system

Abstract

The system according to the embodiment aims to provide individualized instruction according to the characteristics and learning objectives of the learner. [Solution] A system according to an embodiment includes an analysis unit, an instruction unit, and an adjustment unit. The analysis unit analyzes the characteristics or learning objectives of a learner. The instruction unit provides individual instruction to the learner based on the information analyzed by the analysis unit. The adjustment unit adjusts the learning content according to the learner's level of understanding after receiving instruction from the instruction unit.

Description

[Technical Field]

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

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

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

[0004] Conventional techniques do not adequately provide individualized instruction tailored to the learner's characteristics and learning goals, and there is room for improvement.

[0005] The system according to the embodiment aims to provide individualized instruction according to the characteristics and learning objectives of the learner. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an instruction unit, and an adjustment unit. The analysis unit analyzes the characteristics or learning objectives of a learner. The instruction unit provides individual instruction to the learner based on the information analyzed by the analysis unit. The adjustment unit adjusts the learning content according to the learner's level of understanding instructed by the instruction unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide individualized instruction according to the characteristics and learning objectives of the learner. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A learning system according to an embodiment of the present invention is a new learning system that revolutionizes traditional learning methods and uses generative AI to develop human resources. This learning system analyzes a learner's characteristics and learning goals and generates an optimal learning plan. The generative AI then provides individualized instruction to the learner and monitors their learning progress in real time. Furthermore, the generative AI adjusts the learning content according to the learner's level of understanding, providing an optimal learning environment. This system enables learners to study efficiently, and the generative AI acts as a lifelong support for the learner. For example, the generative AI analyzes a learner's characteristics and learning goals. During this process, the generative AI collects and analyzes data such as the learner's past learning history, interests, and learning style. For example, if a learner is interested in mathematics, the generative AI generates a mathematics-related learning plan. The generative AI then provides individualized instruction to the learner. The generative AI monitors the learner's level of understanding and progress in real time and provides appropriate feedback. For example, if a learner does not fully understand a particular problem, the generative AI provides additional explanations and practice questions for that problem. Furthermore, the generative AI adjusts the learning content according to the learner's level of understanding. For example, if a learner demonstrates excellent understanding in a particular field, the generative AI will provide more advanced content in that field. On the other hand, if the learner struggles to understand, the generative AI will return to basic content and explain it again. This system allows learners to progress efficiently. The generative AI adjusts the learning content to match the learner's pace, providing an optimal learning environment. The generative AI also acts as a lifelong companion, supporting the learner and watching over their growth. For example, when a learner attempts a new field, the generative AI generates a learning plan related to that field and supports the learner. In this way, the new learning system using generative AI fundamentally revolutionizes traditional learning methods and supports learners' efficient learning. Furthermore, by supporting learners as a lifelong companion, the generative AI promotes learner growth and contributes to improving the value of human existence. This allows the learning system to support efficient learning by providing individual instruction and adjusting the learning content based on the learner's characteristics and learning goals.

[0029] A learning system according to an embodiment includes an analysis unit, an instruction unit, and an adjustment unit. The analysis unit analyzes the characteristics or learning goals of a learner. Examples of the learner's characteristics include learning style, learning speed, and level of understanding. Examples of the learning goals include passing an exam, acquiring skills, and deepening knowledge. The analysis unit performs the analysis using methods such as data mining, statistical analysis, and machine learning algorithms. The instruction unit provides individual instruction to the learner based on the information analyzed by the analysis unit. The instruction unit provides instruction using methods such as individual instruction, group instruction, and online instruction. The instruction unit monitors the learner's level of understanding and progress in real time and provides appropriate feedback. For example, the instruction unit evaluates the learner's level of understanding based on test results, quiz accuracy, self-assessment, and the like. The adjustment unit adjusts the learning content according to the learner's level of understanding instructed by the instruction unit. The adjustment unit performs the adjustment using methods such as adjusting the difficulty level of the learning content, progress management, and feedback provision. As a result, the learning system according to the embodiment can support efficient learning by providing individual instruction based on the learner's characteristics and learning goals and adjusting the learning content.

[0030] The learning system includes a collection unit that collects learner data. The collection unit collects learner data. The collected data includes, for example, learning history, test results, and behavioral logs. For example, the collection unit stores the learner's past learning content and test results in a database, and the analysis unit uses this data to analyze the learner's characteristics and learning objectives. The collection unit also collects the learner's behavioral logs to understand the learner's learning style and learning speed. For example, the collection unit records the time of day the learner studies and their preferred learning method. This allows the collection unit to collect learner data and perform more accurate analysis. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the learner's behavioral logs into a generation AI, which can analyze the data and extract the learner's characteristics.

[0031] The learning system includes a contract unit that manages a contract for the generation AI to exist as a lifelong partner. The contract unit manages the contract for the generation AI to support the learner as a lifelong partner. The contract includes, for example, the contract period, service content, and fee structure. The contract unit manages the contract between the learner and the generation AI, and the generation AI supports the learner based on the contract content. For example, the contract unit manages the period for which the learner uses the generation AI and the service content, ensuring that the learner receives appropriate support from the generation AI during the contract period. The contract unit also calculates fees based on the contract content and bills the learner. This allows the contract unit to manage the contract for the generation AI to support the learner as a lifelong partner. Some or all of the above-described processing in the contract unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the contract unit inputs the contract content into the generation AI, which analyzes the contract content and proposes an optimal support plan.

[0032] The learning system includes a protection unit that protects learner data. The protection unit protects the learner data. Data protection includes, for example, methods such as encryption, access control, and data backup. The protection unit protects the learner data from unauthorized access and ensures data privacy. For example, the protection unit encrypts the learner data to prevent it from being leaked to third parties. The protection unit also performs access control to limit the users who can access the learner data. Furthermore, the protection unit regularly backs up the data to prevent data loss. In this way, the protection unit can ensure privacy by protecting the learner's data. Some or all of the above-described processing in the protection unit may be performed using, or without, a generation AI. For example, the protection unit can input data encryption and access control settings to the generation AI, which can then suggest an optimal protection method.

[0033] The analysis unit can analyze data on the learner's past learning history, interests, and learning style. The analysis unit, for example, analyzes the learner's past learning history. The learning history includes past learning content, test results, study time, etc. The analysis unit understands the learner's learning pattern based on this data and generates an optimal learning plan. The analysis unit also analyzes the learner's interests. The interests include the learner's topics of interest, hobbies, future goals, etc. The analysis unit generates a learning plan that appeals to the learner based on this data. The analysis unit also analyzes the learner's learning style. Learning styles include visual, auditory, and experiential. The analysis unit suggests the optimal learning method for the learner based on this data. In this way, the analysis unit can generate a more appropriate learning plan by analyzing the learner's past learning history, interests, and learning style. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI or without a generation AI. For example, the analysis unit can input data on a learner's learning history and interests into the generation AI, which can then analyze the data and generate an optimal learning plan.

[0034] The teaching unit can monitor the learner's level of understanding and progress in real time and provide appropriate feedback. For example, the teaching unit monitors the learner's level of understanding in real time. Assessments of comprehension include test results, quiz correct answer rates, self-assessments, etc. The teaching unit assesses the learner's level of understanding based on this data and provides appropriate feedback. The teaching unit also monitors the learner's progress in real time. Assessments of progress include learning progress, achievement, goal achievement rate, etc. The teaching unit assesses the learner's progress based on this data and provides appropriate feedback. For example, if the learner's understanding of a particular problem is insufficient, the teaching unit provides additional explanations or practice questions for that problem. Furthermore, if the learner demonstrates excellent understanding in a particular area, the teaching unit provides more advanced content in that area. In this way, the teaching unit can improve learning effectiveness by monitoring the learner's level of understanding and progress in real time and providing appropriate feedback. Some or all of the above-described processing in the teaching unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, instructors can input data on a learner's level of understanding and progress into the generating AI, which can then analyze the data and provide appropriate feedback.

[0035] The adjustment unit can adjust the learning content according to the learner's level of understanding. The adjustment unit, for example, adjusts the difficulty of the learning content according to the learner's level of understanding. Evaluations of the level of understanding include test results, quiz correct answer rates, self-assessments, etc. The adjustment unit evaluates the learner's level of understanding based on these data and adjusts the difficulty of the learning content. For example, if the learner demonstrates basic understanding, the adjustment unit can provide the learner with content at the next level. Also, if the learner demonstrates intermediate-level understanding, the adjustment unit can provide applied questions. Furthermore, if the learner demonstrates advanced understanding, the adjustment unit can provide the learner with specialized content. In this way, the adjustment unit can provide the learner with an optimal learning environment by adjusting the learning content according to the learner's level of understanding. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the adjustment unit can input data on the learner's level of understanding into a generation AI, which can analyze the data and adjust the difficulty of the learning content.

[0036] The analysis unit can incorporate the learner's lifestyle habits and daily behavior patterns into the analysis in addition to the learner's past learning history. The analysis unit, for example, analyzes the learner's lifestyle habits. Lifestyle habits include sleep patterns, eating habits, exercise habits, etc. The analysis unit understands the learner's lifestyle habits based on this data and generates an optimal study plan. The analysis unit also analyzes the learner's daily behavior patterns. The behavior patterns include daily activities, travel patterns, social media usage, etc. The analysis unit understands the learner's behavior patterns based on this data and generates an optimal study plan. For example, the analysis unit can analyze the learner's sleep patterns and suggest optimal study times. It can also analyze the learner's eating habits and generate a study plan based on their energy levels. It can also analyze the learner's daily behavior patterns and adjust the study time to coincide with the learner's best concentration times. In this way, the analysis unit can generate a more accurate study plan by incorporating the learner's lifestyle habits and daily behavior patterns into the analysis. Some or all of the above-mentioned processes in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit may input data on the learner's lifestyle habits and behavior patterns into the generation AI, which may then analyze the data and generate an optimal learning plan.

[0037] The analysis unit can predict areas of interest that the learner will likely have in the future based on the learner's interests and reflect the prediction in the analysis. The analysis unit, for example, analyzes the learner's interests. Interests include topics of interest, hobbies, and future goals of the learner. The analysis unit generates a learning plan that will capture the learner's interest based on this data. The analysis unit also predicts areas of interest that the learner will likely have in the future. Predictions can include methods such as machine learning algorithms, statistical models, and data mining. For example, the analysis unit can predict future areas of interest based on areas the learner has previously shown interest in. It can also predict areas of interest by analyzing the learner's social media activity. It can also predict future areas of interest by analyzing the learner's reading history. This allows the analysis unit to predict future areas of interest based on the learner's interests and provide a learning plan tailored to the learner. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input data on the learner's interests into a generation AI, which can analyze the data and predict future areas of interest.

[0038] The analysis unit can perform analysis taking into account the learner's geographical and cultural background. For example, the analysis unit analyzes the learner's geographical background. Geographical background includes place of residence, regional characteristics, climate, etc. The analysis unit understands the learner's geographical background based on this data and generates an optimal learning plan. The analysis unit also analyzes the learner's cultural background. Cultural background includes language, religion, customs, etc. The analysis unit understands the learner's cultural background based on this data and generates an optimal learning plan. For example, the analysis unit performs analysis based on the learner's regional educational curriculum. It can also provide appropriate example questions taking into account the learner's cultural background. Furthermore, it can incorporate relevant geographical information into the analysis based on the learner's geographical background. This allows the analysis unit to provide more appropriate analysis results by taking into account the learner's geographical and cultural background. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input data on the learner's geographical and cultural background into a generation AI, which can then analyze the data and generate an optimal learning plan.

[0039] The analysis unit can incorporate the learner's social media activity into the analysis to generate a more accurate study plan. The analysis unit, for example, analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The analysis unit understands the learner's interests based on this data and generates an optimal study plan. For example, the analysis unit can analyze the learner's social media interests and generate a related study plan. It can also analyze the learner's social media activity time and suggest optimal study times. It can also analyze the learner's social media friendships and suggest collaborative study opportunities. In this way, the analysis unit can provide a more accurate study plan by incorporating the learner's social media activity into the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input data on the learner's social media activity into a generation AI, which analyzes the data and generates an optimal study plan.

[0040] The teaching unit can gradually evolve the content of instruction according to the learner's level of understanding. For example, the teaching unit gradually evolves the content of instruction according to the learner's level of understanding. Evaluations of the level of understanding include test results, quiz correct answer rates, self-assessments, etc. The teaching unit evaluates the learner's level of understanding based on these data and evolves the content of instruction. For example, if the learner demonstrates basic understanding, the teaching unit can provide the next level of content. Also, if the learner demonstrates intermediate-level understanding, the teaching unit can provide applied questions. Furthermore, if the learner demonstrates advanced understanding, the teaching unit can provide specialized content. In this way, the teaching unit can provide instruction appropriate for the learner by evolving the content of instruction according to the learner's level of understanding. Some or all of the above-mentioned processing in the teaching unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the teaching unit can input data on the learner's level of understanding into a generation AI, which can analyze the data and evolve the content of instruction.

[0041] The teaching unit can select a teaching format according to the learner's learning style. For example, the teaching unit selects a teaching format according to the learner's learning style. Learning styles include visual, auditory, and experiential. The teaching unit proposes the optimal teaching format for the learner based on this data. For example, if the learner has a visual learning style, video-based instruction can be provided. Also, if the learner has excellent reading comprehension skills, text-based instruction can be provided. Furthermore, if the learner prefers interactive learning, interactive instruction can be provided. In this way, the teaching unit can provide instruction suited to the learner by selecting a teaching format according to the learner's learning style. Some or all of the above-mentioned processing in the teaching unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the teaching unit can input data on the learner's learning style into a generation AI, which can analyze the data and propose the optimal teaching format.

[0042] The teaching unit can customize the teaching content taking into account the learner's geographical and cultural background. For example, the teaching unit analyzes the learner's geographical background. The geographical background includes the place of residence, local characteristics, and climate. The teaching unit understands the learner's geographical background based on this data and provides the most appropriate teaching content. The teaching unit also analyzes the learner's cultural background. The cultural background includes language, religion, and customs. The teaching unit understands the learner's cultural background based on this data and provides the most appropriate teaching content. For example, the teaching unit customizes the teaching content based on the learner's local educational curriculum. The teaching unit can also provide appropriate example questions taking into account the learner's cultural background. Furthermore, the teaching unit can incorporate relevant geographical information into the teaching content based on the learner's geographical background. This allows the teaching unit to provide more appropriate teaching content by taking into account the learner's geographical and cultural background. Some or all of the above-mentioned processing in the teaching unit may be performed, for example, using a generation AI or without a generation AI. For example, teaching staff can input data about learners' geographical and cultural backgrounds into the generation AI, which can then analyze the data and provide optimal teaching content.

[0043] The teaching unit can analyze the learner's social media activity and provide relevant instructional content. For example, the teaching unit analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The teaching unit understands the learner's interests based on this data and provides optimal instructional content. For example, the teaching unit can analyze the learner's social media interests and provide relevant instructional content. The teaching unit can also analyze the learner's social media activity time and suggest optimal instruction timing. Furthermore, the teaching unit can analyze the learner's social media friendships and suggest collaborative learning opportunities. In this way, the teaching unit can provide relevant instructional content by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the teaching unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the teaching unit can input data on the learner's social media activity into a generation AI, which can analyze the data and provide optimal instructional content.

[0044] The adjustment unit can adjust the difficulty of the learning content in real time according to the learner's level of comprehension. The adjustment unit, for example, adjusts the difficulty of the learning content according to the learner's level of comprehension. Evaluations of the level of comprehension include test results, quiz correct answer rates, self-assessments, etc. The adjustment unit evaluates the learner's level of comprehension based on these data and adjusts the difficulty of the learning content. For example, if the learner demonstrates basic understanding, the adjustment unit can adjust the content to the next level. Also, if the learner demonstrates intermediate-level understanding, the adjustment unit can adjust the content to applied questions. Furthermore, if the learner demonstrates advanced understanding, the adjustment unit can adjust the content to specialized content. In this way, the adjustment unit can provide learning content suitable for the learner by adjusting the difficulty of the learning content according to the learner's level of comprehension. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the adjustment unit can input data on the learner's level of comprehension into a generation AI, which can analyze the data and adjust the difficulty of the learning content.

[0045] The adjustment unit can dynamically change the order of the learning content according to the learner's learning progress. The adjustment unit, for example, dynamically changes the order of the learning content according to the learner's learning progress. Evaluation of learning progress includes learning progress, achievement level, goal achievement rate, etc. The adjustment unit evaluates the learner's progress based on this data and changes the order of the learning content. For example, if a learner shows excellent progress in a particular area, the adjustment unit can prioritize providing content in that area. Also, if the learner is struggling to understand, the adjustment unit can return to basic content and provide further explanations. Furthermore, the order of the learning content can be dynamically changed according to the learner's progress. In this way, the adjustment unit can provide learning content appropriate for the learner by changing the order of the learning content according to the learner's learning progress. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the adjustment unit can input the learner's progress data into a generation AI, which can analyze the data and dynamically change the order of the learning content.

[0046] The adjustment unit can customize the learning content taking into account the learner's geographical and cultural background. The adjustment unit, for example, analyzes the learner's geographical background. The geographical background includes the place of residence, local characteristics, climate, etc. The adjustment unit understands the learner's geographical background based on this data and provides the most appropriate learning content. The adjustment unit also analyzes the learner's cultural background. The cultural background includes language, religion, customs, etc. The adjustment unit understands the learner's cultural background based on this data and provides the most appropriate learning content. For example, the adjustment unit customizes the learning content based on the learner's local educational curriculum. The adjustment unit can also provide appropriate example questions taking into account the learner's cultural background. Furthermore, the adjustment unit can incorporate relevant geographical information into the learning content based on the learner's geographical background. In this way, the adjustment unit can provide more appropriate learning content by taking into account the learner's geographical and cultural background. Some or all of the above-described processing in the adjustment unit may be performed, for example, using a generation AI or without using a generation AI. For example, the adjustment unit can input data on the learner's geographical and cultural background into the generation AI, which can then analyze the data and provide optimal learning content.

[0047] The adjustment unit can analyze the learner's social media activity and provide relevant learning content. The adjustment unit, for example, analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The adjustment unit understands the learner's interests based on this data and provides optimal learning content. For example, the adjustment unit can analyze the learner's social media interests and provide relevant learning content. The adjustment unit can also analyze the learner's social media activity time and suggest optimal learning times. Furthermore, the adjustment unit can analyze the learner's social media friendships and suggest collaborative learning opportunities. In this way, the adjustment unit can provide relevant learning content by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the adjustment unit can input data on the learner's social media activity into a generation AI, which can analyze the data and provide optimal learning content.

[0048] The collection unit can predict future learning needs and collect data based on the learner's interests. The collection unit, for example, analyzes the learner's interests. The interests include topics of interest, hobbies, and future goals. The collection unit generates a learning plan that captures the learner's interest based on this data. The collection unit also predicts areas in which the learner is likely to be interested in the future. Prediction methods include machine learning algorithms, statistical models, and data mining. For example, the collection unit predicts future areas of interest based on areas the learner has previously shown interest in. It can also predict areas of interest by analyzing the learner's social media activity. It can also predict future areas of interest by analyzing the learner's reading history. This allows the collection unit to predict future learning needs based on the learner's interests, thereby collecting appropriate data. Some or all of the above-described processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input data on the learner's interests into a generation AI, which then analyzes the data to predict future learning needs.

[0049] The collection unit can collect data taking into account the learner's geographical and cultural background. The collection unit, for example, analyzes the learner's geographical background. The geographical background includes the place of residence, regional characteristics, climate, etc. The collection unit understands the learner's geographical background based on this data and collects optimal data. The collection unit also analyzes the learner's cultural background. The cultural background includes language, religion, customs, etc. The collection unit understands the learner's cultural background based on this data and collects optimal data. For example, the collection unit collects data based on the learner's regional educational curriculum. The collection unit can also collect appropriate data taking into account the learner's cultural background. Furthermore, the collection unit can collect relevant geographical information based on the learner's geographical background. In this way, the collection unit can collect appropriate data by taking into account the learner's geographical and cultural background. Some or all of the above-described processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input data on the learner's geographical and cultural background into a generation AI, which then analyzes the data and collects optimal data.

[0050] The collection unit can analyze the learner's social media activities and collect relevant data. The collection unit, for example, analyzes the learner's social media activities. Social media activities include the content of posts, the number of followers, the number of likes, etc. The collection unit understands the learner's interests based on this data and collects optimal data. For example, the collection unit analyzes the learner's social media interests and collects relevant data. The collection unit can also analyze the learner's social media activity time and suggest the optimal timing for data collection. Furthermore, the collection unit can analyze the learner's social media friendships and suggest collaborative learning opportunities. In this way, the collection unit can collect relevant data by analyzing the learner's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can input data on the learner's social media activities into a generation AI, which then analyzes the data and collects optimal data.

[0051] The contracting department can analyze the learner's past contract history and propose an optimal contract plan. The contracting department, for example, analyzes the learner's past contract history. The contract history includes past contract details, contract periods, contract conditions, etc. The contracting department understands the learner's contract patterns based on this data and proposes an optimal contract plan. For example, the contracting department proposes an optimal plan based on contract plans the learner has used in the past. It can also propose a cost-effective plan based on the learner's past contract history. Furthermore, it can analyze the learner's past contract history and propose the most efficient plan. In this way, the contracting department can provide an optimal contract plan by analyzing the learner's past contract history. Some or all of the above-described processing in the contracting department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the contracting department can input data on the learner's contract history into a generation AI, which analyzes the data and proposes an optimal contract plan.

[0052] The contracting unit can dynamically change the contract content according to the learner's learning progress. The contracting unit dynamically changes the contract content according to, for example, the learner's learning progress. Evaluation of learning progress includes learning progress, achievement level, goal achievement rate, etc. The contracting unit evaluates the learner's progress based on this data and changes the contract content. For example, if a learner shows excellent progress in a particular area, content in that area can be provided preferentially. Also, if a learner is struggling to understand, the contracting unit can return to basic content and provide further explanations. Furthermore, the order of the contract content can be dynamically changed according to the learner's progress. This allows the contracting unit to provide contract content appropriate for the learner by changing the contract content according to the learner's learning progress. Some or all of the above-described processing in the contracting unit may be performed, for example, using a generation AI, or may be performed without a generation AI. For example, the contracting unit can input the learner's progress data into a generation AI, which can analyze the data and dynamically change the contract content.

[0053] The contracting unit can customize the contract content taking into account the learner's geographical and cultural background. For example, the contracting unit analyzes the learner's geographical background. The geographical background includes the place of residence, regional characteristics, and climate. The contracting unit understands the learner's geographical background based on this data and provides the most appropriate contract content. The contracting unit also analyzes the learner's cultural background. The cultural background includes language, religion, and customs. The contracting unit understands the learner's cultural background based on this data and provides the most appropriate contract content. For example, the contracting unit customizes the contract content based on the learner's regional educational curriculum. The contracting unit can also provide appropriate contract content by taking into account the learner's cultural background. Furthermore, the contracting unit can incorporate relevant geographical information into the contract content based on the learner's geographical background. This allows the contracting unit to provide appropriate contract content by taking into account the learner's geographical and cultural background. Some or all of the above-described processing in the contracting unit may be performed, for example, using a generation AI or without a generation AI. For example, the contract department can input data on the learner's geographical and cultural background into the generation AI, which can then analyze the data and provide the most appropriate contract content.

[0054] The contracting department can analyze the learner's social media activity and propose a relevant contract plan. For example, the contracting department analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The contracting department understands the learner's interests based on this data and proposes the optimal contract plan. For example, the contracting department can analyze the learner's social media interests and propose a relevant contract plan. It can also analyze the learner's social media activity time and propose an optimal contract plan. It can also analyze the learner's social media friendships and propose collaborative learning opportunities. In this way, the contracting department can provide a relevant contract plan by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the contracting department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the contracting department can input data on the learner's social media activity into a generation AI, which can analyze the data and propose an optimal contract plan.

[0055] The protection unit can analyze the learner's past data protection history and propose optimal protection measures. The protection unit, for example, analyzes the learner's past data protection history. The data protection history includes past data protection methods, protection frequency, protection success rate, etc. The protection unit understands the learner's data protection patterns based on this data and proposes optimal protection measures. For example, the protection unit proposes optimal measures based on data protection measures used by the learner in the past. The protection unit can also propose cost-effective measures based on the learner's past data protection history. Furthermore, the protection unit can analyze the learner's past data protection history and propose the most efficient measures. In this way, the protection unit can provide optimal protection measures by analyzing the learner's past data protection history. Some or all of the above-mentioned processing in the protection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the protection unit can input data on the learner's data protection history into a generation AI, which can analyze the data and propose optimal protection measures.

[0056] The protection unit can dynamically change the protection measures according to the learner's data protection needs. For example, the protection unit dynamically changes the protection measures according to the learner's data protection needs. Data protection needs include the importance of data, the necessity for protection, risk assessment, etc. The protection unit evaluates the learner's data protection needs based on this data and changes the protection measures. For example, if a learner shows excellent progress in a particular area, the protection unit prioritizes the protection of data in that area. Also, if the learner is struggling to understand, the protection unit can return to basic data and reprotect it. Furthermore, the order of data protection can dynamically change according to the learner's progress. This allows the protection unit to provide appropriate data protection by changing the protection measures according to the learner's data protection needs. Some or all of the above-described processing in the protection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the protection unit can input data on the learner's data protection needs into a generation AI, which can analyze the data and dynamically change the protection measures.

[0057] The protection unit can protect data by taking into account the learner's geographical and cultural background. For example, the protection unit analyzes the learner's geographical background. The geographical background includes the place of residence, regional characteristics, climate, etc. The protection unit understands the learner's geographical background based on this data and provides optimal data protection. The protection unit also analyzes the learner's cultural background. The cultural background includes language, religion, customs, etc. The protection unit understands the learner's cultural background based on this data and provides optimal data protection. For example, the protection unit protects data based on the learner's regional educational curriculum. The protection unit can also provide appropriate data protection by taking into account the learner's cultural background. Furthermore, related geographical information can be incorporated into the data protection based on the learner's geographical background. In this way, the protection unit can provide appropriate data protection by taking into account the learner's geographical and cultural background. Some or all of the above-mentioned processing in the protection unit may be performed using, or without, a generation AI. For example, the protection unit can input data on the learner's geographical and cultural background into the generation AI, which can analyze the data and provide optimal data protection.

[0058] The protection unit can analyze the learner's social media activity and suggest relevant data protection measures. For example, the protection unit analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The protection unit understands the learner's interests based on this data and suggests optimal data protection measures. For example, the protection unit can analyze the learner's social media interests and suggest relevant data protection measures. It can also analyze the learner's social media activity time and suggest optimal data protection measures. It can also analyze the learner's social media friendships and suggest collaborative learning opportunities. In this way, the protection unit can provide appropriate data protection measures by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the protection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the protection unit can input data on the learner's social media activity into a generation AI, which can analyze the data and suggest optimal data protection measures.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The analysis unit can also analyze the learner's physiological data and use it to optimize the learning plan. For example, physiological data such as heart rate, electrodermal activity, and brain waves can be collected to evaluate the learner's level of concentration and fatigue. This allows the analysis unit to suggest the most effective time and learning method for the learner. It can also suggest that the learner take a break if they are tired. Furthermore, the learner's physiological data can be used to provide advice on stress management and relaxation.

[0061] Instructors can also analyze learners' social networks to encourage collaboration among learners. For example, they can analyze data on learners' friendships and group activities to match learners who complement each other. This allows learners to teach each other and improve their learning effectiveness. Instructors can also utilize learners' social networks to provide opportunities for joint projects and discussions. Furthermore, they can suggest events and seminars related to topics that interest learners based on learners' social networks.

[0062] The adjustment unit can also monitor the learner's learning environment in real time and provide an optimal environment. For example, sensors can detect the noise level and lighting conditions around the learner to maintain an environment suitable for learning. This allows the learner to concentrate on their studies. The adjustment unit can also monitor the learner's sitting posture and eye movements and suggest appropriate posture and eye adjustments. Furthermore, it can provide relaxing music and scents according to the learner's learning environment.

[0063] The analysis unit can incorporate the learner's lifestyle habits and daily behavior patterns into the analysis. For example, it can analyze the learner's sleep patterns, eating habits, exercise habits, etc. to generate an optimal study plan. It can also analyze the learner's daily behavior patterns and adjust the study time so that it is easier to concentrate. By incorporating the learner's lifestyle habits and daily behavior patterns into the analysis, the analysis unit can generate a more accurate study plan.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The analysis unit analyzes the learner's characteristics or learning goals. Learner characteristics include, for example, learning style, learning speed, and level of understanding, while learning goals include, for example, passing an exam, acquiring skills, and deepening knowledge. The analysis unit performs the analysis using methods such as data mining, statistical analysis, and machine learning algorithms. Step 2: The instructor provides individual instruction to the learner based on the information analyzed by the analysis unit. The instructor provides instruction using methods such as individual instruction, group instruction, and online instruction, monitors the learner's level of understanding and progress in real time, and provides appropriate feedback. For example, the instructor evaluates the learner's level of understanding based on test results, quiz accuracy, self-evaluation, etc. Step 3: The adjustment unit adjusts the learning content according to the learner's level of understanding as instructed by the instruction unit. The adjustment unit makes adjustments using methods such as adjusting the difficulty level of the learning content, managing progress, and providing feedback.

[0066] (Example 2) A learning system according to an embodiment of the present invention is a new learning system that revolutionizes traditional learning methods and uses generative AI to develop human resources. This learning system analyzes a learner's characteristics and learning goals and generates an optimal learning plan. The generative AI then provides individualized instruction to the learner and monitors their learning progress in real time. Furthermore, the generative AI adjusts the learning content according to the learner's level of understanding, providing an optimal learning environment. This system enables learners to study efficiently, and the generative AI acts as a lifelong support for the learner. For example, the generative AI analyzes a learner's characteristics and learning goals. During this process, the generative AI collects and analyzes data such as the learner's past learning history, interests, and learning style. For example, if a learner is interested in mathematics, the generative AI generates a mathematics-related learning plan. The generative AI then provides individualized instruction to the learner. The generative AI monitors the learner's level of understanding and progress in real time and provides appropriate feedback. For example, if a learner does not fully understand a particular problem, the generative AI provides additional explanations and practice questions for that problem. Furthermore, the generative AI adjusts the learning content according to the learner's level of understanding. For example, if a learner demonstrates excellent understanding in a particular field, the generative AI will provide more advanced content in that field. On the other hand, if the learner struggles to understand, the generative AI will return to basic content and explain it again. This system allows learners to progress efficiently. The generative AI adjusts the learning content to match the learner's pace, providing an optimal learning environment. The generative AI also acts as a lifelong companion, supporting the learner and watching over their growth. For example, when a learner attempts a new field, the generative AI generates a learning plan related to that field and supports the learner. In this way, the new learning system using generative AI fundamentally revolutionizes traditional learning methods and supports learners' efficient learning. Furthermore, by supporting learners as a lifelong companion, the generative AI promotes learner growth and contributes to improving the value of human existence. This allows the learning system to support efficient learning by providing individual instruction and adjusting the learning content based on the learner's characteristics and learning goals.

[0067] A learning system according to an embodiment includes an analysis unit, an instruction unit, and an adjustment unit. The analysis unit analyzes the characteristics or learning goals of a learner. Examples of the learner's characteristics include learning style, learning speed, and level of understanding. Examples of the learning goals include passing an exam, acquiring skills, and deepening knowledge. The analysis unit performs the analysis using methods such as data mining, statistical analysis, and machine learning algorithms. The instruction unit provides individual instruction to the learner based on the information analyzed by the analysis unit. The instruction unit provides instruction using methods such as individual instruction, group instruction, and online instruction. The instruction unit monitors the learner's level of understanding and progress in real time and provides appropriate feedback. For example, the instruction unit evaluates the learner's level of understanding based on test results, quiz accuracy, self-assessment, and the like. The adjustment unit adjusts the learning content according to the learner's level of understanding instructed by the instruction unit. The adjustment unit performs the adjustment using methods such as adjusting the difficulty level of the learning content, progress management, and feedback provision. As a result, the learning system according to the embodiment can support efficient learning by providing individual instruction based on the learner's characteristics and learning goals and adjusting the learning content.

[0068] The learning system includes a collection unit that collects learner data. The collection unit collects learner data. The collected data includes, for example, learning history, test results, and behavioral logs. For example, the collection unit stores the learner's past learning content and test results in a database, and the analysis unit uses this data to analyze the learner's characteristics and learning objectives. The collection unit also collects the learner's behavioral logs to understand the learner's learning style and learning speed. For example, the collection unit records the time of day the learner studies and their preferred learning method. This allows the collection unit to collect learner data and perform more accurate analysis. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input the learner's behavioral logs into a generation AI, which can analyze the data and extract the learner's characteristics.

[0069] The learning system includes a contract unit that manages a contract for the generation AI to exist as a lifelong partner. The contract unit manages the contract for the generation AI to support the learner as a lifelong partner. The contract includes, for example, the contract period, service content, and fee structure. The contract unit manages the contract between the learner and the generation AI, and the generation AI supports the learner based on the contract content. For example, the contract unit manages the period for which the learner uses the generation AI and the service content, ensuring that the learner receives appropriate support from the generation AI during the contract period. The contract unit also calculates fees based on the contract content and bills the learner. This allows the contract unit to manage the contract for the generation AI to support the learner as a lifelong partner. Some or all of the above-described processing in the contract unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the contract unit inputs the contract content into the generation AI, which analyzes the contract content and proposes an optimal support plan.

[0070] The learning system includes a protection unit that protects learner data. The protection unit protects the learner data. Data protection includes, for example, methods such as encryption, access control, and data backup. The protection unit protects the learner data from unauthorized access and ensures data privacy. For example, the protection unit encrypts the learner data to prevent it from being leaked to third parties. The protection unit also performs access control to limit the users who can access the learner data. Furthermore, the protection unit regularly backs up the data to prevent data loss. In this way, the protection unit can ensure privacy by protecting the learner's data. Some or all of the above-described processing in the protection unit may be performed using, or without, a generation AI. For example, the protection unit can input data encryption and access control settings to the generation AI, which can then suggest an optimal protection method.

[0071] The analysis unit can analyze data on the learner's past learning history, interests, and learning style. The analysis unit, for example, analyzes the learner's past learning history. The learning history includes past learning content, test results, study time, etc. The analysis unit understands the learner's learning pattern based on this data and generates an optimal learning plan. The analysis unit also analyzes the learner's interests. The interests include the learner's topics of interest, hobbies, future goals, etc. The analysis unit generates a learning plan that appeals to the learner based on this data. The analysis unit also analyzes the learner's learning style. Learning styles include visual, auditory, and experiential. The analysis unit suggests the optimal learning method for the learner based on this data. In this way, the analysis unit can generate a more appropriate learning plan by analyzing the learner's past learning history, interests, and learning style. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI or without a generation AI. For example, the analysis unit can input data on a learner's learning history and interests into the generation AI, which can then analyze the data and generate an optimal learning plan.

[0072] The teaching unit can monitor the learner's level of understanding and progress in real time and provide appropriate feedback. For example, the teaching unit monitors the learner's level of understanding in real time. Assessments of comprehension include test results, quiz correct answer rates, self-assessments, etc. The teaching unit assesses the learner's level of understanding based on this data and provides appropriate feedback. The teaching unit also monitors the learner's progress in real time. Assessments of progress include learning progress, achievement, goal achievement rate, etc. The teaching unit assesses the learner's progress based on this data and provides appropriate feedback. For example, if the learner's understanding of a particular problem is insufficient, the teaching unit provides additional explanations or practice questions for that problem. Furthermore, if the learner demonstrates excellent understanding in a particular area, the teaching unit provides more advanced content in that area. In this way, the teaching unit can improve learning effectiveness by monitoring the learner's level of understanding and progress in real time and providing appropriate feedback. Some or all of the above-described processing in the teaching unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, instructors can input data on a learner's level of understanding and progress into the generating AI, which can then analyze the data and provide appropriate feedback.

[0073] The adjustment unit can adjust the learning content according to the learner's level of understanding. The adjustment unit, for example, adjusts the difficulty of the learning content according to the learner's level of understanding. Evaluations of the level of understanding include test results, quiz correct answer rates, self-assessments, etc. The adjustment unit evaluates the learner's level of understanding based on these data and adjusts the difficulty of the learning content. For example, if the learner demonstrates basic understanding, the adjustment unit can provide the learner with content at the next level. Also, if the learner demonstrates intermediate-level understanding, the adjustment unit can provide applied questions. Furthermore, if the learner demonstrates advanced understanding, the adjustment unit can provide the learner with specialized content. In this way, the adjustment unit can provide the learner with an optimal learning environment by adjusting the learning content according to the learner's level of understanding. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the adjustment unit can input data on the learner's level of understanding into a generation AI, which can analyze the data and adjust the difficulty of the learning content.

[0074] The analysis unit can estimate the learner's emotions and adjust the accuracy of the analysis based on the estimated learner's emotions. The analysis unit, for example, estimates the learner's emotions. Emotion estimation methods include facial expression recognition, voice analysis, and self-reporting. The analysis unit estimates the learner's emotions based on this data and adjusts the accuracy of the analysis. For example, if the learner is stressed, the generation AI can lower the analysis accuracy and prioritize analyzing easier questions. Alternatively, if the learner is relaxed, the generation AI can increase the analysis accuracy and analyze more difficult questions. Furthermore, if the learner is concentrating, the generation AI can optimize the analysis accuracy and analyze questions that correspond to the learner's level of understanding. This allows the analysis unit to adjust the analysis accuracy based on the learner's emotions and provide analysis results that are appropriate for the learner. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI. For example, the analysis unit may input the learner's emotional data into the generation AI, which may then analyze the data and adjust the accuracy of the analysis.

[0075] The analysis unit can incorporate the learner's lifestyle habits and daily behavior patterns into the analysis in addition to the learner's past learning history. The analysis unit, for example, analyzes the learner's lifestyle habits. Lifestyle habits include sleep patterns, eating habits, exercise habits, etc. The analysis unit understands the learner's lifestyle habits based on this data and generates an optimal study plan. The analysis unit also analyzes the learner's daily behavior patterns. The behavior patterns include daily activities, travel patterns, social media usage, etc. The analysis unit understands the learner's behavior patterns based on this data and generates an optimal study plan. For example, the analysis unit can analyze the learner's sleep patterns and suggest optimal study times. It can also analyze the learner's eating habits and generate a study plan based on their energy levels. It can also analyze the learner's daily behavior patterns and adjust the study time to coincide with the learner's best concentration times. In this way, the analysis unit can generate a more accurate study plan by incorporating the learner's lifestyle habits and daily behavior patterns into the analysis. Some or all of the above-mentioned processes in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit may input data on the learner's lifestyle habits and behavior patterns into the generation AI, which may then analyze the data and generate an optimal learning plan.

[0076] The analysis unit can predict areas of interest that the learner will likely have in the future based on the learner's interests and reflect the prediction in the analysis. The analysis unit, for example, analyzes the learner's interests. Interests include topics of interest, hobbies, and future goals of the learner. The analysis unit generates a learning plan that will capture the learner's interest based on this data. The analysis unit also predicts areas of interest that the learner will likely have in the future. Predictions can include methods such as machine learning algorithms, statistical models, and data mining. For example, the analysis unit can predict future areas of interest based on areas the learner has previously shown interest in. It can also predict areas of interest by analyzing the learner's social media activity. It can also predict future areas of interest by analyzing the learner's reading history. This allows the analysis unit to predict future areas of interest based on the learner's interests and provide a learning plan tailored to the learner. Some or all of the above-described processing in the analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the analysis unit can input data on the learner's interests into a generation AI, which can analyze the data and predict future areas of interest.

[0077] The analysis unit can estimate the learner's emotions and adjust the display method of the analysis results based on the estimated learner's emotions. The analysis unit, for example, estimates the learner's emotions. Emotion estimation methods include facial expression recognition, voice analysis, and self-reporting. The analysis unit estimates the learner's emotions based on these data and adjusts the display method of the analysis results. For example, if the learner is nervous, a simple, highly visible display method can be provided. If the learner is relaxed, a display method including detailed information can be provided. Furthermore, if the learner is in a hurry, a display method that focuses on the main points can be provided. In this way, the analysis unit can adjust the display method of the analysis results based on the learner's emotions and provide a display method that is suitable for the learner. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can input the learner's emotional data into the generation AI, which can then analyze the data and adjust how the analysis results are displayed.

[0078] The analysis unit can perform analysis taking into account the learner's geographical and cultural background. For example, the analysis unit analyzes the learner's geographical background. Geographical background includes place of residence, regional characteristics, climate, etc. The analysis unit understands the learner's geographical background based on this data and generates an optimal learning plan. The analysis unit also analyzes the learner's cultural background. Cultural background includes language, religion, customs, etc. The analysis unit understands the learner's cultural background based on this data and generates an optimal learning plan. For example, the analysis unit performs analysis based on the learner's regional educational curriculum. It can also provide appropriate example questions taking into account the learner's cultural background. Furthermore, it can incorporate relevant geographical information into the analysis based on the learner's geographical background. This allows the analysis unit to provide more appropriate analysis results by taking into account the learner's geographical and cultural background. Some or all of the above-described processing in the analysis unit can be performed using, or without, a generation AI. For example, the analysis unit can input data on the learner's geographical and cultural background into a generation AI, which can then analyze the data and generate an optimal learning plan.

[0079] The analysis unit can incorporate the learner's social media activity into the analysis to generate a more accurate study plan. The analysis unit, for example, analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The analysis unit understands the learner's interests based on this data and generates an optimal study plan. For example, the analysis unit can analyze the learner's social media interests and generate a related study plan. It can also analyze the learner's social media activity time and suggest optimal study times. It can also analyze the learner's social media friendships and suggest collaborative study opportunities. In this way, the analysis unit can provide a more accurate study plan by incorporating the learner's social media activity into the analysis. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can input data on the learner's social media activity into a generation AI, which analyzes the data and generates an optimal study plan.

[0080] The teaching unit can estimate the learner's emotions and adjust the teaching method based on the estimated learner's emotions. The teaching unit, for example, estimates the learner's emotions. Emotion estimation includes methods such as facial expression recognition, voice analysis, and self-reporting. The teaching unit estimates the learner's emotions based on this data and adjusts the teaching method. For example, if the learner is stressed, the teaching unit can provide a teaching method that helps the learner relax. Also, if the learner is relaxed, the teaching unit can provide a challenging teaching method. Furthermore, if the learner is concentrating, the teaching unit can provide a teaching method that helps the learner maintain concentration. In this way, the teaching unit can adjust the teaching method based on the learner's emotions and provide appropriate instruction for the learner. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the teaching unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, instructors can input learner emotional data into the generation AI, which can then analyze the data and adjust its teaching methods.

[0081] The teaching unit can gradually evolve the content of instruction according to the learner's level of understanding. For example, the teaching unit gradually evolves the content of instruction according to the learner's level of understanding. Evaluations of the level of understanding include test results, quiz correct answer rates, self-assessments, etc. The teaching unit evaluates the learner's level of understanding based on these data and evolves the content of instruction. For example, if the learner demonstrates basic understanding, the teaching unit can provide the next level of content. Also, if the learner demonstrates intermediate-level understanding, the teaching unit can provide applied questions. Furthermore, if the learner demonstrates advanced understanding, the teaching unit can provide specialized content. In this way, the teaching unit can provide instruction appropriate for the learner by evolving the content of instruction according to the learner's level of understanding. Some or all of the above-mentioned processing in the teaching unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the teaching unit can input data on the learner's level of understanding into a generation AI, which can analyze the data and evolve the content of instruction.

[0082] The teaching unit can select a teaching format according to the learner's learning style. For example, the teaching unit selects a teaching format according to the learner's learning style. Learning styles include visual, auditory, and experiential. The teaching unit proposes the optimal teaching format for the learner based on this data. For example, if the learner has a visual learning style, video-based instruction can be provided. Also, if the learner has excellent reading comprehension skills, text-based instruction can be provided. Furthermore, if the learner prefers interactive learning, interactive instruction can be provided. In this way, the teaching unit can provide instruction suited to the learner by selecting a teaching format according to the learner's learning style. Some or all of the above-mentioned processing in the teaching unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the teaching unit can input data on the learner's learning style into a generation AI, which can analyze the data and propose the optimal teaching format.

[0083] The teaching unit can estimate the learner's emotions and adjust the timing of instruction based on the estimated learner's emotions. The teaching unit, for example, estimates the learner's emotions. Emotion estimation methods include facial expression recognition, voice analysis, and self-reporting. The teaching unit estimates the learner's emotions based on these data and adjusts the timing of instruction. For example, if the learner is tired, the teaching unit can suggest a break and adjust the timing of instruction. Also, if the learner is concentrating, the teaching unit can provide continuous instruction. Furthermore, if the learner is relaxed, the teaching unit can provide instruction at an appropriate timing. This allows the teaching unit to adjust the timing of instruction based on the learner's emotions and provide instruction that is appropriate for the learner. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the teaching unit may be performed using, for example, a generative AI, or without a generative AI. For example, the teaching staff can input the learner's emotional data into the generation AI, which can then analyze the data and adjust the timing of instruction.

[0084] The teaching unit can customize the teaching content taking into account the learner's geographical and cultural background. For example, the teaching unit analyzes the learner's geographical background. The geographical background includes the place of residence, local characteristics, and climate. The teaching unit understands the learner's geographical background based on this data and provides the most appropriate teaching content. The teaching unit also analyzes the learner's cultural background. The cultural background includes language, religion, and customs. The teaching unit understands the learner's cultural background based on this data and provides the most appropriate teaching content. For example, the teaching unit customizes the teaching content based on the learner's local educational curriculum. The teaching unit can also provide appropriate example questions taking into account the learner's cultural background. Furthermore, the teaching unit can incorporate relevant geographical information into the teaching content based on the learner's geographical background. This allows the teaching unit to provide more appropriate teaching content by taking into account the learner's geographical and cultural background. Some or all of the above-mentioned processing in the teaching unit may be performed, for example, using a generation AI or without a generation AI. For example, teaching staff can input data about learners' geographical and cultural backgrounds into the generation AI, which can then analyze the data and provide optimal teaching content.

[0085] The teaching unit can analyze the learner's social media activity and provide relevant instructional content. For example, the teaching unit analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The teaching unit understands the learner's interests based on this data and provides optimal instructional content. For example, the teaching unit can analyze the learner's social media interests and provide relevant instructional content. The teaching unit can also analyze the learner's social media activity time and suggest optimal instruction timing. Furthermore, the teaching unit can analyze the learner's social media friendships and suggest collaborative learning opportunities. In this way, the teaching unit can provide relevant instructional content by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the teaching unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the teaching unit can input data on the learner's social media activity into a generation AI, which can analyze the data and provide optimal instructional content.

[0086] The adjustment unit can estimate the learner's emotions and adjust the learning content based on the estimated learner's emotions. The adjustment unit, for example, estimates the learner's emotions. Methods for estimating emotions include facial expression recognition, voice analysis, and self-reporting. The adjustment unit estimates the learner's emotions based on these data and adjusts the learning content. For example, if the learner is feeling stressed, the adjustment unit can adjust the learning content to be relaxing. Also, if the learner is relaxed, the adjustment unit can adjust the learning content to be challenging. Furthermore, if the learner is concentrating, the adjustment unit can adjust the learning content to be more focused. In this way, the adjustment unit can provide learning content suitable for the learner by adjusting the learning content based on the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, a generation AI, or without a generation AI. For example, the adjustment unit can input the learner's emotional data into the generation AI, which can then analyze the data and adjust the learning content.

[0087] The adjustment unit can adjust the difficulty of the learning content in real time according to the learner's level of comprehension. The adjustment unit, for example, adjusts the difficulty of the learning content according to the learner's level of comprehension. Evaluations of the level of comprehension include test results, quiz correct answer rates, self-assessments, etc. The adjustment unit evaluates the learner's level of comprehension based on these data and adjusts the difficulty of the learning content. For example, if the learner demonstrates basic understanding, the adjustment unit can adjust the content to the next level. Also, if the learner demonstrates intermediate-level understanding, the adjustment unit can adjust the content to applied questions. Furthermore, if the learner demonstrates advanced understanding, the adjustment unit can adjust the content to specialized content. In this way, the adjustment unit can provide learning content suitable for the learner by adjusting the difficulty of the learning content according to the learner's level of comprehension. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the adjustment unit can input data on the learner's level of comprehension into a generation AI, which can analyze the data and adjust the difficulty of the learning content.

[0088] The adjustment unit can dynamically change the order of the learning content according to the learner's learning progress. The adjustment unit, for example, dynamically changes the order of the learning content according to the learner's learning progress. Evaluation of learning progress includes learning progress, achievement level, goal achievement rate, etc. The adjustment unit evaluates the learner's progress based on this data and changes the order of the learning content. For example, if a learner shows excellent progress in a particular area, the adjustment unit can prioritize providing content in that area. Also, if the learner is struggling to understand, the adjustment unit can return to basic content and provide further explanations. Furthermore, the order of the learning content can be dynamically changed according to the learner's progress. In this way, the adjustment unit can provide learning content appropriate for the learner by changing the order of the learning content according to the learner's learning progress. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the adjustment unit can input the learner's progress data into a generation AI, which can analyze the data and dynamically change the order of the learning content.

[0089] The adjustment unit can estimate the learner's emotions and adjust the display method of the learning content based on the estimated learner's emotions. The adjustment unit, for example, estimates the learner's emotions. Emotion estimation methods include facial expression recognition, voice analysis, and self-reporting. The adjustment unit estimates the learner's emotions based on these data and adjusts the display method of the learning content. For example, if the learner is nervous, a simple, highly visible display method can be provided. If the learner is relaxed, a display method including detailed information can be provided. Furthermore, if the learner is in a hurry, a display method that focuses on the main points can be provided. In this way, the adjustment unit can adjust the display method of the learning content based on the learner's emotions and provide a display method that is suitable for the learner. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the adjustment unit can be performed, for example, using the generation AI, or without the generation AI. For example, the adjustment unit can input the learner's emotional data into the generation AI, which can then analyze the data and adjust the way the learning content is displayed.

[0090] The adjustment unit can customize the learning content taking into account the learner's geographical and cultural background. The adjustment unit, for example, analyzes the learner's geographical background. The geographical background includes the place of residence, local characteristics, climate, etc. The adjustment unit understands the learner's geographical background based on this data and provides the most appropriate learning content. The adjustment unit also analyzes the learner's cultural background. The cultural background includes language, religion, customs, etc. The adjustment unit understands the learner's cultural background based on this data and provides the most appropriate learning content. For example, the adjustment unit customizes the learning content based on the learner's local educational curriculum. The adjustment unit can also provide appropriate example questions taking into account the learner's cultural background. Furthermore, the adjustment unit can incorporate relevant geographical information into the learning content based on the learner's geographical background. In this way, the adjustment unit can provide more appropriate learning content by taking into account the learner's geographical and cultural background. Some or all of the above-described processing in the adjustment unit may be performed, for example, using a generation AI or without using a generation AI. For example, the adjustment unit can input data on the learner's geographical and cultural background into the generation AI, which can then analyze the data and provide optimal learning content.

[0091] The adjustment unit can analyze the learner's social media activity and provide relevant learning content. The adjustment unit, for example, analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The adjustment unit understands the learner's interests based on this data and provides optimal learning content. For example, the adjustment unit can analyze the learner's social media interests and provide relevant learning content. The adjustment unit can also analyze the learner's social media activity time and suggest optimal learning times. Furthermore, the adjustment unit can analyze the learner's social media friendships and suggest collaborative learning opportunities. In this way, the adjustment unit can provide relevant learning content by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the adjustment unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the adjustment unit can input data on the learner's social media activity into a generation AI, which can analyze the data and provide optimal learning content.

[0092] The collection unit can estimate the learner's emotions and adjust the timing of data collection based on the estimated learner's emotions. The collection unit, for example, estimates the learner's emotions. Emotion estimation methods include facial expression recognition, voice analysis, and self-reporting. The collection unit estimates the learner's emotions based on these data and adjusts the timing of data collection. For example, if the learner is relaxed, data collection can be performed more frequently. Also, if the learner is stressed, data collection frequency can be reduced. Furthermore, if the learner is concentrating, the timing of data collection can be optimized. In this way, the collection unit can adjust the timing of data collection based on the learner's emotions, thereby collecting data appropriate for the learner. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using the generation AI, or without the generation AI. For example, the collection unit can input the learner's emotional data into the generation AI, which can then analyze the data and adjust the timing of data collection.

[0093] The collection unit can predict future learning needs and collect data based on the learner's interests. The collection unit, for example, analyzes the learner's interests. The interests include topics of interest, hobbies, and future goals. The collection unit generates a learning plan that captures the learner's interest based on this data. The collection unit also predicts areas in which the learner is likely to be interested in the future. Prediction methods include machine learning algorithms, statistical models, and data mining. For example, the collection unit predicts future areas of interest based on areas the learner has previously shown interest in. It can also predict areas of interest by analyzing the learner's social media activity. It can also predict future areas of interest by analyzing the learner's reading history. This allows the collection unit to predict future learning needs based on the learner's interests, thereby collecting appropriate data. Some or all of the above-described processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input data on the learner's interests into a generation AI, which then analyzes the data to predict future learning needs.

[0094] The collection unit can estimate the learner's emotions and prioritize the data to be collected based on the estimated learner's emotions. The collection unit, for example, estimates the learner's emotions. Emotion estimation methods include facial expression recognition, voice analysis, and self-reporting. The collection unit estimates the learner's emotions based on these data and prioritizes the data to be collected. For example, if the learner is stressed, the collection unit prioritizes collecting data that helps the learner relax. Also, if the learner is relaxed, the collection unit can prioritize collecting challenging data. Furthermore, if the learner is concentrating, the collection unit can prioritize collecting data that helps the learner maintain concentration. Thus, the collection unit prioritizes the data to be collected based on the learner's emotions, thereby collecting data appropriate for the learner. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the collection unit can input the learner's emotional data into the generation AI, which can then analyze the data and determine the priority of the data to be collected.

[0095] The collection unit can collect data taking into account the learner's geographical and cultural background. The collection unit, for example, analyzes the learner's geographical background. The geographical background includes the place of residence, regional characteristics, climate, etc. The collection unit understands the learner's geographical background based on this data and collects optimal data. The collection unit also analyzes the learner's cultural background. The cultural background includes language, religion, customs, etc. The collection unit understands the learner's cultural background based on this data and collects optimal data. For example, the collection unit collects data based on the learner's regional educational curriculum. The collection unit can also collect appropriate data taking into account the learner's cultural background. Furthermore, the collection unit can collect relevant geographical information based on the learner's geographical background. In this way, the collection unit can collect appropriate data by taking into account the learner's geographical and cultural background. Some or all of the above-described processing in the collection unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the collection unit can input data on the learner's geographical and cultural background into a generation AI, which then analyzes the data and collects optimal data.

[0096] The collection unit can analyze the learner's social media activities and collect relevant data. The collection unit, for example, analyzes the learner's social media activities. Social media activities include the content of posts, the number of followers, the number of likes, etc. The collection unit understands the learner's interests based on this data and collects optimal data. For example, the collection unit analyzes the learner's social media interests and collects relevant data. The collection unit can also analyze the learner's social media activity time and suggest the optimal timing for data collection. Furthermore, the collection unit can analyze the learner's social media friendships and suggest collaborative learning opportunities. In this way, the collection unit can collect relevant data by analyzing the learner's social media activities. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the collection unit can input data on the learner's social media activities into a generation AI, which then analyzes the data and collects optimal data.

[0097] The contract unit can estimate the learner's emotions and adjust the contract content based on the estimated learner's emotions. The contract unit, for example, estimates the learner's emotions. Emotion estimation includes methods such as facial expression recognition, voice analysis, and self-reporting. The contract unit estimates the learner's emotions based on this data and adjusts the contract content. For example, if the learner is stressed, the contract content can be simplified and made easier to understand. Alternatively, if the learner is relaxed, the contract content can be provided with detailed contract content and customizable options. Furthermore, if the learner is in a hurry, the contract can be completed quickly. In this way, the contract unit can adjust the contract content based on the learner's emotions to provide contract content that is appropriate for the learner. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the contract unit may be performed using, for example, a generative AI, or without a generative AI. For example, the contract department can input the learner's emotional data into the generation AI, which can then analyze the data and adjust the contract content.

[0098] The contracting department can analyze the learner's past contract history and propose an optimal contract plan. The contracting department, for example, analyzes the learner's past contract history. The contract history includes past contract details, contract periods, contract conditions, etc. The contracting department understands the learner's contract patterns based on this data and proposes an optimal contract plan. For example, the contracting department proposes an optimal plan based on contract plans the learner has used in the past. It can also propose a cost-effective plan based on the learner's past contract history. Furthermore, it can analyze the learner's past contract history and propose the most efficient plan. In this way, the contracting department can provide an optimal contract plan by analyzing the learner's past contract history. Some or all of the above-described processing in the contracting department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the contracting department can input data on the learner's contract history into a generation AI, which analyzes the data and proposes an optimal contract plan.

[0099] The contracting unit can dynamically change the contract content according to the learner's learning progress. The contracting unit dynamically changes the contract content according to, for example, the learner's learning progress. Evaluation of learning progress includes learning progress, achievement level, goal achievement rate, etc. The contracting unit evaluates the learner's progress based on this data and changes the contract content. For example, if a learner shows excellent progress in a particular area, content in that area can be provided preferentially. Also, if a learner is struggling to understand, the contracting unit can return to basic content and provide further explanations. Furthermore, the order of the contract content can be dynamically changed according to the learner's progress. This allows the contracting unit to provide contract content appropriate for the learner by changing the contract content according to the learner's learning progress. Some or all of the above-described processing in the contracting unit may be performed, for example, using a generation AI, or may be performed without a generation AI. For example, the contracting unit can input the learner's progress data into a generation AI, which can analyze the data and dynamically change the contract content.

[0100] The contract unit can estimate the learner's emotions and adjust the timing of contract renewal based on the estimated learner's emotions. The contract unit, for example, estimates the learner's emotions. Emotion estimation includes methods such as facial expression recognition, voice analysis, and self-reporting. The contract unit estimates the learner's emotions based on this data and adjusts the timing of contract renewal. For example, if the learner is relaxed, the contract unit can suggest the timing of contract renewal. Also, if the learner is stressed, the contract unit can delay the timing of contract renewal. Furthermore, if the learner is concentrating, the contract unit can optimize the timing of contract renewal. This allows the contract unit to adjust the timing of contract renewal based on the learner's emotions, thereby performing contract renewal that is appropriate for the learner. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the contract unit may be performed using, for example, a generation AI, or without a generation AI. For example, the contract department can input the learner's emotional data into the generation AI, which can then analyze the data and adjust the timing of contract renewal.

[0101] The contracting unit can customize the contract content taking into account the learner's geographical and cultural background. For example, the contracting unit analyzes the learner's geographical background. The geographical background includes the place of residence, regional characteristics, and climate. The contracting unit understands the learner's geographical background based on this data and provides the most appropriate contract content. The contracting unit also analyzes the learner's cultural background. The cultural background includes language, religion, and customs. The contracting unit understands the learner's cultural background based on this data and provides the most appropriate contract content. For example, the contracting unit customizes the contract content based on the learner's regional educational curriculum. The contracting unit can also provide appropriate contract content by taking into account the learner's cultural background. Furthermore, the contracting unit can incorporate relevant geographical information into the contract content based on the learner's geographical background. This allows the contracting unit to provide appropriate contract content by taking into account the learner's geographical and cultural background. Some or all of the above-described processing in the contracting unit may be performed, for example, using a generation AI or without a generation AI. For example, the contract department can input data on the learner's geographical and cultural background into the generation AI, which can then analyze the data and provide the most appropriate contract content.

[0102] The contracting department can analyze the learner's social media activity and propose a relevant contract plan. For example, the contracting department analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The contracting department understands the learner's interests based on this data and proposes the optimal contract plan. For example, the contracting department can analyze the learner's social media interests and propose a relevant contract plan. It can also analyze the learner's social media activity time and propose an optimal contract plan. It can also analyze the learner's social media friendships and propose collaborative learning opportunities. In this way, the contracting department can provide a relevant contract plan by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the contracting department may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the contracting department can input data on the learner's social media activity into a generation AI, which can analyze the data and propose an optimal contract plan.

[0103] The protection unit can estimate the learner's emotions and adjust the data protection method based on the estimated learner's emotions. The protection unit, for example, estimates the learner's emotions. Emotion estimation includes methods such as facial expression recognition, voice analysis, and self-reporting. The protection unit estimates the learner's emotions based on these data and adjusts the data protection method. For example, if the learner is stressed, the protection unit can simplify the data protection procedure. Also, if the learner is relaxed, the protection unit can provide detailed data protection procedures. Furthermore, if the learner is in a hurry, the protection unit can quickly protect data. In this way, the protection unit can adjust the data protection method based on the learner's emotions, thereby providing data protection that is appropriate for the learner. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the protection unit may be performed using, for example, the generation AI, or without the generation AI. For example, the protection unit can input the learner's emotional data into the generation AI, which can then analyze the data and adjust the method of data protection.

[0104] The protection unit can analyze the learner's past data protection history and propose optimal protection measures. The protection unit, for example, analyzes the learner's past data protection history. The data protection history includes past data protection methods, protection frequency, protection success rate, etc. The protection unit understands the learner's data protection patterns based on this data and proposes optimal protection measures. For example, the protection unit proposes optimal measures based on data protection measures used by the learner in the past. The protection unit can also propose cost-effective measures based on the learner's past data protection history. Furthermore, the protection unit can analyze the learner's past data protection history and propose the most efficient measures. In this way, the protection unit can provide optimal protection measures by analyzing the learner's past data protection history. Some or all of the above-mentioned processing in the protection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the protection unit can input data on the learner's data protection history into a generation AI, which can analyze the data and propose optimal protection measures.

[0105] The protection unit can dynamically change the protection measures according to the learner's data protection needs. For example, the protection unit dynamically changes the protection measures according to the learner's data protection needs. Data protection needs include the importance of data, the necessity for protection, risk assessment, etc. The protection unit evaluates the learner's data protection needs based on this data and changes the protection measures. For example, if a learner shows excellent progress in a particular area, the protection unit prioritizes the protection of data in that area. Also, if the learner is struggling to understand, the protection unit can return to basic data and reprotect it. Furthermore, the order of data protection can dynamically change according to the learner's progress. This allows the protection unit to provide appropriate data protection by changing the protection measures according to the learner's data protection needs. Some or all of the above-described processing in the protection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the protection unit can input data on the learner's data protection needs into a generation AI, which can analyze the data and dynamically change the protection measures.

[0106] The protection unit can estimate the learner's emotions and determine the priority of data protection based on the estimated learner's emotions. The protection unit, for example, estimates the learner's emotions. Emotion estimation includes methods such as facial expression recognition, voice analysis, and self-reporting. The protection unit estimates the learner's emotions based on these data and determines the priority of data protection. For example, if the learner is stressed, data that helps the learner relax can be prioritized for protection. Also, if the learner is relaxed, challenging data can be prioritized for protection. Furthermore, if the learner is concentrating, data that helps the learner maintain concentration can be prioritized for protection. In this way, the protection unit can provide appropriate data protection by determining the priority of data protection based on the learner's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the protection unit can be performed, for example, using the generation AI, or without the generation AI. For example, the protection unit can input the learner's emotional data into the generation AI, which can then analyze the data and determine the priority of data protection.

[0107] The protection unit can protect data by taking into account the learner's geographical and cultural background. For example, the protection unit analyzes the learner's geographical background. The geographical background includes the place of residence, regional characteristics, climate, etc. The protection unit understands the learner's geographical background based on this data and provides optimal data protection. The protection unit also analyzes the learner's cultural background. The cultural background includes language, religion, customs, etc. The protection unit understands the learner's cultural background based on this data and provides optimal data protection. For example, the protection unit protects data based on the learner's regional educational curriculum. The protection unit can also provide appropriate data protection by taking into account the learner's cultural background. Furthermore, related geographical information can be incorporated into the data protection based on the learner's geographical background. In this way, the protection unit can provide appropriate data protection by taking into account the learner's geographical and cultural background. Some or all of the above-mentioned processing in the protection unit may be performed using, or without, a generation AI. For example, the protection unit can input data on the learner's geographical and cultural background into the generation AI, which can analyze the data and provide optimal data protection.

[0108] The protection unit can analyze the learner's social media activity and suggest relevant data protection measures. For example, the protection unit analyzes the learner's social media activity. Social media activity includes the content of posts, the number of followers, the number of likes, etc. The protection unit understands the learner's interests based on this data and suggests optimal data protection measures. For example, the protection unit can analyze the learner's social media interests and suggest relevant data protection measures. It can also analyze the learner's social media activity time and suggest optimal data protection measures. It can also analyze the learner's social media friendships and suggest collaborative learning opportunities. In this way, the protection unit can provide appropriate data protection measures by analyzing the learner's social media activity. Some or all of the above-mentioned processing in the protection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the protection unit can input data on the learner's social media activity into a generation AI, which can analyze the data and suggest optimal data protection measures. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, guidance unit, adjustment unit, collection unit, contract unit, protection unit, and emotion estimation function is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The guidance unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The adjustment unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The collection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The contract unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The protection unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The emotion estimation function is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, guidance unit, adjustment unit, collection unit, contract unit, protection unit, and emotion estimation function is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The guidance unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The adjustment unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The collection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The contract unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The protection unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The emotion estimation function is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, guidance unit, adjustment unit, collection unit, contract unit, protection unit, and emotion estimation function is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The guidance unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The adjustment unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The collection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The contract unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The protection unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The emotion estimation function is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, leadership unit, adjustment unit, collection unit, contract unit, protection unit, and emotion estimation function is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The leadership unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The adjustment unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The collection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The contract unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The protection unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The emotion estimation function is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The analysis unit can also analyze the learner's physiological data and use it to optimize the learning plan. For example, physiological data such as heart rate, electrodermal activity, and brain waves can be collected to evaluate the learner's level of concentration and fatigue. This allows the analysis unit to suggest the most effective time and learning method for the learner. It can also suggest that the learner take a break if they are tired. Furthermore, the learner's physiological data can be used to provide advice on stress management and relaxation.

[0111] Instructors can also analyze learners' social networks to encourage collaboration among learners. For example, they can analyze data on learners' friendships and group activities to match learners who complement each other. This allows learners to teach each other and improve their learning effectiveness. Instructors can also utilize learners' social networks to provide opportunities for joint projects and discussions. Furthermore, they can suggest events and seminars related to topics that interest learners based on learners' social networks.

[0112] The adjustment unit can also monitor the learner's learning environment in real time and provide an optimal environment. For example, sensors can detect the noise level and lighting conditions around the learner to maintain an environment suitable for learning. This allows the learner to concentrate on their studies. The adjustment unit can also monitor the learner's sitting posture and eye movements and suggest appropriate posture and eye adjustments. Furthermore, it can provide relaxing music and scents according to the learner's learning environment.

[0113] The analysis unit can also estimate the learner's emotions and adjust the learning plan based on the estimated emotions. For example, if the learner is feeling anxious, it can suggest content and methods to help the learner relax. If the learner is excited, it can provide challenging tasks. Furthermore, if the learner is concentrating, it can provide a learning plan that makes the most of that concentration. In this way, the analysis unit can provide the optimal learning plan according to the learner's emotions.

[0114] The instructor can also estimate the learner's emotions and adjust the content of the feedback based on the estimated emotions. For example, if the learner is feeling down, they can provide encouraging words and positive feedback. If the learner is feeling confident, they can provide feedback that encourages them to try harder. Furthermore, if the learner is feeling impatient, they can provide advice to help them stay calm. This allows the instructor to provide appropriate feedback according to the learner's emotions.

[0115] The adjustment unit can also estimate the learner's emotions and adjust the display method of the learning content based on the estimated emotions. For example, if the learner is nervous, a simple, highly visible display method can be provided. If the learner is relaxed, a display method including detailed information can be provided. Furthermore, if the learner is in a hurry, a display method that focuses on the main points can be provided. In this way, the adjustment unit can provide a display method that is suitable for the learner by adjusting the display method of the learning content based on the learner's emotions.

[0116] The collection unit can also estimate the learner's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the learner is relaxed, data collection can be performed more frequently. Also, if the learner is feeling stressed, the frequency of data collection can be reduced. Furthermore, if the learner is concentrating, the timing of data collection can be optimized. In this way, the collection unit can collect data that is suitable for the learner by adjusting the timing of data collection based on the learner's emotions.

[0117] The contract department can also estimate the learner's emotions and adjust the contract content based on the estimated emotions. For example, if the learner is feeling stressed, the contract content can be simplified and made easier to understand. If the learner is relaxed, the contract content can be provided in detail and customizable options can be suggested. Furthermore, if the learner is in a hurry, the contract content can be made available for quick completion. This allows the contract department to provide appropriate contract content to the learner by adjusting the contract content based on the learner's emotions.

[0118] The protection unit can also estimate the learner's emotions and adjust the data protection method based on the estimated emotions. For example, if the learner is stressed, the data protection procedure can be simplified. If the learner is relaxed, detailed data protection procedures can be provided. Furthermore, if the learner is in a hurry, data protection can be performed quickly. In this way, the protection unit can adjust the data protection method based on the learner's emotions, thereby providing data protection that is suitable for the learner.

[0119] The analysis unit can incorporate the learner's lifestyle habits and daily behavior patterns into the analysis. For example, it can analyze the learner's sleep patterns, eating habits, exercise habits, etc. to generate an optimal study plan. It can also analyze the learner's daily behavior patterns and adjust the study time so that it is easier to concentrate. By incorporating the learner's lifestyle habits and daily behavior patterns into the analysis, the analysis unit can generate a more accurate study plan.

[0120] The processing flow of the second embodiment will be briefly explained below.

[0121] Step 1: The analysis unit analyzes the learner's characteristics or learning goals. Learner characteristics include, for example, learning style, learning speed, and level of understanding, while learning goals include, for example, passing an exam, acquiring skills, and deepening knowledge. The analysis unit performs the analysis using methods such as data mining, statistical analysis, and machine learning algorithms. Step 2: The instructor provides individual instruction to the learner based on the information analyzed by the analysis unit. The instructor provides instruction using methods such as individual instruction, group instruction, and online instruction, monitors the learner's level of understanding and progress in real time, and provides appropriate feedback. For example, the instructor evaluates the learner's level of understanding based on test results, quiz accuracy, self-evaluation, etc. Step 3: The adjustment unit adjusts the learning content according to the learner's level of understanding as instructed by the instruction unit. The adjustment unit makes adjustments using methods such as adjusting the difficulty level of the learning content, managing progress, and providing feedback.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0124] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 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.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0156] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0159] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0165] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0166] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0167] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0168] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0169] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0170] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0172] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0173] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0174] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0175] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0176] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0177] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0178] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0179] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0180] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0182] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0183] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0184] 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.

[0185] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0186] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0187] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0188] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0189] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0190] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0191] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0192] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0193] [Explanation of symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the characteristics or learning objectives of a learner; a teaching unit that provides individual instruction to the learner based on the information analyzed by the analysis unit; an adjustment unit that adjusts the learning content according to the level of understanding of the learner instructed by the instruction unit; Equipped with A system characterized by:

2. Equipped with a collection unit that collects learner data The system of claim 1 .

3. Equipped with a contract department that manages the contract for the generation AI to exist as a lifelong companion The system of claim 1 .

4. Equipped with a protection section to protect learner data The system of claim 1 .

5. The analysis unit Analyze data on learners' past learning history, interests, and learning styles The system of claim 1 .

6. The leadership team: Monitor learners' understanding and progress in real time and provide appropriate feedback The system of claim 1 .

7. The adjustment unit Adapt learning content according to the learner's level of understanding The system of claim 1 .

8. The analysis unit Estimate the learner's emotions and adjust the accuracy of analysis based on the estimated learner's emotions. The system of claim 1 .

9. The analysis unit In addition to the learner's past learning history, the learner's lifestyle habits and daily behavior patterns are incorporated into the analysis. The system of claim 1 .

Images