system

Abstract

The system according to this embodiment aims to provide high-quality learning content and make it easier for learners to find content that suits them. [Solution] The system according to the embodiment comprises a production unit, a judgment unit, a voting unit, and a publishing unit. The production unit produces learning content. The judgment unit determines the legitimacy and quality of the learning content produced by the production unit. The voting unit casts votes on the learning content judged by the judgment unit and creates a ranking. The publishing unit publishes the learning content based on the ranking created by the voting unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that high-quality learning content is insufficient and it is difficult for learners to find content suitable for themselves.

[0005] The system according to the embodiment aims to provide high-quality learning content and make it easier for learners to find content suitable for themselves.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a production unit, a judgment unit, a voting unit, and a publishing unit. The production unit produces learning content. The judgment unit determines the validity and quality of the learning content produced by the production unit. The voting unit casts votes on the learning content judged by the judgment unit and creates a ranking. The publishing unit publishes the learning content based on the ranking created by the voting unit. [Effects of the Invention]

[0007] The system according to this embodiment provides high-quality learning content and makes it easier for learners to find content that suits them. [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 applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The learning content platform according to an embodiment of the present invention is a system that solicits learning content for elementary, junior high, and high school students in a competition format. In this system, educational video creators, educators, and cram school instructors create their own learning content, and a generating AI judges the validity and quality of that content. Next, current elementary, junior high, and high school students and educators vote to create a ranking. Top-ranked content can be published in print and electronic media. This allows for the spontaneous creation of high-quality learning content, making it easier for learners to find content that suits them. For example, if a video explaining a math problem is submitted, the generating AI judges whether the explanation is accurate and evaluates its educational effectiveness. Next, current elementary, junior high, and high school students and educators vote on the submitted content to create a ranking. Voting is based on the learner's level and needs, making it easier for each individual to find the most suitable learning content. For example, if a video explaining a math problem for beginners and a video explaining a math problem for advanced learners are submitted, beginners will vote for the beginner-level video, and advanced learners will vote for the advanced-level video. Furthermore, top-ranked content can be published in print and electronic media. This will lead to the widespread dissemination and provision of high-quality learning content to learners. This system makes it easier for learners to find high-quality learning content, and gives creators the opportunity to distribute their content widely. Furthermore, since the validity and quality of submitted content are guaranteed by the generation AI, highly reliable learning content will be provided. This is expected to improve Japan's educational standards and national strength. In this way, the learning content platform can make it easier for learners to find high-quality learning content and provide creators with the opportunity to distribute their content widely.

[0029] The learning content platform according to this embodiment comprises a production unit, an evaluation unit, a voting unit, and a publishing unit. The production unit produces learning content. For example, the production unit can be used by educational video creators, educators, and cram school instructors to produce their own learning content. The production unit can produce learning content in video format or text format. The production unit can also use, for example, generative AI to support the production of learning content. The evaluation unit determines the legitimacy and quality of the learning content produced by the production unit. For example, the evaluation unit uses, for example, generative AI to determine the legitimacy and quality of submitted learning content. For example, the evaluation unit analyzes submitted learning content and evaluates the accuracy of the content and its educational effectiveness. For example, if a video explaining a math problem is submitted, the evaluation unit determines whether the explanation is accurate and evaluates whether it has high educational effectiveness. The voting unit casts votes for the learning content judged by the evaluation unit and creates rankings. For example, current elementary, junior high, and high school students and educators cast votes for the submitted content. The voting section allows learners to vote based on their level and needs, making it easier for them to find the most suitable learning content. For example, if beginner-level and advanced-level math problem explanation videos are submitted, beginners will vote for the beginner-level video, and advanced learners will vote for the advanced-level video. The publishing section publishes learning content based on the rankings created by the voting section. The publishing section publishes top-ranked learning content in print and electronic formats. For example, the publishing section can publish in print or as an e-book. The publishing section can also support the publication of learning content using, for example, generative AI. As a result, the learning content platform according to this embodiment can make it easier for learners to find high-quality learning content and provide creators with opportunities to widely distribute their content.

[0030] The production department creates learning content. For example, the production department allows educational video creators, educators, and cram school instructors to create their own learning content. Specifically, educational video creators can create videos based on their areas of expertise, providing clear explanations to viewers. Educators and cram school instructors can create video and text-based learning content based on teaching materials and supplementary resources used in their classes. The production department can create video and text-based learning content, for example. Video content is easier for learners to understand because it contains a lot of visual information. Text-based content can include detailed explanations and examples, allowing learners to progress at their own pace. The production department can also support the creation of learning content using, for example, generative AI. Generative AI can automatically generate detailed explanations and examples based on basic information provided by educators. This reduces the burden of content creation for educators, allowing them to dedicate more time to other educational activities. Furthermore, generative AI can provide customized content according to the learner's level of understanding and progress. For example, if a learner is struggling with a particular topic, the generative AI can provide additional explanations and practice exercises related to that topic. This allows the production department to efficiently create high-quality learning content that meets the learner's needs.

[0031] The evaluation unit determines the legitimacy and quality of learning content produced by the production unit. For example, the evaluation unit uses generative AI to determine the legitimacy and quality of submitted learning content. Specifically, the generative AI analyzes the submitted content and evaluates its accuracy and educational effectiveness. For example, if a video explaining a math problem is submitted, the evaluation unit determines whether the explanation is accurate and evaluates its educational effectiveness. The generative AI checks the accuracy of the explanation based on mathematical formulas and theorems, and verifies that there are no errors. Furthermore, to evaluate educational effectiveness, it can analyze learners' understanding and reactions to measure the effectiveness of the content. In addition, the evaluation unit can utilize past data and statistical information to evaluate the quality of the content. For example, it can analyze the characteristics of content that has received high ratings in the past and compare them with newly submitted content to set quality standards. This allows the evaluation unit to determine the legitimacy and quality of learning content with high accuracy and provide learners with reliable content. Furthermore, the evaluation unit can set evaluation criteria according to different educational fields and levels, and perform evaluations appropriate to each field and level. For example, since the evaluation criteria differ between beginner-level and advanced-level content, applying appropriate evaluations to each allows us to provide learners with the most suitable content. This enables the evaluation unit to accurately determine the legitimacy and quality of the learning content, providing learners with highly reliable content.

[0032] The voting department votes on learning content judged by the evaluation department and creates rankings. For example, current elementary, middle, and high school students and educators vote on submitted content. Specifically, learners and educators evaluate and vote based on factors such as content, clarity, and educational effectiveness. The voting department makes it easier for learners to find the most suitable learning content by voting based on their level and needs. For example, if beginner-level and advanced-level math problem explanation videos are submitted, beginners would vote for the beginner-level video, and advanced learners would vote for the advanced-level video. This makes it easier for learners to find content that matches their level. Furthermore, the voting department can create rankings based on the voting results, providing learners with popular content. Rankings can be created, for example, by category or level, making it easy for learners to find content that suits them. The voting department can update voting results in real time, providing the latest information. This ensures learners always have access to the most popular content. The voting department can also collect feedback from learners and educators to improve the content. For example, based on voting results and comments, creators can identify areas for improvement in their content and incorporate those improvements into future productions. This allows the voting department to continue providing high-quality content to learners.

[0033] The publishing department publishes learning content based on rankings created by the voting department. For example, the publishing department publishes top-ranked learning content in both print and electronic formats. Specifically, it can publish in print or as an e-book. Print publications are often used as textbooks or reference books, allowing learners to keep them on hand for study. E-book publications can be accessed on smartphones, tablets, and e-readers, offering learners the convenience of studying anytime, anywhere. The publishing department can also support the publication of learning content using, for example, generative AI. Generative AI can automatically adjust the layout and design of content, resulting in a clear and easy-to-understand format. This allows creators to focus on the content itself, reducing the burden of publishing. Furthermore, the publishing department can improve published content based on feedback from learners and educators. For example, it can incorporate opinions and requests received after publication into future publications. This allows the publishing department to consistently provide high-quality learning content. The publishing department also manages the sales and distribution of published content, ensuring easy access for learners. For example, learning content could be made available for purchase or download through online stores or learning platforms. This would allow publishers to make it easier for learners to find high-quality learning content and provide creators with opportunities to distribute their content widely.

[0034] The judgment unit can determine the legitimacy and quality of learning content submitted by the generative AI. The judgment unit, for example, uses the generative AI to determine the legitimacy and quality of the submitted learning content. The judgment unit, for example, analyzes the submitted learning content and evaluates the accuracy of the content and its educational effectiveness. For example, if a video explaining a math problem is submitted, the judgment unit will determine whether the explanation is accurate and evaluate whether it has high educational effectiveness. In this way, the legitimacy and quality of learning content can be determined with high accuracy by using the generative AI. The generative AI, for example, uses natural language processing technology to analyze the text of the submitted learning content and evaluate the accuracy of the content. The generative AI, for example, uses machine learning algorithms to evaluate the educational effectiveness of the submitted learning content. The generative AI, for example, analyzes the video of the submitted learning content and evaluates the accuracy of the content. The generative AI, for example, analyzes the audio of the submitted learning content and evaluates the accuracy of the content. The generative AI, for example, analyzes the images of the submitted learning content and evaluates the accuracy of the content. The generative AI comprehensively analyzes the text, video, audio, and images of submitted learning content, for example, to evaluate its accuracy and educational effectiveness. This allows for highly accurate determination of the legitimacy and quality of learning content using the generative AI.

[0035] The voting section can create rankings based on learners' levels and needs. For example, current elementary, middle, and high school students and educators can vote on submitted content. The voting section makes it easier for learners to find the most suitable learning content by voting based on their levels and needs. For example, if beginner-level and advanced-level math problem explanation videos are submitted, beginners will vote for the beginner-level video, and advanced learners will vote for the advanced-level video. This allows for the creation of rankings that are tailored to learners' levels and needs. Some or all of the above processing in the voting section may be performed using AI, for example, or not. For example, the voting section can create rankings using an AI model that takes learners' levels and needs as input and outputs rankings.

[0036] The voting system may include mechanisms to verify voter qualifications. For example, the voting system may include a mechanism to verify voter registration information. For example, the voting system may include a voter authentication process. For example, the voting system may include a login system for verifying voter qualifications. This enables more reliable voting by verifying voter qualifications. Some or all of the above processes in the voting system may be performed using AI, for example, or without AI. For example, the voting system may input voter registration information into AI, and the AI ​​may verify voter qualifications. For example, the voting system may input voter authentication processes into AI, and the AI ​​may verify voter qualifications. For example, the voting system may input voter login information into AI, and the AI ​​may verify voter qualifications. For example, the voting system may use an AI model for verifying voter qualifications to verify voter qualifications.

[0037] The voting unit may include a log management system to ensure voting transparency. The voting unit may include, for example, a system for storing voting logs. The voting unit may include, for example, a system for managing access permissions to voting logs. The voting unit may include, for example, a system for periodically auditing voting logs. This ensures voting transparency and allows for the creation of fair rankings. Some or all of the above processes in the voting unit may be performed using, for example, AI, or not using AI. For example, the voting unit inputs voting logs into an AI, and the AI ​​audits voting transparency. The voting unit may input access permissions to voting logs into an AI, and the AI ​​manages access permissions. The voting unit may, for example, periodically input voting logs into an AI, and the AI ​​audits the logs. The voting unit may ensure voting transparency by using, for example, an AI model for ensuring voting transparency.

[0038] The publishing department can publish top-ranking learning content in print and electronic formats. For example, the publishing department can publish top-ranking learning content in print. For example, the publishing department can publish top-ranking learning content in ebook format. For example, the publishing department can publish top-ranking learning content in PDF format. This allows for the widespread distribution of top-ranking learning content. Some or all of the above processes in the publishing department may be performed using AI, for example, or without AI. For example, the publishing department inputs top-ranking learning content into AI, and the AI ​​assists in publishing in print and electronic formats. For example, the publishing department inputs top-ranking learning content into AI, and the AI ​​assists in publishing in print. For example, the publishing department inputs top-ranking learning content into AI, and the AI ​​assists in publishing in ebook format. For example, the publishing department inputs top-ranking learning content into AI, and the AI ​​assists in publishing in PDF format.

[0039] The production department can select the optimal production method by referring to evaluation data of past learning content. For example, the production department can analyze the production methods of content that received high ratings in the past and apply similar methods to new content. For example, the production department can extract areas for improvement from content that received low ratings and improve the production method. For example, the production department can select a method suitable for a specific learning style based on evaluation data and create personalized content. This allows for the selection of the optimal production method based on past evaluation data. Some or all of the above processes in the production department may be performed using AI, for example, or not using AI. For example, the production department can input past evaluation data into AI, and the AI ​​can select the optimal production method.

[0040] The production department can adjust the difficulty level of the content based on the learner's learning progress. For example, the production department can refer to the learner's past performance data and create content of appropriate difficulty. For example, the production department can evaluate the learner's current level of understanding in real time and provide content of appropriate difficulty. For example, the production department can create content with gradually adjusting difficulty based on the learner's feedback. This allows the production department to provide content of appropriate difficulty according to the learner's progress. Some or all of the above processes in the production department may be performed using AI, or not. For example, the production department inputs the learner's performance data into the AI, and the AI ​​adjusts the difficulty level. For example, the production department inputs the learner's level of understanding into the AI, and the AI ​​adjusts the difficulty level. For example, the production department inputs the learner's feedback into the AI, and the AI ​​adjusts the difficulty level.

[0041] The production department can create content that addresses region-specific learning needs by taking into account the learners' geographical location information. For example, the production department can create content based on the local educational curriculum. For example, the production department can create learning content related to local culture and history. For example, the production department can create learning content that addresses specific local issues. This allows for the provision of content that addresses region-specific learning needs. Some or all of the above processes in the production department may be performed using AI, for example, or not using AI. For example, the production department can input the learners' geographical location information into AI, and the AI ​​can create content that addresses region-specific learning needs.

[0042] The production department can analyze learners' social media activity and create content incorporating relevant topics. For example, the production department can analyze social media topics that learners are interested in and create content based on that. For example, the production department can create content incorporating education-related topics that are trending on social media. For example, the production department can create personalized content based on data obtained from learners' social media activity. This allows for the provision of content on relevant topics based on social media activity. Some or all of the above processes in the production department may be performed using AI, for example, or not using AI. For example, the production department can input learners' social media activity data into AI, and the AI ​​can create content incorporating relevant topics.

[0043] The judgment unit can optimize the judgment algorithm by referring to past judgment data. For example, the judgment unit can improve the accuracy of the judgment algorithm based on past judgment data. For example, the judgment unit can analyze trends in the judgment data and correct biases in the algorithm. For example, the judgment unit can adjust the evaluation criteria for specific learning content based on the judgment data. This allows the judgment algorithm to be optimized based on past judgment data. Some or all of the above processes in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit inputs past judgment data into the AI, and the AI ​​optimizes the judgment algorithm.

[0044] The judgment unit can improve the accuracy of its judgments by taking learner feedback into consideration. For example, the judgment unit adjusts the judgment criteria based on learner feedback. For example, the judgment unit analyzes the feedback data and identifies areas for improvement in the judgment algorithm. For example, the judgment unit reflects learner feedback in real time to improve the accuracy of its judgments. This allows the judgment accuracy to be improved based on learner feedback. Some or all of the above processes in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit inputs learner feedback into the AI, and the AI ​​adjusts the judgment criteria.

[0045] The evaluation unit can determine the priority of evaluation based on the submission timing of the learning content. For example, the evaluation unit prioritizes evaluation of content with an approaching submission deadline. For example, the evaluation unit dynamically adjusts the evaluation priority according to the submission timing. For example, the evaluation unit prioritizes evaluation of content with an early submission date and provides early feedback. This allows evaluation to be performed with priority according to the submission timing. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs the submission timing of the learning content into the AI, and the AI ​​determines the priority.

[0046] The judgment unit can improve the accuracy of its judgment by referring to relevant literature for the learning content. For example, the judgment unit evaluates the validity of the learning content based on the relevant literature. For example, the judgment unit analyzes the data of the relevant literature to improve the accuracy of the judgment algorithm. For example, the judgment unit evaluates the educational effectiveness of the learning content by referring to the relevant literature. This allows the judgment unit to improve the accuracy of its judgment based on the relevant literature. Some or all of the above processes in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit inputs the relevant literature data into the AI, and the AI ​​improves the accuracy of the judgment.

[0047] The voting unit can select the optimal voting method by referring to the learner's past voting history. For example, the voting unit can suggest a voting method suitable for the learner based on past voting history. For example, the voting unit can analyze voting history and identify areas for improvement in voting methods. For example, the voting unit can improve the accuracy of voting by referring to past voting history. This allows the optimal voting method to be selected based on past voting history. Some or all of the above processes in the voting unit may be performed using AI, for example, or without AI. For example, the voting unit can input past voting history into AI, and the AI ​​can select the optimal voting method.

[0048] The voting unit can weight votes based on the learner's learning progress. For example, the voting unit adjusts the weighting of votes based on the learner's progress. For example, the voting unit dynamically changes the weighting of votes according to the learner's level of understanding. For example, the voting unit optimizes the weighting of votes based on the learner's feedback. This allows for weighting of votes according to the learner's progress. Some or all of the above processes in the voting unit may be performed using AI, or not using AI. For example, the voting unit inputs learner progress data into the AI, and the AI ​​adjusts the weighting of votes.

[0049] The voting system can conduct voting that addresses region-specific learning needs by taking into account learners' geographical location information. For example, the voting system can provide voting criteria based on the local educational curriculum. For example, the voting system can promote voting for learning content related to local culture and history. For example, the voting system can prioritize voting for learning content that addresses specific local issues. This allows for voting that addresses region-specific learning needs. Some or all of the above processing in the voting system may be performed using AI, or not. For example, the voting system may input learners' geographical location information into the AI, which then conducts voting that addresses region-specific learning needs.

[0050] The voting unit can analyze learners' social media activity and conduct voting based on relevant topics. For example, the voting unit can analyze social media topics that learners are interested in and facilitate voting based on those topics. For example, the voting unit can facilitate voting on education-related topics that are trending on social media. For example, the voting unit can provide personalized voting criteria based on data obtained from learners' social media activity. This allows voting on relevant topics based on social media activity. Some or all of the above processing in the voting unit may be performed using AI, or not using AI. For example, the voting unit inputs learners' social media activity data into AI, and the AI ​​conducts voting based on relevant topics.

[0051] The publishing department can select the optimal publishing method by referring to past publishing data. For example, the publishing department can analyze the methods of publications that have received high ratings in the past and apply similar methods to new publications. For example, the publishing department can extract areas for improvement from publications that have received low ratings and improve the publishing methods. For example, the publishing department can select methods suitable for a specific readership based on publishing data and provide personalized publications. This allows for the selection of the optimal publishing method based on past publishing data. Some or all of the above processes in the publishing department may be performed using AI, for example, or not using AI. For example, the publishing department can input past publishing data into AI, and the AI ​​can select the optimal publishing method.

[0052] The publishing department can optimize the content of publications by taking learner feedback into consideration. For example, the publishing department can adjust the content of publications based on learner feedback. For example, the publishing department can analyze feedback data to identify areas for improvement in publications. For example, the publishing department can optimize the content of publications by reflecting learner feedback in real time. This allows for the optimization of publication content based on learner feedback. Some or all of the above processes in the publishing department may be performed using AI, for example, or not using AI. For example, the publishing department can input learner feedback into AI, and the AI ​​can optimize the content of publications.

[0053] The publishing department can publish content that addresses region-specific learning needs by taking into account the geographical location of learners. For example, the publishing department can publish content based on the local educational curriculum. For example, the publishing department can publish learning content related to local culture and history. For example, the publishing department can publish learning content that addresses specific local issues. This allows for the provision of content that addresses region-specific learning needs. Some or all of the above processes in the publishing department may be performed using AI, for example, or not using AI. For example, the publishing department can input the geographical location of learners into AI, and the AI ​​can publish content that addresses region-specific learning needs.

[0054] The publishing department can analyze learners' social media activity and publish content incorporating relevant topics. For example, the publishing department can analyze social media topics that learners are interested in and publish content based on that. For example, the publishing department can publish content incorporating education-related topics that are trending on social media. For example, the publishing department can publish personalized content based on data obtained from learners' social media activity. This allows for the provision of content on relevant topics based on social media activity. Some or all of the above processes in the publishing department may be performed using AI, for example, or not using AI. For example, the publishing department can input learners' social media activity data into AI, and the AI ​​can publish content incorporating relevant topics.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The production department can estimate the user's learning style and adjust the format of the learning content based on that estimated style. For example, visual learners can be provided with content that makes extensive use of diagrams and graphs. Auditory learners can be provided with audio commentary or podcast-style content. Furthermore, haptic learners can be provided with content that includes interactive quizzes and experiments. This allows for the creation of optimal learning content tailored to the user's learning style. The estimation of the learning style is performed, for example, based on the user's past learning data and feedback. Some or all of the above processes in the production department may be performed using AI, or not. For example, the production department inputs the user's learning data into AI, and the AI ​​adjusts the format of the content based on the learning style.

[0057] The evaluation unit can assess the diversity of learning content and adjust the balance of content based on the evaluation results. For example, if there is a bias towards a particular subject or theme, it can prioritize the evaluation of content from other subjects or themes. Furthermore, by evaluating content that incorporates different teaching methods and perspectives, it can address diverse learning needs. This ensures diversity in learning content and provides learners with a wide range of choices. The assessment of diversity is based on factors such as the type and format of the content and the level of the target learners. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or not. For example, the evaluation unit inputs content diversity data into the AI, and the AI ​​adjusts the balance based on the evaluation results.

[0058] The evaluation unit can assess the visual elements of learning content and improve the visual quality of the content based on the evaluation results. For example, it can highly evaluate content with a visually appealing design and layout. Furthermore, by evaluating content that includes visually easy-to-understand diagrams and graphs, it can help learners understand the content. This makes it possible to provide learning content with high visual quality. The evaluation of visual elements is based on factors such as the beauty and visibility of the design and the way information is organized. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs visual element data into the AI, and the AI ​​improves the visual quality based on the evaluation results.

[0059] The voting section can suggest content to vote for by referring to the learner's learning history. For example, it can suggest new content similar to content that the learner has previously given a high rating to. Furthermore, it can suggest content related to themes the learner has shown interest in in the past. This allows the system to present content that is highly relevant to the learner as a voting target. The learning history is referenced, for example, based on the learner's past voting data and learning data. Some or all of the above processing in the voting section may be performed using AI, for example, or not using AI. For example, the voting section inputs the learner's learning history data into the AI, and the AI ​​suggests content.

[0060] The evaluation unit can assess the audio quality of learning content and improve the audio quality of the content based on the evaluation results. For example, it can give a high evaluation to content with clear and easy-to-understand audio. Furthermore, by evaluating content with appropriate tone and pace, it can help learners understand the content. This makes it possible to provide learning content with high audio quality. The evaluation of audio quality is based on factors such as clarity of speech, low noise, and accuracy of the speaker's pronunciation. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs audio quality data into the AI, and the AI ​​improves the audio quality based on the evaluation results.

[0061] The production department can estimate learners' learning objectives and design a curriculum for learning content based on those estimated objectives. For example, if a learner is aiming to take university entrance exams, a curriculum specifically tailored for exam preparation can be provided. If a learner is aiming to obtain a specific qualification, a curriculum related to that qualification can be provided. Furthermore, if a learner wishes to learn to deepen their hobbies or interests, a curriculum based on that theme can be provided. This allows for the provision of an optimal curriculum tailored to the learner's learning objectives. The estimation of learning objectives is performed, for example, based on the learner's past learning data and feedback. Some or all of the above processes in the production department may be performed using AI, for example, or not using AI. For example, the production department inputs the learner's learning objective data into AI, and the AI ​​designs a curriculum based on the learning objectives.

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

[0063] Step 1: The production department creates learning content. The production department can, for example, create original learning content for educational video creators, educators, and cram school instructors. The production department can create learning content in video format, text format, etc. The production department can also support the creation of learning content using, for example, generative AI. Step 2: The evaluation unit determines the legitimacy and quality of the learning content produced by the production unit. The evaluation unit uses, for example, generative AI to determine the legitimacy and quality of the submitted learning content. The evaluation unit analyzes the submitted learning content and evaluates the accuracy of the content and its educational effectiveness. For example, if a video explaining a math problem is submitted, the evaluation unit determines whether the explanation is accurate and evaluates whether it has high educational effectiveness. Step 3: The voting team votes on the learning content judged by the evaluation team and creates a ranking. The voting team consists of, for example, current elementary, middle, and high school students and educators who vote on the submitted content. The voting team votes based on, for example, the learner's level and needs, making it easier for each individual to find the most suitable learning content. For example, if a beginner-level math problem explanation video and an advanced-level math problem explanation video are submitted, the voting team will vote for the beginner-level video and the advanced-level video. Step 4: The publishing department publishes learning content based on the rankings created by the voting department. For example, the publishing department publishes top-ranked learning content in print and electronic formats. The publishing department can publish in print or as an ebook. The publishing department can also use generative AI to support the publication of learning content.

[0064] (Example of form 2) The learning content platform according to an embodiment of the present invention is a system that solicits learning content for elementary, junior high, and high school students in a competition format. In this system, educational video creators, educators, and cram school instructors create their own learning content, and a generating AI judges the validity and quality of that content. Next, current elementary, junior high, and high school students and educators vote to create a ranking. Top-ranked content can be published in print and electronic media. This allows for the spontaneous creation of high-quality learning content, making it easier for learners to find content that suits them. For example, if a video explaining a math problem is submitted, the generating AI judges whether the explanation is accurate and evaluates its educational effectiveness. Next, current elementary, junior high, and high school students and educators vote on the submitted content to create a ranking. Voting is based on the learner's level and needs, making it easier for each individual to find the most suitable learning content. For example, if a video explaining a math problem for beginners and a video explaining a math problem for advanced learners are submitted, beginners will vote for the beginner-level video, and advanced learners will vote for the advanced-level video. Furthermore, top-ranked content can be published in print and electronic media. This will lead to the widespread dissemination and provision of high-quality learning content to learners. This system makes it easier for learners to find high-quality learning content, and gives creators the opportunity to distribute their content widely. Furthermore, since the validity and quality of submitted content are guaranteed by the generation AI, highly reliable learning content will be provided. This is expected to improve Japan's educational standards and national strength. In this way, the learning content platform can make it easier for learners to find high-quality learning content and provide creators with the opportunity to distribute their content widely.

[0065] The learning content platform according to this embodiment comprises a production unit, an evaluation unit, a voting unit, and a publishing unit. The production unit produces learning content. For example, the production unit can be used by educational video creators, educators, and cram school instructors to produce their own learning content. The production unit can produce learning content in video format or text format. The production unit can also use, for example, generative AI to support the production of learning content. The evaluation unit determines the legitimacy and quality of the learning content produced by the production unit. For example, the evaluation unit uses, for example, generative AI to determine the legitimacy and quality of submitted learning content. For example, the evaluation unit analyzes submitted learning content and evaluates the accuracy of the content and its educational effectiveness. For example, if a video explaining a math problem is submitted, the evaluation unit determines whether the explanation is accurate and evaluates whether it has high educational effectiveness. The voting unit casts votes for the learning content judged by the evaluation unit and creates rankings. For example, current elementary, junior high, and high school students and educators cast votes for the submitted content. The voting section allows learners to vote based on their level and needs, making it easier for them to find the most suitable learning content. For example, if beginner-level and advanced-level math problem explanation videos are submitted, beginners will vote for the beginner-level video, and advanced learners will vote for the advanced-level video. The publishing section publishes learning content based on the rankings created by the voting section. The publishing section publishes top-ranked learning content in print and electronic formats. For example, the publishing section can publish in print or as an e-book. The publishing section can also support the publication of learning content using, for example, generative AI. As a result, the learning content platform according to this embodiment can make it easier for learners to find high-quality learning content and provide creators with opportunities to widely distribute their content.

[0066] The production department creates learning content. For example, the production department allows educational video creators, educators, and cram school instructors to create their own learning content. Specifically, educational video creators can create videos based on their areas of expertise, providing clear explanations to viewers. Educators and cram school instructors can create video and text-based learning content based on teaching materials and supplementary resources used in their classes. The production department can create video and text-based learning content, for example. Video content is easier for learners to understand because it contains a lot of visual information. Text-based content can include detailed explanations and examples, allowing learners to progress at their own pace. The production department can also support the creation of learning content using, for example, generative AI. Generative AI can automatically generate detailed explanations and examples based on basic information provided by educators. This reduces the burden of content creation for educators, allowing them to dedicate more time to other educational activities. Furthermore, generative AI can provide customized content according to the learner's level of understanding and progress. For example, if a learner is struggling with a particular topic, the generative AI can provide additional explanations and practice exercises related to that topic. This allows the production department to efficiently create high-quality learning content that meets the learner's needs.

[0067] The evaluation unit determines the legitimacy and quality of learning content produced by the production unit. For example, the evaluation unit uses generative AI to determine the legitimacy and quality of submitted learning content. Specifically, the generative AI analyzes the submitted content and evaluates its accuracy and educational effectiveness. For example, if a video explaining a math problem is submitted, the evaluation unit determines whether the explanation is accurate and evaluates its educational effectiveness. The generative AI checks the accuracy of the explanation based on mathematical formulas and theorems, and verifies that there are no errors. Furthermore, to evaluate educational effectiveness, it can analyze learners' understanding and reactions to measure the effectiveness of the content. In addition, the evaluation unit can utilize past data and statistical information to evaluate the quality of the content. For example, it can analyze the characteristics of content that has received high ratings in the past and compare them with newly submitted content to set quality standards. This allows the evaluation unit to determine the legitimacy and quality of learning content with high accuracy and provide learners with reliable content. Furthermore, the evaluation unit can set evaluation criteria according to different educational fields and levels, and perform evaluations appropriate to each field and level. For example, since the evaluation criteria differ between beginner-level and advanced-level content, applying appropriate evaluations to each allows us to provide learners with the most suitable content. This enables the evaluation unit to accurately determine the legitimacy and quality of the learning content, providing learners with highly reliable content.

[0068] The voting department votes on learning content judged by the evaluation department and creates rankings. For example, current elementary, middle, and high school students and educators vote on submitted content. Specifically, learners and educators evaluate and vote based on factors such as content, clarity, and educational effectiveness. The voting department makes it easier for learners to find the most suitable learning content by voting based on their level and needs. For example, if beginner-level and advanced-level math problem explanation videos are submitted, beginners would vote for the beginner-level video, and advanced learners would vote for the advanced-level video. This makes it easier for learners to find content that matches their level. Furthermore, the voting department can create rankings based on the voting results, providing learners with popular content. Rankings can be created, for example, by category or level, making it easy for learners to find content that suits them. The voting department can update voting results in real time, providing the latest information. This ensures learners always have access to the most popular content. The voting department can also collect feedback from learners and educators to improve the content. For example, based on voting results and comments, creators can identify areas for improvement in their content and incorporate those improvements into future productions. This allows the voting department to continue providing high-quality content to learners.

[0069] The publishing department publishes learning content based on rankings created by the voting department. For example, the publishing department publishes top-ranked learning content in both print and electronic formats. Specifically, it can publish in print or as an e-book. Print publications are often used as textbooks or reference books, allowing learners to keep them on hand for study. E-book publications can be accessed on smartphones, tablets, and e-readers, offering learners the convenience of studying anytime, anywhere. The publishing department can also support the publication of learning content using, for example, generative AI. Generative AI can automatically adjust the layout and design of content, resulting in a clear and easy-to-understand format. This allows creators to focus on the content itself, reducing the burden of publishing. Furthermore, the publishing department can improve published content based on feedback from learners and educators. For example, it can incorporate opinions and requests received after publication into future publications. This allows the publishing department to consistently provide high-quality learning content. The publishing department also manages the sales and distribution of published content, ensuring easy access for learners. For example, learning content could be made available for purchase or download through online stores or learning platforms. This would allow publishers to make it easier for learners to find high-quality learning content and provide creators with opportunities to distribute their content widely.

[0070] The judgment unit can determine the legitimacy and quality of learning content submitted by the generative AI. The judgment unit, for example, uses the generative AI to determine the legitimacy and quality of the submitted learning content. The judgment unit, for example, analyzes the submitted learning content and evaluates the accuracy of the content and its educational effectiveness. For example, if a video explaining a math problem is submitted, the judgment unit will determine whether the explanation is accurate and evaluate whether it has high educational effectiveness. In this way, the legitimacy and quality of learning content can be determined with high accuracy by using the generative AI. The generative AI, for example, uses natural language processing technology to analyze the text of the submitted learning content and evaluate the accuracy of the content. The generative AI, for example, uses machine learning algorithms to evaluate the educational effectiveness of the submitted learning content. The generative AI, for example, analyzes the video of the submitted learning content and evaluates the accuracy of the content. The generative AI, for example, analyzes the audio of the submitted learning content and evaluates the accuracy of the content. The generative AI, for example, analyzes the images of the submitted learning content and evaluates the accuracy of the content. The generative AI comprehensively analyzes the text, video, audio, and images of submitted learning content, for example, to evaluate its accuracy and educational effectiveness. This allows for highly accurate determination of the legitimacy and quality of learning content using the generative AI.

[0071] The voting section can create rankings based on learners' levels and needs. For example, current elementary, middle, and high school students and educators can vote on submitted content. The voting section makes it easier for learners to find the most suitable learning content by voting based on their levels and needs. For example, if beginner-level and advanced-level math problem explanation videos are submitted, beginners will vote for the beginner-level video, and advanced learners will vote for the advanced-level video. This allows for the creation of rankings that are tailored to learners' levels and needs. Some or all of the above processing in the voting section may be performed using AI, for example, or not. For example, the voting section can create rankings using an AI model that takes learners' levels and needs as input and outputs rankings.

[0072] The voting system may include mechanisms to verify voter qualifications. For example, the voting system may include a mechanism to verify voter registration information. For example, the voting system may include a voter authentication process. For example, the voting system may include a login system for verifying voter qualifications. This enables more reliable voting by verifying voter qualifications. Some or all of the above processes in the voting system may be performed using AI, for example, or without AI. For example, the voting system may input voter registration information into AI, and the AI ​​may verify voter qualifications. For example, the voting system may input voter authentication processes into AI, and the AI ​​may verify voter qualifications. For example, the voting system may input voter login information into AI, and the AI ​​may verify voter qualifications. For example, the voting system may use an AI model for verifying voter qualifications to verify voter qualifications.

[0073] The voting unit may include a log management system to ensure voting transparency. The voting unit may include, for example, a system for storing voting logs. The voting unit may include, for example, a system for managing access permissions to voting logs. The voting unit may include, for example, a system for periodically auditing voting logs. This ensures voting transparency and allows for the creation of fair rankings. Some or all of the above processes in the voting unit may be performed using, for example, AI, or not using AI. For example, the voting unit inputs voting logs into an AI, and the AI ​​audits voting transparency. The voting unit may input access permissions to voting logs into an AI, and the AI ​​manages access permissions. The voting unit may, for example, periodically input voting logs into an AI, and the AI ​​audits the logs. The voting unit may ensure voting transparency by using, for example, an AI model for ensuring voting transparency.

[0074] The publishing department can publish top-ranking learning content in print and electronic formats. For example, the publishing department can publish top-ranking learning content in print. For example, the publishing department can publish top-ranking learning content in ebook format. For example, the publishing department can publish top-ranking learning content in PDF format. This allows for the widespread distribution of top-ranking learning content. Some or all of the above processes in the publishing department may be performed using AI, for example, or without AI. For example, the publishing department inputs top-ranking learning content into AI, and the AI ​​assists in publishing in print and electronic formats. For example, the publishing department inputs top-ranking learning content into AI, and the AI ​​assists in publishing in print. For example, the publishing department inputs top-ranking learning content into AI, and the AI ​​assists in publishing in ebook format. For example, the publishing department inputs top-ranking learning content into AI, and the AI ​​assists in publishing in PDF format.

[0075] The production department can estimate the user's emotions and adjust the method of creating learning content based on the estimated user emotions. For example, if the user is stressed, the production department can create learning content that incorporates relaxing music and colors. For example, if the user is excited, the production department can create learning content with a simple and visually calming design to enhance concentration. For example, if the user is tired, the production department can create concise content that allows for learning in a short amount of time. This allows for the creation of optimal learning content tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the production department may be performed using AI or not. For example, the production department inputs user emotion data into the AI, and the AI ​​adjusts the method of creating learning content based on the emotions.

[0076] The production department can select the optimal production method by referring to evaluation data of past learning content. For example, the production department can analyze the production methods of content that received high ratings in the past and apply similar methods to new content. For example, the production department can extract areas for improvement from content that received low ratings and improve the production method. For example, the production department can select a method suitable for a specific learning style based on evaluation data and create personalized content. This allows for the selection of the optimal production method based on past evaluation data. Some or all of the above processes in the production department may be performed using AI, for example, or not using AI. For example, the production department can input past evaluation data into AI, and the AI ​​can select the optimal production method.

[0077] The production department can adjust the difficulty level of the content based on the learner's learning progress. For example, the production department can refer to the learner's past performance data and create content of appropriate difficulty. For example, the production department can evaluate the learner's current level of understanding in real time and provide content of appropriate difficulty. For example, the production department can create content with gradually adjusting difficulty based on the learner's feedback. This allows the production department to provide content of appropriate difficulty according to the learner's progress. Some or all of the above processes in the production department may be performed using AI, or not. For example, the production department inputs the learner's performance data into the AI, and the AI ​​adjusts the difficulty level. For example, the production department inputs the learner's level of understanding into the AI, and the AI ​​adjusts the difficulty level. For example, the production department inputs the learner's feedback into the AI, and the AI ​​adjusts the difficulty level.

[0078] The production department can estimate the user's emotions and determine the theme of the content to be produced based on those estimated emotions. For example, the production department can estimate themes that the user is interested in and produce learning content based on those themes. For example, if the user is feeling stressed, the production department can produce content on a relaxing theme. For example, if the user is lacking concentration, the production department can produce content on a theme that enhances concentration. This allows for the production of content with themes that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the production department may be performed using AI or not using AI. For example, the production department inputs user emotion data into AI, and the AI ​​determines the theme of the content based on the emotions.

[0079] The production department can create content that addresses region-specific learning needs by taking into account the learners' geographical location information. For example, the production department can create content based on the local educational curriculum. For example, the production department can create learning content related to local culture and history. For example, the production department can create learning content that addresses specific local issues. This allows for the provision of content that addresses region-specific learning needs. Some or all of the above processes in the production department may be performed using AI, for example, or not using AI. For example, the production department can input the learners' geographical location information into AI, and the AI ​​can create content that addresses region-specific learning needs.

[0080] The production department can analyze learners' social media activity and create content incorporating relevant topics. For example, the production department can analyze social media topics that learners are interested in and create content based on that. For example, the production department can create content incorporating education-related topics that are trending on social media. For example, the production department can create personalized content based on data obtained from learners' social media activity. This allows for the provision of content on relevant topics based on social media activity. Some or all of the above processes in the production department may be performed using AI, for example, or not using AI. For example, the production department can input learners' social media activity data into AI, and the AI ​​can create content incorporating relevant topics.

[0081] The judgment unit can estimate the user's emotions and adjust the criteria for content legitimacy and quality based on the estimated user emotions. For example, if the user is relaxed, the judgment unit applies strict criteria. For example, if the user is stressed, the judgment unit applies flexible criteria. For example, if the user is excited, the judgment unit increases the evaluation of content containing visually stimulating elements. This allows for the application of criteria that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using AI or not using AI. For example, the judgment unit inputs user emotion data into the AI, and the AI ​​adjusts the criteria based on the emotions.

[0082] The judgment unit can optimize the judgment algorithm by referring to past judgment data. For example, the judgment unit can improve the accuracy of the judgment algorithm based on past judgment data. For example, the judgment unit can analyze trends in the judgment data and correct biases in the algorithm. For example, the judgment unit can adjust the evaluation criteria for specific learning content based on the judgment data. This allows the judgment algorithm to be optimized based on past judgment data. Some or all of the above processes in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit inputs past judgment data into the AI, and the AI ​​optimizes the judgment algorithm.

[0083] The judgment unit can improve the accuracy of its judgments by taking learner feedback into consideration. For example, the judgment unit adjusts the judgment criteria based on learner feedback. For example, the judgment unit analyzes the feedback data and identifies areas for improvement in the judgment algorithm. For example, the judgment unit reflects learner feedback in real time to improve the accuracy of its judgments. This allows the judgment accuracy to be improved based on learner feedback. Some or all of the above processes in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit inputs learner feedback into the AI, and the AI ​​adjusts the judgment criteria.

[0084] The judgment unit can estimate the user's emotions and adjust the display method of the judgment result based on the estimated user emotions. For example, if the user is nervous, the judgment unit provides a simple and highly visible display method. For example, if the user is relaxed, the judgment unit provides a display method that includes detailed information. For example, if the user is in a hurry, the judgment unit provides a display method that gets straight to the point. This allows the system to provide a display method that is appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit inputs the user's emotion data into the AI, and the AI ​​adjusts the display method based on the emotion.

[0085] The evaluation unit can determine the priority of evaluation based on the submission timing of the learning content. For example, the evaluation unit prioritizes evaluation of content with an approaching submission deadline. For example, the evaluation unit dynamically adjusts the evaluation priority according to the submission timing. For example, the evaluation unit prioritizes evaluation of content with an early submission date and provides early feedback. This allows evaluation to be performed with priority according to the submission timing. Some or all of the above processes in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs the submission timing of the learning content into the AI, and the AI ​​determines the priority.

[0086] The judgment unit can improve the accuracy of its judgment by referring to relevant literature for the learning content. For example, the judgment unit evaluates the validity of the learning content based on the relevant literature. For example, the judgment unit analyzes the data of the relevant literature to improve the accuracy of the judgment algorithm. For example, the judgment unit evaluates the educational effectiveness of the learning content by referring to the relevant literature. This allows the judgment unit to improve the accuracy of its judgment based on the relevant literature. Some or all of the above processes in the judgment unit may be performed using AI, for example, or without AI. For example, the judgment unit inputs the relevant literature data into the AI, and the AI ​​improves the accuracy of the judgment.

[0087] The voting unit can estimate the user's emotions and adjust the voting criteria based on the estimated emotions. For example, if the user is relaxed, the voting unit provides detailed evaluation criteria. For example, if the user is stressed, the voting unit provides concise evaluation criteria. For example, if the user is excited, the voting unit provides evaluation criteria that include visually stimulating elements. This allows for the provision of voting criteria that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voting unit may be performed using AI or not using AI. For example, the voting unit inputs user emotion data into the AI, and the AI ​​adjusts the voting criteria based on the emotions.

[0088] The voting unit can select the optimal voting method by referring to the learner's past voting history. For example, the voting unit can suggest a voting method suitable for the learner based on past voting history. For example, the voting unit can analyze voting history and identify areas for improvement in voting methods. For example, the voting unit can improve the accuracy of voting by referring to past voting history. This allows the optimal voting method to be selected based on past voting history. Some or all of the above processes in the voting unit may be performed using AI, for example, or without AI. For example, the voting unit can input past voting history into AI, and the AI ​​can select the optimal voting method.

[0089] The voting unit can weight votes based on the learner's learning progress. For example, the voting unit adjusts the weighting of votes based on the learner's progress. For example, the voting unit dynamically changes the weighting of votes according to the learner's level of understanding. For example, the voting unit optimizes the weighting of votes based on the learner's feedback. This allows for weighting of votes according to the learner's progress. Some or all of the above processes in the voting unit may be performed using AI, or not using AI. For example, the voting unit inputs learner progress data into the AI, and the AI ​​adjusts the weighting of votes.

[0090] The voting unit can estimate the user's emotions and adjust the display method of the voting results based on the estimated user emotions. For example, if the user is nervous, the voting unit provides a simple and highly visible display method. For example, if the user is relaxed, the voting unit provides a display method that includes detailed information. For example, if the user is in a hurry, the voting unit provides a display method that gets straight to the point. This allows for a display method of voting results that is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voting unit may be performed using AI or not using AI. For example, the voting unit inputs user emotion data into the AI, and the AI ​​adjusts the display method based on the emotions.

[0091] The voting system can conduct voting that addresses region-specific learning needs by taking into account learners' geographical location information. For example, the voting system can provide voting criteria based on the local educational curriculum. For example, the voting system can promote voting for learning content related to local culture and history. For example, the voting system can prioritize voting for learning content that addresses specific local issues. This allows for voting that addresses region-specific learning needs. Some or all of the above processing in the voting system may be performed using AI, or not. For example, the voting system may input learners' geographical location information into the AI, which then conducts voting that addresses region-specific learning needs.

[0092] The voting unit can analyze learners' social media activity and conduct voting based on relevant topics. For example, the voting unit can analyze social media topics that learners are interested in and facilitate voting based on those topics. For example, the voting unit can facilitate voting on education-related topics that are trending on social media. For example, the voting unit can provide personalized voting criteria based on data obtained from learners' social media activity. This allows voting on relevant topics based on social media activity. Some or all of the above processing in the voting unit may be performed using AI, or not using AI. For example, the voting unit inputs learners' social media activity data into AI, and the AI ​​conducts voting based on relevant topics.

[0093] The publishing department can estimate the user's emotions and adjust the publishing method based on the estimated emotions. For example, if the user is relaxed, the publishing department may provide a publication containing detailed information. If the user is stressed, the publishing department may provide a concise and visually appealing publication. If the user is excited, the publishing department may provide a publication containing visually stimulating elements. This allows for publishing methods tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the publishing department may be performed using AI or not. For example, the publishing department inputs user emotion data into an AI, and the AI ​​adjusts the publishing method based on the emotions.

[0094] The publishing department can select the optimal publishing method by referring to past publishing data. For example, the publishing department can analyze the methods of publications that have received high ratings in the past and apply similar methods to new publications. For example, the publishing department can extract areas for improvement from publications that have received low ratings and improve the publishing methods. For example, the publishing department can select methods suitable for a specific readership based on publishing data and provide personalized publications. This allows for the selection of the optimal publishing method based on past publishing data. Some or all of the above processes in the publishing department may be performed using AI, for example, or not using AI. For example, the publishing department can input past publishing data into AI, and the AI ​​can select the optimal publishing method.

[0095] The publishing department can optimize the content of publications by taking learner feedback into consideration. For example, the publishing department can adjust the content of publications based on learner feedback. For example, the publishing department can analyze feedback data to identify areas for improvement in publications. For example, the publishing department can optimize the content of publications by reflecting learner feedback in real time. This allows for the optimization of publication content based on learner feedback. Some or all of the above processes in the publishing department may be performed using AI, for example, or not using AI. For example, the publishing department can input learner feedback into AI, and the AI ​​can optimize the content of publications.

[0096] The publishing department can estimate the user's emotions and prioritize the content to publish based on those emotions. For example, if the user is relaxed, the publishing department will prioritize content containing detailed information. If the user is stressed, the publishing department will prioritize concise and visually appealing content. If the user is excited, the publishing department will prioritize content containing visually stimulating elements. This allows for the prioritization of content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the publishing department may be performed using AI or not. For example, the publishing department inputs user emotion data into an AI, and the AI ​​determines the content priority based on the emotions.

[0097] The publishing department can publish content that addresses region-specific learning needs by taking into account the geographical location of learners. For example, the publishing department can publish content based on the local educational curriculum. For example, the publishing department can publish learning content related to local culture and history. For example, the publishing department can publish learning content that addresses specific local issues. This allows for the provision of content that addresses region-specific learning needs. Some or all of the above processes in the publishing department may be performed using AI, for example, or not using AI. For example, the publishing department can input the geographical location of learners into AI, and the AI ​​can publish content that addresses region-specific learning needs.

[0098] The publishing department can analyze learners' social media activity and publish content incorporating relevant topics. For example, the publishing department can analyze social media topics that learners are interested in and publish content based on that. For example, the publishing department can publish content incorporating education-related topics that are trending on social media. For example, the publishing department can publish personalized content based on data obtained from learners' social media activity. This allows for the provision of content on relevant topics based on social media activity. Some or all of the above processes in the publishing department may be performed using AI, for example, or not using AI. For example, the publishing department can input learners' social media activity data into AI, and the AI ​​can publish content incorporating relevant topics.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The production department can estimate the user's learning style and adjust the format of the learning content based on that estimated style. For example, visual learners can be provided with content that makes extensive use of diagrams and graphs. Auditory learners can be provided with audio commentary or podcast-style content. Furthermore, haptic learners can be provided with content that includes interactive quizzes and experiments. This allows for the creation of optimal learning content tailored to the user's learning style. The estimation of the learning style is performed, for example, based on the user's past learning data and feedback. Some or all of the above processes in the production department may be performed using AI, or not. For example, the production department inputs the user's learning data into AI, and the AI ​​adjusts the format of the content based on the learning style.

[0101] The evaluation unit can assess the diversity of learning content and adjust the balance of content based on the evaluation results. For example, if there is a bias towards a particular subject or theme, it can prioritize the evaluation of content from other subjects or themes. Furthermore, by evaluating content that incorporates different teaching methods and perspectives, it can address diverse learning needs. This ensures diversity in learning content and provides learners with a wide range of choices. The assessment of diversity is based on factors such as the type and format of the content and the level of the target learners. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or not. For example, the evaluation unit inputs content diversity data into the AI, and the AI ​​adjusts the balance based on the evaluation results.

[0102] The voting unit can estimate the user's emotions and adjust the timing of voting based on those emotions. For example, if the user is relaxed, it can send a notification prompting them to vote. If the user is stressed, it can delay voting. Furthermore, if the user is focused, it can refrain from sending notifications prompting them to vote. This allows the system to prompt voting at the optimal time according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the voting unit may be performed using AI, or not using AI. For example, the voting unit inputs user emotion data into the AI, and the AI ​​adjusts the timing of voting based on the emotions.

[0103] The production department can estimate learners' interests and select learning content themes based on those estimated interests. For example, if a learner is interested in science, content on science-related themes can be produced. If a learner is interested in history, content on history-related themes can be produced. Furthermore, if a learner shows interest in a particular topic, content related to that topic can be produced. This allows for the provision of optimal learning content tailored to the learner's interests. The estimation of interests is performed, for example, based on the learner's past learning data and feedback. Some or all of the above processes in the production department may be performed using AI, for example, or not. For example, the production department inputs learner interest data into AI, and the AI ​​selects themes based on those interests.

[0104] The evaluation unit can assess the visual elements of learning content and improve the visual quality of the content based on the evaluation results. For example, it can highly evaluate content with a visually appealing design and layout. Furthermore, by evaluating content that includes visually easy-to-understand diagrams and graphs, it can help learners understand the content. This makes it possible to provide learning content with high visual quality. The evaluation of visual elements is based on factors such as the beauty and visibility of the design and the way information is organized. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs visual element data into the AI, and the AI ​​improves the visual quality based on the evaluation results.

[0105] The voting section can suggest content to vote for by referring to the learner's learning history. For example, it can suggest new content similar to content that the learner has previously given a high rating to. Furthermore, it can suggest content related to themes the learner has shown interest in in the past. This allows the system to present content that is highly relevant to the learner as a voting target. The learning history is referenced, for example, based on the learner's past voting data and learning data. Some or all of the above processing in the voting section may be performed using AI, for example, or not using AI. For example, the voting section inputs the learner's learning history data into the AI, and the AI ​​suggests content.

[0106] The production department can estimate the user's emotions and adjust the interactivity of the learning content based on those emotions. For example, if the user is relaxed, they can be provided with content containing many interactive elements. If the user is stressed, they can be provided with simple, less interactive content. Furthermore, if the user is focused, they can be provided with content that has an appropriate level of interactivity. This allows for the creation of learning content with optimal interactivity tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above-described processes in the production department may be performed using AI, or not. For example, the production department inputs user emotion data into the AI, and the AI ​​adjusts the interactivity based on the emotions.

[0107] The evaluation unit can assess the audio quality of learning content and improve the audio quality of the content based on the evaluation results. For example, it can give a high evaluation to content with clear and easy-to-understand audio. Furthermore, by evaluating content with appropriate tone and pace, it can help learners understand the content. This makes it possible to provide learning content with high audio quality. The evaluation of audio quality is based on factors such as clarity of speech, low noise, and accuracy of the speaker's pronunciation. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit inputs audio quality data into the AI, and the AI ​​improves the audio quality based on the evaluation results.

[0108] The voting unit can estimate the user's emotions and adjust the feedback method based on the estimated emotions. For example, if the user is relaxed, detailed feedback can be provided. If the user is stressed, concise and positive feedback can be provided. Furthermore, if the user is focused, feedback including specific areas for improvement can be provided. This allows for the provision of optimal feedback tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the voting unit may be performed using AI, or not using AI. For example, the voting unit inputs user emotion data into the AI, and the AI ​​adjusts the feedback method based on the emotions.

[0109] The production department can estimate learners' learning objectives and design a curriculum for learning content based on those estimated objectives. For example, if a learner is aiming to take university entrance exams, a curriculum specifically tailored for exam preparation can be provided. If a learner is aiming to obtain a specific qualification, a curriculum related to that qualification can be provided. Furthermore, if a learner wishes to learn to deepen their hobbies or interests, a curriculum based on that theme can be provided. This allows for the provision of an optimal curriculum tailored to the learner's learning objectives. The estimation of learning objectives is performed, for example, based on the learner's past learning data and feedback. Some or all of the above processes in the production department may be performed using AI, for example, or not using AI. For example, the production department inputs the learner's learning objective data into AI, and the AI ​​designs a curriculum based on the learning objectives.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The production department creates learning content. The production department can, for example, create original learning content for educational video creators, educators, and cram school instructors. The production department can create learning content in video format, text format, etc. The production department can also support the creation of learning content using, for example, generative AI. Step 2: The evaluation unit determines the legitimacy and quality of the learning content produced by the production unit. The evaluation unit uses, for example, generative AI to determine the legitimacy and quality of the submitted learning content. The evaluation unit analyzes the submitted learning content and evaluates the accuracy of the content and its educational effectiveness. For example, if a video explaining a math problem is submitted, the evaluation unit determines whether the explanation is accurate and evaluates whether it has high educational effectiveness. Step 3: The voting team votes on the learning content judged by the evaluation team and creates a ranking. The voting team consists of, for example, current elementary, middle, and high school students and educators who vote on the submitted content. The voting team votes based on, for example, the learner's level and needs, making it easier for each individual to find the most suitable learning content. For example, if a beginner-level math problem explanation video and an advanced-level math problem explanation video are submitted, the voting team will vote for the beginner-level video and the advanced-level video. Step 4: The publishing department publishes learning content based on the rankings created by the voting department. For example, the publishing department publishes top-ranked learning content in print and electronic formats. The publishing department can publish in print or as an ebook. The publishing department can also use generative AI to support the publication of learning content.

[0112] 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.

[0113] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0114] 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.

[0115] Each of the multiple elements described above, including the production unit, judgment unit, voting unit, and publishing unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the production unit is implemented by the control unit 46A of the smart device 14, allowing educational video streamers, educators, and cram school instructors to create their own learning content. The judgment unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which uses a generating AI to determine the legitimacy and quality of the submitted learning content. The voting unit is implemented by, for example, the control unit 46A of the smart device 14, allowing current elementary, junior high, and high school students and educators to vote on the submitted content. The publishing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which publishes the top-ranked learning content in paper or electronic media. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.).

[0128] 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.

[0129] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0130] 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.

[0131] Each of the multiple elements described above, including the production unit, judgment unit, voting unit, and publishing unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the production unit is implemented by the control unit 46A of the smart glasses 214, allowing educational video streamers, educators, and cram school instructors to create their own learning content. The judgment unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which uses a generating AI to determine the legitimacy and quality of the submitted learning content. The voting unit is implemented by, for example, the control unit 46A of the smart glasses 214, allowing current elementary, junior high, and high school students and educators to vote on the submitted content. The publishing unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which publishes the top-ranked learning content in paper or electronic media. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.).

[0144] 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.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] 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.

[0147] Each of the multiple elements described above, including the production department, judgment department, voting department, and publishing department, is implemented by, for example, at least one of the headset terminal 314 and the data processing device 12. For example, the production department is implemented by the control unit 46A of the headset terminal 314, allowing educational video streamers, educators, and cram school instructors to create their own learning content. The judgment department is implemented by, for example, the specific processing unit 290 of the data processing device 12, which uses a generating AI to determine the legitimacy and quality of the submitted learning content. The voting department is implemented by, for example, the control unit 46A of the headset terminal 314, allowing current elementary, junior high, and high school students and educators to vote on the submitted content. The publishing department is implemented by, for example, the specific processing unit 290 of the data processing device 12, which publishes the top-ranked learning content in paper or electronic media. The correspondence between each department and the devices and control units is not limited to the examples described above, and various changes are possible.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.).

[0161] 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.

[0162] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] 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.

[0164] Each of the multiple elements described above, including the production department, judgment department, voting department, and publishing department, is implemented by, for example, at least one of the robot 414 and the data processing device 12. For example, the production department is implemented by the control unit 46A of the robot 414, allowing educational video streamers, educators, and cram school instructors to create their own learning content. The judgment department is implemented by, for example, the specific processing unit 290 of the data processing device 12, which uses a generating AI to determine the legitimacy and quality of the submitted learning content. The voting department is implemented by, for example, the control unit 46A of the robot 414, allowing current elementary, junior high, and high school students and educators to vote on the submitted content. The publishing department is implemented by, for example, the specific processing unit 290 of the data processing device 12, which publishes the top-ranked learning content in paper or electronic media. The correspondence between each department and the devices and control units is not limited to the examples described above, and various changes are possible.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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."

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] (Note 1) The production department creates learning content, A determination unit that determines the legitimacy and quality of learning content produced by the aforementioned production department, A voting unit performs voting on the learning content determined by the aforementioned determination unit and creates a ranking, A publishing department that publishes learning content based on the rankings created by the aforementioned voting department. A system characterized by the following features. (Note 2) The determination unit, The AI ​​generates the learning content to determine its legitimacy and quality. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned voting section, Vote based on learner level and needs to create a ranking. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned voting section, The system includes a mechanism to verify voter eligibility. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned voting section, Equipped with a log management system to ensure transparency in voting. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned publishing department, Publish top-ranked learning content in print and digital formats. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned production department, We estimate user emotions and adjust the creation method of learning content based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned production department, We select the optimal production method by referring to evaluation data of past learning content. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned production department, The difficulty level of the content is adjusted based on the learner's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned production department, We estimate the user's emotions and determine the theme of the content to be created based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned production department, We create content that addresses region-specific learning needs, taking into account the learners' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned production department, Analyze learners' social media activity and create content that incorporates relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 13) The determination unit, We estimate user sentiment and adjust the criteria for content legitimacy and quality based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The determination unit, Optimize the judgment algorithm by referring to past judgment data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The determination unit, We improve the accuracy of the assessment by taking learner feedback into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 16) The determination unit, The system estimates the user's emotions and adjusts how the judgment results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The determination unit, Prioritizing evaluations based on the submission timing of learning content. The system described in Appendix 1, characterized by the features described herein. (Note 18) The determination unit, Improve the accuracy of your assessment by referring to related literature in the learning content. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned voting section, We estimate user sentiment and adjust voting criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned voting section, The optimal voting method is selected by referring to the learner's past voting history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned voting section, The voting weights are determined based on the learners' progress. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned voting section, The system estimates user sentiment and adjusts how voting results are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned voting section, The voting process takes into account the learners' geographical location to address region-specific learning needs. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned voting section, Analyze learners' social media activity and conduct polls based on relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned publishing department, We estimate user sentiment and adjust the publishing method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned publishing department, We select the optimal publishing method by referring to past publishing data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned publishing department, We optimize the publication content by taking learner feedback into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned publishing department, It estimates user sentiment and prioritizes content to publish based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned publishing department, Publish content that addresses region-specific learning needs, taking into account the learners' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned publishing department, Analyze learners' social media activity and publish content incorporating relevant topics. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0184] 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 production department creates learning content, A determination unit that determines the legitimacy and quality of learning content produced by the aforementioned production department, A voting unit performs voting on the learning content determined by the aforementioned determination unit and creates a ranking, A publishing department that publishes learning content based on the rankings created by the aforementioned voting department. A system characterized by the following features.

2. The determination unit, The AI ​​generates the learning content to determine its legitimacy and quality. The system according to feature 1.

3. The aforementioned voting section, Vote based on learner level and needs to create a ranking. The system according to feature 1.

4. The aforementioned voting section, The system includes a mechanism to verify voter eligibility. The system according to feature 1.

5. The aforementioned voting section, Equipped with a log management system to ensure transparency in voting. The system according to feature 1.

6. The aforementioned publishing department, Publish top-ranked learning content in print and digital formats. The system according to feature 1.

7. The aforementioned production department, We estimate user emotions and adjust the creation method of learning content based on the estimated user emotions. The system according to feature 1.

8. The aforementioned production department, We select the optimal production method by referring to evaluation data of past learning content. The system according to feature 1.

9. The aforementioned production department, The difficulty level of the content is adjusted based on the learner's learning progress. The system according to feature 1.

10. The aforementioned production department, We estimate the user's emotions and determine the theme of the content to be created based on those estimated emotions. The system according to feature 1.

Images