system

Abstract

We provide the system. [Solution] An input method for entering the user's educational goals and existing knowledge level, A generation means that generates an individually optimized educational plan based on the data obtained from the input means, A presentation method for presenting the generated educational plan to the user, A means of providing guidance for offering instructional courses tailored to the local curriculum, Includes a dialogue mechanism that generates and presents answers in real time during the learning process, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is necessary to provide a high-quality and individually optimized learning experience to students who cannot receive appropriate education due to limited educational resources or language barriers, and to eliminate the educational gap. In conventional educational platforms, the means for effectively providing a curriculum suitable for individual learners are limited, and also, due to insufficient multilingual learning and individual feedback on learning progress, the needs of a wide range of learners cannot be fully met.

Means for Solving the Problems

[0005] This invention solves the aforementioned problems by providing a generation means that uses an information processing device to generate an individually optimized educational plan based on the user's learning goals and existing knowledge level. Furthermore, it enables the rapid resolution of questions arising during the educational process through an interactive question-answering function, and maintains and improves the user's motivation to learn through an analysis means that analyzes collected learning data and provides individualized feedback. In addition, multilingual support functionality allows for the support of diverse learners, overcoming language barriers.

[0006] An "information processing device" is an electronic device that can input, process, and output data, and is capable of managing educational programs and user data.

[0007] "Users" refers to those who use the system to receive educational content and services, such as students and learners.

[0008] "Educational objectives" refer to the learning goals and achievement criteria that users intend to accomplish through the system.

[0009] "Existing knowledge level" refers to the degree of knowledge and skills a user possesses at the time they begin using the system.

[0010] An "individually optimized educational plan" refers to a learning program customized based on the user's educational goals and existing knowledge level.

[0011] "Generation method" refers to the function or process of creating an educational plan based on data entered by the user.

[0012] "Interactive generation means" refers to a means by which the system generates appropriate answers in real time to user questions.

[0013] "Collection methods" refer to mechanisms and methods for accumulating user learning activities and performance data.

[0014] The "analysis means" represents a process for analyzing the collected learning data to provide improvement points and feedback to the user.

[0015] The "presentation means" has a function of presenting the generated educational plan and feedback to the user visually or as audio.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention realizes an educational system that provides an individually optimized learning experience using an information processing device. This system mainly consists of server, terminal, and user elements.

[0038] First, the user accesses the learning platform through their device and enters information about their educational goals and current knowledge level. The device has a mechanism to send the user's input to the server.

[0039] Upon receiving information from the user, the server uses AI-based generation methods to create an optimized educational plan for that user. This plan includes curriculum, materials, and progress goals, and is customized to the learner's specific needs.

[0040] Next, the server sends the generated learning plan to the terminal, and the user proceeds with learning according to this plan. If the user encounters any questions during the learning process, they can send questions using the terminal. The server passes these questions to an interactive generation system, which generates appropriate answers in real time and provides them to the terminal.

[0041] Furthermore, the server continuously collects data on learning activities. This data is analyzed to monitor user progress and provide necessary feedback. The analysis results are displayed on the device as feedback, allowing users to adjust their learning plans and check their progress.

[0042] As a concrete example, consider a user learning mathematics accessing this system. The user aims to improve a specific mathematical skill and enters "I have basic knowledge of differential calculus" into the terminal. Based on this information, the server generates a curriculum that helps the user progress from the basics of differential calculus to more advanced topics. If the user encounters a problem they don't understand during this process, they can ask a question through the terminal, and the server will provide hints and solution steps to help them solve the problem. In this way, individual learning needs can be met, and an effective learning experience can be obtained.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user accesses the learning platform using their device and registers or logs in. The device sends the authentication information entered by the user to the server.

[0046] Step 2:

[0047] The server compares the transmitted authentication information with records in the database. If authentication is successful, it prepares the user's profile and displays the dashboard on the terminal.

[0048] Step 3:

[0049] The user inputs their learning goals and current knowledge level from their device. The device then sends this information to the server.

[0050] Step 4:

[0051] The server uses an AI model based on the received user information to generate an individually optimized educational plan. The generated plan includes a curriculum and teaching materials tailored to the user's specific needs.

[0052] Step 5:

[0053] The server sends the generated educational plan to the terminal. The terminal displays the plan to the user.

[0054] Step 6:

[0055] The user progresses through the learning process according to the displayed educational plan. If a question arises during the learning process, the user sends the question to the server via their device.

[0056] Step 7:

[0057] The server receives a question from the user and immediately generates an appropriate answer using interactive generation means. The generated answer is sent to the terminal and provided to the user.

[0058] Step 8:

[0059] The server periodically collects user learning progress and activity data. This data is then analyzed to understand user performance and provide necessary feedback.

[0060] Step 9:

[0061] The server generates individual feedback based on the analysis results and sends it to the terminal. The user can then adjust the learning process based on this feedback and make further improvements.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] Traditional education systems have struggled to provide optimal learning plans tailored to the individual learning goals and knowledge levels of each student. Furthermore, they have been unable to promptly address students' questions or effectively manage learning progress using data obtained through learning activities. Therefore, a lack of personalized learning experiences has been a significant challenge.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes an input means for inputting the learner's educational goals and current knowledge level, a generation means for formulating an individually optimized educational plan based on the information obtained from the input means, and a presentation means for presenting the educational plan formulated using a generation AI model to the learner. This makes it possible to provide learners with individually optimized educational plans and realize an effective learning experience.

[0067] An "input method" is an interface that allows learners to input their educational goals and current knowledge levels into the system.

[0068] "Generative means" refers to the process and function of formulating individually optimized educational plans based on information obtained from learners.

[0069] A "generative AI model" is an algorithm that uses artificial intelligence to generate optimal educational plans and problem-solving answers based on learner data.

[0070] "Presentation methods" refer to system components that display formulated educational plans and generated responses to learners in an easily understandable manner.

[0071] "Progress management means" refer to methods and functions for promoting learning and managing progress based on a formulated educational plan.

[0072] A "receiving means" refers to a means of communication for receiving questions and feedback from learners.

[0073] An "interactive generation method" is a dynamic AI process that generates appropriate answers in real time to received questions.

[0074] "Means of delivery" refers to the methods and functions used to provide the generated answers and feedback to the learner.

[0075] A "collection method" is a mechanism for recording and storing learner activity data.

[0076] "Analysis means" refers to the process and function of analyzing collected data and providing learning feedback.

[0077] "Support measures" refer to methods and functions for improving learning plans based on analysis results and supporting learners' progress.

[0078] This system is an educational system that provides an individually optimized learning experience and consists of servers, terminals, and users.

[0079] The server receives data from the terminal to input and accept learners' educational goals and current knowledge levels. The terminal's role is to send the information entered by the user to the server. Standard web interfaces or dedicated applications are used for this data reception.

[0080] The server inputs the received information into an AI-based generative AI model to generate individually optimized educational plans. This generative AI model utilizes machine learning algorithms and natural language processing to create educational plans that recommend the most suitable curriculum and materials for each user.

[0081] The generated educational plan is sent back from the server to the terminal, which then presents the plan to the user through a user interface. This user interface displays the learning program and objectives in a visually easy-to-understand format, promoting effective learning.

[0082] If a user wants to ask a question during the learning process, they can send the question to the server as a prompt via their device. For example, "Please explain how to apply the chain law of differentiation." The server inputs this question into the generating AI model, generates an appropriate answer in real time, and returns it to the device.

[0083] The server continuously collects user learning activities. The collected data is analyzed to evaluate learning progress and provide necessary feedback. The feedback is displayed as feedback information in the user interface, allowing users to understand their learning progress and adjust their learning plan as needed.

[0084] For example, if a user learning mathematics enters "I have basic knowledge of differential calculus," the server will generate an appropriate curriculum ranging from basic to advanced content. In response to any problems the user encounters during this process, the server will provide hints and solution steps to help them overcome the challenges.

[0085] In this way, the system improves the effectiveness and efficiency of learning by providing an optimal learning experience tailored to individual learning needs.

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The terminal provides an interface for users to input their educational goals and current knowledge level. For example, the user might input information such as "I have basic knowledge of differential calculus." This information is sent to the server in digital format. The server stores the received information in a database.

[0089] Step 2:

[0090] The server inputs the received user information into an AI-based generation system. Based on this data, the generating AI model creates an optimal educational plan. An educational plan, including curriculum and material selection, is created and stored on the server.

[0091] Step 3:

[0092] The server sends the generated learning plan to the terminal, which then displays the plan in its user interface. The user can then begin learning according to the presented plan. The terminal supports learning with visual progress bars and reminder functions.

[0093] Step 4:

[0094] If a user has a question during the learning process, they can enter it through their device. For example, they might enter a prompt such as, "Please explain how to apply the chain rule of differentiation." The device then sends this question to the server.

[0095] Step 5:

[0096] The server passes the received prompt to an interactive generation mechanism, which uses a generation AI model to generate an appropriate response. The server quickly organizes the generated response and sends it back to the terminal.

[0097] Step 6:

[0098] The terminal displays the answers received from the server in the user interface. The user can use the presented answers to resolve their questions and continue learning.

[0099] Step 7:

[0100] The server collects user learning activity and progress data. Detailed data, such as learning time and content completion status, is recorded and stored in a database.

[0101] Step 8:

[0102] The server analyzes the collected data and generates feedback to evaluate the learning effect. The analysis results are provided to the user through the user interface, indicating areas for improvement and successes.

[0103] Step 9:

[0104] Users can adjust their learning plans based on the feedback they receive. This promotes more effective learning and allows them to modify their actions to achieve their goals.

[0105] (Application Example 1)

[0106] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0107] In today's urban environment, it is difficult to effectively learn about local culture and history while meeting individual learning needs. Traditional methods tend to focus on general educational content, lacking the provision of knowledge specific to particular regions. As a result, users have limited access to locally relevant information, leading to decreased learning efficiency.

[0108] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0109] In this invention, the server includes input means for inputting the user's educational goals and existing knowledge level, guidance means for providing instructional courses tailored to local learning content, and dialogue means for generating and presenting answers in real time during the learning process. This enables users to receive a region-specific and optimized educational plan and effectively realize a learning experience in a specific location within a city.

[0110] An "information processing device" is an electronic system that integrates the input, generation, and output of data.

[0111] An "input method" is a function that allows the system to receive the user's educational goals and knowledge level.

[0112] "Generation method" refers to the process of creating an optimized educational plan for the user based on input data.

[0113] "Presentation method" refers to a method that can provide the generated educational plan to the user visually or audibly.

[0114] A "guidance method" is a mechanism that presents users with learning content or instructional courses related to a specific region.

[0115] A "dialogue mechanism" is a function that allows users and the system to exchange information in real time and generate answers to questions.

[0116] A "receiving means" is an interface for receiving questions and data from users.

[0117] "Means of provision" refers to a mechanism that supplies generated responses and information to users.

[0118] "Location information processing means" refers to technology for appropriately guiding learners through learning content based on geographical information.

[0119] "Collection method" refers to the function of collecting user learning data and incorporating it into the system.

[0120] "Analysis means" refers to the process of analyzing collected data and generating learning feedback.

[0121] A "support system" is a mechanism that assists and promotes the user's learning activities based on the feedback provided.

[0122] "Visualization means" refers to a function that visually generates and displays information related to learning activities.

[0123] This invention is an individually optimized learning support system within a smart city, implemented using an information processing device. An example thereof is shown below.

[0124] The server first receives information about educational goals and existing knowledge levels from the user's smartphone or other device. The device then allows the user to input educational topics of interest and regionally relevant educational goals through an input mechanism.

[0125] Next, the server uses a generation mechanism based on the received information to create an optimized educational plan for the user. This generation process utilizes technologies such as OpenAI®'s generative AI model to generate content that matches the user's learning needs. This plan includes region-specific instructional courses and related learning content.

[0126] The generated educational plan is presented to the user through guidance methods. Specifically, learning guidance based on geographical location information is provided via a smartphone application, and when the user reaches a specific landmark or learning point, information about the local culture and history is provided.

[0127] During the learning process, if a user has a question, they can send it to the server using their device. The server receives the question using a dialogue mechanism and provides an appropriate answer. Real-time information exchange makes the learning experience more interactive and effective.

[0128] Furthermore, learning data is continuously collected by the collection method, and this data is analyzed by the analysis method. The results of this analysis are provided to the user's device as feedback, and the user can adjust their learning plan based on this feedback.

[0129] As a concrete example, consider a user who is interested in "Edo period architecture" and selects this topic. As the user explores the area with their smartphone, the historical background and characteristics of each landmark are displayed on the device. An example of a prompt message could be, "Generate historical information and a learning quiz about Edo period architecture. The user is at a specific landmark." This message could be instructed to the server.

[0130] In this way, users can gain valuable local knowledge while pursuing individually optimized learning.

[0131] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0132] Step 1:

[0133] The device starts up, and the user enters their educational goals and existing knowledge level. This input is done using the device's UI, and it is also possible to select learning topics relevant to the region. The device then sends this information to the server.

[0134] Step 2:

[0135] The server passes the received educational objectives and knowledge level data to the generation mechanism. The generation mechanism uses a generative AI model to generate an optimal educational plan based on the input. This process involves data calculations to create a curriculum and teaching materials that meet the user's needs.

[0136] Step 3:

[0137] The server sends the created educational plan back to the terminal via a guidance system. The terminal receives this information and presents it to the user visually or audibly. This information includes the order in which learning should proceed and information related to specific geographical locations.

[0138] Step 4:

[0139] As users progress through their learning, if they encounter a question, they can use their device to send it to the server. This process generates a prompt and interactively communicates it to the server.

[0140] Step 5:

[0141] The server receives questions using dialogue mechanisms and generates appropriate answers using interactive generation mechanisms. The generation AI model is then utilized again to form answers in real time.

[0142] Step 6:

[0143] The generated answers are sent from the server to the terminal, which then presents the answers to the user. This deepens the user's understanding of the learning material.

[0144] Step 7:

[0145] Training data is automatically collected from the device and sent to the server. The server analyzes the data obtained by the collection device and generates feedback using the analysis device.

[0146] Step 8:

[0147] The generated feedback is sent to the device via a support system and presented to the user. This allows the user to check their learning progress and adjust their learning plan as needed.

[0148] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0149] This invention combines an information processing device with a function to recognize and reflect the user's emotions in an educational system that provides a personalized learning experience to users. This system consists of a server, a terminal, a user, and an emotion engine.

[0150] First, the user accesses the learning platform via their device and enters their personal educational goals and existing knowledge level. The device sends this information to the server. The server uses AI based on the user information to generate a personalized educational plan, which is then sent to the device and presented to the user.

[0151] Next, as the user progresses through the learning process, the device collects emotional data from the user's facial expressions and voice. This emotional data is sent to the server's emotion engine. The emotion engine analyzes this data in real time to determine the user's emotional state.

[0152] The server adjusts the learning content based on the analysis results obtained from the emotion engine. For example, if the server determines that the user is bored, it immediately updates the learning plan and changes to more interesting materials. Similarly, if the user is stressed, the content can be simplified to reduce the load.

[0153] As a concrete example, suppose a user is solving a math problem and the emotion engine detects that the user is confused. In this case, the server immediately adjusts the difficulty of the problem and presents clearer explanations and examples through the terminal.

[0154] Furthermore, when a user asks a question, the server considers not only the content of the question but also the user's emotional state, and uses interactive generation methods to generate an answer tailored to the user's psychological state. This allows users to continue learning with greater confidence.

[0155] This system analyzes both learning data and emotional data to provide personalized feedback, thereby efficiently and effectively improving the user's learning experience.

[0156] The following describes the processing flow.

[0157] Step 1:

[0158] The user accesses the learning platform using their device and registers or logs in. The device sends the authentication information entered by the user to the server.

[0159] Step 2:

[0160] The server verifies the submitted authentication information against the database to perform authentication. If authentication is successful, it prepares the user's profile and displays the dashboard on the terminal.

[0161] Step 3:

[0162] The user uses a terminal to input learning objectives and their current knowledge level. The terminal sends the entered information to the server.

[0163] Step 4:

[0164] The server uses artificial intelligence to generate a personalized educational plan based on the received user information. This plan includes recommendations for curriculum and teaching materials.

[0165] Step 5:

[0166] The server sends the generated learning plan to the terminal. The terminal displays the plan to the user and the user begins learning.

[0167] Step 6:

[0168] The user progresses through the learning process according to the provided educational plan. During the learning process, the device analyzes the user's facial expressions and voice, and sends emotional data to the server.

[0169] Step 7:

[0170] The server analyzes the emotional data sent from the terminal using an emotion engine to determine the user's emotional state.

[0171] Step 8:

[0172] The server adaptively adjusts the learning content based on the analysis results from the emotion engine. For example, if it determines that the user is experiencing stress, it adjusts the difficulty level of the learning content.

[0173] Step 9:

[0174] The server analyzes the user's learning progress and sentiment data together, generates personalized feedback, and sends it to the device. The user then uses this feedback to continue their learning activities.

[0175] (Example 2)

[0176] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0177] Traditional education systems have struggled with learning efficiency and sustainability because they have not adequately optimized the learning experience by considering the emotional state and psychological aspects of individual users. Furthermore, they can only provide fixed teaching materials, making it difficult to dynamically adjust materials according to users' interests and levels of understanding.

[0178] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0179] In this invention, the server includes a collection means for collecting user emotional data, an analysis means for analyzing the emotional data and determining the emotional state, and an adjustment means for dynamically adjusting the educational plan generated based on the determined emotional state. This makes it possible to appropriately adjust the educational plan according to the user's emotional state and provide a more individually optimized learning experience.

[0180] An "information processing device" is a device or system for inputting, processing, and outputting data, and has a mechanism for performing calculations in response to user operations.

[0181] A "user" is an individual or group that receives services using an information processing device, and is an entity that seeks to gain a learning experience through an educational platform.

[0182] An "educational plan" is a learning course structured based on the user's educational goals and knowledge level, and is an educational program optimized to meet individual needs.

[0183] "Emotional data" refers to indicators of a user's psychological state obtained from their facial expressions and voice, and represents emotional responses perceived in real time.

[0184] An "analysis tool" is a component that has the function of analyzing information based on collected data, and plays a role in clarifying the user's state and needs.

[0185] "Adjustment mechanisms" refer to mechanisms for dynamically changing educational plans and teaching materials based on analysis results, and are functions for optimizing the user's learning experience.

[0186] "Feedback" refers to information that provides responses and advice based on the user's learning progress, understanding, and emotional state, and serves as instructions or guidelines to enhance learning effectiveness.

[0187] This invention uses an information processing device as part of an educational system to provide users with an optimized learning experience. This system consists of a server, a terminal, a user interface, and an emotion analysis engine. Detailed embodiments for carrying out this invention are described below.

[0188] First, users access the educational platform using their device and input specific educational goals and their current knowledge level. This device can be a standard computer or smart device that connects to the server via a web browser. The interface also includes a camera and microphone, allowing for real-time detection of the user's facial expressions and voice. This information is sent to the server as foundational data to gain a detailed understanding of the user's educational needs.

[0189] The server uses a generative AI model based on the received user data to generate individually optimized learning plans. For example, machine learning frameworks such as TENSORFLOW® and PyTorch can be used for this generation. The generated learning plan is sent to the terminal and presented to the user. Specifically, learning materials in HTML or PDF format are displayed, allowing the user to proceed with their learning while viewing them.

[0190] During the learning process, the device analyzes the user's facial expressions and voice and sends them to the server as emotion data. The server processes this data using an emotion analysis engine to determine the user's emotional state. This process can be carried out using libraries such as OpenCV or librosa to capture the characteristics of emotions.

[0191] For example, if the server detects that a user is experiencing confusion while solving a math problem, it dynamically adjusts the learning plan, lowering the difficulty level and providing clearer explanations and examples. This helps maintain the user's motivation to learn. A concrete example of this operation is when a user says, "I don't understand the chain rule for differentiation." In this case, the server generates a prompt message saying, "For the next step, please provide video materials that visually explain the basics of linear algebra," and selects appropriate materials to send to the terminal.

[0192] This system enables a more enriching learning experience by providing feedback that captures the nuances of the user's needs.

[0193] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0194] Step 1:

[0195] Users access the educational platform using their device and input educational goals and existing knowledge levels. This information is sent from the device to the server in JSON format. The input data is parsed on the server and used as foundational data to generate individually optimized educational plans. The device prompts the user for confirmation via an interface to complete the data entry.

[0196] Step 2:

[0197] The server generates an educational plan using a generated AI model based on the received user data. This process involves data calculations using a machine learning framework (e.g., TensorFlow or PyTorch) to select the most suitable learning materials and learning sequence based on the user's knowledge level and goals. The resulting educational plan is then sent from the server to the terminal.

[0198] Step 3:

[0199] The device presents the received educational plan to the user. At this time, the user reviews the learning materials displayed on the device and proceeds with their learning at their own pace. The materials are presented visually in HTML or PDF format, and the user can access them through on-screen interaction.

[0200] Step 4:

[0201] During the learning process, the device uses its built-in camera and microphone to collect the user's facial expressions and voice, generating emotion data. The input facial expression images and voice data are preprocessed using libraries such as OpenCV and librosa, and converted into features that represent the user's emotional state.

[0202] Step 5:

[0203] Emotional data is sent to a server, which uses an emotion analysis engine to analyze the data. In this analysis step, the user's emotional state is determined in real time. The resulting emotional state score is used to adjust the educational plan.

[0204] Step 6:

[0205] The server generates prompt messages using a generative AI model based on the sentiment analysis results and adjusts the learning content. This adjustment involves data processing that changes the difficulty level and format of the learning materials according to the emotional state. For example, if the system determines that the user is bored, the learning plan is updated to select more engaging materials. This adjusted plan is then sent back to the terminal and presented to the user.

[0206] (Application Example 2)

[0207] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0208] Providing an individually optimized learning experience for each user in educational programs is challenging. In particular, the lack of learning adjustments that take into account the user's emotional state leads to problems such as decreased motivation and hindered effective information absorption. Therefore, there is a need to develop a system that dynamically adjusts learning content based on emotions, enabling users to learn in the most optimal state.

[0209] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0210] In this invention, the server includes an input mechanism for inputting the user's educational goals and existing knowledge level, a generation mechanism for generating an individually optimized educational plan based on the data obtained from the input mechanism, a presentation mechanism for presenting the generated educational plan to the user, an emotion recognition mechanism for recognizing the user's emotions, and an adjustment mechanism for dynamically adjusting the learning content based on the recognized emotions. As a result, the user's emotions are reflected in the learning content, providing an appropriately adjusted learning experience, enabling effective knowledge acquisition and improved motivation to learn.

[0211] An "input mechanism" is a device for inputting the user's educational goals and existing knowledge level.

[0212] A "generation mechanism" is a device that constructs individually optimized educational plans based on data obtained from an input mechanism.

[0213] A "presentation mechanism" is a device that displays and presents the generated educational plan to the user.

[0214] An "emotion recognition mechanism" is a device that captures and analyzes emotions using the user's facial expressions and voice.

[0215] A "regulation mechanism" is a device that dynamically changes the learning content based on recognized emotion data.

[0216] A "receiving mechanism" is a device that receives and manages questions from users.

[0217] An "interactive generation mechanism" is a device that generates the optimal answer based on the question handled by the receiving mechanism and the user's emotional state.

[0218] A "distribution mechanism" is a device that distributes the generated responses to users.

[0219] A "data collection mechanism" is a device for collecting user learning data and emotional data.

[0220] An "analysis mechanism" is a device that generates learning feedback based on collected data.

[0221] A "support mechanism" is a device that supports users and improves the quality of learning based on feedback and sentiment analysis results provided by an analysis mechanism.

[0222] This system utilizes multiple interconnected mechanisms to optimize learning while taking user emotions into account. The server first receives the user's educational goals and existing knowledge level through an input mechanism. Based on this data, a generation mechanism develops an individually optimized educational plan. The educational plan is then presented to the user by a presentation mechanism.

[0223] The device is equipped with a camera and microphone, and this hardware is used by an emotion recognition mechanism to analyze the user's facial expressions and voice. The analysis results are sent to a server, where the emotional state is determined in real time. The adjustment mechanism dynamically adjusts the learning plan based on the determined emotional data, providing the user with appropriate learning materials and feedback.

[0224] Furthermore, when a user enters a question, the receiving mechanism receives the question, and the server uses an interactive generation mechanism to generate an answer that takes emotional state into account. This answer is then presented to the user through the delivery mechanism.

[0225] The system also uses a collection mechanism to aggregate learning and sentiment data. This data is then analyzed by an analysis mechanism, and appropriate feedback is provided, thereby enhancing the user's learning experience through a support mechanism.

[0226] For example, when elementary school students are learning kanji, if the emotion recognition mechanism detects that the child is bored, the adjustment mechanism can change the learning plan and present game-style exercises. This helps maintain interest and improves learning effectiveness. By using a generative AI model, the generated content and prompts can be flexibly modified.

[0227] A concrete example of a prompt message would be, "When the user is confused, please gently explain basic mathematical concepts."

[0228] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0229] Step 1:

[0230] The user inputs their educational goals and existing knowledge level into an input mechanism via a terminal. The input data is sent to a server and analyzed by a generation mechanism. Based on the analysis results, an individually optimized educational plan is generated. Here, the input is the educational goals and knowledge level, and the output is the individually optimized educational plan.

[0231] Step 2:

[0232] The server presents the generated educational plan on the terminal using a presentation mechanism. The terminal displays the learning materials in a format that is easy for the user to understand, and the user begins learning. The input is the generated educational plan, and the output is the presentation of the learning materials to the user.

[0233] Step 3:

[0234] The device uses its built-in camera and microphone to collect the user's facial expressions and voice in real time using an emotion recognition mechanism. The collected data is sent to a server for analysis. The input for this step is facial expression and voice data, and the output is the emotion recognition result.

[0235] Step 4:

[0236] The server uses an adjustment mechanism to dynamically adjust the learning plan based on the emotion recognition results obtained from the emotion recognition mechanism. For example, if the server detects that the user is bored, it selects more interactive learning materials. Here, the input is the emotion recognition result, and the output is the updated learning plan.

[0237] Step 5:

[0238] When a user enters a question during learning, the device sends the question to the server via a receiving mechanism. The server uses an interactive generation mechanism to generate the best possible answer, taking into account the question and the user's emotional state. In this step, the input is the user's question and emotional state, and the output is the generated answer.

[0239] Step 6:

[0240] The server sends the generated response to the terminal through the delivery mechanism and presents it to the user. The terminal displays the response in a format that is easy for the user to understand. The input is the generated response, and the output is the presentation of the response.

[0241] Step 7:

[0242] The device continuously collects training data and sentiment data using a collection mechanism and sends it to the server. The server processes the collected data using an analysis mechanism and generates feedback based on the results. The inputs to this step are training data and sentiment data, and the outputs are the analysis results and feedback.

[0243] Step 8:

[0244] The server utilizes the results of the analysis mechanism through the support mechanism to provide appropriate assistance to the user. This ensures that appropriate information and support are presented based on the user's learning progress. The input is the analysis results and feedback, and the output is learning support.

[0245] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0246] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0247] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0248] [Second Embodiment]

[0249] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0250] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0251] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0252] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0253] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0254] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0255] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0256] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0257] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0258] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0259] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0260] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0261] This invention realizes an educational system that provides an individually optimized learning experience using an information processing device. This system mainly consists of server, terminal, and user elements.

[0262] First, the user accesses the learning platform through their device and enters information about their educational goals and current knowledge level. The device has a mechanism to send the user's input to the server.

[0263] Upon receiving information from the user, the server uses AI-based generation methods to create an optimized educational plan for that user. This plan includes curriculum, materials, and progress goals, and is customized to the learner's specific needs.

[0264] Next, the server sends the generated learning plan to the terminal, and the user proceeds with learning according to this plan. If the user encounters any questions during the learning process, they can send questions using the terminal. The server passes these questions to an interactive generation system, which generates appropriate answers in real time and provides them to the terminal.

[0265] Furthermore, the server continuously collects data on learning activities. This data is analyzed to monitor user progress and provide necessary feedback. The analysis results are displayed on the device as feedback, allowing users to adjust their learning plans and check their progress.

[0266] As a concrete example, consider a user learning mathematics accessing this system. The user aims to improve a specific mathematical skill and enters "I have basic knowledge of differential calculus" into the terminal. Based on this information, the server generates a curriculum that helps the user progress from the basics of differential calculus to more advanced topics. If the user encounters a problem they don't understand during this process, they can ask a question through the terminal, and the server will provide hints and solution steps to help them solve the problem. In this way, individual learning needs can be met, and an effective learning experience can be obtained.

[0267] The following describes the processing flow.

[0268] Step 1:

[0269] The user accesses the learning platform using their device and registers or logs in. The device sends the authentication information entered by the user to the server.

[0270] Step 2:

[0271] The server compares the transmitted authentication information with records in the database. If authentication is successful, it prepares the user's profile and displays the dashboard on the terminal.

[0272] Step 3:

[0273] The user inputs their learning goals and current knowledge level from their device. The device then sends this information to the server.

[0274] Step 4:

[0275] The server uses an AI model based on the received user information to generate an individually optimized educational plan. The generated plan includes a curriculum and teaching materials tailored to the user's specific needs.

[0276] Step 5:

[0277] The server sends the generated educational plan to the terminal. The terminal displays the plan to the user.

[0278] Step 6:

[0279] The user progresses through the learning process according to the displayed educational plan. If a question arises during the learning process, the user sends the question to the server via their device.

[0280] Step 7:

[0281] The server receives a question from the user and immediately generates an appropriate answer using interactive generation means. The generated answer is sent to the terminal and provided to the user.

[0282] Step 8:

[0283] The server periodically collects user learning progress and activity data. This data is then analyzed to understand user performance and provide necessary feedback.

[0284] Step 9:

[0285] Based on the analysis results, the server generates individual feedback and sends it to the terminal. The user can adjust their learning based on this feedback and make further improvements.

[0286] (Example 1)

[0287] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0288] In conventional education systems, it has been difficult to provide an optimal education plan according to the educational goals and knowledge levels of individual learners. Also, it has been impossible to immediately respond to learners' questions and effectively manage the learning progress using the data obtained through learning activities. For this reason, the lack of individualized learning experiences has been an issue.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0290] In this invention, the server includes an input means for inputting the educational goals and existing knowledge levels of the learner, a generation means for formulating an individually optimized educational plan based on the information obtained from the input means, and a presentation means for presenting the educational plan formulated using the generation AI model to the learner. Thereby, it becomes possible to provide an individually optimized educational plan to the learner and realize an effective learning experience.

[0291] The "input means" is an interface for the learner to input their educational goals and existing knowledge levels into the system.

[0292] The "generation means" is a process and function for formulating an individually optimized educational plan based on the information obtained from the learner.

[0293] A "generative AI model" is an algorithm that uses artificial intelligence to generate optimal educational plans and problem-solving answers based on learner data.

[0294] "Presentation methods" refer to system components that display formulated educational plans and generated responses to learners in an easily understandable manner.

[0295] "Progress management means" refer to methods and functions for promoting learning and managing progress based on a formulated educational plan.

[0296] A "receiving means" refers to a means of communication for receiving questions and feedback from learners.

[0297] An "interactive generation method" is a dynamic AI process that generates appropriate answers in real time to received questions.

[0298] "Means of delivery" refers to the methods and functions used to provide the generated answers and feedback to the learner.

[0299] A "collection method" is a mechanism for recording and storing learner activity data.

[0300] "Analysis means" refers to the process and function of analyzing collected data and providing learning feedback.

[0301] "Support measures" refer to methods and functions for improving learning plans based on analysis results and supporting learners' progress.

[0302] This system is an educational system that provides an individually optimized learning experience and consists of servers, terminals, and users.

[0303] The server receives data from the terminal in order to accept and receive the educational goals and existing knowledge levels of the learner. The terminal has the role of transmitting the information input by the user to the server. Standard web interfaces or dedicated applications are used for this data reception.

[0304] The server inputs the received information into an AI-based generative AI model to generate an individually optimized educational plan. This generative AI model can create an educational plan that recommends an optimal curriculum and teaching materials for the user by utilizing machine learning algorithms and natural language processing.

[0305] The generated educational plan is transmitted from the server to the terminal again, and the terminal presents the plan to the user through the user interface. This user interface displays learning programs and goals in a visually understandable form, promoting effective learning.

[0306] If the user wants to ask a question during learning, they can send the question as a prompt text to the server via the terminal. For example, something like "Please teach me how to apply the chain rule of differentiation." The server inputs this question into the generative AI model, generates an appropriate answer in real time, and returns it to the terminal.

[0307] The server continuously collects the user's learning activities. The collected data is analyzed to evaluate the progress of learning and provide necessary feedback. The feedback is displayed as feedback information on the user interface, and the user can grasp the progress of their own learning and adjust the learning plan as appropriate.

[0308] As a specific example, when a user learning mathematics inputs that they "have basic knowledge of differentiation," the server generates an appropriate curriculum from basic to advanced content. For prompts regarding problems the user has difficulty with during that process, the server provides hints and solution steps for problem-solving.

[0309] In this way, the system improves the effectiveness and efficiency of learning by providing an optimal learning experience tailored to individual learning needs.

[0310] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0311] Step 1:

[0312] The terminal provides an interface for users to input their educational goals and current knowledge level. For example, the user might input information such as "I have basic knowledge of differential calculus." This information is sent to the server in digital format. The server stores the received information in a database.

[0313] Step 2:

[0314] The server inputs the received user information into an AI-based generation system. Based on this data, the generating AI model creates an optimal educational plan. An educational plan, including curriculum and material selection, is created and stored on the server.

[0315] Step 3:

[0316] The server sends the generated learning plan to the terminal, which then displays the plan in its user interface. The user can then begin learning according to the presented plan. The terminal supports learning with visual progress bars and reminder functions.

[0317] Step 4:

[0318] If a user has a question during the learning process, they can enter it through their device. For example, they might enter a prompt such as, "Please explain how to apply the chain rule of differentiation." The device then sends this question to the server.

[0319] Step 5:

[0320] The server passes the received prompt to an interactive generation mechanism, which uses a generation AI model to generate an appropriate response. The server quickly organizes the generated response and sends it back to the terminal.

[0321] Step 6:

[0322] The terminal displays the answers received from the server in the user interface. The user can use the presented answers to resolve their questions and continue learning.

[0323] Step 7:

[0324] The server collects user learning activity and progress data. Detailed data, such as learning time and content completion status, is recorded and stored in a database.

[0325] Step 8:

[0326] The server analyzes the collected data and generates feedback to evaluate the learning effect. The analysis results are provided to the user through the user interface, indicating areas for improvement and successes.

[0327] Step 9:

[0328] Users can adjust their learning plans based on the feedback they receive. This promotes more effective learning and allows them to modify their actions to achieve their goals.

[0329] (Application Example 1)

[0330] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0331] In today's urban environment, it is difficult to effectively learn about local culture and history while meeting individual learning needs. Traditional methods tend to focus on general educational content, lacking the provision of knowledge specific to particular regions. As a result, users have limited access to locally relevant information, leading to decreased learning efficiency.

[0332] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0333] In this invention, the server includes input means for inputting the user's educational goals and existing knowledge level, guidance means for providing instructional courses tailored to local learning content, and dialogue means for generating and presenting answers in real time during the learning process. This enables users to receive a region-specific and optimized educational plan and effectively realize a learning experience in a specific location within a city.

[0334] An "information processing device" is an electronic system that integrates the input, generation, and output of data.

[0335] An "input method" is a function that allows the system to receive the user's educational goals and knowledge level.

[0336] "Generation method" refers to the process of creating an optimized educational plan for the user based on input data.

[0337] "Presentation method" refers to a method that can provide the generated educational plan to the user visually or audibly.

[0338] A "guidance method" is a mechanism that presents users with learning content or instructional courses related to a specific region.

[0339] A "dialogue mechanism" is a function that allows users and the system to exchange information in real time and generate answers to questions.

[0340] A "receiving means" is an interface for receiving questions and data from users.

[0341] "Means of provision" refers to a mechanism that supplies generated responses and information to users.

[0342] "Location information processing means" refers to technology for appropriately guiding learners through learning content based on geographical information.

[0343] "Collection method" refers to the function of collecting user learning data and incorporating it into the system.

[0344] "Analysis means" refers to the process of analyzing collected data and generating learning feedback.

[0345] A "support system" is a mechanism that assists and promotes the user's learning activities based on the feedback provided.

[0346] "Visualization means" refers to a function that visually generates and displays information related to learning activities.

[0347] This invention is an individually optimized learning support system within a smart city, implemented using an information processing device. An example thereof is shown below.

[0348] The server first receives information about educational goals and existing knowledge levels from the user's smartphone or other device. The device then allows the user to input educational topics of interest and regionally relevant educational goals through an input mechanism.

[0349] Next, the server uses a generation mechanism based on the received information to create an optimized educational plan for the user. This generation process utilizes technologies such as OpenAI's generative AI model to generate content that matches the user's learning needs. This plan includes region-specific instructional courses and related learning content.

[0350] The generated educational plan is presented to the user through guidance methods. Specifically, learning guidance based on geographical location information is provided via a smartphone application, and when the user reaches a specific landmark or learning point, information about the local culture and history is provided.

[0351] During the learning process, if a user has a question, they can send it to the server using their device. The server receives the question using a dialogue mechanism and provides an appropriate answer. Real-time information exchange makes the learning experience more interactive and effective.

[0352] Furthermore, learning data is continuously collected by the collection method, and this data is analyzed by the analysis method. The results of this analysis are provided to the user's device as feedback, and the user can adjust their learning plan based on this feedback.

[0353] As a concrete example, consider a user who is interested in "Edo period architecture" and selects this topic. As the user explores the area with their smartphone, the historical background and characteristics of each landmark are displayed on the device. An example of a prompt message could be, "Generate historical information and a learning quiz about Edo period architecture. The user is at a specific landmark." This message could be instructed to the server.

[0354] In this way, users can gain valuable local knowledge while pursuing individually optimized learning.

[0355] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0356] Step 1:

[0357] The device starts up, and the user enters their educational goals and existing knowledge level. This input is done using the device's UI, and it is also possible to select learning topics relevant to the region. The device then sends this information to the server.

[0358] Step 2:

[0359] The server passes the received educational objectives and knowledge level data to the generation mechanism. The generation mechanism uses a generative AI model to generate an optimal educational plan based on the input. This process involves data calculations to create a curriculum and teaching materials that meet the user's needs.

[0360] Step 3:

[0361] The server sends the created educational plan back to the terminal via a guidance system. The terminal receives this information and presents it to the user visually or audibly. This information includes the order in which learning should proceed and information related to specific geographical locations.

[0362] Step 4:

[0363] As users progress through their learning, if they encounter a question, they can use their device to send it to the server. This process generates a prompt and interactively communicates it to the server.

[0364] Step 5:

[0365] The server receives questions using dialogue mechanisms and generates appropriate answers using interactive generation mechanisms. The generation AI model is then utilized again to form answers in real time.

[0366] Step 6:

[0367] The generated answers are sent from the server to the terminal, which then presents the answers to the user. This deepens the user's understanding of the learning material.

[0368] Step 7:

[0369] Training data is automatically collected from the device and sent to the server. The server analyzes the data obtained by the collection device and generates feedback using the analysis device.

[0370] Step 8:

[0371] The generated feedback is sent to the device via a support system and presented to the user. This allows the user to check their learning progress and adjust their learning plan as needed.

[0372] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0373] This invention combines an information processing device with a function to recognize and reflect the user's emotions in an educational system that provides a personalized learning experience to users. This system consists of a server, a terminal, a user, and an emotion engine.

[0374] First, the user accesses the learning platform via their device and enters their personal educational goals and existing knowledge level. The device sends this information to the server. The server uses AI based on the user information to generate a personalized educational plan, which is then sent to the device and presented to the user.

[0375] Next, as the user progresses through the learning process, the device collects emotional data from the user's facial expressions and voice. This emotional data is sent to the server's emotion engine. The emotion engine analyzes this data in real time to determine the user's emotional state.

[0376] The server adjusts the learning content based on the analysis results obtained from the emotion engine. For example, if the server determines that the user is bored, it immediately updates the learning plan and changes to more interesting materials. Similarly, if the user is stressed, the content can be simplified to reduce the load.

[0377] As a concrete example, suppose a user is solving a math problem and the emotion engine detects that the user is confused. In this case, the server immediately adjusts the difficulty of the problem and presents clearer explanations and examples through the terminal.

[0378] Furthermore, when a user asks a question, the server considers not only the content of the question but also the user's emotional state, and uses interactive generation methods to generate an answer tailored to the user's psychological state. This allows users to continue learning with greater confidence.

[0379] This system analyzes both learning data and emotional data to provide personalized feedback, thereby efficiently and effectively improving the user's learning experience.

[0380] The following describes the processing flow.

[0381] Step 1:

[0382] The user accesses the learning platform using their device and registers or logs in. The device sends the authentication information entered by the user to the server.

[0383] Step 2:

[0384] The server verifies the submitted authentication information against the database to perform authentication. If authentication is successful, it prepares the user's profile and displays the dashboard on the terminal.

[0385] Step 3:

[0386] The user uses a terminal to input learning objectives and their current knowledge level. The terminal sends the entered information to the server.

[0387] Step 4:

[0388] The server uses artificial intelligence to generate a personalized educational plan based on the received user information. This plan includes recommendations for curriculum and teaching materials.

[0389] Step 5:

[0390] The server sends the generated learning plan to the terminal. The terminal displays the plan to the user and the user begins learning.

[0391] Step 6:

[0392] The user progresses through the learning process according to the provided educational plan. During the learning process, the device analyzes the user's facial expressions and voice, and sends emotional data to the server.

[0393] Step 7:

[0394] The server analyzes the emotional data sent from the terminal using an emotion engine to determine the user's emotional state.

[0395] Step 8:

[0396] The server adaptively adjusts the learning content based on the analysis results from the emotion engine. For example, if it determines that the user is experiencing stress, it adjusts the difficulty level of the learning content.

[0397] Step 9:

[0398] The server analyzes the user's learning progress and sentiment data together, generates personalized feedback, and sends it to the device. The user then uses this feedback to continue their learning activities.

[0399] (Example 2)

[0400] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0401] Traditional education systems have struggled with learning efficiency and sustainability because they have not adequately optimized the learning experience by considering the emotional state and psychological aspects of individual users. Furthermore, they can only provide fixed teaching materials, making it difficult to dynamically adjust materials according to users' interests and levels of understanding.

[0402] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0403] In this invention, the server includes a collection means for collecting user emotional data, an analysis means for analyzing the emotional data and determining the emotional state, and an adjustment means for dynamically adjusting the educational plan generated based on the determined emotional state. This makes it possible to appropriately adjust the educational plan according to the user's emotional state and provide a more individually optimized learning experience.

[0404] An "information processing device" is a device or system for inputting, processing, and outputting data, and has a mechanism for performing calculations in response to user operations.

[0405] A "user" is an individual or group that receives services using an information processing device, and is an entity that seeks to gain a learning experience through an educational platform.

[0406] An "educational plan" is a learning course structured based on the user's educational goals and knowledge level, and is an educational program optimized to meet individual needs.

[0407] "Emotional data" refers to indicators of a user's psychological state obtained from their facial expressions and voice, and represents emotional responses perceived in real time.

[0408] An "analysis tool" is a component that has the function of analyzing information based on collected data, and plays a role in clarifying the user's state and needs.

[0409] "Adjustment mechanisms" refer to mechanisms for dynamically changing educational plans and teaching materials based on analysis results, and are functions for optimizing the user's learning experience.

[0410] "Feedback" refers to information that provides responses and advice based on the user's learning progress, understanding, and emotional state, and serves as instructions or guidelines to enhance learning effectiveness.

[0411] This invention uses an information processing device as part of an educational system to provide users with an optimized learning experience. This system consists of a server, a terminal, a user interface, and an emotion analysis engine. Detailed embodiments for carrying out this invention are described below.

[0412] First, users access the educational platform using their device and input specific educational goals and their current knowledge level. This device can be a standard computer or smart device that connects to the server via a web browser. The interface also includes a camera and microphone, allowing for real-time detection of the user's facial expressions and voice. This information is sent to the server as foundational data to gain a detailed understanding of the user's educational needs.

[0413] The server uses a generation AI model based on the received user data to generate individually optimized learning plans. For example, machine learning frameworks such as TensorFlow and PyTorch can be used for this generation. The generated learning plan is sent to the terminal and presented to the user. Specifically, learning materials in HTML or PDF format are displayed, allowing the user to proceed with their learning while viewing them.

[0414] During the learning process, the device analyzes the user's facial expressions and voice and sends them to the server as emotion data. The server processes this data using an emotion analysis engine to determine the user's emotional state. This process can be carried out using libraries such as OpenCV or librosa to capture the characteristics of emotions.

[0415] For example, if the server detects that a user is experiencing confusion while solving a math problem, it dynamically adjusts the learning plan, lowering the difficulty level and providing clearer explanations and examples. This helps maintain the user's motivation to learn. A concrete example of this operation is when a user says, "I don't understand the chain rule for differentiation." In this case, the server generates a prompt message saying, "For the next step, please provide video materials that visually explain the basics of linear algebra," and selects appropriate materials to send to the terminal.

[0416] This system enables a more enriching learning experience by providing feedback that captures the nuances of the user's needs.

[0417] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0418] Step 1:

[0419] Users access the educational platform using their device and input educational goals and existing knowledge levels. This information is sent from the device to the server in JSON format. The input data is parsed on the server and used as foundational data to generate individually optimized educational plans. The device prompts the user for confirmation via an interface to complete the data entry.

[0420] Step 2:

[0421] The server generates an educational plan using a generated AI model based on the received user data. This process involves data calculations using a machine learning framework (e.g., TensorFlow or PyTorch) to select the most suitable learning materials and learning sequence based on the user's knowledge level and goals. The resulting educational plan is then sent from the server to the terminal.

[0422] Step 3:

[0423] The device presents the received educational plan to the user. At this time, the user reviews the learning materials displayed on the device and proceeds with their learning at their own pace. The materials are presented visually in HTML or PDF format, and the user can access them through on-screen interaction.

[0424] Step 4:

[0425] During the learning process, the device uses its built-in camera and microphone to collect the user's facial expressions and voice, generating emotion data. The input facial expression images and voice data are preprocessed using libraries such as OpenCV and librosa, and converted into features that represent the user's emotional state.

[0426] Step 5:

[0427] Emotional data is sent to a server, which uses an emotion analysis engine to analyze the data. In this analysis step, the user's emotional state is determined in real time. The resulting emotional state score is used to adjust the educational plan.

[0428] Step 6:

[0429] The server generates prompt messages using a generative AI model based on the sentiment analysis results and adjusts the learning content. This adjustment involves data processing that changes the difficulty level and format of the learning materials according to the emotional state. For example, if the system determines that the user is bored, the learning plan is updated to select more engaging materials. This adjusted plan is then sent back to the terminal and presented to the user.

[0430] (Application Example 2)

[0431] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0432] Providing an individually optimized learning experience for each user in educational programs is challenging. In particular, the lack of learning adjustments that take into account the user's emotional state leads to problems such as decreased motivation and hindered effective information absorption. Therefore, there is a need to develop a system that dynamically adjusts learning content based on emotions, enabling users to learn in the most optimal state.

[0433] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0434] In this invention, the server includes an input mechanism for inputting the user's educational goals and existing knowledge level, a generation mechanism for generating an individually optimized educational plan based on the data obtained from the input mechanism, a presentation mechanism for presenting the generated educational plan to the user, an emotion recognition mechanism for recognizing the user's emotions, and an adjustment mechanism for dynamically adjusting the learning content based on the recognized emotions. As a result, the user's emotions are reflected in the learning content, providing an appropriately adjusted learning experience, enabling effective knowledge acquisition and improved motivation to learn.

[0435] An "input mechanism" is a device for inputting the user's educational goals and existing knowledge level.

[0436] A "generation mechanism" is a device that constructs individually optimized educational plans based on data obtained from an input mechanism.

[0437] A "presentation mechanism" is a device that displays and presents the generated educational plan to the user.

[0438] An "emotion recognition mechanism" is a device that captures and analyzes emotions using the user's facial expressions and voice.

[0439] A "regulation mechanism" is a device that dynamically changes the learning content based on recognized emotion data.

[0440] A "receiving mechanism" is a device that receives and manages questions from users.

[0441] An "interactive generation mechanism" is a device that generates the optimal answer based on the question handled by the receiving mechanism and the user's emotional state.

[0442] A "distribution mechanism" is a device that distributes the generated responses to users.

[0443] A "data collection mechanism" is a device for collecting user learning data and emotional data.

[0444] An "analysis mechanism" is a device that generates learning feedback based on collected data.

[0445] A "support mechanism" is a device that supports users and improves the quality of learning based on feedback and sentiment analysis results provided by an analysis mechanism.

[0446] This system utilizes multiple interconnected mechanisms to optimize learning while taking user emotions into account. The server first receives the user's educational goals and existing knowledge level through an input mechanism. Based on this data, a generation mechanism develops an individually optimized educational plan. The educational plan is then presented to the user by a presentation mechanism.

[0447] The device is equipped with a camera and microphone, and this hardware is used by an emotion recognition mechanism to analyze the user's facial expressions and voice. The analysis results are sent to a server, where the emotional state is determined in real time. The adjustment mechanism dynamically adjusts the learning plan based on the determined emotional data, providing the user with appropriate learning materials and feedback.

[0448] Furthermore, when a user enters a question, the receiving mechanism receives the question, and the server uses an interactive generation mechanism to generate an answer that takes emotional state into account. This answer is then presented to the user through the delivery mechanism.

[0449] The system also uses a collection mechanism to aggregate learning and sentiment data. This data is then analyzed by an analysis mechanism, and appropriate feedback is provided, thereby enhancing the user's learning experience through a support mechanism.

[0450] For example, when elementary school students are learning kanji, if the emotion recognition mechanism detects that the child is bored, the adjustment mechanism can change the learning plan and present game-style exercises. This helps maintain interest and improves learning effectiveness. By using a generative AI model, the generated content and prompts can be flexibly modified.

[0451] A concrete example of a prompt message would be, "When the user is confused, please gently explain basic mathematical concepts."

[0452] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0453] Step 1:

[0454] The user inputs their educational goals and existing knowledge level into an input mechanism via a terminal. The input data is sent to a server and analyzed by a generation mechanism. Based on the analysis results, an individually optimized educational plan is generated. Here, the input is the educational goals and knowledge level, and the output is the individually optimized educational plan.

[0455] Step 2:

[0456] The server presents the generated educational plan on the terminal using a presentation mechanism. The terminal displays the learning materials in a format that is easy for the user to understand, and the user begins learning. The input is the generated educational plan, and the output is the presentation of the learning materials to the user.

[0457] Step 3:

[0458] The device uses its built-in camera and microphone to collect the user's facial expressions and voice in real time using an emotion recognition mechanism. The collected data is sent to a server for analysis. The input for this step is facial expression and voice data, and the output is the emotion recognition result.

[0459] Step 4:

[0460] The server uses an adjustment mechanism to dynamically adjust the learning plan based on the emotion recognition results obtained from the emotion recognition mechanism. For example, if the server detects that the user is bored, it selects more interactive learning materials. Here, the input is the emotion recognition result, and the output is the updated learning plan.

[0461] Step 5:

[0462] When a user enters a question during learning, the device sends the question to the server via a receiving mechanism. The server uses an interactive generation mechanism to generate the best possible answer, taking into account the question and the user's emotional state. In this step, the input is the user's question and emotional state, and the output is the generated answer.

[0463] Step 6:

[0464] The server sends the generated response to the terminal through the delivery mechanism and presents it to the user. The terminal displays the response in a format that is easy for the user to understand. The input is the generated response, and the output is the presentation of the response.

[0465] Step 7:

[0466] The device continuously collects training data and sentiment data using a collection mechanism and sends it to the server. The server processes the collected data using an analysis mechanism and generates feedback based on the results. The inputs to this step are training data and sentiment data, and the outputs are the analysis results and feedback.

[0467] Step 8:

[0468] The server utilizes the results of the analysis mechanism through the support mechanism to provide appropriate assistance to the user. This ensures that appropriate information and support are presented based on the user's learning progress. The input is the analysis results and feedback, and the output is learning support.

[0469] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0470] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0471] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0472] [Third Embodiment]

[0473] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0474] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0475] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0476] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0477] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0478] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0479] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0480] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0481] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0482] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0483] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0484] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0485] This invention realizes an educational system that provides an individually optimized learning experience using an information processing device. This system mainly consists of server, terminal, and user elements.

[0486] First, the user accesses the learning platform through their device and enters information about their educational goals and current knowledge level. The device has a mechanism to send the user's input to the server.

[0487] Upon receiving information from the user, the server uses AI-based generation methods to create an optimized educational plan for that user. This plan includes curriculum, materials, and progress goals, and is customized to the learner's specific needs.

[0488] Next, the server sends the generated learning plan to the terminal, and the user proceeds with learning according to this plan. If the user encounters any questions during the learning process, they can send questions using the terminal. The server passes these questions to an interactive generation system, which generates appropriate answers in real time and provides them to the terminal.

[0489] Furthermore, the server continuously collects data on learning activities. This data is analyzed to monitor user progress and provide necessary feedback. The analysis results are displayed on the device as feedback, allowing users to adjust their learning plans and check their progress.

[0490] As a concrete example, consider a user learning mathematics accessing this system. The user aims to improve a specific mathematical skill and enters "I have basic knowledge of differential calculus" into the terminal. Based on this information, the server generates a curriculum that helps the user progress from the basics of differential calculus to more advanced topics. If the user encounters a problem they don't understand during this process, they can ask a question through the terminal, and the server will provide hints and solution steps to help them solve the problem. In this way, individual learning needs can be met, and an effective learning experience can be obtained.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] The user accesses the learning platform using their device and registers or logs in. The device sends the authentication information entered by the user to the server.

[0494] Step 2:

[0495] The server compares the transmitted authentication information with records in the database. If authentication is successful, it prepares the user's profile and displays the dashboard on the terminal.

[0496] Step 3:

[0497] The user inputs their learning goals and current knowledge level from their device. The device then sends this information to the server.

[0498] Step 4:

[0499] The server uses an AI model based on the received user information to generate an individually optimized educational plan. The generated plan includes a curriculum and teaching materials tailored to the user's specific needs.

[0500] Step 5:

[0501] The server sends the generated educational plan to the terminal. The terminal displays the plan to the user.

[0502] Step 6:

[0503] The user progresses through the learning process according to the displayed educational plan. If a question arises during the learning process, the user sends the question to the server via their device.

[0504] Step 7:

[0505] The server receives a question from the user and immediately generates an appropriate answer using interactive generation means. The generated answer is sent to the terminal and provided to the user.

[0506] Step 8:

[0507] The server periodically collects user learning progress and activity data. This data is then analyzed to understand user performance and provide necessary feedback.

[0508] Step 9:

[0509] The server generates individual feedback based on the analysis results and sends it to the terminal. The user can then adjust the learning process based on this feedback and make further improvements.

[0510] (Example 1)

[0511] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0512] Traditional education systems have struggled to provide optimal learning plans tailored to the individual learning goals and knowledge levels of each student. Furthermore, they have been unable to promptly address students' questions or effectively manage learning progress using data obtained through learning activities. Therefore, a lack of personalized learning experiences has been a significant challenge.

[0513] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0514] In this invention, the server includes an input means for inputting the learner's educational goals and current knowledge level, a generation means for formulating an individually optimized educational plan based on the information obtained from the input means, and a presentation means for presenting the educational plan formulated using a generation AI model to the learner. This makes it possible to provide learners with individually optimized educational plans and realize an effective learning experience.

[0515] An "input method" is an interface that allows learners to input their educational goals and current knowledge levels into the system.

[0516] "Generative means" refers to the process and function of formulating individually optimized educational plans based on information obtained from learners.

[0517] A "generative AI model" is an algorithm that uses artificial intelligence to generate optimal educational plans and problem-solving answers based on learner data.

[0518] "Presentation methods" refer to system components that display formulated educational plans and generated responses to learners in an easily understandable manner.

[0519] "Progress management means" refer to methods and functions for promoting learning and managing progress based on a formulated educational plan.

[0520] A "receiving means" refers to a means of communication for receiving questions and feedback from learners.

[0521] An "interactive generation method" is a dynamic AI process that generates appropriate answers in real time to received questions.

[0522] "Means of delivery" refers to the methods and functions used to provide the generated answers and feedback to the learner.

[0523] A "collection method" is a mechanism for recording and storing learner activity data.

[0524] "Analysis means" refers to the process and function of analyzing collected data and providing learning feedback.

[0525] "Support measures" refer to methods and functions for improving learning plans based on analysis results and supporting learners' progress.

[0526] This system is an educational system that provides an individually optimized learning experience and consists of servers, terminals, and users.

[0527] The server receives data from the terminal to input and accept learners' educational goals and current knowledge levels. The terminal's role is to send the information entered by the user to the server. Standard web interfaces or dedicated applications are used for this data reception.

[0528] The server inputs the received information into an AI-based generative AI model to generate individually optimized educational plans. This generative AI model utilizes machine learning algorithms and natural language processing to create educational plans that recommend the most suitable curriculum and materials for each user.

[0529] The generated educational plan is sent back from the server to the terminal, which then presents the plan to the user through a user interface. This user interface displays the learning program and objectives in a visually easy-to-understand format, promoting effective learning.

[0530] If a user wants to ask a question during the learning process, they can send the question to the server as a prompt via their device. For example, "Please explain how to apply the chain law of differentiation." The server inputs this question into the generating AI model, generates an appropriate answer in real time, and returns it to the device.

[0531] The server continuously collects user learning activities. The collected data is analyzed to evaluate learning progress and provide necessary feedback. The feedback is displayed as feedback information in the user interface, allowing users to understand their learning progress and adjust their learning plan as needed.

[0532] For example, if a user learning mathematics enters "I have basic knowledge of differential calculus," the server will generate an appropriate curriculum ranging from basic to advanced content. In response to any problems the user encounters during this process, the server will provide hints and solution steps to help them overcome the challenges.

[0533] In this way, the system improves the effectiveness and efficiency of learning by providing an optimal learning experience tailored to individual learning needs.

[0534] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0535] Step 1:

[0536] The terminal provides an interface for users to input their educational goals and current knowledge level. For example, the user might input information such as "I have basic knowledge of differential calculus." This information is sent to the server in digital format. The server stores the received information in a database.

[0537] Step 2:

[0538] The server inputs the received user information into an AI-based generation system. Based on this data, the generating AI model creates an optimal educational plan. An educational plan, including curriculum and material selection, is created and stored on the server.

[0539] Step 3:

[0540] The server sends the generated learning plan to the terminal, which then displays the plan in its user interface. The user can then begin learning according to the presented plan. The terminal supports learning with visual progress bars and reminder functions.

[0541] Step 4:

[0542] If a user has a question during the learning process, they can enter it through their device. For example, they might enter a prompt such as, "Please explain how to apply the chain rule of differentiation." The device then sends this question to the server.

[0543] Step 5:

[0544] The server passes the received prompt to an interactive generation mechanism, which uses a generation AI model to generate an appropriate response. The server quickly organizes the generated response and sends it back to the terminal.

[0545] Step 6:

[0546] The terminal displays the answers received from the server in the user interface. The user can use the presented answers to resolve their questions and continue learning.

[0547] Step 7:

[0548] The server collects user learning activity and progress data. Detailed data, such as learning time and content completion status, is recorded and stored in a database.

[0549] Step 8:

[0550] The server analyzes the collected data and generates feedback to evaluate the learning effect. The analysis results are provided to the user through the user interface, indicating areas for improvement and successes.

[0551] Step 9:

[0552] Users can adjust their learning plans based on the feedback they receive. This promotes more effective learning and allows them to modify their actions to achieve their goals.

[0553] (Application Example 1)

[0554] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0555] In today's urban environment, it is difficult to effectively learn about local culture and history while meeting individual learning needs. Traditional methods tend to focus on general educational content, lacking the provision of knowledge specific to particular regions. As a result, users have limited access to locally relevant information, leading to decreased learning efficiency.

[0556] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0557] In this invention, the server includes input means for inputting the user's educational goals and existing knowledge level, guidance means for providing instructional courses tailored to local learning content, and dialogue means for generating and presenting answers in real time during the learning process. This enables users to receive a region-specific and optimized educational plan and effectively realize a learning experience in a specific location within a city.

[0558] An "information processing device" is an electronic system that integrates the input, generation, and output of data.

[0559] An "input method" is a function that allows the system to receive the user's educational goals and knowledge level.

[0560] "Generation method" refers to the process of creating an optimized educational plan for the user based on input data.

[0561] "Presentation method" refers to a method that can provide the generated educational plan to the user visually or audibly.

[0562] A "guidance method" is a mechanism that presents users with learning content or instructional courses related to a specific region.

[0563] A "dialogue mechanism" is a function that allows users and the system to exchange information in real time and generate answers to questions.

[0564] A "receiving means" is an interface for receiving questions and data from users.

[0565] "Means of provision" refers to a mechanism that supplies generated responses and information to users.

[0566] "Location information processing means" refers to technology for appropriately guiding learners through learning content based on geographical information.

[0567] "Collection method" refers to the function of collecting user learning data and incorporating it into the system.

[0568] "Analysis means" refers to the process of analyzing collected data and generating learning feedback.

[0569] A "support system" is a mechanism that assists and promotes the user's learning activities based on the feedback provided.

[0570] "Visualization means" refers to a function that visually generates and displays information related to learning activities.

[0571] This invention is an individually optimized learning support system within a smart city, implemented using an information processing device. An example thereof is shown below.

[0572] The server first receives information about educational goals and existing knowledge levels from the user's smartphone or other device. The device then allows the user to input educational topics of interest and regionally relevant educational goals through an input mechanism.

[0573] Next, the server uses a generation mechanism based on the received information to create an optimized educational plan for the user. This generation process utilizes technologies such as OpenAI's generative AI model to generate content that matches the user's learning needs. This plan includes region-specific instructional courses and related learning content.

[0574] The generated educational plan is presented to the user through guidance methods. Specifically, learning guidance based on geographical location information is provided via a smartphone application, and when the user reaches a specific landmark or learning point, information about the local culture and history is provided.

[0575] During the learning process, if a user has a question, they can send it to the server using their device. The server receives the question using a dialogue mechanism and provides an appropriate answer. Real-time information exchange makes the learning experience more interactive and effective.

[0576] Furthermore, learning data is continuously collected by the collection method, and this data is analyzed by the analysis method. The results of this analysis are provided to the user's device as feedback, and the user can adjust their learning plan based on this feedback.

[0577] As a concrete example, consider a user who is interested in "Edo period architecture" and selects this topic. As the user explores the area with their smartphone, the historical background and characteristics of each landmark are displayed on the device. An example of a prompt message could be, "Generate historical information and a learning quiz about Edo period architecture. The user is at a specific landmark." This message could be instructed to the server.

[0578] In this way, users can gain valuable local knowledge while pursuing individually optimized learning.

[0579] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0580] Step 1:

[0581] The device starts up, and the user enters their educational goals and existing knowledge level. This input is done using the device's UI, and it is also possible to select learning topics relevant to the region. The device then sends this information to the server.

[0582] Step 2:

[0583] The server passes the received educational objectives and knowledge level data to the generation mechanism. The generation mechanism uses a generative AI model to generate an optimal educational plan based on the input. This process involves data calculations to create a curriculum and teaching materials that meet the user's needs.

[0584] Step 3:

[0585] The server sends the created educational plan back to the terminal via a guidance system. The terminal receives this information and presents it to the user visually or audibly. This information includes the order in which learning should proceed and information related to specific geographical locations.

[0586] Step 4:

[0587] As users progress through their learning, if they encounter a question, they can use their device to send it to the server. This process generates a prompt and interactively communicates it to the server.

[0588] Step 5:

[0589] The server receives questions using dialogue mechanisms and generates appropriate answers using interactive generation mechanisms. The generation AI model is then utilized again to form answers in real time.

[0590] Step 6:

[0591] The generated answers are sent from the server to the terminal, which then presents the answers to the user. This deepens the user's understanding of the learning material.

[0592] Step 7:

[0593] Training data is automatically collected from the device and sent to the server. The server analyzes the data obtained by the collection device and generates feedback using the analysis device.

[0594] Step 8:

[0595] The generated feedback is sent to the device via a support system and presented to the user. This allows the user to check their learning progress and adjust their learning plan as needed.

[0596] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0597] This invention combines an information processing device with a function to recognize and reflect the user's emotions in an educational system that provides a personalized learning experience to users. This system consists of a server, a terminal, a user, and an emotion engine.

[0598] First, the user accesses the learning platform via their device and enters their personal educational goals and existing knowledge level. The device sends this information to the server. The server uses AI based on the user information to generate a personalized educational plan, which is then sent to the device and presented to the user.

[0599] Next, as the user progresses through the learning process, the device collects emotional data from the user's facial expressions and voice. This emotional data is sent to the server's emotion engine. The emotion engine analyzes this data in real time to determine the user's emotional state.

[0600] The server adjusts the learning content based on the analysis results obtained from the emotion engine. For example, if the server determines that the user is bored, it immediately updates the learning plan and changes to more interesting materials. Similarly, if the user is stressed, the content can be simplified to reduce the load.

[0601] As a concrete example, suppose a user is solving a math problem and the emotion engine detects that the user is confused. In this case, the server immediately adjusts the difficulty of the problem and presents clearer explanations and examples through the terminal.

[0602] Furthermore, when a user asks a question, the server considers not only the content of the question but also the user's emotional state, and uses interactive generation methods to generate an answer tailored to the user's psychological state. This allows users to continue learning with greater confidence.

[0603] This system analyzes both learning data and emotional data to provide personalized feedback, thereby efficiently and effectively improving the user's learning experience.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] The user accesses the learning platform using their device and registers or logs in. The device sends the authentication information entered by the user to the server.

[0607] Step 2:

[0608] The server verifies the submitted authentication information against the database to perform authentication. If authentication is successful, it prepares the user's profile and displays the dashboard on the terminal.

[0609] Step 3:

[0610] The user uses a terminal to input learning objectives and their current knowledge level. The terminal sends the entered information to the server.

[0611] Step 4:

[0612] The server uses artificial intelligence to generate a personalized educational plan based on the received user information. This plan includes recommendations for curriculum and teaching materials.

[0613] Step 5:

[0614] The server sends the generated learning plan to the terminal. The terminal displays the plan to the user and the user begins learning.

[0615] Step 6:

[0616] The user progresses through the learning process according to the provided educational plan. During the learning process, the device analyzes the user's facial expressions and voice, and sends emotional data to the server.

[0617] Step 7:

[0618] The server analyzes the emotional data sent from the terminal using an emotion engine to determine the user's emotional state.

[0619] Step 8:

[0620] The server adaptively adjusts the learning content based on the analysis results from the emotion engine. For example, if it determines that the user is experiencing stress, it adjusts the difficulty level of the learning content.

[0621] Step 9:

[0622] The server analyzes the user's learning progress and sentiment data together, generates personalized feedback, and sends it to the device. The user then uses this feedback to continue their learning activities.

[0623] (Example 2)

[0624] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0625] Traditional education systems have struggled with learning efficiency and sustainability because they have not adequately optimized the learning experience by considering the emotional state and psychological aspects of individual users. Furthermore, they can only provide fixed teaching materials, making it difficult to dynamically adjust materials according to users' interests and levels of understanding.

[0626] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0627] In this invention, the server includes a collection means for collecting user emotional data, an analysis means for analyzing the emotional data and determining the emotional state, and an adjustment means for dynamically adjusting the educational plan generated based on the determined emotional state. This makes it possible to appropriately adjust the educational plan according to the user's emotional state and provide a more individually optimized learning experience.

[0628] An "information processing device" is a device or system for inputting, processing, and outputting data, and has a mechanism for performing calculations in response to user operations.

[0629] A "user" is an individual or group that receives services using an information processing device, and is an entity that seeks to gain a learning experience through an educational platform.

[0630] An "educational plan" is a learning course structured based on the user's educational goals and knowledge level, and is an educational program optimized to meet individual needs.

[0631] "Emotional data" refers to indicators of a user's psychological state obtained from their facial expressions and voice, and represents emotional responses perceived in real time.

[0632] An "analysis tool" is a component that has the function of analyzing information based on collected data, and plays a role in clarifying the user's state and needs.

[0633] "Adjustment mechanisms" refer to mechanisms for dynamically changing educational plans and teaching materials based on analysis results, and are functions for optimizing the user's learning experience.

[0634] "Feedback" refers to information that provides responses and advice based on the user's learning progress, understanding, and emotional state, and serves as instructions or guidelines to enhance learning effectiveness.

[0635] This invention uses an information processing device as part of an educational system to provide users with an optimized learning experience. This system consists of a server, a terminal, a user interface, and an emotion analysis engine. Detailed embodiments for carrying out this invention are described below.

[0636] First, users access the educational platform using their device and input specific educational goals and their current knowledge level. This device can be a standard computer or smart device that connects to the server via a web browser. The interface also includes a camera and microphone, allowing for real-time detection of the user's facial expressions and voice. This information is sent to the server as foundational data to gain a detailed understanding of the user's educational needs.

[0637] The server uses a generation AI model based on the received user data to generate individually optimized learning plans. For example, machine learning frameworks such as TensorFlow and PyTorch can be used for this generation. The generated learning plan is sent to the terminal and presented to the user. Specifically, learning materials in HTML or PDF format are displayed, allowing the user to proceed with their learning while viewing them.

[0638] During the learning process, the device analyzes the user's facial expressions and voice and sends them to the server as emotion data. The server processes this data using an emotion analysis engine to determine the user's emotional state. This process can be carried out using libraries such as OpenCV or librosa to capture the characteristics of emotions.

[0639] For example, if the server detects that a user is experiencing confusion while solving a math problem, it dynamically adjusts the learning plan, lowering the difficulty level and providing clearer explanations and examples. This helps maintain the user's motivation to learn. A concrete example of this operation is when a user says, "I don't understand the chain rule for differentiation." In this case, the server generates a prompt message saying, "For the next step, please provide video materials that visually explain the basics of linear algebra," and selects appropriate materials to send to the terminal.

[0640] This system enables a more enriching learning experience by providing feedback that captures the nuances of the user's needs.

[0641] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0642] Step 1:

[0643] Users access the educational platform using their device and input educational goals and existing knowledge levels. This information is sent from the device to the server in JSON format. The input data is parsed on the server and used as foundational data to generate individually optimized educational plans. The device prompts the user for confirmation via an interface to complete the data entry.

[0644] Step 2:

[0645] The server generates an educational plan using a generated AI model based on the received user data. This process involves data calculations using a machine learning framework (e.g., TensorFlow or PyTorch) to select the most suitable learning materials and learning sequence based on the user's knowledge level and goals. The resulting educational plan is then sent from the server to the terminal.

[0646] Step 3:

[0647] The device presents the received educational plan to the user. At this time, the user reviews the learning materials displayed on the device and proceeds with their learning at their own pace. The materials are presented visually in HTML or PDF format, and the user can access them through on-screen interaction.

[0648] Step 4:

[0649] During the learning process, the device uses its built-in camera and microphone to collect the user's facial expressions and voice, generating emotion data. The input facial expression images and voice data are preprocessed using libraries such as OpenCV and librosa, and converted into features that represent the user's emotional state.

[0650] Step 5:

[0651] Emotional data is sent to a server, which uses an emotion analysis engine to analyze the data. In this analysis step, the user's emotional state is determined in real time. The resulting emotional state score is used to adjust the educational plan.

[0652] Step 6:

[0653] The server generates prompt messages using a generative AI model based on the sentiment analysis results and adjusts the learning content. This adjustment involves data processing that changes the difficulty level and format of the learning materials according to the emotional state. For example, if the system determines that the user is bored, the learning plan is updated to select more engaging materials. This adjusted plan is then sent back to the terminal and presented to the user.

[0654] (Application Example 2)

[0655] Next, we will explain Application Example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0656] Providing an individually optimized learning experience for each user in educational programs is challenging. In particular, the lack of learning adjustments that take into account the user's emotional state leads to problems such as decreased motivation and hindered effective information absorption. Therefore, there is a need to develop a system that dynamically adjusts learning content based on emotions, enabling users to learn in the most optimal state.

[0657] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0658] In this invention, the server includes an input mechanism for inputting the user's educational goals and existing knowledge level, a generation mechanism for generating an individually optimized educational plan based on the data obtained from the input mechanism, a presentation mechanism for presenting the generated educational plan to the user, an emotion recognition mechanism for recognizing the user's emotions, and an adjustment mechanism for dynamically adjusting the learning content based on the recognized emotions. As a result, the user's emotions are reflected in the learning content, providing an appropriately adjusted learning experience, enabling effective knowledge acquisition and improved motivation to learn.

[0659] An "input mechanism" is a device for inputting the user's educational goals and existing knowledge level.

[0660] A "generation mechanism" is a device that constructs individually optimized educational plans based on data obtained from an input mechanism.

[0661] A "presentation mechanism" is a device that displays and presents the generated educational plan to the user.

[0662] An "emotion recognition mechanism" is a device that captures and analyzes emotions using the user's facial expressions and voice.

[0663] A "regulation mechanism" is a device that dynamically changes the learning content based on recognized emotion data.

[0664] A "receiving mechanism" is a device that receives and manages questions from users.

[0665] An "interactive generation mechanism" is a device that generates the optimal answer based on the question handled by the receiving mechanism and the user's emotional state.

[0666] A "distribution mechanism" is a device that distributes the generated responses to users.

[0667] A "data collection mechanism" is a device for collecting user learning data and emotional data.

[0668] An "analysis mechanism" is a device that generates learning feedback based on collected data.

[0669] A "support mechanism" is a device that supports users and improves the quality of learning based on feedback and sentiment analysis results provided by an analysis mechanism.

[0670] This system utilizes multiple interconnected mechanisms to optimize learning while taking user emotions into account. The server first receives the user's educational goals and existing knowledge level through an input mechanism. Based on this data, a generation mechanism develops an individually optimized educational plan. The educational plan is then presented to the user by a presentation mechanism.

[0671] The device is equipped with a camera and microphone, and this hardware is used by an emotion recognition mechanism to analyze the user's facial expressions and voice. The analysis results are sent to a server, where the emotional state is determined in real time. The adjustment mechanism dynamically adjusts the learning plan based on the determined emotional data, providing the user with appropriate learning materials and feedback.

[0672] Furthermore, when a user enters a question, the receiving mechanism receives the question, and the server uses an interactive generation mechanism to generate an answer that takes emotional state into account. This answer is then presented to the user through the delivery mechanism.

[0673] The system also uses a collection mechanism to aggregate learning and sentiment data. This data is then analyzed by an analysis mechanism, and appropriate feedback is provided, thereby enhancing the user's learning experience through a support mechanism.

[0674] For example, when elementary school students are learning kanji, if the emotion recognition mechanism detects that the child is bored, the adjustment mechanism can change the learning plan and present game-style exercises. This helps maintain interest and improves learning effectiveness. By using a generative AI model, the generated content and prompts can be flexibly modified.

[0675] A concrete example of a prompt message would be, "When the user is confused, please gently explain basic mathematical concepts."

[0676] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0677] Step 1:

[0678] The user inputs their educational goals and existing knowledge level into an input mechanism via a terminal. The input data is sent to a server and analyzed by a generation mechanism. Based on the analysis results, an individually optimized educational plan is generated. Here, the input is the educational goals and knowledge level, and the output is the individually optimized educational plan.

[0679] Step 2:

[0680] The server presents the generated educational plan on the terminal using a presentation mechanism. The terminal displays the learning materials in a format that is easy for the user to understand, and the user begins learning. The input is the generated educational plan, and the output is the presentation of the learning materials to the user.

[0681] Step 3:

[0682] The device uses its built-in camera and microphone to collect the user's facial expressions and voice in real time using an emotion recognition mechanism. The collected data is sent to a server for analysis. The input for this step is facial expression and voice data, and the output is the emotion recognition result.

[0683] Step 4:

[0684] The server uses an adjustment mechanism to dynamically adjust the learning plan based on the emotion recognition results obtained from the emotion recognition mechanism. For example, if the server detects that the user is bored, it selects more interactive learning materials. Here, the input is the emotion recognition result, and the output is the updated learning plan.

[0685] Step 5:

[0686] When a user enters a question during learning, the device sends the question to the server via a receiving mechanism. The server uses an interactive generation mechanism to generate the best possible answer, taking into account the question and the user's emotional state. In this step, the input is the user's question and emotional state, and the output is the generated answer.

[0687] Step 6:

[0688] The server sends the generated response to the terminal through the delivery mechanism and presents it to the user. The terminal displays the response in a format that is easy for the user to understand. The input is the generated response, and the output is the presentation of the response.

[0689] Step 7:

[0690] The device continuously collects training data and sentiment data using a collection mechanism and sends it to the server. The server processes the collected data using an analysis mechanism and generates feedback based on the results. The inputs to this step are training data and sentiment data, and the outputs are the analysis results and feedback.

[0691] Step 8:

[0692] The server utilizes the results of the analysis mechanism through the support mechanism to provide appropriate assistance to the user. This ensures that appropriate information and support are presented based on the user's learning progress. The input is the analysis results and feedback, and the output is learning support.

[0693] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0694] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0695] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0696] [Fourth Embodiment]

[0697] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0698] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0699] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0700] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0701] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0702] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0703] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0704] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0705] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0706] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0707] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0708] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0709] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0710] This invention realizes an educational system that provides an individually optimized learning experience using an information processing device. This system mainly consists of server, terminal, and user elements.

[0711] First, the user accesses the learning platform through their device and enters information about their educational goals and current knowledge level. The device has a mechanism to send the user's input to the server.

[0712] Upon receiving information from the user, the server uses AI-based generation methods to create an optimized educational plan for that user. This plan includes curriculum, materials, and progress goals, and is customized to the learner's specific needs.

[0713] Next, the server sends the generated learning plan to the terminal, and the user proceeds with learning according to this plan. If the user encounters any questions during the learning process, they can send questions using the terminal. The server passes these questions to an interactive generation system, which generates appropriate answers in real time and provides them to the terminal.

[0714] Furthermore, the server continuously collects data on learning activities. This data is analyzed to monitor user progress and provide necessary feedback. The analysis results are displayed on the device as feedback, allowing users to adjust their learning plans and check their progress.

[0715] As a concrete example, consider a user learning mathematics accessing this system. The user aims to improve a specific mathematical skill and enters "I have basic knowledge of differential calculus" into the terminal. Based on this information, the server generates a curriculum that helps the user progress from the basics of differential calculus to more advanced topics. If the user encounters a problem they don't understand during this process, they can ask a question through the terminal, and the server will provide hints and solution steps to help them solve the problem. In this way, individual learning needs can be met, and an effective learning experience can be obtained.

[0716] The following describes the processing flow.

[0717] Step 1:

[0718] The user accesses the learning platform using their device and registers or logs in. The device sends the authentication information entered by the user to the server.

[0719] Step 2:

[0720] The server compares the transmitted authentication information with records in the database. If authentication is successful, it prepares the user's profile and displays the dashboard on the terminal.

[0721] Step 3:

[0722] The user inputs their learning goals and current knowledge level from their device. The device then sends this information to the server.

[0723] Step 4:

[0724] The server uses an AI model based on the received user information to generate an individually optimized educational plan. The generated plan includes a curriculum and teaching materials tailored to the user's specific needs.

[0725] Step 5:

[0726] The server sends the generated educational plan to the terminal. The terminal displays the plan to the user.

[0727] Step 6:

[0728] The user progresses through the learning process according to the displayed educational plan. If a question arises during the learning process, the user sends the question to the server via their device.

[0729] Step 7:

[0730] The server receives a question from the user and immediately generates an appropriate answer using interactive generation means. The generated answer is sent to the terminal and provided to the user.

[0731] Step 8:

[0732] The server periodically collects user learning progress and activity data. This data is then analyzed to understand user performance and provide necessary feedback.

[0733] Step 9:

[0734] The server generates individual feedback based on the analysis results and sends it to the terminal. The user can then adjust the learning process based on this feedback and make further improvements.

[0735] (Example 1)

[0736] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0737] Traditional education systems have struggled to provide optimal learning plans tailored to the individual learning goals and knowledge levels of each student. Furthermore, they have been unable to promptly address students' questions or effectively manage learning progress using data obtained through learning activities. Therefore, a lack of personalized learning experiences has been a significant challenge.

[0738] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0739] In this invention, the server includes an input means for inputting the learner's educational goals and current knowledge level, a generation means for formulating an individually optimized educational plan based on the information obtained from the input means, and a presentation means for presenting the educational plan formulated using a generation AI model to the learner. This makes it possible to provide learners with individually optimized educational plans and realize an effective learning experience.

[0740] An "input method" is an interface that allows learners to input their educational goals and current knowledge levels into the system.

[0741] "Generative means" refers to the process and function of formulating individually optimized educational plans based on information obtained from learners.

[0742] A "generative AI model" is an algorithm that uses artificial intelligence to generate optimal educational plans and problem-solving answers based on learner data.

[0743] "Presentation methods" refer to system components that display formulated educational plans and generated responses to learners in an easily understandable manner.

[0744] "Progress management means" refer to methods and functions for promoting learning and managing progress based on a formulated educational plan.

[0745] A "receiving means" refers to a means of communication for receiving questions and feedback from learners.

[0746] An "interactive generation method" is a dynamic AI process that generates appropriate answers in real time to received questions.

[0747] "Means of delivery" refers to the methods and functions used to provide the generated answers and feedback to the learner.

[0748] A "collection method" is a mechanism for recording and storing learner activity data.

[0749] "Analysis means" refers to the process and function of analyzing collected data and providing learning feedback.

[0750] "Support measures" refer to methods and functions for improving learning plans based on analysis results and supporting learners' progress.

[0751] This system is an educational system that provides an individually optimized learning experience and consists of servers, terminals, and users.

[0752] The server receives data from the terminal to input and accept learners' educational goals and current knowledge levels. The terminal's role is to send the information entered by the user to the server. Standard web interfaces or dedicated applications are used for this data reception.

[0753] The server inputs the received information into an AI-based generative AI model to generate individually optimized educational plans. This generative AI model utilizes machine learning algorithms and natural language processing to create educational plans that recommend the most suitable curriculum and materials for each user.

[0754] The generated educational plan is sent back from the server to the terminal, which then presents the plan to the user through a user interface. This user interface displays the learning program and objectives in a visually easy-to-understand format, promoting effective learning.

[0755] If a user wants to ask a question during the learning process, they can send the question to the server as a prompt via their device. For example, "Please explain how to apply the chain law of differentiation." The server inputs this question into the generating AI model, generates an appropriate answer in real time, and returns it to the device.

[0756] The server continuously collects user learning activities. The collected data is analyzed to evaluate learning progress and provide necessary feedback. The feedback is displayed as feedback information in the user interface, allowing users to understand their learning progress and adjust their learning plan as needed.

[0757] For example, if a user learning mathematics enters "I have basic knowledge of differential calculus," the server will generate an appropriate curriculum ranging from basic to advanced content. In response to any problems the user encounters during this process, the server will provide hints and solution steps to help them overcome the challenges.

[0758] In this way, the system improves the effectiveness and efficiency of learning by providing an optimal learning experience tailored to individual learning needs.

[0759] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0760] Step 1:

[0761] The terminal provides an interface for users to input their educational goals and current knowledge level. For example, the user might input information such as "I have basic knowledge of differential calculus." This information is sent to the server in digital format. The server stores the received information in a database.

[0762] Step 2:

[0763] The server inputs the received user information into an AI-based generation system. Based on this data, the generating AI model creates an optimal educational plan. An educational plan, including curriculum and material selection, is created and stored on the server.

[0764] Step 3:

[0765] The server sends the generated learning plan to the terminal, which then displays the plan in its user interface. The user can then begin learning according to the presented plan. The terminal supports learning with visual progress bars and reminder functions.

[0766] Step 4:

[0767] If a user has a question during the learning process, they can enter it through their device. For example, they might enter a prompt such as, "Please explain how to apply the chain rule of differentiation." The device then sends this question to the server.

[0768] Step 5:

[0769] The server passes the received prompt to an interactive generation mechanism, which uses a generation AI model to generate an appropriate response. The server quickly organizes the generated response and sends it back to the terminal.

[0770] Step 6:

[0771] The terminal displays the answers received from the server in the user interface. The user can use the presented answers to resolve their questions and continue learning.

[0772] Step 7:

[0773] The server collects user learning activity and progress data. Detailed data, such as learning time and content completion status, is recorded and stored in a database.

[0774] Step 8:

[0775] The server analyzes the collected data and generates feedback to evaluate the learning effect. The analysis results are provided to the user through the user interface, indicating areas for improvement and successes.

[0776] Step 9:

[0777] Users can adjust their learning plans based on the feedback they receive. This promotes more effective learning and allows them to modify their actions to achieve their goals.

[0778] (Application Example 1)

[0779] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0780] In today's urban environment, it is difficult to effectively learn about local culture and history while meeting individual learning needs. Traditional methods tend to focus on general educational content, lacking the provision of knowledge specific to particular regions. As a result, users have limited access to locally relevant information, leading to decreased learning efficiency.

[0781] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0782] In this invention, the server includes input means for inputting the user's educational goals and existing knowledge level, guidance means for providing instructional courses tailored to local learning content, and dialogue means for generating and presenting answers in real time during the learning process. This enables users to receive a region-specific and optimized educational plan and effectively realize a learning experience in a specific location within a city.

[0783] An "information processing device" is an electronic system that integrates the input, generation, and output of data.

[0784] An "input method" is a function that allows the system to receive the user's educational goals and knowledge level.

[0785] "Generation method" refers to the process of creating an optimized educational plan for the user based on input data.

[0786] "Presentation method" refers to a method that can provide the generated educational plan to the user visually or audibly.

[0787] A "guidance method" is a mechanism that presents users with learning content or instructional courses related to a specific region.

[0788] A "dialogue mechanism" is a function that allows users and the system to exchange information in real time and generate answers to questions.

[0789] A "receiving means" is an interface for receiving questions and data from users.

[0790] "Means of provision" refers to a mechanism that supplies generated responses and information to users.

[0791] "Location information processing means" refers to technology for appropriately guiding learners through learning content based on geographical information.

[0792] "Collection method" refers to the function of collecting user learning data and incorporating it into the system.

[0793] "Analysis means" refers to the process of analyzing collected data and generating learning feedback.

[0794] A "support system" is a mechanism that assists and promotes the user's learning activities based on the feedback provided.

[0795] "Visualization means" refers to a function that visually generates and displays information related to learning activities.

[0796] This invention is an individually optimized learning support system within a smart city, implemented using an information processing device. An example thereof is shown below.

[0797] The server first receives information about educational goals and existing knowledge levels from the user's smartphone or other device. The device then allows the user to input educational topics of interest and regionally relevant educational goals through an input mechanism.

[0798] Next, the server uses a generation mechanism based on the received information to create an optimized educational plan for the user. This generation process utilizes technologies such as OpenAI's generative AI model to generate content that matches the user's learning needs. This plan includes region-specific instructional courses and related learning content.

[0799] The generated educational plan is presented to the user through guidance methods. Specifically, learning guidance based on geographical location information is provided via a smartphone application, and when the user reaches a specific landmark or learning point, information about the local culture and history is provided.

[0800] During the learning process, if a user has a question, they can send it to the server using their device. The server receives the question using a dialogue mechanism and provides an appropriate answer. Real-time information exchange makes the learning experience more interactive and effective.

[0801] Furthermore, learning data is continuously collected by the collection method, and this data is analyzed by the analysis method. The results of this analysis are provided to the user's device as feedback, and the user can adjust their learning plan based on this feedback.

[0802] As a concrete example, consider a user who is interested in "Edo period architecture" and selects this topic. As the user explores the area with their smartphone, the historical background and characteristics of each landmark are displayed on the device. An example of a prompt message could be, "Generate historical information and a learning quiz about Edo period architecture. The user is at a specific landmark." This message could be instructed to the server.

[0803] In this way, users can gain valuable local knowledge while pursuing individually optimized learning.

[0804] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0805] Step 1:

[0806] The device starts up, and the user enters their educational goals and existing knowledge level. This input is done using the device's UI, and it is also possible to select learning topics relevant to the region. The device then sends this information to the server.

[0807] Step 2:

[0808] The server passes the received educational objectives and knowledge level data to the generation mechanism. The generation mechanism uses a generative AI model to generate an optimal educational plan based on the input. This process involves data calculations to create a curriculum and teaching materials that meet the user's needs.

[0809] Step 3:

[0810] The server sends the created educational plan back to the terminal via a guidance system. The terminal receives this information and presents it to the user visually or audibly. This information includes the order in which learning should proceed and information related to specific geographical locations.

[0811] Step 4:

[0812] As users progress through their learning, if they encounter a question, they can use their device to send it to the server. This process generates a prompt and interactively communicates it to the server.

[0813] Step 5:

[0814] The server receives questions using dialogue mechanisms and generates appropriate answers using interactive generation mechanisms. The generation AI model is then utilized again to form answers in real time.

[0815] Step 6:

[0816] The generated answers are sent from the server to the terminal, which then presents the answers to the user. This deepens the user's understanding of the learning material.

[0817] Step 7:

[0818] Training data is automatically collected from the device and sent to the server. The server analyzes the data obtained by the collection device and generates feedback using the analysis device.

[0819] Step 8:

[0820] The generated feedback is sent to the device via a support system and presented to the user. This allows the user to check their learning progress and adjust their learning plan as needed.

[0821] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0822] This invention combines an information processing device with a function to recognize and reflect the user's emotions in an educational system that provides a personalized learning experience to users. This system consists of a server, a terminal, a user, and an emotion engine.

[0823] First, the user accesses the learning platform via their device and enters their personal educational goals and existing knowledge level. The device sends this information to the server. The server uses AI based on the user information to generate a personalized educational plan, which is then sent to the device and presented to the user.

[0824] Next, as the user progresses through the learning process, the device collects emotional data from the user's facial expressions and voice. This emotional data is sent to the server's emotion engine. The emotion engine analyzes this data in real time to determine the user's emotional state.

[0825] The server adjusts the learning content based on the analysis results obtained from the emotion engine. For example, if the server determines that the user is bored, it immediately updates the learning plan and changes to more interesting materials. Similarly, if the user is stressed, the content can be simplified to reduce the load.

[0826] As a concrete example, suppose a user is solving a math problem and the emotion engine detects that the user is confused. In this case, the server immediately adjusts the difficulty of the problem and presents clearer explanations and examples through the terminal.

[0827] Furthermore, when a user asks a question, the server considers not only the content of the question but also the user's emotional state, and uses interactive generation methods to generate an answer tailored to the user's psychological state. This allows users to continue learning with greater confidence.

[0828] This system analyzes both learning data and emotional data to provide personalized feedback, thereby efficiently and effectively improving the user's learning experience.

[0829] The following describes the processing flow.

[0830] Step 1:

[0831] The user accesses the learning platform using their device and registers or logs in. The device sends the authentication information entered by the user to the server.

[0832] Step 2:

[0833] The server verifies the submitted authentication information against the database to perform authentication. If authentication is successful, it prepares the user's profile and displays the dashboard on the terminal.

[0834] Step 3:

[0835] The user uses a terminal to input learning objectives and their current knowledge level. The terminal sends the entered information to the server.

[0836] Step 4:

[0837] The server uses artificial intelligence to generate a personalized educational plan based on the received user information. This plan includes recommendations for curriculum and teaching materials.

[0838] Step 5:

[0839] The server sends the generated learning plan to the terminal. The terminal displays the plan to the user and the user begins learning.

[0840] Step 6:

[0841] The user progresses through the learning process according to the provided educational plan. During the learning process, the device analyzes the user's facial expressions and voice, and sends emotional data to the server.

[0842] Step 7:

[0843] The server analyzes the emotional data sent from the terminal using an emotion engine to determine the user's emotional state.

[0844] Step 8:

[0845] The server adaptively adjusts the learning content based on the analysis results from the emotion engine. For example, if it determines that the user is experiencing stress, it adjusts the difficulty level of the learning content.

[0846] Step 9:

[0847] The server analyzes the user's learning progress and sentiment data together, generates personalized feedback, and sends it to the device. The user then uses this feedback to continue their learning activities.

[0848] (Example 2)

[0849] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0850] Traditional education systems have struggled with learning efficiency and sustainability because they have not adequately optimized the learning experience by considering the emotional state and psychological aspects of individual users. Furthermore, they can only provide fixed teaching materials, making it difficult to dynamically adjust materials according to users' interests and levels of understanding.

[0851] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0852] In this invention, the server includes a collection means for collecting user emotional data, an analysis means for analyzing the emotional data and determining the emotional state, and an adjustment means for dynamically adjusting the educational plan generated based on the determined emotional state. This makes it possible to appropriately adjust the educational plan according to the user's emotional state and provide a more individually optimized learning experience.

[0853] An "information processing device" is a device or system for inputting, processing, and outputting data, and has a mechanism for performing calculations in response to user operations.

[0854] A "user" is an individual or group that receives services using an information processing device, and is an entity that seeks to gain a learning experience through an educational platform.

[0855] An "educational plan" is a learning course structured based on the user's educational goals and knowledge level, and is an educational program optimized to meet individual needs.

[0856] "Emotional data" refers to indicators of a user's psychological state obtained from their facial expressions and voice, and represents emotional responses perceived in real time.

[0857] An "analysis tool" is a component that has the function of analyzing information based on collected data, and plays a role in clarifying the user's state and needs.

[0858] "Adjustment mechanisms" refer to mechanisms for dynamically changing educational plans and teaching materials based on analysis results, and are functions for optimizing the user's learning experience.

[0859] "Feedback" refers to information that provides responses and advice based on the user's learning progress, understanding, and emotional state, and serves as instructions or guidelines to enhance learning effectiveness.

[0860] This invention uses an information processing device as part of an educational system to provide users with an optimized learning experience. This system consists of a server, a terminal, a user interface, and an emotion analysis engine. Detailed embodiments for carrying out this invention are described below.

[0861] First, users access the educational platform using their device and input specific educational goals and their current knowledge level. This device can be a standard computer or smart device that connects to the server via a web browser. The interface also includes a camera and microphone, allowing for real-time detection of the user's facial expressions and voice. This information is sent to the server as foundational data to gain a detailed understanding of the user's educational needs.

[0862] The server uses a generation AI model based on the received user data to generate individually optimized learning plans. For example, machine learning frameworks such as TensorFlow and PyTorch can be used for this generation. The generated learning plan is sent to the terminal and presented to the user. Specifically, learning materials in HTML or PDF format are displayed, allowing the user to proceed with their learning while viewing them.

[0863] During the learning process, the device analyzes the user's facial expressions and voice and sends them to the server as emotion data. The server processes this data using an emotion analysis engine to determine the user's emotional state. This process can be carried out using libraries such as OpenCV or librosa to capture the characteristics of emotions.

[0864] For example, if the server detects that a user is experiencing confusion while solving a math problem, it dynamically adjusts the learning plan, lowering the difficulty level and providing clearer explanations and examples. This helps maintain the user's motivation to learn. A concrete example of this operation is when a user says, "I don't understand the chain rule for differentiation." In this case, the server generates a prompt message saying, "For the next step, please provide video materials that visually explain the basics of linear algebra," and selects appropriate materials to send to the terminal.

[0865] This system enables a more enriching learning experience by providing feedback that captures the nuances of the user's needs.

[0866] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0867] Step 1:

[0868] Users access the educational platform using their device and input educational goals and existing knowledge levels. This information is sent from the device to the server in JSON format. The input data is parsed on the server and used as foundational data to generate individually optimized educational plans. The device prompts the user for confirmation via an interface to complete the data entry.

[0869] Step 2:

[0870] The server generates an educational plan using a generated AI model based on the received user data. This process involves data calculations using a machine learning framework (e.g., TensorFlow or PyTorch) to select the most suitable learning materials and learning sequence based on the user's knowledge level and goals. The resulting educational plan is then sent from the server to the terminal.

[0871] Step 3:

[0872] The device presents the received educational plan to the user. At this time, the user reviews the learning materials displayed on the device and proceeds with their learning at their own pace. The materials are presented visually in HTML or PDF format, and the user can access them through on-screen interaction.

[0873] Step 4:

[0874] During the learning process, the device uses its built-in camera and microphone to collect the user's facial expressions and voice, generating emotion data. The input facial expression images and voice data are preprocessed using libraries such as OpenCV and librosa, and converted into features that represent the user's emotional state.

[0875] Step 5:

[0876] Emotional data is sent to a server, which uses an emotion analysis engine to analyze the data. In this analysis step, the user's emotional state is determined in real time. The resulting emotional state score is used to adjust the educational plan.

[0877] Step 6:

[0878] The server generates prompt messages using a generative AI model based on the sentiment analysis results and adjusts the learning content. This adjustment involves data processing that changes the difficulty level and format of the learning materials according to the emotional state. For example, if the system determines that the user is bored, the learning plan is updated to select more engaging materials. This adjusted plan is then sent back to the terminal and presented to the user.

[0879] (Application Example 2)

[0880] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0881] Providing an individually optimized learning experience for each user in educational programs is challenging. In particular, the lack of learning adjustments that take into account the user's emotional state leads to problems such as decreased motivation and hindered effective information absorption. Therefore, there is a need to develop a system that dynamically adjusts learning content based on emotions, enabling users to learn in the most optimal state.

[0882] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0883] In this invention, the server includes an input mechanism for inputting the user's educational goals and existing knowledge level, a generation mechanism for generating an individually optimized educational plan based on the data obtained from the input mechanism, a presentation mechanism for presenting the generated educational plan to the user, an emotion recognition mechanism for recognizing the user's emotions, and an adjustment mechanism for dynamically adjusting the learning content based on the recognized emotions. As a result, the user's emotions are reflected in the learning content, providing an appropriately adjusted learning experience, enabling effective knowledge acquisition and improved motivation to learn.

[0884] An "input mechanism" is a device for inputting the user's educational goals and existing knowledge level.

[0885] A "generation mechanism" is a device that constructs individually optimized educational plans based on data obtained from an input mechanism.

[0886] A "presentation mechanism" is a device that displays and presents the generated educational plan to the user.

[0887] An "emotion recognition mechanism" is a device that captures and analyzes emotions using the user's facial expressions and voice.

[0888] A "regulation mechanism" is a device that dynamically changes the learning content based on recognized emotion data.

[0889] A "receiving mechanism" is a device that receives and manages questions from users.

[0890] An "interactive generation mechanism" is a device that generates the optimal answer based on the question handled by the receiving mechanism and the user's emotional state.

[0891] A "distribution mechanism" is a device that distributes the generated responses to users.

[0892] A "data collection mechanism" is a device for collecting user learning data and emotional data.

[0893] An "analysis mechanism" is a device that generates learning feedback based on collected data.

[0894] A "support mechanism" is a device that supports users and improves the quality of learning based on feedback and sentiment analysis results provided by an analysis mechanism.

[0895] This system utilizes multiple interconnected mechanisms to optimize learning while taking user emotions into account. The server first receives the user's educational goals and existing knowledge level through an input mechanism. Based on this data, a generation mechanism develops an individually optimized educational plan. The educational plan is then presented to the user by a presentation mechanism.

[0896] The device is equipped with a camera and microphone, and this hardware is used by an emotion recognition mechanism to analyze the user's facial expressions and voice. The analysis results are sent to a server, where the emotional state is determined in real time. The adjustment mechanism dynamically adjusts the learning plan based on the determined emotional data, providing the user with appropriate learning materials and feedback.

[0897] Furthermore, when a user enters a question, the receiving mechanism receives the question, and the server uses an interactive generation mechanism to generate an answer that takes emotional state into account. This answer is then presented to the user through the delivery mechanism.

[0898] The system also uses a collection mechanism to aggregate learning and sentiment data. This data is then analyzed by an analysis mechanism, and appropriate feedback is provided, thereby enhancing the user's learning experience through a support mechanism.

[0899] For example, when elementary school students are learning kanji, if the emotion recognition mechanism detects that the child is bored, the adjustment mechanism can change the learning plan and present game-style exercises. This helps maintain interest and improves learning effectiveness. By using a generative AI model, the generated content and prompts can be flexibly modified.

[0900] A concrete example of a prompt message would be, "When the user is confused, please gently explain basic mathematical concepts."

[0901] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0902] Step 1:

[0903] The user inputs their educational goals and existing knowledge level into an input mechanism via a terminal. The input data is sent to a server and analyzed by a generation mechanism. Based on the analysis results, an individually optimized educational plan is generated. Here, the input is the educational goals and knowledge level, and the output is the individually optimized educational plan.

[0904] Step 2:

[0905] The server presents the generated educational plan on the terminal using a presentation mechanism. The terminal displays the learning materials in a format that is easy for the user to understand, and the user begins learning. The input is the generated educational plan, and the output is the presentation of the learning materials to the user.

[0906] Step 3:

[0907] The device uses its built-in camera and microphone to collect the user's facial expressions and voice in real time using an emotion recognition mechanism. The collected data is sent to a server for analysis. The input for this step is facial expression and voice data, and the output is the emotion recognition result.

[0908] Step 4:

[0909] The server uses an adjustment mechanism to dynamically adjust the learning plan based on the emotion recognition results obtained from the emotion recognition mechanism. For example, if the server detects that the user is bored, it selects more interactive learning materials. Here, the input is the emotion recognition result, and the output is the updated learning plan.

[0910] Step 5:

[0911] When a user enters a question during learning, the device sends the question to the server via a receiving mechanism. The server uses an interactive generation mechanism to generate the best possible answer, taking into account the question and the user's emotional state. In this step, the input is the user's question and emotional state, and the output is the generated answer.

[0912] Step 6:

[0913] The server sends the generated response to the terminal through the delivery mechanism and presents it to the user. The terminal displays the response in a format that is easy for the user to understand. The input is the generated response, and the output is the presentation of the response.

[0914] Step 7:

[0915] The device continuously collects training data and sentiment data using a collection mechanism and sends it to the server. The server processes the collected data using an analysis mechanism and generates feedback based on the results. The inputs to this step are training data and sentiment data, and the outputs are the analysis results and feedback.

[0916] Step 8:

[0917] The server utilizes the results of the analysis mechanism through the support mechanism to provide appropriate assistance to the user. This ensures that appropriate information and support are presented based on the user's learning progress. The input is the analysis results and feedback, and the output is learning support.

[0918] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0919] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0920] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0921] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0922] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0923] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0924] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0925] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0926] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0927] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0928] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0929] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0930] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0931] 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.

[0932] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0933] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0934] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0935] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0936] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0937] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0938] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0939] The following is further disclosed regarding the embodiments described above.

[0940] (Claim 1)

[0941] An information processing device provides an input means for inputting the user's educational goals and existing knowledge level,

[0942] A generation means that generates an individually optimized educational plan based on the data obtained from the input means,

[0943] A presentation method for presenting the generated educational plan to the user,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] A means of receiving questions from users,

[0947] An interactive generation means that generates an answer to a question received by the receiving means,

[0948] A means of providing the generated answers to the user,

[0949] The system according to claim 1, including the following:

[0950] (Claim 3)

[0951] A means of collecting user learning data,

[0952] An analysis means that analyzes the data obtained by the aforementioned collection means and provides learning feedback,

[0953] Support tools to assist users' learning based on the feedback provided,

[0954] The system according to claim 1, including the following:

[0955] "Example 1"

[0956] (Claim 1)

[0957] An input method for inputting the learner's educational objectives and current knowledge level,

[0958] A generation means for formulating an individually optimized educational plan based on the information obtained from the input means,

[0959] A presentation method for presenting educational plans formulated using a generative AI model to learners,

[0960] A means of managing the progress of learning based on the formulated educational plan,

[0961] A system that includes this.

[0962] (Claim 2)

[0963] A means of receiving questions from learners,

[0964] An interactive generation means that generates an answer using a generation AI model to a question received by the aforementioned receiving means,

[0965] A means of providing the generated answers to the learners,

[0966] The system according to claim 1, including the following:

[0967] (Claim 3)

[0968] A means of recording learners' learning activities,

[0969] An analysis means that analyzes the data obtained by the collection means and provides learning feedback,

[0970] A support tool for improving the learning plan based on the analysis results,

[0971] The system according to claim 1, including the following:

[0972] "Application Example 1"

[0973] (Claim 1)

[0974] An input method for entering the user's educational goals and existing knowledge level,

[0975] A generation means that generates an individually optimized educational plan based on the data obtained from the input means,

[0976] A presentation method for presenting the generated educational plan to the user,

[0977] A means of providing guidance for offering instructional courses tailored to the local curriculum,

[0978] Includes a dialogue mechanism that generates and presents answers in real time during the learning process,

[0979] A system that includes this.

[0980] (Claim 2)

[0981] A means of receiving questions from users,

[0982] A generation means that generates an answer to a question received by the receiving means,

[0983] A means of providing the generated answers to the user,

[0984] Includes location information processing means that guides learning content based on geographical information,

[0985] The system according to claim 1.

[0986] (Claim 3)

[0987] A means of collecting user learning data,

[0988] An analysis means that analyzes the data obtained by the aforementioned collection means and provides learning feedback,

[0989] Support tools to assist users' learning based on the feedback provided,

[0990] Includes visualization means for generating information related to learning activities,

[0991] The system according to claim 1.

[0992] "Example 2 of combining an emotion engine"

[0993] (Claim 1)

[0994] An input method for entering the user's educational goals and existing knowledge level,

[0995] A generation means that generates an individually optimized educational plan based on the data obtained from the input means,

[0996] A presentation method for presenting the generated educational plan to the user,

[0997] A means of collecting user emotional data,

[0998] An analysis means for analyzing emotional data obtained by the aforementioned collection means and determining the emotional state,

[0999] An adjustment mechanism for dynamically adjusting the educational plan generated based on the determined emotional state,

[1000] A system that includes this.

[1001] (Claim 2)

[1002] A means of receiving questions from users,

[1003] An interactive generation means that generates an answer to a question received by the receiving means,

[1004] A means of providing generated answers while taking into account the user's emotional state,

[1005] The system according to claim 1, including the following:

[1006] (Claim 3)

[1007] A means of collecting user learning data and emotional data,

[1008] An analysis means that analyzes the data obtained by the aforementioned collection means and provides feedback based on the educational plan and emotional state,

[1009] Support tools to assist users' learning based on the feedback provided,

[1010] The system according to claim 1, including the following:

[1011] "Application example 2 when combining with an emotional engine"

[1012] (Claim 1)

[1013] An input mechanism for inputting the user's educational goals and existing knowledge level,

[1014] A generation mechanism that generates an individually optimized educational plan based on data obtained from the input mechanism,

[1015] A presentation mechanism that presents the generated educational plan to the user,

[1016] An emotion recognition mechanism for recognizing the user's emotions,

[1017] An adjustment mechanism that dynamically adjusts learning content based on recognized emotions,

[1018] A system that includes this.

[1019] (Claim 2)

[1020] A receiving mechanism for receiving questions from users,

[1021] An interactive generation mechanism that generates an answer based on the question received by the receiving mechanism and the user's emotional state,

[1022] A provision mechanism that provides the generated answers to users,

[1023] The system according to claim 1, including the following:

[1024] (Claim 3)

[1025] A collection mechanism for collecting user learning data and emotional data,

[1026] An analysis mechanism that analyzes the data obtained by the aforementioned collection mechanism and provides learning feedback,

[1027] A support organization that assists users in their learning based on the feedback and sentiment analysis results provided,

[1028] The system according to claim 1, including the following: [Explanation of Symbols]

[1029] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An input method for entering the user's educational goals and existing knowledge level, A generation means that generates an individually optimized educational plan based on the data obtained from the input means, A presentation method for presenting the generated educational plan to the user, A means of providing guidance for offering instructional courses tailored to the local curriculum, Includes a dialogue mechanism that generates and presents answers in real time during the learning process, A system that includes this.

2. A means of receiving questions from users, A generation means that generates an answer to a question received by the receiving means, A means of providing the generated answers to the user, Includes location information processing means that guides learning content based on geographical information, The system according to claim 1.

3. A means of collecting user learning data, An analysis means that analyzes the data obtained by the aforementioned collection means and provides learning feedback, Support tools to assist users' learning based on the feedback provided, Includes visualization means for generating information related to learning activities, The system according to claim 1.

Images