner's social media activity data and suggests an optimal presentation method based on the results.

[0044] When analyzing the reaction data, the analysis unit can adjust the analysis algorithm by referring to the learner's past reaction data. For example, when analyzing the reaction data, the analysis unit can optimize the analysis algorithm by referring to the learner's past reaction data. The past reaction data includes, for example, past answer data, reaction time, and accuracy rate. For example, the analysis unit selects an optimal analysis algorithm based on the learner's past reaction data. The analysis unit can also analyze the learner's past reaction patterns to improve the accuracy of the analysis. Furthermore, the analysis unit can customize the analysis results by referring to the learner's past reaction data. In this way, the analysis algorithm can be optimized by referring to the learner's past reaction data. Some or all of the above-described processing in the analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the analysis unit can supervise a process in which the generation AI analyzes the learner's past reaction data and optimizes the analysis algorithm based on the results.

[0045] The analysis unit can customize the analysis method based on the learner's attribute information when analyzing the reaction data. For example, the analysis unit customizes the analysis means based on the learner's attribute information when analyzing the reaction data. The learner's attribute information includes, for example, age, gender, and grade. The analysis unit selects an appropriate analysis means based on, for example, the learner's age. The analysis unit can also customize the analysis means based on the learner's learning style. Furthermore, the analysis unit can optimize the analysis means based on the learner's learning history. In this way, customizing the analysis means based on the learner's attribute information improves the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can supervise the process in which the generation AI analyzes the learner's attribute information and customizes the analysis means based on the results.

[0046] When analyzing the response data, the analysis unit can select an appropriate analysis method by taking into account the learner's geographical location information. For example, when analyzing the response data, the analysis unit selects the optimal analysis method by taking into account the learner's geographical location information. Geographical location information includes, for example, GPS data and questions specific to the region. For example, if the learner is studying in a specific region, the analysis unit can prioritize analyzing response data related to that region. Furthermore, if the learner is traveling, the analysis unit can prioritize analyzing response data related to the learner's current location. Furthermore, if the learner is studying at a specific school, the analysis unit can prioritize analyzing response data related to the school's curriculum. In this way, the optimal analysis method can be selected by taking into account the learner's geographical location information. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can supervise a process in which the generation AI analyzes the learner's geographical location information and selects the optimal analysis method based on the results.

[0047] When analyzing the response data, the analysis unit can analyze the learner's social media activity data and propose an analysis method. For example, when analyzing the response data, the analysis unit analyzes the learner's social media activity and analyzes related response data. The social media activity data includes, for example, the content of the post, the number of likes, the number of followers, etc. The analysis unit can analyze related response data based on, for example, learning resources shared by the learner on social media. The analysis unit can also analyze posts by educational experts followed by the learner on social media and analyze related response data. Furthermore, the analysis unit can analyze related response data based on topics in educational communities in which the learner participates on social media. This allows the analysis of the learner's social media activity to propose optimal analysis methods. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can supervise a process in which the generation AI analyzes the learner's social media activity data and proposes optimal analysis methods based on the results.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The reception unit can analyze a teacher's past lesson evaluation data and suggest the optimal way to input questions. For example, it can suggest a similar question format and input method based on data from lessons that a teacher has received high marks in the past. The reception unit can also analyze data from lessons that a teacher has received low marks in the past, identify the cause, and suggest improvements. Furthermore, the reception unit can collect a teacher's lesson evaluation data in real time and dynamically suggest the optimal way to input questions according to the progress of the lesson. This allows teachers to use past lesson evaluation data to prepare for lessons more effectively.

[0050] The generator can adjust the algorithm for generating incorrect answers based on the learner's learning history data. For example, it can analyze patterns of questions that the learner has gotten wrong in the past and generate answers containing similar errors. The generator can also generate more challenging incorrect answers for questions in areas in which the learner excels. Furthermore, the generator can dynamically adjust the difficulty of the incorrect answers according to the learner's learning progress. This makes it possible to generate more effective incorrect answers by utilizing the learner's learning history data.

[0051] The analysis unit can assist in selecting teaching materials to be used in the next lesson based on learner response data. For example, if a learner demonstrates a high level of understanding of a particular teaching material, it can suggest that that material be used in the next lesson. Alternatively, if a learner demonstrates a low level of understanding of a particular teaching material, it can suggest alternative teaching materials. Furthermore, the analysis unit can collect learner response data in real time and dynamically suggest optimal teaching materials as the lesson progresses. This makes it possible to utilize learner response data for more effective lesson preparation.

[0052] The reception unit can suggest the optimal question presentation order based on the teacher's past question input history. For example, it can suggest a similar order based on a question presentation order that the teacher has found effective in the past. The reception unit can also analyze the teacher's past question input history and dynamically adjust the optimal question presentation order. Furthermore, the reception unit can also suggest the optimal question presentation order in real time according to the teacher's lesson progress. This makes it possible to utilize the teacher's past question input history to prepare lessons more effectively.

[0053] The input system can adjust the difficulty level of questions based on the teacher's current lesson plan and curriculum when questions are entered. For example, it can adjust the difficulty level of a specific unit based on the lesson plan. It can also automatically suggest questions of an appropriate difficulty level based on the curriculum. Furthermore, the input system can adjust the difficulty level of questions in real time according to the teacher's progress in the lesson. This allows for more efficient lesson preparation by adjusting the difficulty level of questions based on the teacher's lesson plan and curriculum.

[0054] The reception system can suggest relevant educational resources based on the teacher's geographical location when a question is entered. For example, it can prioritize suggesting teaching materials and resources used in a specific region. It can also automatically suggest educational resources relevant to the teacher's current location if the teacher is traveling. Furthermore, if the teacher is teaching at a specific school, the reception system can suggest educational resources related to that school's curriculum. This allows for efficient suggestion of relevant educational resources by considering the teacher's geographical location.

[0055] The reception desk can suggest the most suitable question format based on the teacher's social media activity data when a question is entered. For example, it can suggest relevant question formats based on educational resources the teacher has shared on social media. It can also analyze posts from educational experts the teacher follows on social media and suggest the most suitable question format. Furthermore, the reception desk can suggest relevant question formats based on topics in educational communities the teacher participates in on social media. This allows for the efficient suggestion of the most suitable question format by analyzing the teacher's social media activity.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The teacher inputs original questions into the reception unit. The original questions that the teacher inputs include math questions, physics questions, language questions, etc. The reception unit can accept questions by text input, voice input, image input, etc. Step 2: The generation unit uses the generation AI to generate a "deliberately incorrect answer" to the question entered by the reception unit. The generation AI uses a specific machine learning model or natural language generation technology to intentionally generate an incorrect answer. The generation unit receives a prompt from the generation AI saying, "Please generate an incorrect answer for this question," and generates an incorrect answer. Step 3: The presentation unit presents the incorrect answers generated by the generation unit to the learner. The presentation unit can present the incorrect answers by means of text display, audio presentation, visual presentation, or the like. For example, the generated incorrect answers can be displayed on a screen and presented to the learner. Alternatively, the incorrect answers can be presented audibly using speech synthesis technology. Step 4: The analysis unit analyzes the learner's response data to the incorrect answers presented by the presentation unit. The analysis unit collects and analyzes the learner's response data, such as response time, correct answer rate, and emotional data. The analysis unit evaluates how the learner responded to the incorrect answers and, based on the evaluation results, improves the quality of the incorrect answers presented in the next lesson.

[0058] (Example 2) An educational support system according to an embodiment of the present invention uses a generative AI to present "intentionally incorrect answers" to students, thereby increasing their motivation and promoting active, independent learning. In this educational support system, a teacher inputs an original problem into the generative AI, which then generates an "intentionally incorrect answer" for that problem. The generated incorrect answer is then presented to the student. The student then realizes that the answer is incorrect and thinks to arrive at the correct answer. This process encourages the student to utilize their own knowledge and learn independently. Furthermore, the generative AI analyzes the student's response and evaluates how the student responded to the incorrect answer. Based on this evaluation, the quality of the incorrect answer presented in the next lesson can be improved. This system reduces the teacher's lesson preparation burden and provides high-quality education. The use of generative AI allows the system to present original answers to problems, thereby increasing students' motivation and promoting active, independent learning. For example, when a teacher inputs a math problem into the generative AI, the generative AI intentionally generates an incorrect answer for that problem. Next, the generated incorrect answer is presented to the learner, who then realizes that the answer is incorrect and thinks about it to arrive at the correct answer. In this process, the learner utilizes their own knowledge and is encouraged to learn independently. Furthermore, the generating AI analyzes the learner's response and evaluates how the learner reacted to the incorrect answer. Based on this evaluation, the quality of the incorrect answer presented in the next lesson can be improved. This system reduces the burden on teachers of lesson preparation and provides high-quality education. In this way, the educational support system can increase learners' motivation to learn and promote active, "independent learning."

[0059] An educational support system according to an embodiment includes a receiving unit, a generating unit, a presenting unit, and an analyzing unit. The receiving unit receives original questions from a teacher. Examples of original questions input by the teacher include, but are not limited to, mathematics questions, physics questions, and language questions. The receiving unit can receive questions via, for example, text input, voice input, image input, or other methods. The generating unit uses a generation AI to generate an "intentionally incorrect answer" for the question input by the receiving unit. The generation AI generates an intentionally incorrect answer, for example, using a specific machine learning model or natural language generation technology. For example, the generating AI receives a prompt such as "Please generate an incorrect answer for this question," and generates the incorrect answer. The presenting unit presents the incorrect answer generated by the generating unit to a learner. The presenting unit can present the incorrect answer via, for example, text display, audio presentation, or visual presentation. For example, the presenting unit displays the generated incorrect answer on a screen and presents it to the learner. The presenting unit can also present the incorrect answer via audio using speech synthesis technology. The analysis unit analyzes the learner's reaction data to the incorrect answers presented by the presentation unit. The analysis unit collects and analyzes the learner's reaction data, such as the time it takes to answer, the correct answer rate, and emotional data. The analysis unit evaluates, for example, how the learner reacted to the incorrect answers and, based on the evaluation results, improves the quality of the incorrect answers presented in the next lesson. In this way, the education support system according to the embodiment can increase the learner's motivation to learn and promote active, "proactive learning."

[0060] The generation unit can generate an "intentionally incorrect answer" to the original problem using the generation AI. For example, the generation unit causes the generation AI to intentionally generate an incorrect answer to the original problem. The generation AI generates the incorrect answer using, for example, a specific machine learning model or natural language generation technology. For example, the generation unit generates an incorrect answer when the generation AI receives a prompt such as, "Please generate an incorrect answer to this problem." The generation AI can generate an incorrect answer, for example, for a math problem, that includes a calculation error. The generation AI can also generate an incorrect answer for a history problem that includes a chronological error. Furthermore, the generation AI can generate an incorrect answer for a science problem that includes a conceptual misunderstanding. This improves the accuracy of generating incorrect answers to the original problem by using the generation AI. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can supervise the process by which the generation AI generates an incorrect answer to the original problem and evaluate the quality of the generated answer.

[0061] The analysis unit can acquire the learner's response data and reflect it in generating an incorrect answer to be presented in the next lesson. The analysis unit, for example, collects the learner's response data and reflects it in generating an incorrect answer to be presented in the next lesson. The learner's response data includes, but is not limited to, response time, correct answer rate, and emotional data. The analysis unit, for example, evaluates how the learner responded to an incorrect answer and improves the quality of the incorrect answer to be presented in the next lesson based on the evaluation results. The analysis unit, for example, analyzes the learner's response data and evaluates how the learner responded to an incorrect answer. This allows the learner's response data to be collected and the quality of the incorrect answer to be presented in the next lesson to be improved. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI or without a generation AI. For example, the analysis unit can supervise the process in which the generation AI analyzes the learner's response data and improves the quality of the incorrect answer to be presented in the next lesson based on the results.

[0062] The reception unit can estimate the teacher's emotional data and adjust the timing of question input based on the estimated emotional data. The reception unit, for example, estimates the teacher's emotional data and adjusts the timing of question input based on the estimated emotional data. The teacher's emotional data includes, for example, data obtained by methods such as facial expression recognition, voice analysis, and self-reporting. For example, if the teacher is feeling stressed, the reception unit can have the generation AI automatically delay the timing of question input, providing the teacher with time to relax. Furthermore, if the teacher is relaxed, the reception unit can prompt the generation AI to immediately input questions, supporting efficient lesson preparation. Furthermore, if the teacher is busy, the reception unit can suggest the optimal timing for question input, thereby reducing the teacher's burden. This reduces the teacher's burden by adjusting the timing of question input according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the reception unit may supervise the process in which the generation AI analyzes the teacher's emotional data and adjusts the timing of question input based on the results.

[0063] The reception unit can analyze the teacher's past question input history and select an appropriate input method. The reception unit, for example, analyzes the teacher's past question input history and selects the optimal input method. The past question input history includes, for example, the type, frequency, and difficulty of the entered questions. The reception unit, for example, preferentially suggests input methods (such as voice input or text input) that the teacher has frequently used in the past. The reception unit can also suggest the optimal input method for a specific time period based on the teacher's past input history. Furthermore, the reception unit can analyze the patterns of questions that the teacher has previously entered and suggest an efficient input method. In this way, the optimal input method can be suggested by analyzing the teacher's past question input history. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can supervise a process in which the generation AI analyzes the teacher's past question input history and suggests the optimal input method based on the results.

[0064] The reception unit can perform filtering processing based on the teacher's current lesson plan or curriculum when inputting questions. For example, the reception unit filters questions based on the teacher's current lesson plan or curriculum when inputting questions. Lesson plans and curricula include, for example, annual plans and unit goals. The reception unit, for example, displays only relevant questions as input candidates based on the teacher's lesson plan. The reception unit can also automatically filter questions of appropriate difficulty based on the teacher's curriculum. Furthermore, the reception unit can also suggest inputting questions at the optimal timing depending on the teacher's lesson progress. This enables efficient lesson preparation by filtering questions based on the teacher's lesson plan or curriculum. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can supervise a process in which the generation AI analyzes the teacher's lesson plan or curriculum and filters questions based on the results.

[0065] The reception unit can estimate the teacher's emotional data and determine the priority of questions to be entered based on the estimated emotional data. The reception unit, for example, estimates the teacher's emotional data and determines the priority of questions to be entered based on the estimated emotional data. The teacher's emotional data includes data obtained by methods such as facial expression recognition, voice analysis, and self-reporting. For example, if the teacher is tired, the reception unit can suggest that the teacher prioritize easy questions. The reception unit can also suggest that the teacher prioritize more difficult questions if the teacher is relaxed. Furthermore, if the teacher is feeling stressed, the reception unit can automatically adjust the priority of questions to reduce the teacher's burden. Thus, by determining the priority of questions according to the teacher's emotions, the teacher's burden can be reduced. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit can be performed using, for example, the generation AI, or without the generation AI. For example, the reception department can oversee the process in which generative AI analyzes teachers' emotional data and prioritizes problems based on the results.

[0066] When inputting questions, the reception unit can prioritize inputting highly relevant questions based on the geographical location information of the teacher. For example, when inputting questions, the reception unit prioritizes inputting highly relevant questions taking into account the geographical location information of the teacher. Geographical location information includes, for example, GPS data, questions specific to a region, etc. For example, if a teacher is teaching in a specific region, the reception unit prioritizes inputting questions related to that region. In addition, if a teacher is traveling, the reception unit can automatically suggest questions related to the teacher's current location. Furthermore, if a teacher is teaching in a specific school, the reception unit can prioritize inputting questions related to the school's curriculum. In this way, highly relevant questions can be prioritized by taking the geographical location information of the teacher into consideration. Some or all of the above-described processing in the reception unit may be performed using, or without, a generation AI. For example, the reception unit can supervise a process in which the generation AI analyzes the teacher's geographical location information and prioritizes inputting highly relevant questions based on the results.

[0067] The reception unit can analyze the teacher's social media activity data and input related questions when a question is entered. For example, the reception unit can analyze the teacher's social media activity and input related questions when a question is entered. Social media activity data includes, for example, the content of posts, the number of likes, and the number of followers. For example, the reception unit can suggest related questions based on educational resources shared by the teacher on social media. The reception unit can also analyze posts by educational experts the teacher follows on social media and input related questions. Furthermore, the reception unit can suggest related questions based on topics in educational communities in which the teacher participates on social media. This allows for efficient input of related questions by analyzing the teacher's social media activity. Some or all of the above-described processing in the reception unit can be performed using, or without, a generation AI. For example, the reception unit can supervise a process in which the generation AI analyzes the teacher's social media activity data and inputs related questions based on the results.

[0068] The generation unit can estimate the learner's emotional data and adjust the way incorrect answers are presented based on the estimated learner's emotional data. For example, the generation unit estimates the learner's emotional data and adjusts the way incorrect answers are presented based on the estimated learner's emotions. The learner's emotional data includes data obtained by methods such as facial recognition, speech analysis, and self-reporting. For example, if the learner is stressed, the generation unit will present an incorrect answer in a gentle way. The generation unit can also present an incorrect answer with a detailed explanation if the learner is relaxed. Furthermore, if the learner is excited, the generation unit can present an incorrect answer with a visually stimulating effect. This allows for a deeper understanding of the learner by adjusting the way incorrect answers are presented according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generative AI, for example, or without a generative AI. For example, the generation department can oversee the process by which the generation AI analyzes the learner's emotional data and adjusts the way incorrect answers are presented based on the results.

[0069] When generating an incorrect answer, the generation unit can adjust the specificity of the generated answer based on the difficulty of the question. For example, when generating an incorrect answer, the generation unit adjusts the level of detail of the generated answer based on the difficulty of the question. The difficulty of the question includes, for example, the correct answer rate and the answer time. For example, for an easy question, the generation unit generates a simple incorrect answer. For a difficult question, the generation unit can also generate an incorrect answer with detailed explanation. Furthermore, for a medium-difficulty question, the generation unit can generate an incorrect answer with moderate detail. This allows the learner to deepen their understanding by adjusting the level of detail of the incorrect answer depending on the difficulty of the question. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can supervise a process in which the generation AI analyzes the difficulty of the question and adjusts the level of detail of the incorrect answer based on the result.

[0070] The generation unit can use different generation algorithms depending on the problem category when generating an incorrect answer. For example, the generation unit applies different generation algorithms depending on the problem category when generating an incorrect answer. Problem categories include, for example, mathematics, physics, and language. For example, the generation unit generates an incorrect answer including a calculation error for a mathematics problem. Furthermore, the generation unit can generate an incorrect answer including a chronological error for a history problem. Furthermore, the generation unit can generate an incorrect answer including a conceptual misunderstanding for a science problem. In this way, by applying a generation algorithm depending on the problem category, a more appropriate incorrect answer can be generated. Some or all of the above-described processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can supervise a process in which the generation AI analyzes the problem category and applies different generation algorithms based on the results.

[0071] The generation unit can estimate the learner's emotional data and adjust the length of incorrect answers based on the estimated learner's emotional data. For example, the generation unit estimates the learner's emotional data and adjusts the length of incorrect answers based on the estimated learner's emotions. The learner's emotional data includes data obtained by methods such as facial recognition, speech analysis, and self-reporting. For example, if the learner is in a hurry, the generation unit can generate a short, concise incorrect answer. The generation unit can also generate a longer incorrect answer with a more detailed explanation if the learner is relaxed. Furthermore, if the learner is excited, the generation unit can generate an incorrect answer with a visually stimulating effect. This allows for a deeper understanding of the learner by adjusting the length of incorrect answers according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generative AI, for example, or without a generative AI. For example, the generation department can oversee the process by which the generation AI analyzes the learner's emotional data and adjusts the length of incorrect answers based on the results.

[0072] When generating incorrect answers, the generation unit can determine the order of generation based on the time when the question was submitted. For example, when generating incorrect answers, the generation unit determines the priority of generation based on the time when the question was submitted. The time when the question was submitted includes, for example, during the semester or before an exam. For example, the generation unit quickly generates incorrect answers for questions with an approaching deadline. The generation unit can also generate detailed incorrect answers for questions with a long submission deadline. Furthermore, the generation unit can generate incorrect answers with moderate detail for questions with a medium submission deadline. This enables efficient problem solving by determining the priority of generation based on the time when the question was submitted. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can supervise a process in which the generation AI analyzes the time when the question was submitted and determines the priority of generation based on the results.

[0073] The generation unit can set the order of generation based on the relevance of questions when generating incorrect answers. For example, the generation unit can adjust the order of generation based on the relevance of questions when generating incorrect answers. The relevance of questions includes, for example, the relevance to previous and subsequent questions and the relevance to the learning content. For example, the generation unit can prioritize generating incorrect answers related to questions that the learner has previously answered incorrectly. The generation unit can also prioritize generating incorrect answers related to a topic the learner is currently studying. Furthermore, the generation unit can prioritize generating incorrect answers related to a topic in which the learner is interested. This enables efficient problem solving by adjusting the order of generation based on the relevance of questions. Some or all of the above-described processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can supervise a process in which the generation AI analyzes the relevance of questions and adjusts the order of generation based on the results.

[0074] The presentation unit can estimate the learner's emotional data and adjust the method of presenting incorrect answers based on the estimated learner's emotional data. For example, the presentation unit estimates the learner's emotional data and adjusts the method of presenting incorrect answers based on the estimated learner's emotions. The learner's emotional data includes data obtained by methods such as facial recognition, speech analysis, and self-reporting. For example, if the learner is stressed, the presentation unit may present the incorrect answer in a gentle tone. The presentation unit may also present the incorrect answer with a detailed explanation if the learner is relaxed. Furthermore, if the learner is excited, the presentation unit may present the incorrect answer with a visually stimulating effect. This allows for a deeper understanding of the learner by adjusting the method of presenting incorrect answers according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the presentation unit may be performed using, for example, a generative AI or not using a generative AI. For example, the presentation unit can oversee the process by which the generative AI analyzes the learner's emotional data and adjusts the way it presents incorrect answers based on the results.

[0075] The presentation unit can select an appropriate presentation method by referring to the learner's past response history when presenting an incorrect answer. For example, when presenting an incorrect answer, the presentation unit can select an optimal presentation method by referring to the learner's past response history. The past response history includes, for example, past answer data, reaction time, and correct answer rate. For example, the presentation unit preferentially uses a presentation method that the learner previously preferred. The presentation unit can also select the most effective presentation method from the learner's past response history. Furthermore, the presentation unit can avoid presentation methods that the learner previously found difficult. In this way, the optimal presentation method can be selected by referring to the learner's past response history. Some or all of the above-described processing in the presentation unit can be performed, for example, using a generation AI or without using a generation AI. For example, the presentation unit can supervise a process in which the generation AI analyzes the learner's past response history and selects an optimal presentation method based on the results.

[0076] The presentation unit can customize the presentation method based on the learner's current learning situation when presenting an incorrect answer. For example, when presenting an incorrect answer, the presentation unit customizes the presentation means based on the learner's current learning situation. The current learning situation includes, for example, progress, level of understanding, learning pace, etc. The presentation unit, for example, presents an incorrect answer related to the topic the learner is currently studying. The presentation unit can also present an incorrect answer at an appropriate time depending on the learner's progress. Furthermore, the presentation unit can present an incorrect answer with a detailed explanation depending on the learner's level of understanding. This allows the learner to deepen their understanding by customizing the presentation means based on the learner's current learning situation. Some or all of the above-mentioned processing in the presentation unit may be performed using, or without, a generation AI. For example, the presentation unit can supervise a process in which the generation AI analyzes the learner's current learning situation and customizes the presentation means based on the results.

[0077] The presentation unit can estimate the learner's emotional data and determine the order in which to present the incorrect answers based on the estimated emotional data. The presentation unit, for example, estimates the learner's emotional data and determines the order in which to present the incorrect answers based on the estimated emotional data. The learner's emotional data includes data obtained by methods such as facial expression recognition, voice analysis, and self-reporting. For example, if the learner is stressed, the presentation unit can present the incorrect answers starting with the easier ones. If the learner is relaxed, the presentation unit can also present the incorrect answers starting with the more difficult ones. Furthermore, if the learner is excited, the presentation unit can also present the incorrect answers starting with the more visually stimulating ones. This allows the learner's understanding to be deepened by determining the order in which to present the incorrect answers based on the learner's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the presentation unit can be performed using, for example, the generation AI, or without the generation AI. For example, the presentation unit can oversee the process by which the generating AI analyzes the learner's emotional data and determines the order in which incorrect answers are presented based on the results.

[0078] The presentation unit can select an appropriate presentation method by taking into account the learner's geographical location information when presenting an incorrect answer. For example, the presentation unit selects the optimal presentation method by taking into account the learner's geographical location information when presenting an incorrect answer. Geographical location information includes, for example, GPS data, questions specific to a region, etc. For example, if the learner is studying in a specific region, the presentation unit can present an incorrect answer related to that region. Furthermore, if the learner is traveling, the presentation unit can present an incorrect answer related to the learner's current location. Furthermore, if the learner is studying at a specific school, the presentation unit can present an incorrect answer related to the school's curriculum. In this way, the optimal presentation method can be selected by taking into account the learner's geographical location information. Some or all of the above-described processing in the presentation unit may be performed using, or without, a generation AI. For example, the presentation unit can supervise a process in which the generation AI analyzes the learner's geographical location information and selects the optimal presentation method based on the results.

[0079] When presenting an incorrect answer, the suggestion unit can analyze the learner's social media activity data to suggest a presentation method. For example, when presenting an incorrect answer, the suggestion unit analyzes the learner's social media activity and suggests a related incorrect answer. Social media activity data includes, for example, the content of posts, the number of likes, the number of followers, etc. The suggestion unit can suggest a related incorrect answer based on, for example, learning resources shared by the learner on social media. The suggestion unit can also analyze posts from educational experts the learner follows on social media and suggest a related incorrect answer. Furthermore, the suggestion unit can suggest a related incorrect answer based on topics in educational communities in which the learner participates on social media. In this way, the optimal presentation method can be suggested by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the suggestion unit may be performed using, or without, a generation AI. For example, the suggestion unit can supervise a process in which the generation AI analyzes the learner's social media activity data and suggests an optimal presentation method based on the results.

[0080] The analysis unit can estimate the learner's emotional data and adjust the method of analyzing the response data based on the estimated learner's emotional data. For example, the analysis unit estimates the learner's emotional data and adjusts the method of analyzing the response data based on the estimated learner's emotions. The learner's emotional data includes data obtained by methods such as facial recognition, voice analysis, and self-reporting. For example, if the learner is stressed, the analysis unit analyzes the response data in a gentle tone. The analysis unit can also perform a detailed analysis if the learner is relaxed. Furthermore, if the learner is excited, the analysis unit can perform an analysis with visually stimulating effects. This improves the accuracy of the analysis by adjusting the method of analyzing the response data according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can oversee the process by which the generative AI analyzes the learner's emotional data and adjusts the way it analyzes the reaction data based on the results.

[0081] When analyzing the reaction data, the analysis unit can adjust the analysis algorithm by referring to the learner's past reaction data. For example, when analyzing the reaction data, the analysis unit can optimize the analysis algorithm by referring to the learner's past reaction data. The past reaction data includes, for example, past answer data, reaction time, and accuracy rate. For example, the analysis unit selects an optimal analysis algorithm based on the learner's past reaction data. The analysis unit can also analyze the learner's past reaction patterns to improve the accuracy of the analysis. Furthermore, the analysis unit can customize the analysis results by referring to the learner's past reaction data. In this way, the analysis algorithm can be optimized by referring to the learner's past reaction data. Some or all of the above-described processing in the analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the analysis unit can supervise a process in which the generation AI analyzes the learner's past reaction data and optimizes the analysis algorithm based on the results.

[0082] The analysis unit can customize the analysis method based on the learner's attribute information when analyzing the reaction data. For example, the analysis unit customizes the analysis means based on the learner's attribute information when analyzing the reaction data. The learner's attribute information includes, for example, age, gender, and grade. The analysis unit selects an appropriate analysis means based on, for example, the learner's age. The analysis unit can also customize the analysis means based on the learner's learning style. Furthermore, the analysis unit can optimize the analysis means based on the learner's learning history. In this way, customizing the analysis means based on the learner's attribute information improves the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can supervise the process in which the generation AI analyzes the learner's attribute information and customizes the analysis means based on the results.

[0083] The analysis unit can estimate the learner's emotional data and determine the priority of response data based on the estimated learner's emotional data. For example, the analysis unit estimates the learner's emotional data and determines the priority of response data based on the estimated learner's emotions. The learner's emotional data includes data obtained by methods such as facial recognition, voice analysis, and self-reporting. For example, if the learner is stressed, the analysis unit will prioritize analyzing response data related to stress reduction. The analysis unit can also prioritize analyzing detailed response data if the learner is relaxed. Furthermore, if the learner is excited, the analysis unit can prioritize analyzing visually stimulating response data. This improves the efficiency of the analysis by prioritizing response data according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can oversee the process in which the generative AI analyzes the learner's emotional data and prioritizes the reaction data based on the results.

[0084] When analyzing the response data, the analysis unit can select an appropriate analysis method by taking into account the learner's geographical location information. For example, when analyzing the response data, the analysis unit selects the optimal analysis method by taking into account the learner's geographical location information. Geographical location information includes, for example, GPS data and questions specific to the region. For example, if the learner is studying in a specific region, the analysis unit can prioritize analyzing response data related to that region. Furthermore, if the learner is traveling, the analysis unit can prioritize analyzing response data related to the learner's current location. Furthermore, if the learner is studying at a specific school, the analysis unit can prioritize analyzing response data related to the school's curriculum. In this way, the optimal analysis method can be selected by taking into account the learner's geographical location information. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can supervise a process in which the generation AI analyzes the learner's geographical location information and selects the optimal analysis method based on the results.

[0085] When analyzing the response data, the analysis unit can analyze the learner's social media activity data and propose an analysis method. For example, when analyzing the response data, the analysis unit analyzes the learner's social media activity and analyzes related response data. The social media activity data includes, for example, the content of the post, the number of likes, the number of followers, etc. The analysis unit can analyze related response data based on, for example, learning resources shared by the learner on social media. The analysis unit can also analyze posts by educational experts followed by the learner on social media and analyze related response data. Furthermore, the analysis unit can analyze related response data based on topics in educational communities in which the learner participates on social media. This allows the analysis of the learner's social media activity to propose optimal analysis methods. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can supervise a process in which the generation AI analyzes the learner's social media activity data and proposes optimal analysis methods based on the results. === Hard Collateral 1-1 === Each of the multiple elements described above, including the reception unit, generation unit, presentation unit, and analysis unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14, where the teacher inputs the original problem. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, where a generation AI is used to generate a "deliberately incorrect answer". The presentation unit is implemented by the control unit 46A of the smart device 14, where the generated incorrect answer is presented to the learner. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12, where the learner's reaction data is analyzed. The reception unit estimates the teacher's emotional data and adjusts the timing of problem input. === Hard Collateral 1-2 === Each of the multiple elements described above, including the reception unit, generation unit, presentation unit, and analysis unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214, where the teacher inputs the original question. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, where a generation AI is used to generate a "deliberately incorrect answer". The presentation unit is implemented, for example, by the control unit 46A of the smart glasses 214, where the generated incorrect answer is presented to the learner. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, where the learner's reaction data is analyzed. The reception unit estimates the teacher's emotional data and adjusts the timing of question input. === Hard Collateral 1-3 === Each of the multiple elements described above, including the reception unit, generation unit, presentation unit, and analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314, where the teacher inputs the original question. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12, where a generation AI is used to generate a "deliberately incorrect answer". The presentation unit is implemented by the control unit 46A of the headset terminal 314, where the generated incorrect answer is presented to the learner. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12, where the learner's response data is analyzed. The reception unit estimates the teacher's emotional data and adjusts the timing of question input. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, generation unit, presentation unit, and analysis unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414, and the teacher inputs original questions. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates a "deliberately incorrect answer" using a generation AI. The presentation unit is realized, for example, by the control unit 46A of the robot 414, and presents the generated incorrect answer to the learner. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the learner's reaction data. The reception unit, for example, estimates the teacher's emotional data and adjusts the timing of question input.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The reception unit can analyze a teacher's past lesson evaluation data and suggest the optimal way to input questions. For example, it can suggest a similar question format and input method based on data from lessons that a teacher has received high marks in the past. The reception unit can also analyze data from lessons that a teacher has received low marks in the past, identify the cause, and suggest improvements. Furthermore, the reception unit can collect a teacher's lesson evaluation data in real time and dynamically suggest the optimal way to input questions according to the progress of the lesson. This allows teachers to use past lesson evaluation data to prepare for lessons more effectively.

[0088] The generator can adjust the algorithm for generating incorrect answers based on the learner's learning history data. For example, it can analyze patterns of questions that the learner has gotten wrong in the past and generate answers containing similar errors. The generator can also generate more challenging incorrect answers for questions in areas in which the learner excels. Furthermore, the generator can dynamically adjust the difficulty of the incorrect answers according to the learner's learning progress. This makes it possible to generate more effective incorrect answers by utilizing the learner's learning history data.

[0089] The analysis unit can assist in selecting teaching materials to be used in the next lesson based on learner response data. For example, if a learner demonstrates a high level of understanding of a particular teaching material, it can suggest that that material be used in the next lesson. Alternatively, if a learner demonstrates a low level of understanding of a particular teaching material, it can suggest alternative teaching materials. Furthermore, the analysis unit can collect learner response data in real time and dynamically suggest optimal teaching materials as the lesson progresses. This makes it possible to utilize learner response data for more effective lesson preparation.

[0090] The reception system can estimate the teacher's emotional data and adjust the difficulty level of the problems based on that data. For example, if the teacher is stressed, the generating AI will automatically suggest easier problems to reduce the teacher's burden. Conversely, if the teacher is relaxed, the generating AI can suggest more difficult problems to improve the quality of the lesson. Furthermore, the reception system can collect the teacher's emotional data in real time and dynamically adjust the difficulty level of the problems according to the progress of the lesson. This allows the system to adjust the difficulty level of the problems according to the teacher's emotions, thereby reducing the teacher's burden and improving the quality of the lesson.

[0091] The reception unit can suggest the optimal question presentation order based on the teacher's past question input history. For example, it can suggest a similar order based on a question presentation order that the teacher has found effective in the past. The reception unit can also analyze the teacher's past question input history and dynamically adjust the optimal question presentation order. Furthermore, the reception unit can also suggest the optimal question presentation order in real time according to the teacher's lesson progress. This makes it possible to utilize the teacher's past question input history to prepare lessons more effectively.

[0092] The input system can adjust the difficulty level of questions based on the teacher's current lesson plan and curriculum when questions are entered. For example, it can adjust the difficulty level of a specific unit based on the lesson plan. It can also automatically suggest questions of an appropriate difficulty level based on the curriculum. Furthermore, the input system can adjust the difficulty level of questions in real time according to the teacher's progress in the lesson. This allows for more efficient lesson preparation by adjusting the difficulty level of questions based on the teacher's lesson plan and curriculum.

[0093] The reception unit can estimate the teacher's emotional data and adjust the feedback method for questions based on the estimated teacher's emotional data. For example, if the teacher is feeling stressed, the generation AI can automatically provide feedback in a gentle tone, reducing the teacher's burden. Alternatively, if the teacher is relaxed, the generation AI can provide detailed feedback, improving the quality of the lesson. Furthermore, the reception unit can collect the teacher's emotional data in real time and dynamically adjust the feedback method according to the progress of the lesson. This allows the feedback method to be adjusted according to the teacher's emotions, reducing the teacher's burden and improving the quality of the lesson.

[0094] The reception system can suggest relevant educational resources based on the teacher's geographical location when a question is entered. For example, it can prioritize suggesting teaching materials and resources used in a specific region. It can also automatically suggest educational resources relevant to the teacher's current location if the teacher is traveling. Furthermore, if the teacher is teaching at a specific school, the reception system can suggest educational resources related to that school's curriculum. This allows for efficient suggestion of relevant educational resources by considering the teacher's geographical location.

[0095] The reception desk can suggest the most suitable question format based on the teacher's social media activity data when a question is entered. For example, it can suggest relevant question formats based on educational resources the teacher has shared on social media. It can also analyze posts from educational experts the teacher follows on social media and suggest the most suitable question format. Furthermore, the reception desk can suggest relevant question formats based on topics in educational communities the teacher participates in on social media. This allows for the efficient suggestion of the most suitable question format by analyzing the teacher's social media activity.

[0096] The generation unit can estimate the learner's emotional data and adjust the timing of presenting incorrect answers based on the estimated emotional data. For example, if the learner is feeling stressed, the generation AI can automatically delay presenting incorrect answers to provide time for the learner to relax. Alternatively, if the learner is relaxed, the generation AI can immediately present incorrect answers to support efficient learning. Furthermore, the generation unit can collect the learner's emotional data in real time and dynamically adjust the timing of presenting incorrect answers according to the progress of the learning. This allows the learner's understanding to be deepened by adjusting the timing of presenting incorrect answers according to the learner's emotions.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The teacher inputs original questions into the reception unit. The original questions that the teacher inputs include math questions, physics questions, language questions, etc. The reception unit can accept questions by text input, voice input, image input, etc. Step 2: The generation unit uses the generation AI to generate a "deliberately incorrect answer" to the question entered by the reception unit. The generation AI uses a specific machine learning model or natural language generation technology to intentionally generate an incorrect answer. The generation unit receives a prompt from the generation AI saying, "Please generate an incorrect answer for this question," and generates an incorrect answer. Step 3: The presentation unit presents the incorrect answers generated by the generation unit to the learner. The presentation unit can present the incorrect answers by means of text display, audio presentation, visual presentation, or the like. For example, the generated incorrect answers can be displayed on a screen and presented to the learner. Alternatively, the incorrect answers can be presented audibly using speech synthesis technology. Step 4: The analysis unit analyzes the learner's response data to the incorrect answers presented by the presentation unit. The analysis unit collects and analyzes the learner's response data, such as response time, correct answer rate, and emotional data. The analysis unit evaluates how the learner responded to the incorrect answers and, based on the evaluation results, improves the quality of the incorrect answers presented in the next lesson.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0100] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0101] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0102] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0110] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0111] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0113] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0117] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0118] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0122] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0123] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0125] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0126] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0127] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0128] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0129] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0130] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0133] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 7, a 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.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0142] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0143] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0144] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0145] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0146] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0147] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0148] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0149] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0150] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0151] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] 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.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0170] [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception desk where teachers can input original questions, a generator that intentionally generates an incorrect answer to the question input by the receiver; a presentation unit that presents the incorrect answer generated by the generation unit to the learner; an analysis unit that analyzes the learner's response data to the incorrect answer presented by the presentation unit; A system characterized by:

2. The generation unit Generative AI generates intentionally incorrect answers to the original questions 2. The system of claim 1.

3. The analysis unit Obtaining student response data and reflecting it in generating incorrect answers to be presented in the next lesson 2. The system of claim 1.

4. The reception unit Estimate the teacher's emotional data and adjust the timing of question input based on the estimated emotional data.

2. The system of claim 1.

5. The reception unit Analyze the teacher's past question entry history and select the appropriate entry method 2. The system of claim 1.

6. The reception unit Filter questions as they are entered based on the teacher's current lesson plan and curriculum 2. The system of claim 1.

7. The reception unit Estimate teacher sentiment data and prioritize questions to be entered based on the estimated teacher sentiment data 2. The system of claim 1.

8. The reception unit When entering questions, prioritize questions that are more relevant to you based on your geographic location 2. The system of claim 1.

Images