system

Abstract

The system according to this embodiment aims to identify the causes of learners' incorrect answers and provide appropriate countermeasures. [Solution] The system according to this embodiment comprises a reception unit, an inference unit, and a generation unit. The reception unit receives the learner's answer. If the answer received by the reception unit is incorrect, the inference unit infers the cause of the incorrect answer. The generation unit generates countermeasures based on the cause inferred by the inference unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, when a learner gives an incorrect answer, the cause thereof has not been sufficiently identified and appropriate countermeasures have not been provided, and there is room for improvement.

[0005] The system according to the embodiment aims to identify the cause of an incorrect answer of a learner and provide appropriate countermeasures.

Means for Solving the Problems

[0006] The system according to the embodiment includes a reception unit, an inference unit, and a generation unit. The reception unit receives an answer of a learner. The inference unit infers the cause of an incorrect answer when the answer received by the reception unit is incorrect. The generation unit generates a countermeasure based on the cause inferred by the inference unit.

Effects of the Invention

[0007] The system according to this embodiment can identify the cause of learners' incorrect answers and provide appropriate countermeasures. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The self-learning support system according to an embodiment of the present invention is a self-learning support system for preschool children to junior high school students. This self-learning support system is a mechanism in which, when a student uses a tablet to self-learn, an AI agent generates "cause inference" and "countermeasures" for incorrect answers. This allows learners to understand where and why they made a mistake and to take appropriate measures to avoid making the same mistake again. First, the learner answers a problem on the tablet. If the answer is incorrect, the AI ​​agent analyzes the incorrect answer and infers the cause of the error. For example, calculation errors or insufficient understanding of the problem may be the cause. Next, based on the inferred cause, the AI ​​agent generates countermeasures to prevent the learner from making the same mistake again. For example, if the cause is a calculation error, it suggests reviewing calculation methods. If the cause is insufficient understanding of the problem, it suggests reviewing related basic knowledge. Through this mechanism, learners can understand the cause of their incorrect answers and obtain specific measures to avoid making the same mistake again. This improves learning efficiency and is expected to improve the learner's academic performance. In this way, the self-learning support system can improve learning efficiency by inferring the cause of the learner's incorrect answers and generating appropriate countermeasures.

[0029] The self-learning support system according to this embodiment comprises a reception unit, an inference unit, and a generation unit. The reception unit receives the learner's answers. The reception unit allows the learner to input answers using, for example, a tablet. If the answer is incorrect, the reception unit transmits the incorrect answer to the inference unit. The inference unit infers the cause of the incorrect answer. The inference unit analyzes the pattern of the incorrect answer and evaluates the learner's level of understanding. The inference unit can infer that the cause of the incorrect answer is a calculation error or insufficient understanding of the problem. After inferring the cause of the incorrect answer, the inference unit transmits that information to the generation unit. The generation unit generates countermeasures based on the cause inferred by the inference unit. The generation unit generates countermeasures such as reviewing calculation methods or providing relevant basic knowledge. The generation unit provides the generated countermeasures to the learner. As a result, the self-learning support system according to this embodiment can improve the efficiency of learning by inferring the cause of the learner's incorrect answers and generating appropriate countermeasures.

[0030] The reception desk receives learners' answers. Learners can input their answers to questions using devices such as tablets and personal computers. The reception desk receives the answers entered from these devices in real time and stores them in a database. If the answer is correct, feedback is provided directly to the learner; if the answer is incorrect, the incorrect answer is sent to the reasoning unit. The reception desk also has the function of managing the learner's answer history and learning progress and presenting the most suitable questions for each individual learner. For example, if a learner repeatedly makes mistakes in a particular area, the reception desk can deepen the learner's understanding by prioritizing questions related to that area. The reception desk can also analyze the learner's answer time and answer trends to evaluate the learner's concentration and level of understanding. In this way, the reception desk plays an important role in efficiently receiving learners' answers and managing learning progress. Furthermore, the reception desk has security features to safely manage learners' answer data and prevent unauthorized access and data tampering. This allows learners to proceed with their studies with peace of mind.

[0031] The inference unit infers the cause of incorrect answers. Using AI, the inference unit analyzes the learner's error patterns and evaluates their level of understanding. Specifically, it identifies where the learner is struggling based on the content and frequency of errors, as well as their past answer history. For example, if there are many calculation errors, it is likely due to a lack of understanding of calculation methods or a lack of attention. Also, if many errors are due to a lack of understanding of the problem, it can be inferred that there is a problem with reading and interpreting the problem statement. Based on this information, the inference unit clarifies the learner's weaknesses and areas for improvement. Furthermore, the inference unit can cluster the learner's error patterns and group learners with similar error patterns together to identify common problems. This allows the inference unit to grasp the learning trends of not only individual learners but also the entire group, enabling it to provide effective learning support. In addition, the inference unit can utilize past data to evaluate the learner's performance trends and learning effectiveness, and formulate long-term learning plans. In this way, the inference unit accurately infers the cause of learners' errors and provides the basic information necessary to take appropriate measures.

[0032] The generation unit generates countermeasures based on the causes inferred by the inference unit. The generation unit uses AI to generate optimal learning content tailored to the learner's reasons for errors. For example, if the cause is a calculation error, it provides review of calculation methods and presents specific calculation problems to help the learner acquire the correct calculation methods. If the cause is a lack of understanding of the problem, it generates content that explains in detail how to read and interpret the problem statement, enabling the learner to accurately understand the problem. The generation unit can customize and provide these countermeasures individually according to the learner's level and progress. Furthermore, the generation unit continuously improves the content by collecting learner feedback and evaluating the effectiveness of the countermeasures. For example, it analyzes the learner's performance and understanding after using the countermeasure content and adjusts the content and difficulty level as needed. This allows the generation unit to provide optimal learning support to learners and improve learning efficiency. The generation unit can also incorporate game elements and reward systems to maintain learner motivation. For example, it can increase learning motivation by awarding points or badges when learners achieve certain goals. This allows the generation unit to provide effective countermeasures based on the learner's reasons for errors, improving learning efficiency and motivation.

[0033] The inference unit includes a data collection unit that collects the learner's past learning history and the content of the problems. The data collection unit can collect, for example, the learner's past answer data and learning time. Based on the learner's past learning history, the data collection unit provides data for inferring the cause of incorrect answers. The data collection unit can also collect data related to the content of the problems. For example, it can collect information such as the type and difficulty level of the problems. As a result, the inference unit can more accurately infer the cause of incorrect answers based on the learner's past learning history and the content of the problems.

[0034] The generation unit includes a provider unit that provides data such as relevant foundational knowledge and calculation methods. The provider unit can, for example, provide relevant theories and basic concepts. It can also provide data such as explanations of calculation methods and calculation procedures. This allows the generation unit to strengthen measures to prevent learners from making the same mistakes again.

[0035] The reception desk can analyze a learner's past answer history and select the optimal reception method. For example, it can carefully receive answers to questions that a learner has frequently answered incorrectly in the past and encourage them to review. The reception desk can also quickly receive answers to questions in areas where the learner excels and allow them to move on to the next question. The reception desk can also analyze a learner's past answer history to identify tendencies for increased concentration during specific time periods and accept answers during those times. In this way, the reception desk can select the optimal reception method by analyzing a learner's past answer history.

[0036] The reception system can filter submitted answers based on the learner's current learning situation and areas of interest. For example, the reception system can only accept questions related to the unit the learner is currently working on. The reception system can prioritize accepting questions related to the learner's areas of interest. The reception system can also accept questions of appropriate difficulty level according to the learner's current learning progress. In this way, by filtering based on the learner's current learning situation and areas of interest, the system can accept appropriate questions.

[0037] The reception desk can prioritize accepting highly relevant answers by considering the learner's geographical location when receiving responses. For example, if the learner is at school, the reception desk can prioritize receiving questions related to the school curriculum. If the learner is at home, the reception desk can prioritize receiving questions for home study. If the learner is at the library, the reception desk can also prioritize receiving questions related to reference materials available at the library. In this way, by considering the learner's geographical location, it is possible to prioritize accepting highly relevant answers.

[0038] The reception desk can analyze learners' social media activity when receiving answers and accept relevant answers. For example, the reception desk can prioritize questions related to learning content shared by learners on social media. The reception desk can also accept questions related to topics that learners have shown interest in on social media. The reception desk can also determine the optimal timing for receiving answers based on the amount of time learners spend on social media. This allows the reception desk to accept relevant answers by analyzing learners' social media activity.

[0039] The inference unit can adjust the level of detail of its inferences based on the importance of the incorrect answers. For example, it can perform a detailed causal analysis for important incorrect answers, and a concise explanation for minor incorrect answers. The inference unit can also adjust the level of detail based on the frequency of incorrect answers. This allows for efficient causal inference by adjusting the level of detail based on the importance of the incorrect answers.

[0040] The inference unit can apply different inference algorithms depending on the category of the incorrect answer during the inference process. For example, for calculation errors, the inference unit can apply an algorithm that analyzes the calculation process in detail. For lack of understanding, the inference unit can apply an algorithm that refers to relevant background knowledge. For misreading, the inference unit can also apply an algorithm that enhances the reading of the problem statement. By applying different inference algorithms depending on the category of the incorrect answer, highly accurate causal inference becomes possible.

[0041] The inference unit can determine the priority of inferences based on when incorrect answers were submitted. For example, it can prioritize inferences for recently submitted incorrect answers. It can also prioritize inferences for incorrect answers that have been frequently submitted in the past. The inference unit can also determine the priority of inferences based on the learner's learning schedule. This enables efficient causal inference by prioritizing inferences based on when incorrect answers were submitted.

[0042] The inference unit can adjust the order of inferences based on the relevance of the incorrect answers during the inference process. For example, the inference unit can prioritize inferences for highly relevant incorrect answers, and postpone inferences for less relevant incorrect answers. The inference unit can also dynamically adjust the order of inferences based on the relevance of the incorrect answers. This allows for efficient causal inference by adjusting the order of inferences based on the relevance of the incorrect answers.

[0043] The generation unit can adjust the level of detail of countermeasures based on the importance of the incorrect answers when generating countermeasures. For example, the generation unit can provide detailed countermeasures for important incorrect answers, and concise countermeasures for minor incorrect answers. The generation unit can also adjust the level of detail of countermeasures based on the frequency of incorrect answers. This allows for efficient countermeasure generation by adjusting the level of detail of countermeasures based on the importance of the incorrect answers.

[0044] The generation unit can apply different countermeasure algorithms depending on the category of the incorrect answer when generating countermeasures. For example, for calculation errors, the generation unit can apply an algorithm that suggests reviewing calculation methods. For lack of understanding, the generation unit can apply an algorithm that suggests reviewing relevant basic knowledge. For misreading, the generation unit can also apply an algorithm that enhances the reading of the problem statement. By applying different countermeasure algorithms depending on the category of the incorrect answer, it becomes possible to generate highly accurate countermeasures.

[0045] The generation unit can determine the priority of countermeasures based on when incorrect answers were submitted. For example, it can prioritize countermeasures for recently submitted incorrect answers. It can also prioritize countermeasures for incorrect answers that have been frequently submitted in the past. The generation unit can also determine the priority of countermeasures based on the learner's learning schedule. This enables efficient countermeasure generation by prioritizing countermeasures based on when incorrect answers were submitted.

[0046] The generation unit can adjust the order of countermeasures based on the relevance of incorrect answers when generating countermeasures. For example, the generation unit can prioritize providing countermeasures for highly relevant incorrect answers. The generation unit can also postpone providing countermeasures for less relevant incorrect answers. The generation unit can also dynamically adjust the order of countermeasures based on the relevance of incorrect answers. This enables efficient countermeasure generation by adjusting the order of countermeasures based on the relevance of incorrect answers.

[0047] The data collection unit can optimize its collection algorithm by referring to past learning data when collecting learning history. For example, the data collection unit can analyze the learner's past learning data and select the optimal collection method. The data collection unit can prioritize the collection of important data from the learner's past learning data. The data collection unit can also dynamically adjust the collection algorithm based on the learner's past learning data. This enables efficient collection of learning history by optimizing the collection algorithm by referring to past learning data.

[0048] The data collection unit can weight the collected data based on the learner's submission timing when collecting learning history. For example, the unit can assign a higher weight to recent learning history and a lower weight to past learning history. The unit can also dynamically adjust the weighting of the collected data based on the learner's learning schedule. This enables efficient collection of learning history by weighting the collected data based on the learner's submission timing.

[0049] The information provider can select the optimal method of providing basic knowledge and calculation methods by referring to the learner's past learning history. For example, the information provider can analyze the learner's past learning history and select the optimal method. Based on the learner's past learning history, the information provider can prioritize providing important basic knowledge and calculation methods. The information provider can also dynamically adjust the method of providing based on the learner's past learning history. This enables efficient provision by selecting the optimal method of providing based on the learner's past learning history.

[0050] The system can select the optimal delivery method for providing basic knowledge and calculation methods, taking into account the learner's device information. For example, if the learner is using a tablet, the system can provide a delivery method optimized for touch operation. If the learner is using a smartphone, the system can provide a delivery method adapted to the screen size. If the learner is using a personal computer, the system can also provide a delivery method optimized for keyboard operation. This allows for efficient delivery by selecting the optimal delivery method based on the learner's device information.

[0051] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0052] The reception desk can measure the learner's response speed when receiving their answers and adjust the difficulty level of the questions based on that speed. For example, if a learner enters their answer quickly, the difficulty level of the next question can be increased. Conversely, if a learner takes a long time to answer, the difficulty level of the next question can be decreased. Furthermore, the system can analyze the learner's response speed history and evaluate their progress. This allows for improved learning efficiency by providing questions of appropriate difficulty levels according to the learner's response speed.

[0053] The inference unit includes a data collection unit that collects the learner's past learning history and the content of the problems. The data collection unit can collect, for example, the learner's past answer data and learning time. Based on the learner's past learning history, the data collection unit provides data for inferring the cause of incorrect answers. The data collection unit can also collect data related to the content of the problems. For example, it can collect information such as the type and difficulty level of the problems. This allows the inference unit to more accurately infer the cause of incorrect answers based on the learner's past learning history and the content of the problems. Furthermore, the data collection unit can also collect data related to the learner's learning style and preferences. For example, if the learner prefers visual information, it can provide visual hints. This allows for the provision of measures tailored to the learner's individual needs.

[0054] The generation unit includes a provider unit that provides data such as relevant foundational knowledge and calculation methods. The provider unit can, for example, provide relevant theories and basic concepts. It can also provide data such as explanations of calculation methods and calculation procedures. This allows the generation unit to strengthen measures to prevent learners from making the same mistakes again. Furthermore, the provider unit can provide data in different formats depending on the learner's learning style. For example, it can provide diagrams and graphs to visual learners and audio guides to auditory learners. This allows for the provision of effective measures tailored to the learner's learning style.

[0055] The reception desk can analyze a learner's past answer history and select the optimal reception method. For example, it can carefully receive answers to questions that a learner has frequently answered incorrectly in the past and encourage them to review. It can also quickly receive answers to questions in areas where the learner excels and allow them to move on to the next question. The reception desk can also analyze a learner's past answer history to identify tendencies for increased concentration during specific time periods and accept answers during those times. In this way, the reception desk can select the optimal reception method by analyzing a learner's past answer history. Furthermore, based on the learner's answer history, the reception desk can identify the learner's strengths and weaknesses and propose an individualized learning plan. This enables effective learning support tailored to the individual needs of each learner.

[0056] The reception system can filter submitted answers based on the learner's current learning situation and areas of interest. For example, it can only accept questions related to the unit the learner is currently working on. It can also prioritize accepting questions related to the learner's areas of interest. Furthermore, it can accept questions of appropriate difficulty level according to the learner's current learning progress. This allows for the acceptance of appropriate questions by filtering based on the learner's current learning situation and areas of interest. In addition, the reception system can propose long-term learning plans according to the learner's learning goals. This enables effective learning support to help learners achieve their goals.

[0057] The reception desk can prioritize accepting highly relevant answers by considering the learner's geographical location when receiving responses. For example, if the learner is at school, the reception desk can prioritize receiving questions related to the school curriculum. If the learner is at home, the reception desk can prioritize receiving questions for home study. If the learner is at a library, the reception desk can also prioritize receiving questions related to reference materials available at the library. This allows for the prioritization of highly relevant answers by considering the learner's geographical location. Furthermore, the reception desk can analyze the learner's travel history and suggest the optimal learning environment. This enables effective learning support tailored to the learner's learning environment.

[0058] The reception desk can analyze learners' social media activity when receiving answers and accept relevant answers. For example, the reception desk can prioritize questions related to learning content shared by learners on social media. The reception desk can also accept questions related to topics that learners have shown interest in on social media. The reception desk can also determine the optimal timing for receiving answers based on the learners' social media activity time. This allows for the acceptance of relevant answers by analyzing learners' social media activity. Furthermore, the reception desk can analyze learners' social media interaction history and suggest learning content based on learners' interests. This enables effective learning support tailored to learners' interests.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The reception unit receives the learner's answer. For example, the learner can input their answer using a tablet. If the answer is incorrect, the reception unit sends the incorrect answer to the reasoning unit. Step 2: If the answer received by the reception unit is incorrect, the inference unit infers the cause of the error. For example, it analyzes the pattern of the incorrect answer and evaluates the learner's level of understanding. The inference unit can infer that the cause of the error is a calculation error or a lack of understanding of the problem. After inferring the cause of the error, the inference unit sends that information to the generation unit. Step 3: The generation unit generates countermeasures based on the causes inferred by the inference unit. For example, it generates countermeasures such as reviewing calculation methods or providing relevant basic knowledge. The generation unit then provides the generated countermeasures to the learner.

[0061] (Example of form 2) The self-learning support system according to an embodiment of the present invention is a self-learning support system for preschool children to junior high school students. This self-learning support system is a mechanism in which, when a student uses a tablet to self-learn, an AI agent generates "cause inference" and "countermeasures" for incorrect answers. This allows learners to understand where and why they made a mistake and to take appropriate measures to avoid making the same mistake again. First, the learner answers a problem on the tablet. If the answer is incorrect, the AI ​​agent analyzes the incorrect answer and infers the cause of the error. For example, calculation errors or insufficient understanding of the problem may be the cause. Next, based on the inferred cause, the AI ​​agent generates countermeasures to prevent the learner from making the same mistake again. For example, if the cause is a calculation error, it suggests reviewing calculation methods. If the cause is insufficient understanding of the problem, it suggests reviewing related basic knowledge. Through this mechanism, learners can understand the cause of their incorrect answers and obtain specific measures to avoid making the same mistake again. This improves learning efficiency and is expected to improve the learner's academic performance. In this way, the self-learning support system can improve learning efficiency by inferring the cause of the learner's incorrect answers and generating appropriate countermeasures.

[0062] The self-learning support system according to this embodiment comprises a reception unit, an inference unit, and a generation unit. The reception unit receives the learner's answers. The reception unit allows the learner to input answers using, for example, a tablet. If the answer is incorrect, the reception unit transmits the incorrect answer to the inference unit. The inference unit infers the cause of the incorrect answer. The inference unit analyzes the pattern of the incorrect answer and evaluates the learner's level of understanding. The inference unit can infer that the cause of the incorrect answer is a calculation error or insufficient understanding of the problem. After inferring the cause of the incorrect answer, the inference unit transmits that information to the generation unit. The generation unit generates countermeasures based on the cause inferred by the inference unit. The generation unit generates countermeasures such as reviewing calculation methods or providing relevant basic knowledge. The generation unit provides the generated countermeasures to the learner. As a result, the self-learning support system according to this embodiment can improve the efficiency of learning by inferring the cause of the learner's incorrect answers and generating appropriate countermeasures.

[0063] The reception desk receives learners' answers. Learners can input their answers to questions using devices such as tablets and personal computers. The reception desk receives the answers entered from these devices in real time and stores them in a database. If the answer is correct, feedback is provided directly to the learner; if the answer is incorrect, the incorrect answer is sent to the reasoning unit. The reception desk also has the function of managing the learner's answer history and learning progress and presenting the most suitable questions for each individual learner. For example, if a learner repeatedly makes mistakes in a particular area, the reception desk can deepen the learner's understanding by prioritizing questions related to that area. The reception desk can also analyze the learner's answer time and answer trends to evaluate the learner's concentration and level of understanding. In this way, the reception desk plays an important role in efficiently receiving learners' answers and managing learning progress. Furthermore, the reception desk has security features to safely manage learners' answer data and prevent unauthorized access and data tampering. This allows learners to proceed with their studies with peace of mind.

[0064] The inference unit infers the cause of incorrect answers. Using AI, the inference unit analyzes the learner's error patterns and evaluates their level of understanding. Specifically, it identifies where the learner is struggling based on the content and frequency of errors, as well as their past answer history. For example, if there are many calculation errors, it is likely due to a lack of understanding of calculation methods or a lack of attention. Also, if many errors are due to a lack of understanding of the problem, it can be inferred that there is a problem with reading and interpreting the problem statement. Based on this information, the inference unit clarifies the learner's weaknesses and areas for improvement. Furthermore, the inference unit can cluster the learner's error patterns and group learners with similar error patterns together to identify common problems. This allows the inference unit to grasp the learning trends of not only individual learners but also the entire group, enabling it to provide effective learning support. In addition, the inference unit can utilize past data to evaluate the learner's performance trends and learning effectiveness, and formulate long-term learning plans. In this way, the inference unit accurately infers the cause of learners' errors and provides the basic information necessary to take appropriate measures.

[0065] The generation unit generates countermeasures based on the causes inferred by the inference unit. The generation unit uses AI to generate optimal learning content tailored to the learner's reasons for errors. For example, if the cause is a calculation error, it provides review of calculation methods and presents specific calculation problems to help the learner acquire the correct calculation methods. If the cause is a lack of understanding of the problem, it generates content that explains in detail how to read and interpret the problem statement, enabling the learner to accurately understand the problem. The generation unit can customize and provide these countermeasures individually according to the learner's level and progress. Furthermore, the generation unit continuously improves the content by collecting learner feedback and evaluating the effectiveness of the countermeasures. For example, it analyzes the learner's performance and understanding after using the countermeasure content and adjusts the content and difficulty level as needed. This allows the generation unit to provide optimal learning support to learners and improve learning efficiency. The generation unit can also incorporate game elements and reward systems to maintain learner motivation. For example, it can increase learning motivation by awarding points or badges when learners achieve certain goals. This allows the generation unit to provide effective countermeasures based on the learner's reasons for errors, improving learning efficiency and motivation.

[0066] The inference unit includes a data collection unit that collects the learner's past learning history and the content of the problems. The data collection unit can collect, for example, the learner's past answer data and learning time. Based on the learner's past learning history, the data collection unit provides data for inferring the cause of incorrect answers. The data collection unit can also collect data related to the content of the problems. For example, it can collect information such as the type and difficulty level of the problems. As a result, the inference unit can more accurately infer the cause of incorrect answers based on the learner's past learning history and the content of the problems.

[0067] The generation unit includes a provider unit that provides data such as relevant foundational knowledge and calculation methods. The provider unit can, for example, provide relevant theories and basic concepts. It can also provide data such as explanations of calculation methods and calculation procedures. This allows the generation unit to strengthen measures to prevent learners from making the same mistakes again.

[0068] The reception system can estimate the learner's emotions and adjust the timing of response submission based on the estimated emotions. For example, if the learner is stressed, the reception system can temporarily delay response submission to provide time for relaxation. If the learner is focused, the reception system can quickly submit responses to avoid interrupting the learning flow. If the learner is tired, the reception system can also delay response submission and display a message encouraging a break. By adjusting the response submission timing according to the learner's emotions, learning efficiency can be improved. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0069] The reception desk can analyze a learner's past answer history and select the optimal reception method. For example, it can carefully receive answers to questions that a learner has frequently answered incorrectly in the past and encourage them to review. The reception desk can also quickly receive answers to questions in areas where the learner excels and allow them to move on to the next question. The reception desk can also analyze a learner's past answer history to identify tendencies for increased concentration during specific time periods and accept answers during those times. In this way, the reception desk can select the optimal reception method by analyzing a learner's past answer history.

[0070] The reception system can filter submitted answers based on the learner's current learning situation and areas of interest. For example, the reception system can only accept questions related to the unit the learner is currently working on. The reception system can prioritize accepting questions related to the learner's areas of interest. The reception system can also accept questions of appropriate difficulty level according to the learner's current learning progress. In this way, by filtering based on the learner's current learning situation and areas of interest, the system can accept appropriate questions.

[0071] The reception system can estimate the learner's emotions and determine the priority of the answers to be accepted based on the estimated emotions. For example, if the learner is feeling anxious, the reception system can prioritize accepting easy questions to help them build confidence. If the learner is relaxed, the reception system can prioritize accepting difficult questions to challenge them. If the learner is focused, the reception system can also accept questions continuously to maintain the flow of learning. In this way, the efficiency of learning can be improved by determining the priority of answers according to the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0072] The reception desk can prioritize accepting highly relevant answers by considering the learner's geographical location when receiving responses. For example, if the learner is at school, the reception desk can prioritize receiving questions related to the school curriculum. If the learner is at home, the reception desk can prioritize receiving questions for home study. If the learner is at the library, the reception desk can also prioritize receiving questions related to reference materials available at the library. In this way, by considering the learner's geographical location, it is possible to prioritize accepting highly relevant answers.

[0073] The reception desk can analyze learners' social media activity when receiving answers and accept relevant answers. For example, the reception desk can prioritize questions related to learning content shared by learners on social media. The reception desk can also accept questions related to topics that learners have shown interest in on social media. The reception desk can also determine the optimal timing for receiving answers based on the amount of time learners spend on social media. This allows the reception desk to accept relevant answers by analyzing learners' social media activity.

[0074] The inference unit can estimate the learner's emotions and adjust the way it expresses the cause of incorrect answers based on the estimated emotions. For example, if the learner is feeling anxious, the inference unit can explain the cause of the incorrect answer in gentle language. If the learner is relaxed, the inference unit can provide a detailed explanation of the cause of the incorrect answer. If the learner is focused, the inference unit can also present a concise and to-the-point explanation of the cause of the incorrect answer. By adjusting the way the cause of incorrect answers is expressed according to the learner's emotions, it becomes easier for the learner to understand. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0075] The inference unit can adjust the level of detail of its inferences based on the importance of the incorrect answers. For example, it can perform a detailed causal analysis for important incorrect answers, and a concise explanation for minor incorrect answers. The inference unit can also adjust the level of detail based on the frequency of incorrect answers. This allows for efficient causal inference by adjusting the level of detail based on the importance of the incorrect answers.

[0076] The inference unit can apply different inference algorithms depending on the category of the incorrect answer during the inference process. For example, for calculation errors, the inference unit can apply an algorithm that analyzes the calculation process in detail. For lack of understanding, the inference unit can apply an algorithm that refers to relevant background knowledge. For misreading, the inference unit can also apply an algorithm that enhances the reading of the problem statement. By applying different inference algorithms depending on the category of the incorrect answer, highly accurate causal inference becomes possible.

[0077] The inference unit can estimate the learner's emotions and adjust the length of the inference based on the estimated emotions. For example, if the learner is in a hurry, the inference unit can provide a short, concise inference. If the learner is relaxed, the inference unit can provide a longer inference with more detailed explanations. If the learner is focused, the inference unit can also provide an inference of moderate length. By adjusting the length of the inference according to the learner's emotions, the inference can be made easier for the learner to understand. Emotion estimation is achieved using emotion estimation functions, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0078] The inference unit can determine the priority of inferences based on when incorrect answers were submitted. For example, it can prioritize inferences for recently submitted incorrect answers. It can also prioritize inferences for incorrect answers that have been frequently submitted in the past. The inference unit can also determine the priority of inferences based on the learner's learning schedule. This enables efficient causal inference by prioritizing inferences based on when incorrect answers were submitted.

[0079] The inference unit can adjust the order of inferences based on the relevance of the incorrect answers during the inference process. For example, the inference unit can prioritize inferences for highly relevant incorrect answers, and postpone inferences for less relevant incorrect answers. The inference unit can also dynamically adjust the order of inferences based on the relevance of the incorrect answers. This allows for efficient causal inference by adjusting the order of inferences based on the relevance of the incorrect answers.

[0080] The generation unit can estimate the learner's emotions and adjust the way the countermeasures are presented based on the estimated emotions. For example, if the learner is feeling anxious, the generation unit will explain the countermeasures in gentle language. If the learner is relaxed, the generation unit can provide countermeasures that include detailed explanations. If the learner is focused, the generation unit can also present concise and to-the-point countermeasures. In this way, by adjusting the way the countermeasures are presented according to the learner's emotions, countermeasures that are easy for the learner to understand can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0081] The generation unit can adjust the level of detail of countermeasures based on the importance of the incorrect answers when generating countermeasures. For example, the generation unit can provide detailed countermeasures for important incorrect answers, and concise countermeasures for minor incorrect answers. The generation unit can also adjust the level of detail of countermeasures based on the frequency of incorrect answers. This allows for efficient countermeasure generation by adjusting the level of detail of countermeasures based on the importance of the incorrect answers.

[0082] The generation unit can apply different countermeasure algorithms depending on the category of the incorrect answer when generating countermeasures. For example, for calculation errors, the generation unit can apply an algorithm that suggests reviewing calculation methods. For lack of understanding, the generation unit can apply an algorithm that suggests reviewing relevant basic knowledge. For misreading, the generation unit can also apply an algorithm that enhances the reading of the problem statement. By applying different countermeasure algorithms depending on the category of the incorrect answer, it becomes possible to generate highly accurate countermeasures.

[0083] The generation unit can estimate the learner's emotions and adjust the length of the response based on the estimated emotions. For example, if the learner is in a hurry, the generation unit can provide a short, concise response. If the learner is relaxed, the generation unit can provide a longer response that includes detailed explanations. If the learner is focused, the generation unit can also provide a response of appropriate length. By adjusting the length of the response according to the learner's emotions, the system can provide responses that are easy for the learner to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0084] The generation unit can determine the priority of countermeasures based on when incorrect answers were submitted. For example, it can prioritize countermeasures for recently submitted incorrect answers. It can also prioritize countermeasures for incorrect answers that have been frequently submitted in the past. The generation unit can also determine the priority of countermeasures based on the learner's learning schedule. This enables efficient countermeasure generation by prioritizing countermeasures based on when incorrect answers were submitted.

[0085] The generation unit can adjust the order of countermeasures based on the relevance of incorrect answers when generating countermeasures. For example, the generation unit can prioritize providing countermeasures for highly relevant incorrect answers. The generation unit can also postpone providing countermeasures for less relevant incorrect answers. The generation unit can also dynamically adjust the order of countermeasures based on the relevance of incorrect answers. This enables efficient countermeasure generation by adjusting the order of countermeasures based on the relevance of incorrect answers.

[0086] The data collection unit can estimate the learner's emotions and adjust the method of collecting learning history based on the estimated emotions. For example, if the learner is relaxed, the data collection unit can collect detailed learning history. If the learner is in a hurry, the data collection unit can collect concise learning history. If the learner is focused, the data collection unit can also collect learning history with a moderate level of detail. This allows for efficient collection of learning history by adjusting the method of collecting learning history 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.

[0087] The data collection unit can optimize its collection algorithm by referring to past learning data when collecting learning history. For example, the data collection unit can analyze the learner's past learning data and select the optimal collection method. The data collection unit can prioritize the collection of important data from the learner's past learning data. The data collection unit can also dynamically adjust the collection algorithm based on the learner's past learning data. This enables efficient collection of learning history by optimizing the collection algorithm by referring to past learning data.

[0088] The data collection unit can estimate the learner's emotions and adjust the frequency of collecting learning history based on the estimated emotions. For example, if the learner is relaxed, the data collection unit will collect learning history frequently. If the learner is in a hurry, the data collection unit can reduce the frequency of collection to avoid interfering with learning. If the learner is focused, the data collection unit can also collect learning history at a moderate frequency. This allows for efficient collection of learning history by adjusting the frequency of collection 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 may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The data collection unit can weight the collected data based on the learner's submission timing when collecting learning history. For example, the unit can assign a higher weight to recent learning history and a lower weight to past learning history. The unit can also dynamically adjust the weighting of the collected data based on the learner's learning schedule. This enables efficient collection of learning history by weighting the collected data based on the learner's submission timing.

[0090] The system can estimate the learner's emotions and adjust the way basic knowledge and calculation methods are presented based on those estimated emotions. For example, if the learner is feeling anxious, the system will explain the basic knowledge and calculation methods in gentle language. If the learner is relaxed, the system can provide basic knowledge and calculation methods with detailed explanations. If the learner is focused, the system can also present basic knowledge and calculation methods in a concise and to-the-point manner. By adjusting the way basic knowledge and calculation methods are presented according to the learner's emotions, the system can provide information that is easy for the learner to understand. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The information provider can select the optimal method of providing basic knowledge and calculation methods by referring to the learner's past learning history. For example, the information provider can analyze the learner's past learning history and select the optimal method. Based on the learner's past learning history, the information provider can prioritize providing important basic knowledge and calculation methods. The information provider can also dynamically adjust the method of providing based on the learner's past learning history. This enables efficient provision by selecting the optimal method of providing based on the learner's past learning history.

[0092] The information provider can estimate the learner's emotions and determine the priority of providing basic knowledge and calculation methods based on the estimated emotions. For example, if the learner is feeling anxious, the provider will prioritize providing simple basic knowledge and calculation methods. If the learner is relaxed, the provider can prioritize providing more difficult basic knowledge and calculation methods. If the learner is focused, the provider can also provide basic knowledge and calculation methods continuously. This enables efficient delivery by determining the priority of providing basic knowledge and calculation methods 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.

[0093] The system can select the optimal delivery method for providing basic knowledge and calculation methods, taking into account the learner's device information. For example, if the learner is using a tablet, the system can provide a delivery method optimized for touch operation. If the learner is using a smartphone, the system can provide a delivery method adapted to the screen size. If the learner is using a personal computer, the system can also provide a delivery method optimized for keyboard operation. This allows for efficient delivery by selecting the optimal delivery method based on the learner's device information.

[0094] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0095] The reception desk can measure the learner's response speed when receiving their answers and adjust the difficulty level of the questions based on that speed. For example, if a learner enters their answer quickly, the difficulty level of the next question can be increased. Conversely, if a learner takes a long time to answer, the difficulty level of the next question can be decreased. Furthermore, the system can analyze the learner's response speed history and evaluate their progress. This allows for improved learning efficiency by providing questions of appropriate difficulty levels according to the learner's response speed.

[0096] The inference unit includes a data collection unit that collects the learner's past learning history and the content of the problems. The data collection unit can collect, for example, the learner's past answer data and learning time. Based on the learner's past learning history, the data collection unit provides data for inferring the cause of incorrect answers. The data collection unit can also collect data related to the content of the problems. For example, it can collect information such as the type and difficulty level of the problems. This allows the inference unit to more accurately infer the cause of incorrect answers based on the learner's past learning history and the content of the problems. Furthermore, the data collection unit can also collect data related to the learner's learning style and preferences. For example, if the learner prefers visual information, it can provide visual hints. This allows for the provision of measures tailored to the learner's individual needs.

[0097] The generation unit includes a provider unit that provides data such as relevant foundational knowledge and calculation methods. The provider unit can, for example, provide relevant theories and basic concepts. It can also provide data such as explanations of calculation methods and calculation procedures. This allows the generation unit to strengthen measures to prevent learners from making the same mistakes again. Furthermore, the provider unit can provide data in different formats depending on the learner's learning style. For example, it can provide diagrams and graphs to visual learners and audio guides to auditory learners. This allows for the provision of effective measures tailored to the learner's learning style.

[0098] The reception system can estimate the learner's emotions and adjust the timing of response submission based on those estimates. For example, if a learner is feeling stressed, the reception system can temporarily delay response submission to give them time to relax. If a learner is focused, the reception system can quickly submit responses to avoid interrupting the learning flow. If a learner is tired, the reception system can also delay response submission and display a message encouraging them to take a break. This allows for improved learning efficiency by adjusting response timing according to the learner's emotions. Furthermore, the reception system can monitor changes in the learner's emotions in real time and provide feedback at the appropriate time. This enables flexible responses that respond to the learner's emotions.

[0099] The reception desk can analyze a learner's past answer history and select the optimal reception method. For example, it can carefully receive answers to questions that a learner has frequently answered incorrectly in the past and encourage them to review. It can also quickly receive answers to questions in areas where the learner excels and allow them to move on to the next question. The reception desk can also analyze a learner's past answer history to identify tendencies for increased concentration during specific time periods and accept answers during those times. In this way, the reception desk can select the optimal reception method by analyzing a learner's past answer history. Furthermore, based on the learner's answer history, the reception desk can identify the learner's strengths and weaknesses and propose an individualized learning plan. This enables effective learning support tailored to the individual needs of each learner.

[0100] The reception system can filter submitted answers based on the learner's current learning situation and areas of interest. For example, it can only accept questions related to the unit the learner is currently working on. It can also prioritize accepting questions related to the learner's areas of interest. Furthermore, it can accept questions of appropriate difficulty level according to the learner's current learning progress. This allows for the acceptance of appropriate questions by filtering based on the learner's current learning situation and areas of interest. In addition, the reception system can propose long-term learning plans according to the learner's learning goals. This enables effective learning support to help learners achieve their goals.

[0101] The reception system can estimate the learner's emotions and prioritize the answers it accepts based on those emotions. For example, if a learner is feeling anxious, it can prioritize easier questions to help them build confidence. If a learner is relaxed, it can prioritize more difficult questions to challenge them. If a learner is focused, it can accept questions continuously to maintain the flow of learning. This improves learning efficiency by prioritizing answers according to the learner's emotions. Furthermore, the reception system can monitor changes in the learner's emotions in real time and provide feedback at the appropriate time. This enables flexible responses that respond to the learner's emotions.

[0102] The reception desk can prioritize accepting highly relevant answers by considering the learner's geographical location when receiving responses. For example, if the learner is at school, the reception desk can prioritize receiving questions related to the school curriculum. If the learner is at home, the reception desk can prioritize receiving questions for home study. If the learner is at a library, the reception desk can also prioritize receiving questions related to reference materials available at the library. This allows for the prioritization of highly relevant answers by considering the learner's geographical location. Furthermore, the reception desk can analyze the learner's travel history and suggest the optimal learning environment. This enables effective learning support tailored to the learner's learning environment.

[0103] The reception desk can analyze learners' social media activity when receiving answers and accept relevant answers. For example, the reception desk can prioritize questions related to learning content shared by learners on social media. The reception desk can also accept questions related to topics that learners have shown interest in on social media. The reception desk can also determine the optimal timing for receiving answers based on the learners' social media activity time. This allows for the acceptance of relevant answers by analyzing learners' social media activity. Furthermore, the reception desk can analyze learners' social media interaction history and suggest learning content based on learners' interests. This enables effective learning support tailored to learners' interests.

[0104] The inference unit can estimate the learner's emotions and adjust the way it presents the cause of incorrect answers based on those emotions. For example, if the learner is feeling anxious, the inference unit will explain the cause of the incorrect answer in gentle terms. If the learner is relaxed, the inference unit can provide a detailed explanation of the cause of the incorrect answer. If the learner is focused, the inference unit can also present a concise and to-the-point explanation of the cause of the incorrect answer. By adjusting the way the cause of incorrect answers is presented according to the learner's emotions, it becomes easier for the learner to understand. Furthermore, the inference unit can monitor changes in the learner's emotions in real time and provide feedback at the appropriate time. This enables flexible responses that are in line with the learner's emotions.

[0105] The following briefly describes the processing flow for example form 2.

[0106] Step 1: The reception unit receives the learner's answer. For example, the learner can input their answer using a tablet. If the answer is incorrect, the reception unit sends the incorrect answer to the reasoning unit. Step 2: If the answer received by the reception unit is incorrect, the inference unit infers the cause of the error. For example, it analyzes the pattern of the incorrect answer and evaluates the learner's level of understanding. The inference unit can infer that the cause of the error is a calculation error or a lack of understanding of the problem. After inferring the cause of the error, the inference unit sends that information to the generation unit. Step 3: The generation unit generates countermeasures based on the causes inferred by the inference unit. For example, it generates countermeasures such as reviewing calculation methods or providing relevant basic knowledge. The generation unit then provides the generated countermeasures to the learner.

[0107] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0108] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0109] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0110] Each of the multiple elements described above, including the reception unit, inference unit, generation unit, collection unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives the learner's answer. The inference unit is implemented by the identification processing unit 290 of the data processing device 12 and infers the cause of the incorrect answer. The generation unit is implemented by the identification processing unit 290 of the data processing device 12 and generates appropriate countermeasures. The collection unit is implemented by the control unit 46A of the smart device 14 or the identification processing unit 290 of the data processing device 12 and collects the learning history and the content of the questions. The provision unit is implemented by the control unit 46A of the smart device 14 and provides relevant basic knowledge and calculation methods. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0111] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0112] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0114] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0115] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0117] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0118] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0119] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0120] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0121] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0122] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0125] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the reception unit, inference unit, generation unit, collection unit, and provision unit, is implemented 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 and receives the learner's answer. The inference unit is implemented by the identification processing unit 290 of the data processing unit 12 and infers the cause of the incorrect answer. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates an appropriate countermeasure. The collection unit is implemented by the control unit 46A of the smart glasses 214 or the identification processing unit 290 of the data processing unit 12 and collects the learning history and the content of the questions. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides relevant basic knowledge and calculation methods. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0128] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the reception unit, inference unit, generation unit, collection unit, and provision unit, is implemented, for example, by 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 and receives the learner's answer. The inference unit is implemented by the identification processing unit 290 of the data processing unit 12 and infers the cause of the incorrect answer. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates appropriate countermeasures. The collection unit is implemented by the control unit 46A of the headset terminal 314 or the identification processing unit 290 of the data processing unit 12 and collects the learning history and the content of the questions. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides relevant basic knowledge and calculation methods. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0144] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0146] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

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

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0151] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0152] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0153] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0154] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0155] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0156] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0158] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0159] Each of the multiple elements described above, including the reception unit, inference unit, generation unit, collection unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives the learner's answer. The inference unit is implemented by the specific processing unit 290 of the data processing unit 12 and infers the cause of the incorrect answer. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates appropriate countermeasures. The collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12 and collects the learning history and the content of the problem. The provision unit is implemented by the control unit 46A of the robot 414 and provides relevant basic knowledge and calculation methods. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0160] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0161] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0162] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0163] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0164] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0165] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0167] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0168] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0169] 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.

[0170] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0171] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0172] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0173] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0174] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0175] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0176] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0177] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0178] (Note 1) A reception desk that accepts learners' answers, If the answer received by the reception unit is incorrect, the inference unit infers the cause of the incorrect answer, The system comprises a generation unit that generates countermeasures based on the causes inferred by the inference unit. A system characterized by the following features. (Note 2) The inference unit, It includes a data collection unit that collects learners' past learning history and the content of their problems. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is It includes a section that provides data such as relevant basic knowledge and calculation methods. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned reception unit is The system estimates the learner's emotions and adjusts the timing of response submission based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is Analyze the learner's past answer history and select the optimal submission method. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is When receiving responses, filtering is performed based on the learner's current learning status and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system estimates the learner's emotions and determines the priority of the answers to be accepted based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When receiving answers, the system will prioritize accepting answers that are highly relevant to the learner's geographical location, taking into account their location information. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving responses, the system analyzes the learner's social media activity and accepts responses that are relevant to that activity. The system described in Appendix 1, characterized by the features described herein. (Note 10) The inference unit, The system estimates the learner's emotions and adjusts the way it expresses the cause of incorrect answers based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The inference unit, During reasoning, adjust the level of detail of the reasoning based on the importance of the incorrect answer. The system described in Appendix 1, characterized by the features described herein. (Note 12) The inference unit, During inference, different inference algorithms are applied depending on the category of incorrect answer. The system described in Appendix 1, characterized by the features described herein. (Note 13) The inference unit, The system estimates the learner's emotions and adjusts the length of the inference based on the estimated learner's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The inference unit, During the reasoning process, the priority of the reasoning is determined based on when incorrect answers were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 15) The inference unit, During reasoning, adjust the order of inferences based on the relevance of incorrect answers. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is The system estimates the learner's emotions and adjusts the way the countermeasures are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating countermeasures, adjust the level of detail in the countermeasures based on the importance of the incorrect answers. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating countermeasures, different countermeasure algorithms are applied depending on the category of the incorrect answer. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is The system estimates the learner's emotions and adjusts the length of the response based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating countermeasures, the priority of countermeasures is determined based on when incorrect answers were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating countermeasures, adjust the order of countermeasures based on the relevance of incorrect answers. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned collection unit is We estimate learners' emotions and adjust the method of collecting learning history based on the estimated learners' emotions. The system described in Appendix 2, characterized by the features described herein. (Note 23) The aforementioned collection unit is When collecting learning history, the collection algorithm is optimized by referring to past learning data. The system described in Appendix 2, characterized by the features described herein. (Note 24) The aforementioned collection unit is The system estimates the learner's emotions and adjusts the frequency of collecting learning history based on the estimated learner emotions. The system described in Appendix 2, characterized by the features described herein. (Note 25) The aforementioned collection unit is When collecting learning history, the collected data is weighted based on when the learner submitted their work. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned supply unit is, The system estimates the learner's emotions and adjusts the way basic knowledge and calculation methods are provided based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing basic knowledge and calculation methods, the system selects the most appropriate method of delivery by referring to the learner's past learning history. The system described in Appendix 3, characterized by the features described herein. (Note 28) The aforementioned supply unit is, The system estimates the learner's emotions and determines the priority of providing basic knowledge and calculation methods based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing basic knowledge and calculation methods, the optimal delivery method is selected considering the learner's device information. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that accepts learners' answers, If the answer received by the reception unit is incorrect, the inference unit infers the cause of the incorrect answer, The system comprises a generation unit that generates countermeasures based on the causes inferred by the inference unit. A system characterized by the following features.

2. The inference unit, It includes a data collection unit that collects learners' past learning history and the content of their problems. The system according to feature 1.

3. The generating unit is It includes a section that provides data such as relevant basic knowledge and calculation methods. The system according to feature 1.

4. The aforementioned reception unit is The system estimates the learner's emotions and adjusts the timing of response submission based on those estimated emotions. The system according to feature 1.

5. The aforementioned reception unit is Analyze the learner's past answer history and select the optimal submission method. The system according to feature 1.

6. The aforementioned reception unit is When receiving responses, filtering is performed based on the learner's current learning status and areas of interest. The system according to feature 1.

7. The aforementioned reception unit is The system estimates the learner's emotions and determines the priority of the answers to be accepted based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is When receiving answers, the system will prioritize accepting answers that are highly relevant to the learner's geographical location, taking into account their location information. The system according to feature 1.

9. The aforementioned reception unit is When receiving responses, the system analyzes the learner's social media activity and accepts responses that are relevant to that activity. The system according to feature 1.

10. The inference unit, The system estimates the learner's emotions and adjusts the way it expresses the cause of incorrect answers based on those estimated emotions. The system according to feature 1.

Images