System

Abstract

An object of the system according to the embodiment is to immediately explain a part in which the learner has a question.SOLUTION: A system according to an embodiment includes a selection unit, an analysis unit, and a provision unit. The selection unit selects a portion in which the learner has a question. The analysis unit analyzes the range selected by the selection unit. The providing unit provides an explanation based on the result analyzed by the analyzing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, even when using digital textbooks, there is not enough of a system in place to provide immediate explanations for any parts of the text that learners are unsure about, so there is room for improvement.

[0005] The system according to the embodiment aims to provide immediate explanations to learners about any points they are unsure about. [Means for solving the problem]

[0006] The system according to the embodiment includes a selection unit, an analysis unit, and a provision unit. The selection unit selects a portion about which the learner has questions. The analysis unit analyzes the range selected by the selection unit. The provision unit provides an explanation based on the results of the analysis by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can immediately provide explanations on any points that the learner is unsure about. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A learning support system according to an embodiment of the present invention is a system in which, when a learner selects a section in a digital textbook about which they have questions, an AI instantly provides an explanation for that section. The learning support system allows a learner to select a section about which they have questions, and an AI analyzes that section and provides an explanation. The learning support system also provides in-depth information related to the selected section. For example, the learning support system allows a learner to select a section of a digital textbook about which they have questions. For example, the learning support system allows a learner to select a section of text, a diagram, or the like. The learning support system then uses an AI to provide an explanation based on the selected section. The AI ​​analyzes the content of the selected text or diagram and provides related information. For example, the AI ​​may provide a detailed explanation or background information about a specific historical event. Furthermore, the learning support system also provides in-depth information related to the selected section. For example, the AI ​​may provide information about other events or people related to the specific historical event. This allows the learning support system to instantly resolve any questions the learner has, improving learning efficiency. Furthermore, by delving deeper into areas of interest, learning becomes more enjoyable and motivation increases. This allows the learning support system to immediately resolve any questions the learner has, improving learning efficiency. For example, if a learner has questions about a particular historical event, providing detailed explanations and background information about that event will help the learner gain a deeper understanding. Furthermore, digging deeper into areas of interest makes learning more enjoyable and increases motivation to learn.

[0029] A learning assistance system according to an embodiment includes a selection unit, an analysis unit, and a provision unit. The selection unit selects a portion about which the learner has questions. The portion about which the learner has questions may include, but is not limited to, a specific keyword, a context, or a portion related to a specific topic. The selection unit may make a selection by, for example, a mouse click, a touch operation, or a voice input. The selection unit may also select a range of text, a diagram, or the like. For example, the selection unit may select by highlighting a portion of text. The selection unit may also select a specific portion of a diagram. The analysis unit analyzes the range selected by the selection unit. The analysis unit performs the analysis using, for example, text analysis, image analysis, natural language processing technology, or the like. For example, the analysis unit may analyze the content of the selected text and extract related information. The analysis unit may also analyze the content of the selected diagram and extract related information. The provision unit provides an explanation based on the results of the analysis by the analysis unit. The explanation may be provided in the form of, for example, text, audio, video, or the like, but is not limited to, these examples. For example, the providing unit provides a detailed explanation of the selected range in text format. The providing unit can also provide the explanation of the selected range in audio format. The providing unit can also provide the explanation of the selected range in video format. As a result, the learning assistance system according to the embodiment can immediately explain parts that the learner is unsure about and provide in-depth information, thereby improving the efficiency and enjoyment of learning.

[0030] The providing unit can provide in-depth information related to the selected range. Examples of in-depth information include, but are not limited to, additional reference materials, detailed explanations, and related topics. For example, the providing unit can provide information about other events or people related to the selected range. The providing unit can also provide detailed background information related to the selected range. The providing unit can also provide additional reference materials related to the selected range. This allows learners to gain a deeper understanding by providing in-depth information related to the selected range. Some or all of the above-described processing by the providing unit can be performed using, or without, AI. For example, the providing unit can input information related to the selected range into a generation AI and cause the generation AI to generate in-depth information.

[0031] The analysis unit may include a related information search unit that analyzes the content of the selected text or figure and searches for related information. Related information includes, but is not limited to, related literature, related data, and related images. For example, the related information search unit may analyze the content of the selected text and search for related literature. The related information search unit may also analyze the content of the selected figure and search for related data. The related information search unit may also search for images related to the selected range. By analyzing the content of the selected text or figure and searching for related information, appropriate information can be provided to the learner. Some or all of the above-described processing in the related information search unit may be performed using, for example, AI, or may be performed without using AI. For example, the related information search unit may input the content of the selected text into the generation AI and cause the generation AI to search for related information.

[0032] The providing unit may include a reliability evaluation unit that evaluates the accuracy of the information to be provided. Evaluation criteria for accuracy include, but are not limited to, reliability of the information source, consistency of the data, and expert review. For example, the reliability evaluation unit evaluates the information source of the information to be provided and determines its reliability. The reliability evaluation unit can also evaluate the consistency of the data of the information to be provided. The reliability evaluation unit can also evaluate whether the information to be provided has been reviewed by an expert. By evaluating the accuracy of the information to be provided, highly reliable information can be provided to learners. Some or all of the above-described processing in the reliability evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reliability evaluation unit can input the reliability of the information to be provided to the generating AI and cause the generating AI to evaluate the reliability.

[0033] The selection unit can select a range of text or a diagram. Examples of text or a diagram include, but are not limited to, sentences, tables, graphs, illustrations, etc. The selection unit can, for example, highlight a portion of text to select it. The selection unit can also select a specific portion of a diagram. The selection unit can also select both text and a diagram simultaneously. In this way, by selecting a range of text, a diagram, etc., the learner can accurately specify the part about which they have questions. Some or all of the above-mentioned processing in the selection unit can be performed, for example, using AI or without AI. For example, the selection unit can input the range of text or a diagram to a generation AI and have the generation AI analyze the selected range.

[0034] The selection unit can analyze the learner's past selection history and suggest an optimal selection method. The past selection history includes, but is not limited to, selected topics, selection frequency, and selected time period. For example, the selection unit can automatically display as candidates the ranges that the learner has frequently selected in the past. The selection unit can also preferentially suggest selection methods (text, diagrams, etc.) that the learner has used in the past. The selection unit can also predict and suggest the range to be selected in a specific time period based on the learner's past selection history. In this way, the optimal selection method can be suggested by analyzing the learner's past selection history. Some or all of the above-described processing in the selection unit may be performed using, or without, AI. For example, the selection unit can input the learner's past selection history data into a generation AI and have the generation AI suggest an optimal selection method.

[0035] When making a selection, the selection unit can filter the selection range based on the learner's current learning progress and level of understanding. Examples of learning progress and level of understanding include, but are not limited to, test results, study time, and self-assessment. The selection unit automatically filters appropriate ranges based on, for example, the learner's current learning progress. The selection unit can also exclude difficult ranges and suggest appropriate ranges based on the learner's level of understanding. The selection unit can also filter the optimal selection range based on the learner's past learning history. In this way, appropriate ranges can be suggested by filtering the selection range based on the learner's learning progress and level of understanding. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the learner's learning progress data to the generation AI and have the generation AI filter the selection range.

[0036] The selection unit can provide an optimal selection means according to the learner's input method when making a selection. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, when a learner specifies a selection range by voice, the selection unit provides a selection means corresponding to the voice input. Furthermore, when a learner specifies a selection range by text, the selection unit can also provide a selection means corresponding to the text input. Furthermore, when a learner specifies a selection range by image, the selection unit can also provide a selection means corresponding to the image input. This improves the convenience of selection by providing an optimal selection means according to the learner's input method. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the learner's input data to a generation AI and cause the generation AI to provide an optimal selection means.

[0037] When making a selection, the selection unit may prioritize selecting a highly relevant range by taking into consideration the learner's geographical location information. Examples of geographical location information include, but are not limited to, GPS data, IP addresses, and location information services. For example, if the learner is in a specific region, the selection unit may prioritize presenting a range related to that region. Furthermore, if the learner is in a specific location, the selection unit may prioritize presenting a range related to that location. Furthermore, the selection unit may prioritize selecting a highly relevant range based on the learner's geographical location information. In this way, highly relevant ranges can be prioritized by taking the learner's geographical location information into consideration. Some or all of the above-described processing by the selection unit may be performed using, or without, AI. For example, the selection unit may input the learner's geographical location information data into the generation AI and cause the generation AI to select a highly relevant range.

[0038] When making the selection, the selection unit may analyze the learner's social media activity and select the relevant range. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, and the number of followers. For example, the selection unit may select the range related to topics in which the learner has shown interest on social media. The selection unit may also analyze the content of the learner's social media posts and select the relevant range. The selection unit may also select the relevant range with reference to the activities of the learner's friends on social media. In this way, the relevant range can be selected by analyzing the learner's social media activity. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input the learner's social media activity data into the generation AI and cause the generation AI to select the relevant range.

[0039] The selection unit can customize the selection method by reflecting the learner's past feedback when making a selection. Past feedback includes, but is not limited to, evaluation comments, survey results, and usage history. For example, the selection unit suggests an optimal selection method based on feedback previously provided by the learner. The selection unit can also preferentially suggest a specific selection method based on the learner's past feedback. The selection unit can also customize the selection method by reflecting the learner's feedback. In this way, the optimal selection method can be customized by reflecting the learner's past feedback. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the learner's past feedback data into the generation AI and cause the generation AI to customize the selection method.

[0040] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the selected range. Criteria for evaluating importance include, but are not limited to, relevance to the learning goal, the learner's interest, and expert evaluation. For example, if the selected range is important, the analysis unit can perform a detailed analysis and provide relevant information. Furthermore, if the selected range has basic content, the analysis unit can perform a simplified analysis and provide basic information. The analysis unit can also adjust the level of detail of the analysis according to the importance of the selected range. This allows appropriate information to be provided by adjusting the level of detail of the analysis according to the importance of the selected range. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input importance data of the selected range to a generation AI and have the generation AI adjust the level of detail of the analysis.

[0041] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the selected range. Examples of categories include, but are not limited to, topic, difficulty level, and format. For example, if the history range is selected, the analysis unit can apply an algorithm that analyzes historical background. Furthermore, if the science range is selected, the analysis unit can apply an algorithm that analyzes scientific theories. Furthermore, if the literature range is selected, the analysis unit can apply an algorithm that performs literary analysis. By applying different analysis algorithms depending on the category of the selected range, appropriate analysis results can be provided. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input category data of the selected range into a generation AI and have the generation AI apply the analysis algorithm.

[0042] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the learner's past analysis results. Examples of past analysis results include, but are not limited to, methods for saving, reusing, and comparing analysis results. The analysis unit improves the accuracy of the analysis, for example, based on the learner's past analysis results. The analysis unit can also suggest an optimal analysis method by referring to the learner's past analysis history. The analysis unit can also improve the accuracy of the analysis by reflecting the learner's past analysis results. In this way, the accuracy of the analysis is improved by referring to the learner's past analysis results. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the learner's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0043] During analysis, the analysis unit can determine the analysis priority based on the submission time of the selected range. The submission time includes, but is not limited to, the submission date and time, the submission deadline, and the submission frequency. For example, the analysis unit prioritizes analysis of ranges with upcoming submission deadlines. The analysis unit can also postpone analysis of ranges with more distant submission deadlines. The analysis unit can also adjust the analysis priority based on the submission time. By determining the analysis priority based on the submission time of the selected range, analysis results can be provided at an appropriate time. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input submission time data of the selected range into a generation AI and have the generation AI determine the analysis priority.

[0044] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the selected range. Relevance evaluation criteria include, but are not limited to, topic consistency, keyword co-occurrence, and the number of citations of related literature. For example, the analysis unit prioritizes analysis of highly relevant ranges. The analysis unit can also postpone analysis of less relevant ranges. The analysis unit can also adjust the order of analysis based on the relevance of the selected range. By adjusting the order of analysis based on the relevance of the selected range, highly relevant information can be provided preferentially. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input relevance data of the selected range into a generation AI and have the generation AI adjust the order of analysis.

[0045] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the learner's level of expertise. Examples of expertise levels include, but are not limited to, test results, self-assessments, and learning histories. For example, if the learner's level of expertise is low, the analysis unit can provide analysis results using simple terms. Alternatively, if the learner's level of expertise is high, the analysis unit can provide detailed analysis results using technical terms. The analysis unit can also adjust the use of technical terms in the analysis according to the learner's level of expertise. This allows for appropriate analysis results to be provided by adjusting the use of technical terms in the analysis according to the learner's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the learner's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms.

[0046] When providing an explanation, the providing unit can adjust the level of detail of the explanation based on the importance of the selected range. Examples of the level of detail of the explanation include, but are not limited to, the length of the explanation, the depth of the information, and the number of specific examples. For example, the providing unit provides a detailed explanation if the selected range is important. Furthermore, the providing unit can also provide a brief explanation if the selected range has basic content. Furthermore, the providing unit can adjust the level of detail of the explanation according to the importance of the selected range. This allows appropriate information to be provided by adjusting the level of detail of the explanation according to the importance of the selected range. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input importance data of the selected range to a generating AI and cause the generating AI to adjust the level of detail of the explanation.

[0047] When providing an explanation, the providing unit can apply different explanation algorithms depending on the category of the selected range. Explanation algorithms include, but are not limited to, natural language generation algorithms and template-based generation methods. For example, if the history range is selected, the providing unit can apply an algorithm that explains the historical background. Furthermore, if the science range is selected, the providing unit can apply an algorithm that explains scientific theories. Furthermore, if the literature range is selected, the providing unit can apply an algorithm that performs literary analysis. In this way, by applying different explanation algorithms depending on the category of the selected range, appropriate explanations can be provided. Some or all of the above-mentioned processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input category data of the selected range into a generation AI and cause the generation AI to apply an explanation algorithm.

[0048] When providing an explanation, the providing unit can improve the accuracy of the explanation by referring to the learner's past explanation results. Past explanation results include, for example, a method for saving, reusing, and comparing explanations, but are not limited to these examples. The providing unit improves the accuracy of the explanation, for example, based on the learner's past explanation results. The providing unit can also suggest an optimal explanation method by referring to the learner's past explanation history. The providing unit can also improve the accuracy of the explanation by reflecting the learner's past explanation results. In this way, the accuracy of the explanation is improved by referring to the learner's past explanation results. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input the learner's past explanation result data into the generation AI and cause the generation AI to improve the accuracy of the explanation.

[0049] When providing an explanation, the providing unit can determine the priority of the explanation based on the submission time of the selected range. The priority of the explanation includes, but is not limited to, for example, the submission time, the urgency of the information, and the importance of the information. For example, the providing unit can prioritize the provision of explanations for a range with an upcoming submission deadline. The providing unit can also postpone the provision of explanations for a range with a distant submission deadline. The providing unit can also adjust the priority of the explanation based on the submission time. This allows the explanation to be provided at an appropriate time by determining the priority of the explanation based on the submission time of the selected range. Some or all of the above-described processing by the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input submission time data for the selected range into a generating AI and cause the generating AI to determine the priority of the explanations.

[0050] When providing explanations, the providing unit can adjust the order of explanations based on the relevance of the selected range. Examples of the order of explanations include, but are not limited to, a method of prioritizing highly relevant information and a method based on the learner's level of interest. For example, the providing unit can provide explanations for highly relevant ranges first. The providing unit can also provide explanations for less relevant ranges later. The providing unit can also adjust the order of explanations based on the relevance of the selected range. Thus, by adjusting the order of explanations based on the relevance of the selected range, highly relevant information can be provided first. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input relevance data for the selected range to a generating AI and cause the generating AI to adjust the order of explanations.

[0051] When providing an explanation, the providing unit can adjust the use of technical terms in the explanation according to the learner's level of expertise. Examples of the use of technical terms include, but are not limited to, selecting terms and explaining methods according to the learner's level of expertise. For example, if the learner's level of expertise is low, the providing unit can provide an explanation using simple terms. Furthermore, if the learner's level of expertise is high, the providing unit can provide a detailed explanation using technical terms. Furthermore, the providing unit can adjust the use of technical terms in the explanation according to the learner's level of expertise. This allows for the provision of an appropriate explanation by adjusting the use of technical terms in the explanation according to the learner's level of expertise. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit can input the learner's level of expertise data into the generating AI and cause the generating AI to adjust the use of technical terms.

[0052] When searching for related information, the related information search unit can adjust the level of search detail based on the importance of the selected range. Examples of the level of search detail include, but are not limited to, the number of search results, the depth of information, and filtering criteria. For example, if the selected range is important, the related information search unit can perform a detailed search to provide related information. Furthermore, if the selected range has basic content, the related information search unit can perform a simplified search to provide basic information. Furthermore, the related information search unit can adjust the level of search detail based on the importance of the selected range. This allows appropriate information to be provided by adjusting the level of search detail based on the importance of the selected range. Some or all of the above-described processing in the related information search unit may be performed using, for example, AI, or may be performed without AI. For example, the related information search unit can input importance data of the selected range into a generation AI and cause the generation AI to adjust the level of search detail.

[0053] When searching for related information, the related information search unit can apply different search algorithms depending on the category of the selected range. Search algorithms include, but are not limited to, full-text search algorithms and pattern matching algorithms. For example, if the history range is selected, the related information search unit can apply an algorithm to search for historical background. Furthermore, if the science range is selected, the related information search unit can apply an algorithm to search for scientific theories. Furthermore, if the literature range is selected, the related information search unit can apply an algorithm to perform literary analysis. This allows appropriate information to be provided by applying different search algorithms depending on the category of the selected range. Some or all of the above-described processing in the related information search unit can be performed using, for example, AI, or without AI. For example, the related information search unit can input category data for the selected range into a generation AI and cause the generation AI to apply a search algorithm.

[0054] When searching for related information, the related information search unit can determine search priorities based on the submission dates of the selected range. Search priorities include, but are not limited to, submission dates, urgency of the information, and importance of the information. For example, the related information search unit can prioritize providing related information with an upcoming submission deadline. The related information search unit can also delay providing related information with a distant submission deadline. The related information search unit can also adjust the priority of related information based on the submission dates. By determining search priorities based on the submission dates of the selected range, information can be provided at an appropriate time. Some or all of the above-described processing in the related information search unit may be performed using, for example, AI, or may be performed without AI. For example, the related information search unit can input submission date data of the selected range into a generation AI and have the generation AI determine the search priorities.

[0055] When searching for related information, the related information search unit can adjust the search order based on the relevance of the selected range. Examples of the search order include, but are not limited to, a method that prioritizes highly relevant information or a method based on the learner's level of interest. For example, the related information search unit can provide related information in a highly relevant range first. The related information search unit can also provide related information in a less relevant range later. The related information search unit can also adjust the search order of related information based on the relevance of the selected range. By adjusting the search order based on the relevance of the selected range, highly relevant information can be provided first. Some or all of the above-described processing in the related information search unit may be performed using, for example, AI, or may be performed without AI. For example, the related information search unit can input the relevance data of the selected range into a generation AI and cause the generation AI to adjust the search order.

[0056] The reliability evaluation unit can adjust the level of detail of the evaluation based on the importance of the selected range during reliability evaluation. The level of detail of the evaluation includes, but is not limited to, the depth of the evaluation, the number of evaluation items, and the frequency of the evaluation. For example, if the selected range is important, the reliability evaluation unit can perform a detailed reliability evaluation. Furthermore, if the selected range has basic content, the reliability evaluation unit can also perform a simplified reliability evaluation. The reliability evaluation unit can also adjust the level of detail of the reliability evaluation according to the importance of the selected range. By adjusting the level of detail of the evaluation according to the importance of the selected range, appropriate information can be provided. Some or all of the above-described processing in the reliability evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reliability evaluation unit can input importance data of the selected range to the generation AI and cause the generation AI to adjust the level of detail of the evaluation.

[0057] The reliability evaluation unit can apply different evaluation algorithms depending on the category of the selected range during reliability evaluation. Examples of evaluation algorithms include, but are not limited to, scoring algorithms and ranking algorithms. For example, if the history range is selected, the reliability evaluation unit can apply an algorithm that evaluates historical background. Furthermore, if the science range is selected, the reliability evaluation unit can apply an algorithm that evaluates scientific theories. Furthermore, if the literature range is selected, the reliability evaluation unit can apply an algorithm that performs literary analysis. By applying different evaluation algorithms depending on the category of the selected range, appropriate information can be provided. Some or all of the above-described processing in the reliability evaluation unit can be performed using, for example, AI, or without AI. For example, the reliability evaluation unit can input category data of the selected range into a generation AI and cause the generation AI to apply the evaluation algorithm.

[0058] During the reliability evaluation, the reliability evaluation unit can determine the priority of the evaluation based on the submission time of the selected range. Examples of the priority of the evaluation include, but are not limited to, the submission time, the urgency of the information, and the importance of the information. For example, the reliability evaluation unit prioritizes the reliability evaluation of the range with the nearest submission deadline. The reliability evaluation unit can also postpone the reliability evaluation of the range with the further away submission deadline. The reliability evaluation unit can also adjust the priority of the reliability evaluation based on the submission time. By determining the priority of the evaluation based on the submission time of the selected range, information can be provided at an appropriate time. Some or all of the above-described processing in the reliability evaluation unit may be performed using, for example, AI, or may be performed without AI. For example, the reliability evaluation unit can input the submission time data of the selected range into the generation AI and have the generation AI determine the priority of the evaluation.

[0059] The reliability evaluation unit can adjust the order of evaluation based on the relevance of the selected range during reliability evaluation. Examples of the order of evaluation include, but are not limited to, a method of prioritizing highly relevant information and a method based on the learner's interest. For example, the reliability evaluation unit prioritizes reliability evaluation of highly relevant ranges. The reliability evaluation unit can also postpone reliability evaluation of less relevant ranges. The reliability evaluation unit can also adjust the order of reliability evaluation based on the relevance of the selected range. By adjusting the order of evaluation based on the relevance of the selected range, highly relevant information can be provided preferentially. Some or all of the above-described processing in the reliability evaluation unit may be performed using, or without, AI. For example, the reliability evaluation unit can input relevance data of the selected range into a generation AI and cause the generation AI to adjust the order of evaluation.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] Learning support systems can provide customized learning plans based on a learner's learning style. For example, visual learners can be provided with explanations that make extensive use of diagrams and videos. Auditory learners can be provided with audio commentary or podcast-style information. Furthermore, tactile learners can experience the learning content through interactive quizzes and simulations. This allows learners to receive the optimal learning experience based on their individual learning styles.

[0062] Learning support systems can analyze a learner's learning history and suggest what they should study next based on their learning progress. For example, if a learner is struggling with a particular topic, they can be suggested to review basic content related to that topic. Also, if a learner excels in a particular field, they can be suggested to study more advanced content related to that field. Furthermore, they can automatically adjust their learning schedule according to the learner's learning pace. This allows learners to progress efficiently.

[0063] Learning support systems can utilize learners' geographic location information to provide learning content relevant to the region. For example, if a learner is in a specific region, they can be provided with information about the history and culture of that region. If a learner is traveling, they can be provided with information about tourist attractions and local specialties. Furthermore, if a learner is learning a language from a specific region, they can be provided with information about the dialect and idioms of that region. This allows learners to learn based on a geographical context.

[0064] The learning support system can analyze a learner's social media activity and provide learning content related to topics that interest the learner. For example, it can provide articles and videos related to topics that the learner frequently mentions on social media. It can also provide learning resources recommended by influencers that the learner follows. It can also provide information related to topics that are trending in online communities in which the learner participates. This makes it possible to provide a personalized learning experience based on the learner's interests.

[0065] The learning support system can automatically recommend what a learner should learn next based on the learner's learning progress. For example, if a learner has completed a specific topic, it can suggest the next step related to that topic. Also, if a learner is struggling in a particular area, it can suggest that they review basic content related to that area. Furthermore, if a learner excels in a particular area, it can suggest that they study advanced content related to that area. This allows learners to progress efficiently in their studies.

[0066] The learning support system can analyze a learner's learning history and suggest review timing based on what the learner has learned in the past. For example, it can suggest that a learner review a specific topic after a certain period of time has passed since learning that topic. It can also suggest that a learner periodically review topics that the learner struggled with in the past. Furthermore, if a learner is studying for a specific exam or assessment, it can suggest that the learner review content related to that exam or assessment. This allows the learner to review effectively and solidify what they have learned.

[0067] The processing flow of the first embodiment will be briefly explained below.

[0068] Step 1: In the selection section, learners select the part of the text they are unsure about. Learners can select parts related to specific keywords, context, or a specific topic. Selection methods include mouse clicks, touch operations, and voice input, and can select ranges of text or figures. For example, learners can highlight and select a portion of text or select a specific part of a figure. Step 2: The analysis unit analyzes the range selected by the selection unit. The analysis unit performs the analysis using text analysis, image analysis, natural language processing technology, etc. For example, the analysis unit analyzes the content of the selected text and extracts related information. It can also analyze the content of the selected chart or diagram and extract related information. Step 3: The providing unit provides an explanation based on the results of the analysis by the analyzing unit. The explanation is provided in the form of text, audio, video, etc. For example, a detailed explanation of the selected range can be provided in text format, audio format, or video format.

[0069] (Example 2) A learning support system according to an embodiment of the present invention is a system in which, when a learner selects a section in a digital textbook about which they have questions, an AI instantly provides an explanation for that section. The learning support system allows a learner to select a section about which they have questions, and an AI analyzes that section and provides an explanation. The learning support system also provides in-depth information related to the selected section. For example, the learning support system allows a learner to select a section of a digital textbook about which they have questions. For example, the learning support system allows a learner to select a section of text, a diagram, or the like. The learning support system then uses an AI to provide an explanation based on the selected section. The AI ​​analyzes the content of the selected text or diagram and provides related information. For example, the AI ​​may provide a detailed explanation or background information about a specific historical event. Furthermore, the learning support system also provides in-depth information related to the selected section. For example, the AI ​​may provide information about other events or people related to the specific historical event. This allows the learning support system to instantly resolve any questions the learner has, improving learning efficiency. Furthermore, by delving deeper into areas of interest, learning becomes more enjoyable and motivation increases. This allows the learning support system to immediately resolve any questions the learner has, improving learning efficiency. For example, if a learner has questions about a particular historical event, providing detailed explanations and background information about that event will help the learner gain a deeper understanding. Furthermore, digging deeper into areas of interest makes learning more enjoyable and increases motivation to learn.

[0070] A learning assistance system according to an embodiment includes a selection unit, an analysis unit, and a provision unit. The selection unit selects a portion about which the learner has questions. The portion about which the learner has questions may include, but is not limited to, a specific keyword, a context, or a portion related to a specific topic. The selection unit may make a selection by, for example, a mouse click, a touch operation, or a voice input. The selection unit may also select a range of text, a diagram, or the like. For example, the selection unit may select by highlighting a portion of text. The selection unit may also select a specific portion of a diagram. The analysis unit analyzes the range selected by the selection unit. The analysis unit performs the analysis using, for example, text analysis, image analysis, natural language processing technology, or the like. For example, the analysis unit may analyze the content of the selected text and extract related information. The analysis unit may also analyze the content of the selected diagram and extract related information. The provision unit provides an explanation based on the results of the analysis by the analysis unit. The explanation may be provided in the form of, for example, text, audio, video, or the like, but is not limited to, these examples. For example, the providing unit provides a detailed explanation of the selected range in text format. The providing unit can also provide the explanation of the selected range in audio format. The providing unit can also provide the explanation of the selected range in video format. As a result, the learning assistance system according to the embodiment can immediately explain parts that the learner is unsure about and provide in-depth information, thereby improving the efficiency and enjoyment of learning.

[0071] The providing unit can provide in-depth information related to the selected range. Examples of in-depth information include, but are not limited to, additional reference materials, detailed explanations, and related topics. For example, the providing unit can provide information about other events or people related to the selected range. The providing unit can also provide detailed background information related to the selected range. The providing unit can also provide additional reference materials related to the selected range. This allows learners to gain a deeper understanding by providing in-depth information related to the selected range. Some or all of the above-described processing by the providing unit can be performed using, or without, AI. For example, the providing unit can input information related to the selected range into a generation AI and cause the generation AI to generate in-depth information.

[0072] The analysis unit may include a related information search unit that analyzes the content of the selected text or figure and searches for related information. Related information includes, but is not limited to, related literature, related data, and related images. For example, the related information search unit may analyze the content of the selected text and search for related literature. The related information search unit may also analyze the content of the selected figure and search for related data. The related information search unit may also search for images related to the selected range. By analyzing the content of the selected text or figure and searching for related information, appropriate information can be provided to the learner. Some or all of the above-described processing in the related information search unit may be performed using, for example, AI, or may be performed without using AI. For example, the related information search unit may input the content of the selected text into the generation AI and cause the generation AI to search for related information.

[0073] The providing unit may include a reliability evaluation unit that evaluates the accuracy of the information to be provided. Evaluation criteria for accuracy include, but are not limited to, reliability of the information source, consistency of the data, and expert review. For example, the reliability evaluation unit evaluates the information source of the information to be provided and determines its reliability. The reliability evaluation unit can also evaluate the consistency of the data of the information to be provided. The reliability evaluation unit can also evaluate whether the information to be provided has been reviewed by an expert. By evaluating the accuracy of the information to be provided, highly reliable information can be provided to learners. Some or all of the above-described processing in the reliability evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reliability evaluation unit can input the reliability of the information to be provided to the generating AI and cause the generating AI to evaluate the reliability.

[0074] The selection unit can select a range of text or a diagram. Examples of text or a diagram include, but are not limited to, sentences, tables, graphs, illustrations, etc. The selection unit can, for example, highlight a portion of text to select it. The selection unit can also select a specific portion of a diagram. The selection unit can also select both text and a diagram simultaneously. In this way, by selecting a range of text, a diagram, etc., the learner can accurately specify the part about which they have questions. Some or all of the above-mentioned processing in the selection unit can be performed, for example, using AI or without AI. For example, the selection unit can input the range of text or a diagram to a generation AI and have the generation AI analyze the selected range.

[0075] The selection unit can estimate the learner's emotions and adjust the presentation method of the selection range based on the estimated learner's emotions. Examples of learner emotions include, but are not limited to, stress, relaxation, and excitement. For example, if the learner is stressed, the selection unit can provide a simple interface and simplify the presentation of the selection range. Furthermore, if the learner is relaxed, the selection unit can provide detailed selection options and suggest a customizable selection method. Furthermore, if the learner is excited, the selection unit can present the selection range with visually appealing effects. This allows for an optimal interface for the learner by adjusting the presentation method of the selection range according to the learner's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the selection unit may be performed using, for example, an AI. For example, the selection unit can input the learner's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0076] The selection unit can analyze the learner's past selection history and suggest an optimal selection method. The past selection history includes, but is not limited to, selected topics, selection frequency, and selected time period. For example, the selection unit can automatically display as candidates the ranges that the learner has frequently selected in the past. The selection unit can also preferentially suggest selection methods (text, diagrams, etc.) that the learner has used in the past. The selection unit can also predict and suggest the range to be selected in a specific time period based on the learner's past selection history. In this way, the optimal selection method can be suggested by analyzing the learner's past selection history. Some or all of the above-described processing in the selection unit may be performed using, or without, AI. For example, the selection unit can input the learner's past selection history data into a generation AI and have the generation AI suggest an optimal selection method.

[0077] When making a selection, the selection unit can filter the selection range based on the learner's current learning progress and level of understanding. Examples of learning progress and level of understanding include, but are not limited to, test results, study time, and self-assessment. The selection unit automatically filters appropriate ranges based on, for example, the learner's current learning progress. The selection unit can also exclude difficult ranges and suggest appropriate ranges based on the learner's level of understanding. The selection unit can also filter the optimal selection range based on the learner's past learning history. In this way, appropriate ranges can be suggested by filtering the selection range based on the learner's learning progress and level of understanding. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the learner's learning progress data to the generation AI and have the generation AI filter the selection range.

[0078] The selection unit can provide an optimal selection means according to the learner's input method when making a selection. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, when a learner specifies a selection range by voice, the selection unit provides a selection means corresponding to the voice input. Furthermore, when a learner specifies a selection range by text, the selection unit can also provide a selection means corresponding to the text input. Furthermore, when a learner specifies a selection range by image, the selection unit can also provide a selection means corresponding to the image input. This improves the convenience of selection by providing an optimal selection means according to the learner's input method. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the learner's input data to a generation AI and cause the generation AI to provide an optimal selection means.

[0079] The selection unit can estimate the learner's emotions and prioritize the selection ranges based on the estimated learner's emotions. Examples of learner emotions include, but are not limited to, stress, relaxation, and excitement. For example, if the learner is stressed, the selection unit can prioritize presenting simple ranges. Furthermore, if the learner is relaxed, the selection unit can prioritize presenting detailed ranges. Furthermore, if the learner is excited, the selection unit can prioritize presenting interesting ranges. By prioritizing the selection ranges according to the learner's emotions, the optimal range for the learner can be presented. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the selection unit may be performed using, for example, an AI. For example, the selection unit can input the learner's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0080] When making a selection, the selection unit may prioritize selecting a highly relevant range by taking into consideration the learner's geographical location information. Examples of geographical location information include, but are not limited to, GPS data, IP addresses, and location information services. For example, if the learner is in a specific region, the selection unit may prioritize presenting a range related to that region. Furthermore, if the learner is in a specific location, the selection unit may prioritize presenting a range related to that location. Furthermore, the selection unit may prioritize selecting a highly relevant range based on the learner's geographical location information. In this way, highly relevant ranges can be prioritized by taking the learner's geographical location information into consideration. Some or all of the above-described processing by the selection unit may be performed using, or without, AI. For example, the selection unit may input the learner's geographical location information data into the generation AI and cause the generation AI to select a highly relevant range.

[0081] When making the selection, the selection unit may analyze the learner's social media activity and select the relevant range. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, and the number of followers. For example, the selection unit may select the range related to topics in which the learner has shown interest on social media. The selection unit may also analyze the content of the learner's social media posts and select the relevant range. The selection unit may also select the relevant range with reference to the activities of the learner's friends on social media. In this way, the relevant range can be selected by analyzing the learner's social media activity. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit may input the learner's social media activity data into the generation AI and cause the generation AI to select the relevant range.

[0082] The selection unit can customize the selection method by reflecting the learner's past feedback when making a selection. Past feedback includes, but is not limited to, evaluation comments, survey results, and usage history. For example, the selection unit suggests an optimal selection method based on feedback previously provided by the learner. The selection unit can also preferentially suggest a specific selection method based on the learner's past feedback. The selection unit can also customize the selection method by reflecting the learner's feedback. In this way, the optimal selection method can be customized by reflecting the learner's past feedback. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the learner's past feedback data into the generation AI and cause the generation AI to customize the selection method.

[0083] The analysis unit can estimate the learner's emotions and adjust the accuracy of the analysis based on the estimated learner's emotions. Examples of learner emotions include, but are not limited to, stress, relaxation, and excitement. For example, if the learner is stressed, the analysis unit can simplify the analysis accuracy and provide basic information. Furthermore, if the learner is relaxed, the analysis unit can perform a detailed analysis and provide in-depth information. Furthermore, if the learner is excited, the analysis unit can provide visually appealing analysis results. Thus, by adjusting the analysis accuracy according to the learner's emotions, appropriate analysis results can be provided. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the learner's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0084] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the selected range. Criteria for evaluating importance include, but are not limited to, relevance to the learning goal, the learner's interest, and expert evaluation. For example, if the selected range is important, the analysis unit can perform a detailed analysis and provide relevant information. Furthermore, if the selected range has basic content, the analysis unit can perform a simplified analysis and provide basic information. The analysis unit can also adjust the level of detail of the analysis according to the importance of the selected range. This allows appropriate information to be provided by adjusting the level of detail of the analysis according to the importance of the selected range. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input importance data of the selected range to a generation AI and have the generation AI adjust the level of detail of the analysis.

[0085] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the selected range. Examples of categories include, but are not limited to, topic, difficulty level, and format. For example, if the history range is selected, the analysis unit can apply an algorithm that analyzes historical background. Furthermore, if the science range is selected, the analysis unit can apply an algorithm that analyzes scientific theories. Furthermore, if the literature range is selected, the analysis unit can apply an algorithm that performs literary analysis. By applying different analysis algorithms depending on the category of the selected range, appropriate analysis results can be provided. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input category data of the selected range into a generation AI and have the generation AI apply the analysis algorithm.

[0086] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the learner's past analysis results. Examples of past analysis results include, but are not limited to, methods for saving, reusing, and comparing analysis results. The analysis unit improves the accuracy of the analysis, for example, based on the learner's past analysis results. The analysis unit can also suggest an optimal analysis method by referring to the learner's past analysis history. The analysis unit can also improve the accuracy of the analysis by reflecting the learner's past analysis results. In this way, the accuracy of the analysis is improved by referring to the learner's past analysis results. Some or all of the above-described processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the learner's past analysis result data into the generation AI and have the generation AI improve the accuracy of the analysis.

[0087] The analysis unit can estimate the learner's emotions and determine analysis priorities based on the estimated learner's emotions. Examples of learner emotions include, but are not limited to, stress, relaxation, and excitement. For example, if the learner is stressed, the analysis unit can prioritize simple analysis. Furthermore, if the learner is relaxed, the analysis unit can prioritize detailed analysis. Furthermore, if the learner is excited, the analysis unit can prioritize interesting analysis. By determining the analysis priorities according to the learner's emotions, appropriate analysis results can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI. For example, the analysis unit can input the learner's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0088] During analysis, the analysis unit can determine the analysis priority based on the submission time of the selected range. The submission time includes, but is not limited to, the submission date and time, the submission deadline, and the submission frequency. For example, the analysis unit prioritizes analysis of ranges with upcoming submission deadlines. The analysis unit can also postpone analysis of ranges with more distant submission deadlines. The analysis unit can also adjust the analysis priority based on the submission time. By determining the analysis priority based on the submission time of the selected range, analysis results can be provided at an appropriate time. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input submission time data of the selected range into a generation AI and have the generation AI determine the analysis priority.

[0089] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the selected range. Relevance evaluation criteria include, but are not limited to, topic consistency, keyword co-occurrence, and the number of citations of related literature. For example, the analysis unit prioritizes analysis of highly relevant ranges. The analysis unit can also postpone analysis of less relevant ranges. The analysis unit can also adjust the order of analysis based on the relevance of the selected range. By adjusting the order of analysis based on the relevance of the selected range, highly relevant information can be provided preferentially. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input relevance data of the selected range into a generation AI and have the generation AI adjust the order of analysis.

[0090] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the learner's level of expertise. Examples of expertise levels include, but are not limited to, test results, self-assessments, and learning histories. For example, if the learner's level of expertise is low, the analysis unit can provide analysis results using simple terms. Alternatively, if the learner's level of expertise is high, the analysis unit can provide detailed analysis results using technical terms. The analysis unit can also adjust the use of technical terms in the analysis according to the learner's level of expertise. This allows for appropriate analysis results to be provided by adjusting the use of technical terms in the analysis according to the learner's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the learner's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms.

[0091] The providing unit can estimate the learner's emotions and adjust the way in which the commentary is expressed based on the estimated learner's emotions. Examples of learner emotions include, but are not limited to, stress, relaxation, and excitement. For example, if the learner is stressed, the providing unit can provide a simple and easy-to-understand way of expression. Furthermore, if the learner is relaxed, the providing unit can provide a way of expression that includes detailed information. Furthermore, if the learner is excited, the providing unit can provide a visually appealing way of expression. This allows the way in which the commentary is expressed to be adjusted according to the learner's emotions to provide the most appropriate commentary for the learner. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI. For example, the providing unit can input the learner's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0092] When providing an explanation, the providing unit can adjust the level of detail of the explanation based on the importance of the selected range. Examples of the level of detail of the explanation include, but are not limited to, the length of the explanation, the depth of the information, and the number of specific examples. For example, the providing unit provides a detailed explanation if the selected range is important. Furthermore, the providing unit can also provide a brief explanation if the selected range has basic content. Furthermore, the providing unit can adjust the level of detail of the explanation according to the importance of the selected range. This allows appropriate information to be provided by adjusting the level of detail of the explanation according to the importance of the selected range. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input importance data of the selected range to a generating AI and cause the generating AI to adjust the level of detail of the explanation.

[0093] When providing an explanation, the providing unit can apply different explanation algorithms depending on the category of the selected range. Explanation algorithms include, but are not limited to, natural language generation algorithms and template-based generation methods. For example, if the history range is selected, the providing unit can apply an algorithm that explains the historical background. Furthermore, if the science range is selected, the providing unit can apply an algorithm that explains scientific theories. Furthermore, if the literature range is selected, the providing unit can apply an algorithm that performs literary analysis. In this way, by applying different explanation algorithms depending on the category of the selected range, appropriate explanations can be provided. Some or all of the above-mentioned processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input category data of the selected range into a generation AI and cause the generation AI to apply an explanation algorithm.

[0094] When providing an explanation, the providing unit can improve the accuracy of the explanation by referring to the learner's past explanation results. Past explanation results include, for example, a method for saving, reusing, and comparing explanations, but are not limited to these examples. The providing unit improves the accuracy of the explanation, for example, based on the learner's past explanation results. The providing unit can also suggest an optimal explanation method by referring to the learner's past explanation history. The providing unit can also improve the accuracy of the explanation by reflecting the learner's past explanation results. In this way, the accuracy of the explanation is improved by referring to the learner's past explanation results. Some or all of the above-mentioned processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input the learner's past explanation result data into the generation AI and cause the generation AI to improve the accuracy of the explanation.

[0095] The providing unit can estimate the learner's emotions and adjust the length of the commentary based on the estimated learner's emotions. Examples of the length of the commentary include, but are not limited to, the number of characters in the commentary, the duration, and the depth of the information. For example, if the learner is stressed, the providing unit can provide a short, concise commentary. If the learner is relaxed, the providing unit can provide a longer commentary with detailed explanations. If the learner is excited, the providing unit can provide a commentary with visually stimulating effects. By adjusting the length of the commentary according to the learner's emotions, the optimal commentary can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI. For example, the providing unit can input the learner's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0096] When providing an explanation, the providing unit can determine the priority of the explanation based on the submission time of the selected range. The priority of the explanation includes, but is not limited to, for example, the submission time, the urgency of the information, and the importance of the information. For example, the providing unit can prioritize the provision of explanations for a range with an upcoming submission deadline. The providing unit can also postpone the provision of explanations for a range with a distant submission deadline. The providing unit can also adjust the priority of the explanation based on the submission time. This allows the explanation to be provided at an appropriate time by determining the priority of the explanation based on the submission time of the selected range. Some or all of the above-described processing by the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input submission time data for the selected range into a generating AI and cause the generating AI to determine the priority of the explanations.

[0097] When providing explanations, the providing unit can adjust the order of explanations based on the relevance of the selected range. Examples of the order of explanations include, but are not limited to, a method of prioritizing highly relevant information and a method based on the learner's level of interest. For example, the providing unit can provide explanations for highly relevant ranges first. The providing unit can also provide explanations for less relevant ranges later. The providing unit can also adjust the order of explanations based on the relevance of the selected range. Thus, by adjusting the order of explanations based on the relevance of the selected range, highly relevant information can be provided first. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input relevance data for the selected range to a generating AI and cause the generating AI to adjust the order of explanations.

[0098] When providing an explanation, the providing unit can adjust the use of technical terms in the explanation according to the learner's level of expertise. Examples of the use of technical terms include, but are not limited to, selecting terms and explaining methods according to the learner's level of expertise. For example, if the learner's level of expertise is low, the providing unit can provide an explanation using simple terms. Furthermore, if the learner's level of expertise is high, the providing unit can provide a detailed explanation using technical terms. Furthermore, the providing unit can adjust the use of technical terms in the explanation according to the learner's level of expertise. This allows for the provision of an appropriate explanation by adjusting the use of technical terms in the explanation according to the learner's level of expertise. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without AI. For example, the providing unit can input the learner's level of expertise data into the generating AI and cause the generating AI to adjust the use of technical terms.

[0099] The related information search unit can estimate the learner's emotions and adjust the related information search method based on the estimated learner's emotions. Examples of related information search methods include, but are not limited to, keyword search, content-based search, and recommendation systems. For example, the related information search unit can provide a simple search method when the learner is stressed. For example, the related information search unit can provide detailed search options when the learner is relaxed. For example, the related information search unit can provide a visually appealing search method when the learner is excited. This allows appropriate information to be provided by adjusting the related information search method according to the learner's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the related information search unit may be performed using AI, or without AI. For example, the related information search unit can input the learner's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0100] When searching for related information, the related information search unit can adjust the level of search detail based on the importance of the selected range. Examples of the level of search detail include, but are not limited to, the number of search results, the depth of information, and filtering criteria. For example, if the selected range is important, the related information search unit can perform a detailed search to provide related information. Furthermore, if the selected range has basic content, the related information search unit can perform a simplified search to provide basic information. Furthermore, the related information search unit can adjust the level of search detail based on the importance of the selected range. This allows appropriate information to be provided by adjusting the level of search detail based on the importance of the selected range. Some or all of the above-described processing in the related information search unit may be performed using, for example, AI, or may be performed without AI. For example, the related information search unit can input importance data of the selected range into a generation AI and cause the generation AI to adjust the level of search detail.

[0101] When searching for related information, the related information search unit can apply different search algorithms depending on the category of the selected range. Search algorithms include, but are not limited to, full-text search algorithms and pattern matching algorithms. For example, if the history range is selected, the related information search unit can apply an algorithm to search for historical background. Furthermore, if the science range is selected, the related information search unit can apply an algorithm to search for scientific theories. Furthermore, if the literature range is selected, the related information search unit can apply an algorithm to perform literary analysis. This allows appropriate information to be provided by applying different search algorithms depending on the category of the selected range. Some or all of the above-described processing in the related information search unit can be performed using, for example, AI, or without AI. For example, the related information search unit can input category data for the selected range into a generation AI and cause the generation AI to apply a search algorithm.

[0102] The related information search unit can estimate the learner's emotions and prioritize related information based on the estimated learner's emotions. Examples of the prioritization of related information include, but are not limited to, the learner's level of interest, the importance of the information, and the reliability of the information. For example, if the learner is stressed, the related information search unit can prioritize providing simple related information. Furthermore, if the learner is relaxed, the related information search unit can prioritize providing detailed related information. Furthermore, if the learner is excited, the related information search unit can prioritize providing interesting related information. Thus, by prioritizing related information according to the learner's emotions, appropriate information can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the related information search unit may be performed using, for example, an AI, or without an AI. For example, the related information search unit can input the learner's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0103] When searching for related information, the related information search unit can determine search priorities based on the submission dates of the selected range. Search priorities include, but are not limited to, submission dates, urgency of the information, and importance of the information. For example, the related information search unit can prioritize providing related information with an upcoming submission deadline. The related information search unit can also delay providing related information with a distant submission deadline. The related information search unit can also adjust the priority of related information based on the submission dates. By determining search priorities based on the submission dates of the selected range, information can be provided at an appropriate time. Some or all of the above-described processing in the related information search unit may be performed using, for example, AI, or may be performed without AI. For example, the related information search unit can input submission date data of the selected range into a generation AI and have the generation AI determine the search priorities.

[0104] When searching for related information, the related information search unit can adjust the search order based on the relevance of the selected range. Examples of the search order include, but are not limited to, a method that prioritizes highly relevant information or a method based on the learner's level of interest. For example, the related information search unit can provide related information in a highly relevant range first. The related information search unit can also provide related information in a less relevant range later. The related information search unit can also adjust the search order of related information based on the relevance of the selected range. By adjusting the search order based on the relevance of the selected range, highly relevant information can be provided first. Some or all of the above-described processing in the related information search unit may be performed using, for example, AI, or may be performed without AI. For example, the related information search unit can input the relevance data of the selected range into a generation AI and cause the generation AI to adjust the search order.

[0105] The reliability evaluation unit can estimate the learner's emotions and evaluate the reliability of the information to be provided based on the estimated learner's emotions. Information reliability includes, but is not limited to, the reliability of the information source, the consistency of the data, and expert reviews. For example, if the learner is feeling stressed, the reliability evaluation unit can prioritize providing highly reliable information. Furthermore, if the learner is relaxed, the reliability evaluation unit can provide detailed information and evaluate its reliability. Furthermore, if the learner is excited, the reliability evaluation unit can provide visually appealing information and evaluate its reliability. This allows appropriate information to be provided by evaluating the reliability of the information to be provided based on the learner's emotions. The estimation of emotions is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reliability evaluation unit may be performed using AI, or without AI. For example, the reliability evaluation unit can input the learner's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0106] The reliability evaluation unit can adjust the level of detail of the evaluation based on the importance of the selected range during reliability evaluation. The level of detail of the evaluation includes, but is not limited to, the depth of the evaluation, the number of evaluation items, and the frequency of the evaluation. For example, if the selected range is important, the reliability evaluation unit can perform a detailed reliability evaluation. Furthermore, if the selected range has basic content, the reliability evaluation unit can also perform a simplified reliability evaluation. The reliability evaluation unit can also adjust the level of detail of the reliability evaluation according to the importance of the selected range. By adjusting the level of detail of the evaluation according to the importance of the selected range, appropriate information can be provided. Some or all of the above-described processing in the reliability evaluation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reliability evaluation unit can input importance data of the selected range to the generation AI and cause the generation AI to adjust the level of detail of the evaluation.

[0107] The reliability evaluation unit can apply different evaluation algorithms depending on the category of the selected range during reliability evaluation. Examples of evaluation algorithms include, but are not limited to, scoring algorithms and ranking algorithms. For example, if the history range is selected, the reliability evaluation unit can apply an algorithm that evaluates historical background. Furthermore, if the science range is selected, the reliability evaluation unit can apply an algorithm that evaluates scientific theories. Furthermore, if the literature range is selected, the reliability evaluation unit can apply an algorithm that performs literary analysis. By applying different evaluation algorithms depending on the category of the selected range, appropriate information can be provided. Some or all of the above-described processing in the reliability evaluation unit can be performed using, for example, AI, or without AI. For example, the reliability evaluation unit can input category data of the selected range into a generation AI and cause the generation AI to apply the evaluation algorithm.

[0108] The reliability evaluation unit can estimate the learner's emotions and determine the priority of the reliability of information to be provided based on the estimated learner's emotions. Examples of reliability priorities include, but are not limited to, the importance of information, the urgency of information, and the reliability of information. For example, if a learner is stressed, the reliability evaluation unit can prioritize providing highly reliable information. Furthermore, if a learner is relaxed, the reliability evaluation unit can prioritize providing detailed information. Furthermore, if a learner is excited, the reliability evaluation unit can prioritize providing visually appealing information. Thus, by determining the priority of the reliability of information to be provided according to the learner's emotions, appropriate information can be provided. The estimation of emotions is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the reliability evaluation unit may be performed using, for example, an AI. For example, the reliability evaluation unit can input the learner's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0109] During the reliability evaluation, the reliability evaluation unit can determine the priority of the evaluation based on the submission time of the selected range. Examples of the priority of the evaluation include, but are not limited to, the submission time, the urgency of the information, and the importance of the information. For example, the reliability evaluation unit prioritizes the reliability evaluation of the range with the nearest submission deadline. The reliability evaluation unit can also postpone the reliability evaluation of the range with the further away submission deadline. The reliability evaluation unit can also adjust the priority of the reliability evaluation based on the submission time. By determining the priority of the evaluation based on the submission time of the selected range, information can be provided at an appropriate time. Some or all of the above-described processing in the reliability evaluation unit may be performed using, for example, AI, or may be performed without AI. For example, the reliability evaluation unit can input the submission time data of the selected range into the generation AI and have the generation AI determine the priority of the evaluation.

[0110] The reliability evaluation unit can adjust the order of evaluation based on the relevance of the selected range during reliability evaluation. Examples of the order of evaluation include, but are not limited to, a method of prioritizing highly relevant information and a method based on the learner's interest. For example, the reliability evaluation unit prioritizes reliability evaluation of highly relevant ranges. The reliability evaluation unit can also postpone reliability evaluation of less relevant ranges. The reliability evaluation unit can also adjust the order of reliability evaluation based on the relevance of the selected range. By adjusting the order of evaluation based on the relevance of the selected range, highly relevant information can be provided preferentially. Some or all of the above-described processing in the reliability evaluation unit may be performed using, or without, AI. For example, the reliability evaluation unit can input relevance data of the selected range into a generation AI and cause the generation AI to adjust the order of evaluation. === Hard Collateral 1-1 === Each of the multiple elements including the selection unit, analysis unit, and provision unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the selection unit is realized using an input device such as the touch panel 38A of the smart device 14 or a mouse click. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the content of the selected text or diagram. The provision unit provides an explanation using, for example, the display 40A or speaker 40B of the smart device 14. The provision unit may also be realized by the specific processing unit 290 of the data processing device 12 and can generate an explanation based on the analysis results. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned selection unit, analysis unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the selection unit is realized using the microphone 238 of the smart glasses 214 or touch operation. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of the selected text or diagram. The provision unit provides an explanation using, for example, the speaker 240 of the smart glasses 214. The provision unit may also be realized by the specific processing unit 290 of the data processing device 12, and can generate an explanation based on the analysis result. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned selection unit, analysis unit, and provision unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the selection unit is realized using the microphone 238 of the headset type terminal 314 or touch operation. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of the selected text or diagram. The provision unit provides an explanation using, for example, the speaker 240 or display 343 of the headset type terminal 314. The provision unit may also be realized by the specific processing unit 290 of the data processing device 12, and can generate an explanation based on the analysis result. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned selection unit, analysis unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the selection unit is realized using the microphone 238 of the robot 414 or touch operation. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of the selected text or diagram. The provision unit provides an explanation using, for example, the speaker 240 or display device of the robot 414. The provision unit may also be realized by the specific processing unit 290 of the data processing device 12, and can generate an explanation based on the analysis result.

[0111] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0112] Learning support systems can provide customized learning plans based on a learner's learning style. For example, visual learners can be provided with explanations that make extensive use of diagrams and videos. Auditory learners can be provided with audio commentary or podcast-style information. Furthermore, tactile learners can experience the learning content through interactive quizzes and simulations. This allows learners to receive the optimal learning experience based on their individual learning styles.

[0113] Learning support systems can analyze a learner's learning history and suggest what they should study next based on their learning progress. For example, if a learner is struggling with a particular topic, they can be suggested to review basic content related to that topic. Also, if a learner excels in a particular field, they can be suggested to study more advanced content related to that field. Furthermore, they can automatically adjust their learning schedule according to the learner's learning pace. This allows learners to progress efficiently.

[0114] The learning support system can estimate the learner's emotions and provide feedback to improve their motivation to learn based on the estimated emotions. For example, if a learner is feeling stressed, it can provide them with an encouraging message or advice to relax. If the learner is relaxed, it can provide them with a message praising their learning progress. Furthermore, if the learner is excited, it can provide them with a challenging task to maintain their excitement. In this way, it is possible to improve their motivation to learn by providing appropriate feedback according to the learner's emotions.

[0115] Learning support systems can utilize learners' geographic location information to provide learning content relevant to the region. For example, if a learner is in a specific region, they can be provided with information about the history and culture of that region. If a learner is traveling, they can be provided with information about tourist attractions and local specialties. Furthermore, if a learner is learning a language from a specific region, they can be provided with information about the dialect and idioms of that region. This allows learners to learn based on a geographical context.

[0116] The learning support system can analyze a learner's social media activity and provide learning content related to topics that interest the learner. For example, it can provide articles and videos related to topics that the learner frequently mentions on social media. It can also provide learning resources recommended by influencers that the learner follows. It can also provide information related to topics that are trending in online communities in which the learner participates. This makes it possible to provide a personalized learning experience based on the learner's interests.

[0117] The learning support system can estimate the learner's emotions and adjust the learning environment based on the estimated emotions. For example, if a learner is feeling stressed, the system can adjust the volume and lighting of the learning environment to provide a relaxing environment. If the learner is relaxed, the system can provide environmental settings to improve concentration. Furthermore, if the learner is excited, the system can provide interactive learning tools to maintain that excitement. In this way, the system can provide an optimal learning environment according to the learner's emotions.

[0118] The learning support system can automatically recommend what a learner should learn next based on the learner's learning progress. For example, if a learner has completed a specific topic, it can suggest the next step related to that topic. Also, if a learner is struggling in a particular area, it can suggest that they review basic content related to that area. Furthermore, if a learner excels in a particular area, it can suggest that they study advanced content related to that area. This allows learners to progress efficiently in their studies.

[0119] The learning support system can estimate the learner's emotions and evaluate the learner's progress based on the estimated emotions. For example, if the learner is feeling stressed, the learning progress can be evaluated gently and an encouraging message can be provided. If the learner is relaxed, the learning progress can be evaluated in detail and specific feedback can be provided. Furthermore, if the learner is excited, a challenging task can be provided to maintain the learner's excitement. This makes it possible to appropriately evaluate the learner's progress according to their emotions.

[0120] The learning support system can analyze a learner's learning history and suggest review timing based on what the learner has learned in the past. For example, it can suggest that a learner review a specific topic after a certain period of time has passed since learning that topic. It can also suggest that a learner periodically review topics that the learner struggled with in the past. Furthermore, if a learner is studying for a specific exam or assessment, it can suggest that the learner review content related to that exam or assessment. This allows the learner to review effectively and solidify what they have learned.

[0121] The learning support system can estimate the learner's emotions and evaluate the learner's progress based on the estimated emotions. For example, if the learner is feeling stressed, the learning progress can be evaluated gently and an encouraging message can be provided. If the learner is relaxed, the learning progress can be evaluated in detail and specific feedback can be provided. Furthermore, if the learner is excited, a challenging task can be provided to maintain the learner's excitement. This makes it possible to appropriately evaluate the learner's progress according to their emotions.

[0122] The processing flow of the second embodiment will be briefly explained below.

[0123] Step 1: In the selection section, learners select the part of the text they are unsure about. Learners can select parts related to specific keywords, context, or a specific topic. Selection methods include mouse clicks, touch operations, and voice input, and can select ranges of text or figures. For example, learners can highlight and select a portion of text or select a specific part of a figure. Step 2: The analysis unit analyzes the range selected by the selection unit. The analysis unit performs the analysis using text analysis, image analysis, natural language processing technology, etc. For example, the analysis unit analyzes the content of the selected text and extracts related information. It can also analyze the content of the selected chart or diagram and extract related information. Step 3: The providing unit provides an explanation based on the results of the analysis by the analyzing unit. The explanation is provided in the form of text, audio, video, etc. For example, a detailed explanation of the selected range can be provided in text format, audio format, or video format.

[0124] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0125] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0126] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0127] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0128] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0129] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0130] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0131] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0132] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0133] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0134] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0135] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0136] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0138] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0139] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0140] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0142] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0145] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0147] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0148] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0150] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0151] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

[0154] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0155] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0156] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0158] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0161] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0162] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0163] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0164] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0166] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0167] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0168] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0169] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0170] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0171] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0172] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0173] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0174] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0175] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0176] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0177] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0178] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0179] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0180] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0181] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0182] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0184] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0185] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0186] 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.

[0187] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0188] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0189] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0190] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0192] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0193] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0194] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0195] [Explanation of symbols]

[0196] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A selection section for the learner to select the part about which he / she has questions; an analysis unit that analyzes the range selected by the selection unit; a providing unit that provides a commentary based on the result of the analysis by the analyzing unit; Equipped with A system characterized by:

2. The providing unit Provides in-depth information related to the selected area 2. The system of claim 1.

3. The analysis unit A related information search unit is provided that analyzes the content of the selected text or chart and searches for related information.

2. The system of claim 1.

4. The providing unit Equipped with a reliability evaluation unit that evaluates the accuracy of the information provided 2. The system of claim 1.

5. The selection unit Select a range of text or a diagram 2. The system of claim 1.

6. The selection unit Inferring learner emotions and adjusting the presentation of choices based on the inferred emotions 2. The system of claim 1.

7. The selection unit Analyzes learners' past selection history and suggests optimal selection methods 2. The system of claim 1.

8. The selection unit As you make your selections, filter your selections based on the learner's current progress and comprehension level 2. The system of claim 1.

9. The selection unit When selecting, provide the most appropriate option depending on the learner's input method.

2. The system of claim 1.

Images