system

Abstract

The system according to this embodiment aims to analyze learning materials, identify areas where the user struggles, and encourage effective review. [Solution] The system according to the embodiment comprises an analysis unit, a generation unit, a specification unit, and a review unit. The analysis unit analyzes learning materials. The generation unit generates content in a visual format based on the content analyzed by the analysis unit. The specification unit identifies the user's weak areas based on the test results for each chapter generated by the generation unit. The review unit prompts review at specific times based on the weak areas identified by the specification unit.

Description

Technical Field

[0006] ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the analysis of learning materials and the identification of the user's weak fields have not been sufficiently carried out, and there is room for improvement in improving learning efficiency.

[0005] The system according to the embodiment aims to analyze learning materials, identify the user's weak fields, and promote effective review.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a generation unit, a specification unit, and a review unit. The analysis unit analyzes learning materials. The generation unit generates content in a visual format based on the content analyzed by the analysis unit. The specification unit identifies the user's weak areas based on the test results for each chapter generated by the generation unit. The review unit prompts review at specific times based on the weak areas identified by the specification unit. [Effects of the Invention]

[0007] The system according to this embodiment can analyze learning materials, identify areas where the user struggles, and encourage effective review. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The learning support system according to an embodiment of the present invention is a system that provides learning content for obtaining qualifications. This learning support system trains an AI with learning materials and provides learning content in a visual format. Each chapter has a test, and it also has a function to repeat learning at timings based on the forgetting curve and to overcome weak areas. For users aiming to obtain qualifications, it can be deployed worldwide. Furthermore, by applying this system to internal business operations, it can visualize the level of proficiency in basic to intermediate knowledge of new employees and transferees, and become an effective tool for placing the right people in the right positions. For example, the learning support system trains an AI with learning materials. The AI ​​analyzes the learning content and generates learning content in a visual format. For example, by explaining the content of a qualification exam in an easy-to-understand visual way, users can learn in an enjoyable way. Next, each chapter has a test, allowing users to check their learning content. Based on the test results, the AI ​​identifies the user's weak areas and encourages repeated learning. For example, by reviewing at timings based on the forgetting curve, the learning effect can be enhanced. Moreover, this system can be deployed worldwide and is extremely useful for users aiming to obtain qualifications. For example, by providing learning content that supports different languages ​​and cultures, it can be used by users all over the world. Furthermore, by applying this system to internal business processes, it becomes possible to visualize the level of proficiency in basic to intermediate knowledge for new employees and transferees. For instance, by having AI learn the business processes and generating learning content, new employees and transferees can acquire skills more efficiently. This also makes it an effective tool for placing the right people in the right positions. Thus, the learning support system can provide learning content for obtaining qualifications, thereby enhancing the learning effectiveness for users. Additionally, by applying it to internal business processes, it becomes possible to visualize the level of proficiency in basic to intermediate knowledge for new employees and transferees, making it an effective tool for placing the right people in the right positions.

[0029] The learning support system according to this embodiment comprises an analysis unit, a generation unit, a specification unit, and a review unit. The analysis unit analyzes learning materials. Learning materials include, but are not limited to, text, video, and slides. The analysis unit performs, for example, text analysis to extract the content of the learning materials. The analysis unit can also perform image analysis to analyze the content of visual content. Furthermore, the analysis unit can use data mining techniques to analyze patterns in the learning materials. For example, as text analysis, the analysis unit uses natural language processing techniques to analyze text data and extract important information. As image analysis, it uses computer vision techniques to analyze image data and extract visual information. As data mining, it uses machine learning algorithms to analyze data patterns and extract features of the learning materials. The generation unit generates learning content in a visual format based on the content analyzed by the analysis unit. Visual formats include, but are not limited to, graphs, charts, and infographics. The generation unit generates, for example, graphs to visually show data trends. The generation unit can also generate charts to visually compare data. Furthermore, the generation unit can generate infographics to visually present complex information in an easy-to-understand way. For example, the generation unit can generate bar graphs and line graphs to visually show data fluctuations. It can generate pie charts and histograms to visually show data distributions. It can use icons and illustrations to visually present information as infographics. The identification unit identifies the user's weak areas based on the test results for each chapter generated by the generation unit. Identifying weak areas may use, but is not limited to, test score results or the frequency of incorrect answers. For example, the identification unit can analyze test score results to identify the user's weak areas. It can also analyze the frequency of incorrect answers to identify the user's weak areas. Furthermore, the identification unit can analyze the user's learning history to identify weak areas. For example, the identification unit can analyze the test scores for each chapter as test score results and identify chapters with low scores as weak areas.The frequency of incorrect answers is analyzed by examining the number of incorrect answers in each chapter, and chapters with many incorrect answers are identified as areas of weakness. As part of the learning history, the user's past learning data is analyzed to identify areas of weakness. The review unit prompts review at specific times based on the areas of weakness identified by the identification unit. The timing of review may be based on, but is not limited to, the forgetting curve or the learning schedule. For example, the review unit may set review timing based on the forgetting curve and prompt the user to review. The review unit can also set review timing based on the learning schedule and prompt the user to review. Furthermore, the review unit can adjust the review timing according to the user's learning progress. For example, the review unit may use Ebbinghaus's forgetting curve as the forgetting curve to set review timing and prompt the user to review. As a learning schedule, it may set review timing based on the user's learning plan and prompt the user to review. As a learning status, it may adjust the review timing according to the user's learning progress and prompt the user to review. As a result, the learning support system according to this embodiment can analyze learning materials, generate content in a visual format, identify the user's weak areas, and prompt review at timings based on the forgetting curve.

[0030] The analytics department can analyze specific business operations within the company. These specific operations include, but are not limited to, sales activities, project management, and customer service. For example, the analytics department can analyze sales activity data to improve the efficiency of the sales process. It can also analyze project management data to understand project progress. Furthermore, it can analyze customer service data to improve customer satisfaction. For instance, the analytics department can analyze sales performance and customer visit history to identify areas for improvement in sales strategies. For project management, it can analyze project task progress and resource allocation to improve project efficiency. For customer service, it can analyze customer feedback and complaint handling history to identify areas for improvement in customer service. By analyzing internal business operations, the department can visualize the level of proficiency in basic to intermediate knowledge among new employees and those transferred from other departments.

[0031] The generation unit can generate learning content based on the company's internal business processes. This learning content may include, but is not limited to, text, video, and slides. For example, the generation unit can generate text-based learning content that explains work procedures in detail. It can also generate video-based learning content that visually demonstrates practical work examples. Furthermore, it can generate slide-based learning content that clearly presents key points of the work. For instance, the generation unit can generate work manuals and procedure documents in text format, explaining detailed work procedures; film practical work examples and visually demonstrate them in video format; and generate presentation materials summarizing key points of the work in slide format. This allows new employees and transferees to efficiently acquire work skills by generating learning content based on the company's internal business processes.

[0032] A specific department can identify the level of proficiency in specific knowledge levels of new employees or transferees. These specific knowledge levels include, but are not limited to, basic knowledge, intermediate knowledge, and specialized knowledge. For example, a department can analyze the results of a basic knowledge test to identify the level of basic knowledge proficiency of new employees. Similarly, a department can analyze the results of an intermediate knowledge test to identify the level of intermediate knowledge proficiency of transferees. Furthermore, a department can analyze the results of a specialized knowledge test to identify the knowledge level of professionals. For example, a department could test and identify proficiency in basic work procedures and terminology as basic knowledge; test and identify proficiency in applied work procedures and problem-solving abilities as intermediate knowledge; and test and identify proficiency in advanced work techniques and specialized knowledge as specialized knowledge. This allows for the identification of the level of proficiency in basic to intermediate knowledge of new employees and transferees, making it an effective tool for placing the right people in the right positions.

[0033] The review function can encourage review based on the user's level of proficiency. This level of proficiency includes, but is not limited to, test scores, work experience, and feedback. For example, the review function can encourage review based on test scores to improve user comprehension. It can also encourage review based on work experience to improve user practical skills. Furthermore, it can encourage review based on feedback to clearly identify areas for improvement. For example, the review function can focus on reviewing chapters with low test scores, encourage review based on real-world challenges, and encourage review based on feedback from supervisors and colleagues. By encouraging review based on proficiency, the learning effect can be enhanced.

[0034] The analysis unit can apply different analysis algorithms depending on the type of learning material. For example, it can apply a natural language processing algorithm to text-based materials to analyze their content. It can also apply an image recognition algorithm to materials containing mathematical formulas and graphs to analyze their content. Furthermore, it can combine speech recognition and video analysis algorithms to analyze video materials. For example, for text-based materials, the analysis unit uses natural language processing technology to analyze text data and extract important information. For materials containing mathematical formulas and graphs, it uses computer vision technology to analyze image data and extract visual information. For video materials, it combines speech recognition and video analysis technologies to analyze video data and extract audio and video information. This allows for improved analysis accuracy by applying the appropriate analysis algorithm according to the type of learning material.

[0035] The analysis unit can appropriately adjust its analysis method based on the specific update frequency of the learning materials during analysis. For example, for frequently updated materials, the analysis unit applies an algorithm that prioritizes analyzing the latest information. Furthermore, for materials with infrequent updates, the analysis unit can apply an analysis algorithm based on past data. Additionally, for materials with irregular updates, the analysis unit can select the optimal analysis method by referring to the update history. For example, as a frequently updated material, the analysis unit analyzes daily updated news articles and prioritizes extracting the latest information. As a low-update material, it analyzes annually updated statistical data and performs analysis based on past data. For materials with irregular updates, it refers to the update history and selects the optimal analysis method. By optimizing the analysis method considering the update frequency of the learning materials, the analysis unit can provide analysis results that reflect the latest information.

[0036] The analysis unit can perform analysis based on the specific language and cultural background of the learning materials. For example, if the learning materials are provided in multiple languages, the analysis unit applies an appropriate analysis algorithm to each language. Furthermore, if the learning materials have a specific cultural background, the analysis unit can consider that background during the analysis. Additionally, if the learning materials include information from different regions, the analysis unit can consider the characteristics of each region during the analysis. For example, if the learning materials are provided in multiple languages ​​such as English, Japanese, and French, the analysis unit applies a natural language processing algorithm appropriate for each language. If the learning materials have a specific cultural background, the analysis takes into account those cultural customs and values. If the learning materials include information from different regions, the analysis takes into account the characteristics of each region. This allows for the provision of more appropriate analysis results by considering the language and cultural background of the learning materials during the analysis.

[0037] The analysis unit can improve the accuracy of its analysis based on specific relevant literature for the learning materials. For example, the analysis unit can automatically search for literature related to the learning materials and incorporate it into the analysis. Furthermore, the analysis unit can incorporate information from relevant literature into the analysis to complement the content of the learning materials. In addition, the analysis unit can perform analysis by referencing data from relevant literature to enhance the reliability of the learning materials. For example, the analysis unit can automatically search for academic papers related to the learning materials and incorporate their content into the analysis. It can also incorporate information from relevant literature into the analysis to complement the content of the learning materials. Finally, it can perform analysis by referencing data from relevant literature to enhance the reliability of the learning materials. This allows for the provision of more reliable analysis results by improving the accuracy of the analysis through reference to relevant literature for the learning materials.

[0038] The generation unit can adjust the level of detail of the content based on the importance of the learning material during generation. For example, the generation unit can generate content with detailed explanations for highly important learning material. It can also generate content with concise explanations for less important learning material. Furthermore, it can generate content with an appropriate level of detail for moderately important learning material. For example, the generation unit can generate content that explains in detail topics that frequently appear on the exam as highly important learning material. It can generate content that explains topics that rarely appear on the exam concisely as less important learning material. It can generate content that explains topics that appear moderately frequently on the exam with an appropriate level of detail as moderately important learning material. In this way, efficient learning can be achieved by adjusting the level of detail of the content based on the importance of the learning material.

[0039] The generation unit can apply different generation algorithms depending on the category of learning content during generation. For example, for theoretical learning content, the generation unit can apply a generation algorithm that emphasizes logical explanations. Furthermore, for practical learning content, it can apply a generation algorithm that emphasizes concrete examples. In addition, for applied learning content, it can apply a generation algorithm that emphasizes application examples. For example, for theoretical learning content, the generation unit can generate content that emphasizes explanations based on logical frameworks. For practical learning content, it can generate content that emphasizes explanations using concrete examples. For applied learning content, it can generate content that emphasizes explanations using application examples. This allows for the provision of effective learning content by applying the appropriate generation algorithm according to the category of learning content.

[0040] The generation unit can prioritize content based on the submission deadlines of learning materials during generation. For example, the generation unit will prioritize generating content for learning materials with approaching deadlines. It can also postpone generating content for learning materials with distant deadlines. Furthermore, it can generate content with a moderate priority for learning materials with medium-term deadlines. For example, the generation unit will prioritize generating content for assignments with approaching deadlines, postpone generating content for assignments with distant deadlines, and generate content for assignments with medium-term deadlines with a moderate priority. By prioritizing content based on the submission deadlines of learning materials, efficient learning can be achieved.

[0041] The generation unit can adjust the order of content based on the relevance of the learning material during generation. For example, the generation unit can prioritize and adjust the order of highly relevant learning material. It can also adjust the order of less relevant learning material by placing it later. Furthermore, it can adjust the order of moderately relevant learning material by placing it in an appropriate order. For example, the generation unit prioritizes topics requiring prior knowledge as highly relevant learning material. It places topics that do not require prior knowledge later as less relevant learning material. It places topics that require some prior knowledge as moderately relevant learning material in an appropriate order. In this way, efficient learning can be achieved by adjusting the order of content based on the relevance of the learning material.

[0042] The identification unit can appropriately adjust the identification method based on the specific level of detail of the test results during identification. For example, the identification unit can apply a highly accurate identification method to detailed test results. It can also apply a concise identification method to simplified test results. Furthermore, it can apply a moderately detailed identification method to test results with a moderate level of detail. For example, for detailed test results, the identification unit can analyze the correct answer rate and error trends for each question and apply a highly accurate identification method. For simplified test results, it can analyze the total score and average score and apply a concise identification method. For test results with a moderate level of detail, it can analyze the score for each chapter and the frequency of errors and apply a moderately detailed identification method. In this way, efficient identification can be achieved by optimizing the identification method based on the level of detail of the test results.

[0043] The identification unit can improve the accuracy of identification based on the user's specific past learning history. For example, the identification unit improves the accuracy of identification based on the user's past learning history. The identification unit can also identify areas of weakness from the user's past learning history and improve accuracy. Furthermore, the identification unit can analyze the user's past learning history and apply the most efficient identification method. For example, the identification unit analyzes past test results and study time as part of the user's past learning history to improve the accuracy of identification. To identify areas of weakness, it analyzes past incorrect answer trends to improve accuracy. To apply the most efficient identification method, it analyzes past learning data and selects the optimal identification method. In this way, the accuracy of identification can be improved by referring to the user's past learning history.

[0044] The identification unit can determine the order of identification based on the specific submission dates of the test results. For example, the identification unit can prioritize identification of test results with approaching submission deadlines. It can also postpone identification of test results with distant submission deadlines. Furthermore, it can assign a moderate priority to test results with medium submission deadlines. For example, the identification unit can prioritize identification of test results with approaching deadlines, postpone identification of test results with further deadlines, and assign a moderate priority to test results with medium deadlines. By determining the priority of identification based on the submission dates of the test results, efficient identification can be achieved.

[0045] The identification unit can adjust the order of identification based on the specific relevance of the test results during the identification process. For example, the identification unit can prioritize identifying highly relevant test results and adjust their order. It can also postpone identifying less relevant test results and adjust their order. Furthermore, it can identify moderately relevant test results in an appropriate order and adjust their order. For example, the identification unit prioritizes identifying test results that require prior knowledge as highly relevant test results. It postpones identifying test results that do not require prior knowledge as less relevant test results. It identifies test results that require some prior knowledge in an appropriate order as moderately relevant test results. This allows for efficient identification by adjusting the order of identification based on the relevance of the test results.

[0046] The review function can optimize the frequency of review based on the shape of the forgetting curve. For example, the review function can prompt frequent review in the steeper parts of the forgetting curve. It can also prompt moderate review in the gentler parts of the forgetting curve. Furthermore, it can prompt less frequent review in the flatter parts of the forgetting curve. For example, based on Ebbinghaus's forgetting curve, the review function can prompt frequent review in the first few days as the steeper part of the forgetting curve. It can prompt moderate review in the gentler parts of the forgetting curve after a few weeks. It can prompt less frequent review in the flatter parts of the forgetting curve after a few months. This optimizes the frequency of review based on the shape of the forgetting curve, enabling efficient review.

[0047] The review function can improve the accuracy of review by referring to the user's past review history. For example, the review function can improve the accuracy of review based on the user's past review history. Furthermore, the review function can identify areas of weakness from the user's past review history and improve accuracy. In addition, the review function can analyze the user's past review history and apply the most efficient review method. For example, the review function analyzes the number of past reviews and the content of those reviews as part of the user's past review history to improve review accuracy. It analyzes past review data to identify areas of weakness and improve accuracy. It analyzes past review data to select the most efficient review method. In this way, by referring to the user's past review history, the accuracy of review can be improved.

[0048] The review team can prioritize review based on the submission deadlines of the learning materials. For example, the review team can encourage students to review learning materials with approaching deadlines first. Conversely, it can also encourage students to postpone reviewing learning materials with distant deadlines. Furthermore, it can encourage students to review learning materials with medium-term deadlines with an appropriate level of priority. For example, the review team can prioritize reviewing assignments with approaching deadlines, postpone reviewing assignments with further deadlines, and encourage reviewing assignments with medium-term deadlines with an appropriate level of priority. By determining review priorities based on the submission deadlines of the learning materials, efficient review can be achieved.

[0049] The review function can adjust the order of review based on the relevance of the learning content. For example, the review function can prioritize reviewing highly relevant learning content and adjust the order accordingly. It can also postpone reviewing less relevant learning content and adjust the order accordingly. Furthermore, it can review learning content of moderate relevance in an appropriate order and adjust the order accordingly. For example, the review function can prioritize reviewing topics requiring prerequisite knowledge as highly relevant learning content, postpone reviewing topics that do not require prerequisite knowledge as less relevant learning content, and review topics requiring some prerequisite knowledge in an appropriate order as moderately relevant learning content. By adjusting the order of review based on the relevance of the learning content, efficient review can be achieved.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The analysis unit can estimate the user's learning style and adjust the analysis method based on that estimated style. For example, if the user is a visual learner, the analysis can prioritize images and videos. If the user is an auditory learner, the analysis can prioritize audio data. Furthermore, if the user is an experiential learner, the analysis can prioritize interactive content. By tailoring the analysis to the user's learning style, more effective learning support can be provided.

[0052] The analysis unit can analyze the user's learning progress in real time based on their learning history and provide appropriate feedback. For example, if a user is struggling with a particular chapter, it can provide supplementary materials related to that chapter. If the user is progressing well, it can also provide advice on how to move on to the next step. Furthermore, if a user interrupts their learning, it can suggest the most suitable review points when they resume. This allows for flexible support tailored to the user's learning progress.

[0053] The generation unit can also generate personalized learning plans based on the user's learning history. For example, it can generate a plan that focuses on areas the user has struggled with in the past. It can also generate a plan that further deepens the user's strengths. Furthermore, it can suggest a schedule that matches the user's learning pace. This allows for the provision of learning plans that meet the individual needs of each user.

[0054] The system can evaluate the effectiveness of learning based on the user's learning history and suggest the next learning steps. For example, if a user achieves a high score in a particular area, it can suggest application problems in that area. Conversely, if a user achieves a low score, it can provide materials for reviewing from the basics. Furthermore, it can analyze the user's learning history and suggest the optimal learning sequence. This allows the system to provide support to maximize the user's learning effectiveness.

[0055] The review function can also optimize the timing of reviews based on the user's learning history. For example, if a user struggles with a particular area, it can prompt them to review that area more frequently. It can also prompt them to review areas they excel at at an appropriate frequency. Furthermore, it can adjust the timing of reviews according to the user's learning progress. This allows the system to provide review support that maximizes the user's learning effectiveness.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The analysis unit analyzes the learning materials. The learning materials include text, videos, slides, etc. The analysis unit extracts content from the learning materials and analyzes patterns using text analysis, image analysis, and data mining techniques. For example, it uses natural language processing techniques to analyze text data and extract important information. It uses computer vision techniques to analyze image data and extract visual information. It uses machine learning algorithms to analyze data patterns and extract features of the learning materials. Step 2: The generation unit generates learning content in a visual format based on the analysis performed by the analysis unit. Visual formats include graphs, charts, and infographics. The generation unit generates graphs to visually show data trends. It generates charts to visually show data comparisons. It generates infographics to visually present complex information in an easy-to-understand way. For example, it generates bar graphs and line graphs to visually show data fluctuations. It generates pie charts and histograms to visually show data distributions. It uses icons and illustrations to visually present information. Step 3: The identification unit identifies the user's weak areas based on the test results for each chapter generated by the generation unit. Test scores and the frequency of incorrect answers are used to identify weak areas. The identification unit analyzes the test scores to identify the user's weak areas. It analyzes the frequency of incorrect answers to identify the user's weak areas. It analyzes the user's learning history to identify weak areas. For example, it analyzes the test scores for each chapter and identifies chapters with low scores as weak areas. It analyzes the number of incorrect answers in each chapter and identifies chapters with many incorrect answers as weak areas. It analyzes the user's past learning data to identify weak areas. Step 4: The review unit prompts review at specific times based on the areas of weakness identified by the specific unit. The timing of review may be determined by the forgetting curve or the learning schedule. The review unit sets review timing based on the forgetting curve and prompts the user to review. It sets review timing based on the learning schedule and prompts the user to review. It adjusts the review timing according to the user's learning progress. For example, it sets review timing using Ebbinghaus's forgetting curve and prompts the user to review. It sets review timing based on the user's learning plan and prompts the user to review. It adjusts the review timing according to the user's learning progress and prompts the user to review.

[0058] (Example of form 2) The learning support system according to an embodiment of the present invention is a system that provides learning content for obtaining qualifications. This learning support system trains an AI with learning materials and provides learning content in a visual format. Each chapter has a test, and it also has a function to repeat learning at timings based on the forgetting curve and to overcome weak areas. For users aiming to obtain qualifications, it can be deployed worldwide. Furthermore, by applying this system to internal business operations, it can visualize the level of proficiency in basic to intermediate knowledge of new employees and transferees, and become an effective tool for placing the right people in the right positions. For example, the learning support system trains an AI with learning materials. The AI ​​analyzes the learning content and generates learning content in a visual format. For example, by explaining the content of a qualification exam in an easy-to-understand visual way, users can learn in an enjoyable way. Next, each chapter has a test, allowing users to check their learning content. Based on the test results, the AI ​​identifies the user's weak areas and encourages repeated learning. For example, by reviewing at timings based on the forgetting curve, the learning effect can be enhanced. Moreover, this system can be deployed worldwide and is extremely useful for users aiming to obtain qualifications. For example, by providing learning content that supports different languages ​​and cultures, it can be used by users all over the world. Furthermore, by applying this system to internal business processes, it becomes possible to visualize the level of proficiency in basic to intermediate knowledge for new employees and transferees. For instance, by having AI learn the business processes and generating learning content, new employees and transferees can acquire skills more efficiently. This also makes it an effective tool for placing the right people in the right positions. Thus, the learning support system can provide learning content for obtaining qualifications, thereby enhancing the learning effectiveness for users. Additionally, by applying it to internal business processes, it becomes possible to visualize the level of proficiency in basic to intermediate knowledge for new employees and transferees, making it an effective tool for placing the right people in the right positions.

[0059] The learning support system according to this embodiment comprises an analysis unit, a generation unit, a specification unit, and a review unit. The analysis unit analyzes learning materials. Learning materials include, but are not limited to, text, video, and slides. The analysis unit performs, for example, text analysis to extract the content of the learning materials. The analysis unit can also perform image analysis to analyze the content of visual content. Furthermore, the analysis unit can use data mining techniques to analyze patterns in the learning materials. For example, as text analysis, the analysis unit uses natural language processing techniques to analyze text data and extract important information. As image analysis, it uses computer vision techniques to analyze image data and extract visual information. As data mining, it uses machine learning algorithms to analyze data patterns and extract features of the learning materials. The generation unit generates learning content in a visual format based on the content analyzed by the analysis unit. Visual formats include, but are not limited to, graphs, charts, and infographics. The generation unit generates, for example, graphs to visually show data trends. The generation unit can also generate charts to visually compare data. Furthermore, the generation unit can generate infographics to visually present complex information in an easy-to-understand way. For example, the generation unit can generate bar graphs and line graphs to visually show data fluctuations. It can generate pie charts and histograms to visually show data distributions. It can use icons and illustrations to visually present information as infographics. The identification unit identifies the user's weak areas based on the test results for each chapter generated by the generation unit. Identifying weak areas may use, but is not limited to, test score results or the frequency of incorrect answers. For example, the identification unit can analyze test score results to identify the user's weak areas. It can also analyze the frequency of incorrect answers to identify the user's weak areas. Furthermore, the identification unit can analyze the user's learning history to identify weak areas. For example, the identification unit can analyze the test scores for each chapter as test score results and identify chapters with low scores as weak areas.The frequency of incorrect answers is analyzed by examining the number of incorrect answers in each chapter, and chapters with many incorrect answers are identified as areas of weakness. As part of the learning history, the user's past learning data is analyzed to identify areas of weakness. The review unit prompts review at specific times based on the areas of weakness identified by the identification unit. The timing of review may be based on, but is not limited to, the forgetting curve or the learning schedule. For example, the review unit may set review timing based on the forgetting curve and prompt the user to review. The review unit can also set review timing based on the learning schedule and prompt the user to review. Furthermore, the review unit can adjust the review timing according to the user's learning progress. For example, the review unit may use Ebbinghaus's forgetting curve as the forgetting curve to set review timing and prompt the user to review. As a learning schedule, it may set review timing based on the user's learning plan and prompt the user to review. As a learning status, it may adjust the review timing according to the user's learning progress and prompt the user to review. As a result, the learning support system according to this embodiment can analyze learning materials, generate content in a visual format, identify the user's weak areas, and prompt review at timings based on the forgetting curve.

[0060] The analytics department can analyze specific business operations within the company. These specific operations include, but are not limited to, sales activities, project management, and customer service. For example, the analytics department can analyze sales activity data to improve the efficiency of the sales process. It can also analyze project management data to understand project progress. Furthermore, it can analyze customer service data to improve customer satisfaction. For instance, the analytics department can analyze sales performance and customer visit history to identify areas for improvement in sales strategies. For project management, it can analyze project task progress and resource allocation to improve project efficiency. For customer service, it can analyze customer feedback and complaint handling history to identify areas for improvement in customer service. By analyzing internal business operations, the department can visualize the level of proficiency in basic to intermediate knowledge among new employees and those transferred from other departments.

[0061] The generation unit can generate learning content based on the company's internal business processes. This learning content may include, but is not limited to, text, video, and slides. For example, the generation unit can generate text-based learning content that explains work procedures in detail. It can also generate video-based learning content that visually demonstrates practical work examples. Furthermore, it can generate slide-based learning content that clearly presents key points of the work. For instance, the generation unit can generate work manuals and procedure documents in text format, explaining detailed work procedures; film practical work examples and visually demonstrate them in video format; and generate presentation materials summarizing key points of the work in slide format. This allows new employees and transferees to efficiently acquire work skills by generating learning content based on the company's internal business processes.

[0062] A specific department can identify the level of proficiency in specific knowledge levels of new employees or transferees. These specific knowledge levels include, but are not limited to, basic knowledge, intermediate knowledge, and specialized knowledge. For example, a department can analyze the results of a basic knowledge test to identify the level of basic knowledge proficiency of new employees. Similarly, a department can analyze the results of an intermediate knowledge test to identify the level of intermediate knowledge proficiency of transferees. Furthermore, a department can analyze the results of a specialized knowledge test to identify the knowledge level of professionals. For example, a department could test and identify proficiency in basic work procedures and terminology as basic knowledge; test and identify proficiency in applied work procedures and problem-solving abilities as intermediate knowledge; and test and identify proficiency in advanced work techniques and specialized knowledge as specialized knowledge. This allows for the identification of the level of proficiency in basic to intermediate knowledge of new employees and transferees, making it an effective tool for placing the right people in the right positions.

[0063] The review function can encourage review based on the user's level of proficiency. This level of proficiency includes, but is not limited to, test scores, work experience, and feedback. For example, the review function can encourage review based on test scores to improve user comprehension. It can also encourage review based on work experience to improve user practical skills. Furthermore, it can encourage review based on feedback to clearly identify areas for improvement. For example, the review function can focus on reviewing chapters with low test scores, encourage review based on real-world challenges, and encourage review based on feedback from supervisors and colleagues. By encouraging review based on proficiency, the learning effect can be enhanced.

[0064] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit can increase the accuracy of the analysis and prioritize analyzing simpler content. If the user is relaxed, the analysis unit can perform a detailed analysis and analyze content that promotes deeper understanding. Furthermore, if the user is focused, the analysis unit can prioritize analyzing more difficult content to maximize the learning effect. For example, the analysis unit uses facial expression analysis technology to estimate the user's emotions. Facial expression analysis technology analyzes the user's facial expression data captured by a camera and estimates the emotions. The analysis unit can also estimate the user's emotions using voice analysis technology. Voice analysis technology analyzes the user's voice data recorded by a microphone and estimates the emotions. Furthermore, the analysis unit can also estimate the user's emotions based on survey results. Survey results analyze the content of the questions answered by the user and estimate the emotions. By adjusting the accuracy of the analysis based on the user's emotions, more appropriate analysis results can be provided.

[0065] The analysis unit can apply different analysis algorithms depending on the type of learning material. For example, it can apply a natural language processing algorithm to text-based materials to analyze their content. It can also apply an image recognition algorithm to materials containing mathematical formulas and graphs to analyze their content. Furthermore, it can combine speech recognition and video analysis algorithms to analyze video materials. For example, for text-based materials, the analysis unit uses natural language processing technology to analyze text data and extract important information. For materials containing mathematical formulas and graphs, it uses computer vision technology to analyze image data and extract visual information. For video materials, it combines speech recognition and video analysis technologies to analyze video data and extract audio and video information. This allows for improved analysis accuracy by applying the appropriate analysis algorithm according to the type of learning material.

[0066] The analysis unit can appropriately adjust its analysis method based on the specific update frequency of the learning materials during analysis. For example, for frequently updated materials, the analysis unit applies an algorithm that prioritizes analyzing the latest information. Furthermore, for materials with infrequent updates, the analysis unit can apply an analysis algorithm based on past data. Additionally, for materials with irregular updates, the analysis unit can select the optimal analysis method by referring to the update history. For example, as a frequently updated material, the analysis unit analyzes daily updated news articles and prioritizes extracting the latest information. As a low-update material, it analyzes annually updated statistical data and performs analysis based on past data. For materials with irregular updates, it refers to the update history and selects the optimal analysis method. By optimizing the analysis method considering the update frequency of the learning materials, the analysis unit can provide analysis results that reflect the latest information.

[0067] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, the analysis unit can provide a simple and highly visible display method. If the user is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that gets straight to the point. For example, the analysis unit uses facial expression analysis technology to estimate the user's emotions. Facial expression analysis technology analyzes the user's facial expression data captured by a camera and estimates the emotions. The analysis unit can also estimate the user's emotions using voice analysis technology. Voice analysis technology analyzes the user's voice data recorded by a microphone and estimates the emotions. Furthermore, the analysis unit can also estimate the user's emotions based on survey results. Survey results analyze the content of the questions answered by the user and estimate the emotions. By adjusting the display method of the analysis results based on the user's emotions, the optimal display method can be provided to the user.

[0068] The analysis unit can perform analysis based on the specific language and cultural background of the learning materials. For example, if the learning materials are provided in multiple languages, the analysis unit applies an appropriate analysis algorithm to each language. Furthermore, if the learning materials have a specific cultural background, the analysis unit can consider that background during the analysis. Additionally, if the learning materials include information from different regions, the analysis unit can consider the characteristics of each region during the analysis. For example, if the learning materials are provided in multiple languages ​​such as English, Japanese, and French, the analysis unit applies a natural language processing algorithm appropriate for each language. If the learning materials have a specific cultural background, the analysis takes into account those cultural customs and values. If the learning materials include information from different regions, the analysis takes into account the characteristics of each region. This allows for the provision of more appropriate analysis results by considering the language and cultural background of the learning materials during the analysis.

[0069] The analysis unit can improve the accuracy of its analysis based on specific relevant literature for the learning materials. For example, the analysis unit can automatically search for literature related to the learning materials and incorporate it into the analysis. Furthermore, the analysis unit can incorporate information from relevant literature into the analysis to complement the content of the learning materials. In addition, the analysis unit can perform analysis by referencing data from relevant literature to enhance the reliability of the learning materials. For example, the analysis unit can automatically search for academic papers related to the learning materials and incorporate their content into the analysis. It can also incorporate information from relevant literature into the analysis to complement the content of the learning materials. Finally, it can perform analysis by referencing data from relevant literature to enhance the reliability of the learning materials. This allows for the provision of more reliable analysis results by improving the accuracy of the analysis through reference to relevant literature for the learning materials.

[0070] The generation unit can estimate the user's emotions and adjust the way the generated content is presented based on those estimated emotions. For example, if the user is relaxed, the generation unit will generate content that progresses at a leisurely pace. If the user is in a hurry, the generation unit can also generate content that emphasizes the shortest route. Furthermore, if the user is excited, the generation unit can generate content with visually stimulating effects. For example, the generation unit can use facial expression analysis technology to estimate the user's emotions. Facial expression analysis technology analyzes the user's facial expression data captured by a camera and estimates their emotions. The generation unit can also estimate the user's emotions using voice analysis technology. Voice analysis technology analyzes the user's voice data recorded by a microphone and estimates their emotions. Furthermore, the generation unit can also estimate the user's emotions based on survey results. Survey results analyze the content of the questions the user answered and estimate their emotions. By adjusting the way the content is presented based on the user's emotions, the system can provide the user with the optimal learning experience.

[0071] The generation unit can adjust the level of detail of the content based on the importance of the learning material during generation. For example, the generation unit can generate content with detailed explanations for highly important learning material. It can also generate content with concise explanations for less important learning material. Furthermore, it can generate content with an appropriate level of detail for moderately important learning material. For example, the generation unit can generate content that explains in detail topics that frequently appear on the exam as highly important learning material. It can generate content that explains topics that rarely appear on the exam concisely as less important learning material. It can generate content that explains topics that appear moderately frequently on the exam with an appropriate level of detail as moderately important learning material. In this way, efficient learning can be achieved by adjusting the level of detail of the content based on the importance of the learning material.

[0072] The generation unit can apply different generation algorithms depending on the category of learning content during generation. For example, for theoretical learning content, the generation unit can apply a generation algorithm that emphasizes logical explanations. Furthermore, for practical learning content, it can apply a generation algorithm that emphasizes concrete examples. In addition, for applied learning content, it can apply a generation algorithm that emphasizes application examples. For example, for theoretical learning content, the generation unit can generate content that emphasizes explanations based on logical frameworks. For practical learning content, it can generate content that emphasizes explanations using concrete examples. For applied learning content, it can generate content that emphasizes explanations using application examples. This allows for the provision of effective learning content by applying the appropriate generation algorithm according to the category of learning content.

[0073] The generation unit can estimate the user's emotions and adjust the length of the generated content based on those emotions. For example, if the user is in a hurry, the generation unit will generate short, concise content. If the user is relaxed, the generation unit can generate longer content with detailed explanations. Furthermore, if the user is excited, the generation unit can generate content with visually stimulating effects. For example, the generation unit can use facial expression analysis technology to estimate the user's emotions. Facial expression analysis technology analyzes the user's facial expression data captured by a camera and estimates their emotions. The generation unit can also estimate the user's emotions using voice analysis technology. Voice analysis technology analyzes the user's voice data recorded by a microphone and estimates their emotions. Furthermore, the generation unit can also estimate the user's emotions based on survey results. Survey results analyze the content of the questions the user answered and estimate their emotions. This allows the generation unit to provide the user with an optimal learning experience by adjusting the length of the content based on their emotions.

[0074] The generation unit can prioritize content based on the submission deadlines of learning materials during generation. For example, the generation unit will prioritize generating content for learning materials with approaching deadlines. It can also postpone generating content for learning materials with distant deadlines. Furthermore, it can generate content with a moderate priority for learning materials with medium-term deadlines. For example, the generation unit will prioritize generating content for assignments with approaching deadlines, postpone generating content for assignments with distant deadlines, and generate content for assignments with medium-term deadlines with a moderate priority. By prioritizing content based on the submission deadlines of learning materials, efficient learning can be achieved.

[0075] The generation unit can adjust the order of content based on the relevance of the learning material during generation. For example, the generation unit can prioritize and adjust the order of highly relevant learning material. It can also adjust the order of less relevant learning material by placing it later. Furthermore, it can adjust the order of moderately relevant learning material by placing it in an appropriate order. For example, the generation unit prioritizes topics requiring prior knowledge as highly relevant learning material. It places topics that do not require prior knowledge later as less relevant learning material. It places topics that require some prior knowledge as moderately relevant learning material in an appropriate order. In this way, efficient learning can be achieved by adjusting the order of content based on the relevance of the learning material.

[0076] The identification unit can estimate the user's emotions and adjust the accuracy of identification based on the estimated emotions. For example, if the user is stressed, the identification unit can increase the accuracy of identification and prioritize identifying simpler content. If the user is relaxed, the identification unit can perform detailed identification and identify content that promotes deeper understanding. Furthermore, if the user is focused, the identification unit can prioritize identifying more difficult content to maximize learning effectiveness. For example, the identification unit can use facial expression analysis technology to estimate the user's emotions. Facial expression analysis technology analyzes the user's facial expression data captured by a camera and estimates the emotions. The identification unit can also estimate the user's emotions using voice analysis technology. Voice analysis technology analyzes the user's voice data recorded by a microphone and estimates the emotions. Furthermore, the identification unit can also estimate the user's emotions based on survey results. Survey results analyze the content of the questions the user answered and estimate the emotions. This allows for more appropriate identification results by adjusting the accuracy of identification based on the user's emotions.

[0077] The identification unit can appropriately adjust the identification method based on the specific level of detail of the test results during identification. For example, the identification unit can apply a highly accurate identification method to detailed test results. It can also apply a concise identification method to simplified test results. Furthermore, it can apply a moderately detailed identification method to test results with a moderate level of detail. For example, for detailed test results, the identification unit can analyze the correct answer rate and error trends for each question and apply a highly accurate identification method. For simplified test results, it can analyze the total score and average score and apply a concise identification method. For test results with a moderate level of detail, it can analyze the score for each chapter and the frequency of errors and apply a moderately detailed identification method. In this way, efficient identification can be achieved by optimizing the identification method based on the level of detail of the test results.

[0078] The identification unit can improve the accuracy of identification based on the user's specific past learning history. For example, the identification unit improves the accuracy of identification based on the user's past learning history. The identification unit can also identify areas of weakness from the user's past learning history and improve accuracy. Furthermore, the identification unit can analyze the user's past learning history and apply the most efficient identification method. For example, the identification unit analyzes past test results and study time as part of the user's past learning history to improve the accuracy of identification. To identify areas of weakness, it analyzes past incorrect answer trends to improve accuracy. To apply the most efficient identification method, it analyzes past learning data and selects the optimal identification method. In this way, the accuracy of identification can be improved by referring to the user's past learning history.

[0079] The identification unit can estimate the user's emotions and adjust the display method of the identification results based on the estimated user emotions. For example, if the user is nervous, the identification unit can provide a simple and highly visible display method. If the user is relaxed, the identification unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the identification unit can provide a display method that gets straight to the point. For example, the identification unit uses facial expression analysis technology to estimate the user's emotions. Facial expression analysis technology analyzes the user's facial expression data captured by a camera and estimates the emotions. The identification unit can also estimate the user's emotions using voice analysis technology. Voice analysis technology analyzes the user's voice data recorded by a microphone and estimates the emotions. Furthermore, the identification unit can also estimate the user's emotions based on survey results. Survey results analyze the content of the questions answered by the user and estimate the emotions. By adjusting the display method of the identification results based on the user's emotions, the system can provide the optimal display method for the user.

[0080] The identification unit can determine the order of identification based on the specific submission dates of the test results. For example, the identification unit can prioritize identification of test results with approaching submission deadlines. It can also postpone identification of test results with distant submission deadlines. Furthermore, it can assign a moderate priority to test results with medium submission deadlines. For example, the identification unit can prioritize identification of test results with approaching deadlines, postpone identification of test results with further deadlines, and assign a moderate priority to test results with medium deadlines. By determining the priority of identification based on the submission dates of the test results, efficient identification can be achieved.

[0081] The identification unit can adjust the order of identification based on the specific relevance of the test results during the identification process. For example, the identification unit can prioritize identifying highly relevant test results and adjust their order. It can also postpone identifying less relevant test results and adjust their order. Furthermore, it can identify moderately relevant test results in an appropriate order and adjust their order. For example, the identification unit prioritizes identifying test results that require prior knowledge as highly relevant test results. It postpones identifying test results that do not require prior knowledge as less relevant test results. It identifies test results that require some prior knowledge in an appropriate order as moderately relevant test results. This allows for efficient identification by adjusting the order of identification based on the relevance of the test results.

[0082] The review function can estimate the user's emotions and adjust the timing of reviews based on those emotions. For example, if the user is feeling stressed, the review function can delay the review to encourage a more relaxed state. Conversely, if the user is relaxed, the review function can prompt a review at an appropriate time. Furthermore, if the user is focused, the review function can prompt a review earlier to maximize learning effectiveness. For example, the review function uses facial expression analysis technology to estimate the user's emotions. Facial expression analysis technology analyzes the user's facial expression data captured by a camera to estimate emotions. The review function can also estimate the user's emotions using voice analysis technology. Voice analysis technology analyzes the user's voice data recorded by a microphone to estimate emotions. Furthermore, the review function can also estimate the user's emotions based on survey results. Survey results analyze the content of the questions the user answered to estimate emotions. By adjusting the timing of reviews based on the user's emotions, more effective reviews can be achieved.

[0083] The review function can optimize the frequency of review based on the shape of the forgetting curve. For example, the review function can prompt frequent review in the steeper parts of the forgetting curve. It can also prompt moderate review in the gentler parts of the forgetting curve. Furthermore, it can prompt less frequent review in the flatter parts of the forgetting curve. For example, based on Ebbinghaus's forgetting curve, the review function can prompt frequent review in the first few days as the steeper part of the forgetting curve. It can prompt moderate review in the gentler parts of the forgetting curve after a few weeks. It can prompt less frequent review in the flatter parts of the forgetting curve after a few months. This optimizes the frequency of review based on the shape of the forgetting curve, enabling efficient review.

[0084] The review function can improve the accuracy of review by referring to the user's past review history. For example, the review function can improve the accuracy of review based on the user's past review history. Furthermore, the review function can identify areas of weakness from the user's past review history and improve accuracy. In addition, the review function can analyze the user's past review history and apply the most efficient review method. For example, the review function analyzes the number of past reviews and the content of those reviews as part of the user's past review history to improve review accuracy. It analyzes past review data to identify areas of weakness and improve accuracy. It analyzes past review data to select the most efficient review method. In this way, by referring to the user's past review history, the accuracy of review can be improved.

[0085] The review function can estimate the user's emotions and adjust the display method of the review content based on those estimated emotions. For example, if the user is nervous, the review function can provide a simple and highly visible display method. If the user is relaxed, it can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, it can provide a display method that focuses on the key points. For example, the review function can use facial expression analysis technology to estimate the user's emotions. Facial expression analysis technology analyzes the user's facial expression data captured by a camera and estimates their emotions. The review function can also estimate the user's emotions using voice analysis technology. Voice analysis technology analyzes the user's voice data recorded by a microphone and estimates their emotions. Furthermore, the review function can also estimate the user's emotions based on survey results. Survey results analyze the content of the questions the user answered and estimate their emotions. By adjusting the display method of the review content based on the user's emotions, the system can provide the optimal display method for the user.

[0086] The review team can prioritize review based on the submission deadlines of the learning materials. For example, the review team can encourage students to review learning materials with approaching deadlines first. Conversely, it can also encourage students to postpone reviewing learning materials with distant deadlines. Furthermore, it can encourage students to review learning materials with medium-term deadlines with an appropriate level of priority. For example, the review team can prioritize reviewing assignments with approaching deadlines, postpone reviewing assignments with further deadlines, and encourage reviewing assignments with medium-term deadlines with an appropriate level of priority. By determining review priorities based on the submission deadlines of the learning materials, efficient review can be achieved.

[0087] The review function can adjust the order of review based on the relevance of the learning content. For example, the review function can prioritize reviewing highly relevant learning content and adjust the order accordingly. It can also postpone reviewing less relevant learning content and adjust the order accordingly. Furthermore, it can review learning content of moderate relevance in an appropriate order and adjust the order accordingly. For example, the review function can prioritize reviewing topics requiring prerequisite knowledge as highly relevant learning content, postpone reviewing topics that do not require prerequisite knowledge as less relevant learning content, and review topics requiring some prerequisite knowledge in an appropriate order as moderately relevant learning content. By adjusting the order of review based on the relevance of the learning content, efficient review can be achieved. === Hard Collateral 1-1 === Each of the multiple elements described above, including the analysis unit, generation unit, identification unit, and review unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes learning materials. The generation unit is implemented by the processor 46 of the smart device 14 and generates learning content in a visual format. The identification unit is implemented by the identification processing unit 290 of the data processing device 12 and identifies the user's areas of difficulty. The review unit is implemented by the identification processing unit 290 of the data processing device 12 and prompts review at timings based on the forgetting curve. Each of the analysis unit, generation unit, identification unit, and review unit may be implemented in at least one of the smart device 14 and the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements described above, including the analysis unit, generation unit, identification unit, and review unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes learning materials. The generation unit is implemented by the processor 46 of the smart glasses 214 and generates learning content in a visual format. The identification unit is implemented by the identification processing unit 290 of the data processing device 12 and identifies the user's areas of difficulty. The review unit is implemented by the identification processing unit 290 of the data processing device 12 and prompts review at timings based on the forgetting curve. Each of the analysis unit, generation unit, identification unit, and review unit may be implemented in at least one of the smart glasses 214 and the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements described above, including the analysis unit, generation unit, identification unit, and review unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes learning materials. The generation unit is implemented by the processor 46 of the headset terminal 314 and generates learning content in a visual format. The identification unit is implemented by the identification processing unit 290 of the data processing device 12 and identifies the user's areas of difficulty. The review unit is implemented by the identification processing unit 290 of the data processing device 12 and prompts review at timings based on the forgetting curve. Each of the analysis unit, generation unit, identification unit, and review unit may be implemented in at least one of the headset terminal 314 and the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements described above, including the analysis unit, generation unit, identification unit, and review unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes learning materials. The generation unit is implemented by the processor 46 of the robot 414 and generates learning content in a visual format. The identification unit is implemented by the identification processing unit 290 of the data processing unit 12 and identifies the user's weak areas. The review unit is implemented by the identification processing unit 290 of the data processing unit 12 and prompts review at timings based on the forgetting curve. Each of the analysis unit, generation unit, identification unit, and review unit may be implemented in at least one of the robot 414 and the data processing unit 12.

[0088] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0089] The analysis unit can estimate the user's learning style and adjust the analysis method based on that estimated style. For example, if the user is a visual learner, the analysis can prioritize images and videos. If the user is an auditory learner, the analysis can prioritize audio data. Furthermore, if the user is an experiential learner, the analysis can prioritize interactive content. By tailoring the analysis to the user's learning style, more effective learning support can be provided.

[0090] The analysis unit can analyze the user's learning progress in real time based on their learning history and provide appropriate feedback. For example, if a user is struggling with a particular chapter, it can provide supplementary materials related to that chapter. If the user is progressing well, it can also provide advice on how to move on to the next step. Furthermore, if a user interrupts their learning, it can suggest the most suitable review points when they resume. This allows for flexible support tailored to the user's learning progress.

[0091] The generation unit can also generate personalized learning plans based on the user's learning history. For example, it can generate a plan that focuses on areas the user has struggled with in the past. It can also generate a plan that further deepens the user's strengths. Furthermore, it can suggest a schedule that matches the user's learning pace. This allows for the provision of learning plans that meet the individual needs of each user.

[0092] The system can evaluate the effectiveness of learning based on the user's learning history and suggest the next learning steps. For example, if a user achieves a high score in a particular area, it can suggest application problems in that area. Conversely, if a user achieves a low score, it can provide materials for reviewing from the basics. Furthermore, it can analyze the user's learning history and suggest the optimal learning sequence. This allows the system to provide support to maximize the user's learning effectiveness.

[0093] The review function can also optimize the timing of reviews based on the user's learning history. For example, if a user struggles with a particular area, it can prompt them to review that area more frequently. It can also prompt them to review areas they excel at at an appropriate frequency. Furthermore, it can adjust the timing of reviews according to the user's learning progress. This allows the system to provide review support that maximizes the user's learning effectiveness.

[0094] The analysis unit can estimate the user's emotions and adjust the analysis priority based on those emotions. For example, if the user is stressed, it will prioritize analyzing simpler content. If the user is relaxed, it can perform more detailed analysis. Furthermore, if the user is focused, it can prioritize analyzing more difficult content. This allows for flexible analysis tailored to the user's emotions.

[0095] The generation unit can also estimate the user's emotions and adjust the difficulty level of the generated content based on those emotions. For example, if the user is stressed, it can generate content with many easy questions. If the user is relaxed, it can generate content with detailed explanations. Furthermore, if the user is focused, it can generate content with many difficult questions. This allows for the provision of optimal learning content tailored to the user's emotions.

[0096] The identification unit can also estimate the user's emotions and adjust the prioritization of specific items based on those emotions. For example, if the user is stressed, it can prioritize identifying simpler items. If the user is relaxed, it can prioritize identifying more detailed items. Furthermore, if the user is focused, it can prioritize identifying more difficult items. This allows for flexible identification that responds to the user's emotions.

[0097] The review function can estimate the user's emotions and adjust the review content based on those estimates. For example, if the user is stressed, it will encourage them to review simpler content. If the user is relaxed, it can review more detailed content. Furthermore, if the user is focused, it can review more difficult content. This allows the system to provide optimal review content tailored to the user's emotions.

[0098] The generation unit can also estimate the user's emotions and adjust the format of the generated content based on those emotions. For example, if the user is stressed, it can generate visually simple content. If the user is relaxed, it can generate content with more detailed information. Furthermore, if the user is focused, it can generate interactive content. This allows for the provision of optimal learning content tailored to the user's emotions.

[0099] The following briefly describes the processing flow for example form 2.

[0100] Step 1: The analysis unit analyzes the learning materials. The learning materials include text, videos, slides, etc. The analysis unit extracts content from the learning materials and analyzes patterns using text analysis, image analysis, and data mining techniques. For example, it uses natural language processing techniques to analyze text data and extract important information. It uses computer vision techniques to analyze image data and extract visual information. It uses machine learning algorithms to analyze data patterns and extract features of the learning materials. Step 2: The generation unit generates learning content in a visual format based on the analysis performed by the analysis unit. Visual formats include graphs, charts, and infographics. The generation unit generates graphs to visually show data trends. It generates charts to visually show data comparisons. It generates infographics to visually present complex information in an easy-to-understand way. For example, it generates bar graphs and line graphs to visually show data fluctuations. It generates pie charts and histograms to visually show data distributions. It uses icons and illustrations to visually present information. Step 3: The identification unit identifies the user's weak areas based on the test results for each chapter generated by the generation unit. Test scores and the frequency of incorrect answers are used to identify weak areas. The identification unit analyzes the test scores to identify the user's weak areas. It analyzes the frequency of incorrect answers to identify the user's weak areas. It analyzes the user's learning history to identify weak areas. For example, it analyzes the test scores for each chapter and identifies chapters with low scores as weak areas. It analyzes the number of incorrect answers in each chapter and identifies chapters with many incorrect answers as weak areas. It analyzes the user's past learning data to identify weak areas. Step 4: The review unit prompts review at specific times based on the areas of weakness identified by the specific unit. The timing of review may be determined by the forgetting curve or the learning schedule. The review unit sets review timing based on the forgetting curve and prompts the user to review. It sets review timing based on the learning schedule and prompts the user to review. It adjusts the review timing according to the user's learning progress. For example, it sets review timing using Ebbinghaus's forgetting curve and prompts the user to review. It sets review timing based on the user's learning plan and prompts the user to review. It adjusts the review timing according to the user's learning progress and prompts the user to review.

[0101] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0102] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0103] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0104] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0105] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0106] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0107] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0108] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0109] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0111] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0112] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0113] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0114] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0115] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0119] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0120] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0121] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0122] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0124] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0125] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0127] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0128] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0129] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0130] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0131] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0137] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0138] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0145] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0146] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0147] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0148] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0153] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0154] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0155] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0156] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0157] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0158] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0159] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0160] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0161] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0162] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0163] 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.

[0164] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0165] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0166] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0167] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0168] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0169] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0170] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0171] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0172] [Explanation of Symbols]

[0173] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The analysis unit analyzes the learning materials, A generation unit generates content in a visual format based on the content analyzed by the analysis unit, Based on the test results for each chapter generated by the generation unit, an identification unit identifies the user's weak areas, Based on the areas of weakness identified by the aforementioned specific unit, a review unit prompts review at specific times, Equipped with A system characterized by the following features.

2. The aforementioned analysis unit, Analyze the specific tasks performed within the company. The system according to feature 1.

3. The generating unit is Generate learning content based on the company's business operations. The system according to feature 1.

4. The specified part is, Identify the specific knowledge level and proficiency of new employees or those transferring to other departments. The system according to feature 1.

5. The aforementioned review section is, Encourage review based on proficiency level. The system according to feature 1.

6. The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system according to feature 1.

7. The aforementioned analysis unit, Apply different analysis algorithms depending on the type of learning material. The system according to feature 1.

8. The aforementioned analysis unit, During analysis, the analysis method should be appropriately adjusted based on the specific update frequency of the learning materials. The system according to feature 1.

Images