system

Abstract

We provide the system. [Solution] A means of receiving learning content keywords entered by learners, A means of obtaining relevant learning materials from online information sources based on the aforementioned learning content keywords, A means for filtering the acquired learning materials according to the learner's learning level and history, A means for presenting the filtered learning material to the learner, 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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, learners often spend a lot of time searching for appropriate learning materials from a vast amount of information sources. In particular, it is inefficient to select suitable learning content from the learning content provided for free online, and it often becomes a factor that dampens the motivation for learning. In addition, there is a lack of personalized learning support according to the individual levels and needs of learners. In such a situation, there is a need to support learning efficiently and effectively and automatically provide the necessary learning materials in an optimized form.

Means for Solving the Problems

[0005] This invention provides a system that receives learning content keywords entered by learners and retrieves relevant learning materials from online sources based on those keywords. It also filters the retrieved learning materials according to the learner's learning level and history, and presents appropriate materials. This system records the learner's selections and history information and utilizes it for providing future learning materials, thereby realizing personalized learning support. Furthermore, by using web scraping technology and public application programming interfaces, it is possible to efficiently collect data from a wide range of sources. Through these means, this invention can provide learners with an optimal learning experience and improve learning efficiency.

[0006] A "learner" is an individual who engages in learning in order to deepen their knowledge of a particular topic or skill.

[0007] "Learning content keywords" are words or phrases that learners are interested in as learning topics and can enter into the system to search for related information.

[0008] "Online information sources" is a general term for websites and platforms that provide education-related content accessible via the internet.

[0009] "Learning materials" refer to educational content such as workbooks, videos, and articles that learners can use to study a specific topic.

[0010] "Filtering" is the process of removing elements that do not match the purpose from acquired information or data based on specific criteria, and extracting only the necessary information.

[0011] "Learning level" is an indicator that shows the degree to which a learner has mastered knowledge and skills on a specific topic.

[0012] "History" refers to a record of what learning materials a learner has used in the past and how they have progressed in their learning.

[0013] "Web scraping" is a technique that automatically extracts, organizes, and analyzes specific information from websites.

[0014] A "Public Application Programming Interface (API)" is a set of protocols and toolsets made public for exchanging data between software and services. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This 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

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the language used in the following description will be explained.

[0018] In the following embodiments, a 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.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is an online learning support system that meets the needs of learners and efficiently provides optimal learning materials based on learner input. This system is realized through the interaction of a server, a terminal, and a user.

[0037] Users enter learning keywords via their device. This information is sent from the device to the server. The server uses the received keywords to search for relevant learning materials from various online sources on the web. Specifically, it quickly collects diverse educational content using web scraping techniques and APIs.

[0038] Next, the server analyzes the collected learning materials and filters them, taking into account the user's learning level and history. This process extracts only the information best suited to the learner. The filtered results are sent to the terminal as an organized list and displayed on the interface for easy selection by the user.

[0039] Furthermore, the server records the user's selections and learning history, updating the learner profile to provide more precisely personalized suggestions for future use. In this way, users can quickly access the learning content they need and obtain appropriate learning resources.

[0040] For example, if a user enters "basics of differential and integral calculus," the server will find relevant introductory videos and problem sets and present them according to the user's learning level. It can also suggest additional resources within the same difficulty range based on previously learned content. This allows users to expand their knowledge seamlessly and effectively.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user enters learning content keywords on their device and presses the search button. The device collects this input data and sends it to the server as an HTTP request.

[0044] Step 2:

[0045] The server analyzes the learning content keywords received from the terminal. Based on these keywords, the server initiates appropriate API calls or web scraping procedures to collect relevant learning materials.

[0046] Step 3:

[0047] The server retrieves data from relevant sources on the internet. Specifically, it retrieves video data from YouTube® and other educational platforms via APIs, and collects practice questions from open websites.

[0048] Step 4:

[0049] The server analyzes the acquired data and filters it based on the learner's profile information and past learning history. This filtering selects the most suitable learning materials according to the learner's level.

[0050] Step 5:

[0051] The server formats the filtered learning materials and converts them into a user-friendly format. This includes a list containing the title, link, brief description, and recommended level of the learning material.

[0052] Step 6:

[0053] The server sends a list of organized learning materials to the device.

[0054] Step 7:

[0055] The list of materials received by the device is displayed on the user interface and presented to the user in a selectable format. The user can then choose materials that match their interests.

[0056] Step 8:

[0057] When a user selects specific learning material, that selection information is sent from the device to the server. The server uses this information to record the user's learning history in a database.

[0058] Step 9:

[0059] The server updates this historical data to prepare for providing more personalized learning materials in future searches.

[0060] (Example 1)

[0061] 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."

[0062] Traditional online learning support systems struggle to efficiently provide optimal educational materials tailored to each learner's individual needs and level. This results in learners spending considerable time and effort finding materials that match their learning progress. Furthermore, providing a personalized experience based on learning history is also difficult.

[0063] 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.

[0064] In this invention, the server includes means for receiving educational content keywords entered by the learner, means for obtaining relevant educational materials from electronic information sources, and means for selecting the obtained educational materials according to the learner's educational level and history. This makes it possible to quickly provide educational materials that are suitable for the individual needs of the learner and to realize a personalized learning experience.

[0065] A "learner" refers to an individual whose purpose is to acquire knowledge through educational materials.

[0066] "Educational content keywords" refer to words or phrases that learners enter to express specific themes or topics they want to learn about.

[0067] "Electronic information sources" refer to various education-related databases and platforms provided on the internet or in digital format.

[0068] "Educational materials" refer to content such as textbooks, videos, and workbooks used by learners for educational purposes.

[0069] "Educational level" refers to a measure that indicates a learner's current level of knowledge and progress in learning.

[0070] "History" refers to a record of what a learner has studied in the past and the educational materials they have selected.

[0071] "Selection" refers to the filtering process of choosing educational materials that are suitable for the learner from the materials that have been acquired.

[0072] "Learner characteristics" refer to an individual learning profile of a learner, constructed based on their past learning history and selected educational materials.

[0073] An "application program interface" refers to an interface used to link functions and data between different software programs.

[0074] This system is an online learning support system that provides individually optimized educational materials based on educational content keywords entered by learners. The system is built on the interaction between the server, terminal, and user.

[0075] First, the user enters educational keywords indicating the topic they want to learn about via their device. For example, they might enter the keyword "Fundamentals of Differential and Integral Calculus" into their device. The device then sends this information to the server. The server analyzes this data and uses web scraping techniques and publicly available application programming interfaces to search for corresponding educational materials. Specifically, it utilizes Python libraries such as Beautiful Soup and APIs provided by various educational platforms.

[0076] The server uses the acquired educational materials to select appropriate materials, taking into account the learner's current educational level and past history. This filtering process utilizes machine learning techniques based on learner characteristics. Specifically, it performs analysis using machine learning libraries such as Scikit-learn.

[0077] Next, the server sends the selection results to the terminal and displays them in a format that the user can easily view on the interface. The user's selected materials and their learning history are also recorded on the server and updated in the database as learner characteristics. This allows the system to provide even more refined personalized support the next time the user uses it.

[0078] A concrete example of a prompt is, "Please suggest the best learning materials for the user to learn the basics of differential and integral calculus." This prompt is sent to a generative AI model, which helps learners efficiently deepen their knowledge by suggesting the most suitable educational materials.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The user enters educational content keywords into the device that indicate what they want to learn. The entered data is treated as keywords and prepared to be sent to the server. Specifically, a simple UI is displayed on the device, and when the user enters keywords and presses the send button, the entered data is converted into a format that can be sent to the server.

[0082] Step 2:

[0083] The terminal sends the keyword entered by the user to the server. The server receives the transmitted keyword, decodes it, and prepares for the next processing step. It receives the keyword sent from the terminal as input data and uses it in the next data retrieval process.

[0084] Step 3:

[0085] The server searches for and collects relevant educational materials from electronic sources based on the received keywords. This is done using web scraping techniques and a publicly available application programming interface. The input is the keywords to be processed, and the output is a list of relevant educational materials. In this process, the Python library Beautiful Soup is used to parse web pages, and the necessary data is pulled using a public API.

[0086] Step 4:

[0087] The server sorts the collected educational materials based on the learner's educational level and history. Machine learning techniques are used here to select the most suitable materials. The input is the educational materials collected in the previous step, and the output is the sorted educational materials. Specifically, the Scikit-learn library is used to select materials based on a predictive model.

[0088] Step 5:

[0089] The server sends selected educational materials to the terminal. The terminal displays the received materials in an organized manner on its user interface. The input is the selected educational materials from the server, and the output is a display of materials in a user-friendly format. On the terminal side, materials are displayed in list or card format, providing the user with intuitive access.

[0090] Step 6:

[0091] The server records the learner's selected materials and learning history in a database and updates the learner profile. This allows for further optimization of future learning support. The input is the user's selected materials and operation history, and the output is the updated learner profile. The database update process is integrated into a specific learning management system to reflect the learning history.

[0092] (Application Example 1)

[0093] 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."

[0094] With the spread of online education, it is not easy for learners to find suitable learning materials from the vast amount of information available. Furthermore, there is a need for material recommendations tailored to each learner's knowledge level and past learning history, but existing systems are insufficient to address this. Additionally, providing an interface that displays filtered information in an intuitive and easily understandable way is another challenge.

[0095] 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.

[0096] In this invention, the server includes means for receiving learning content keywords entered by the learner, means for obtaining relevant information from online information sources based on the learning content keywords, and means for selecting the obtained information according to the learner's knowledge level and history. This makes it possible for learners to easily find learning materials optimized for them.

[0097] "Learning content keywords entered by the learner" are words or phrases that express the content the learner wants to learn.

[0098] "Online information sources" refer to a collection of digital information accessible via the internet.

[0099] "Related information" refers to educational materials that are deemed to be related to the learning content keywords.

[0100] "Knowledge level" is an indicator that represents a learner's current level of understanding and ability.

[0101] "History" refers to a record of what a learner has studied in the past and the materials they have selected.

[0102] "Selecting" refers to the act of choosing information that is suitable for the learner's needs.

[0103] A "device" is an electronic device used to display or manipulate presented information.

[0104] A "communication terminal" is a device used to send and receive information.

[0105] A "digital interface" refers to the screens and operating methods that users use to interact with a computer system.

[0106] "Data analysis technology" refers to methods and techniques for extracting meaningful information based on collected data.

[0107] "Open Application Interface Technology" refers to a protocol that defines how external systems can utilize specific functions.

[0108] The embodiments for carrying out the present invention are mainly based on the interaction between a server, a terminal, and a user.

[0109] First, the user uses a communication device to input learning content keywords. These devices, such as smartphones and tablets, are electronic devices capable of transmitting data to a server via the internet. The entered keywords accurately reflect the content the learner is seeking.

[0110] Next, the server collects relevant information from online sources based on the received keywords. The server utilizes data analysis techniques using Python and publicly available application interface technologies to efficiently gather information. Web scraping techniques using tools like BeautifulSoup may also be employed.

[0111] The collected information is filtered according to the learner's knowledge level and past history. The server refers to past learning history data to identify the most suitable learning materials for the learner and provides personalized recommendations as needed. The filtered information is sent to the user's device as an organized list.

[0112] For example, if a user enters the keyword "machine learning for beginners" using a communication device, the server uses that information to select and present appropriate tutorials and explanatory videos to the user. The user can then proceed with their learning based on the presented information.

[0113] Furthermore, the server can continuously record the learning history in the learner program, making it possible to provide more precise information in subsequent sessions.

[0114] A concrete example of a prompt would be, "Suggest online learning resources related to the following keyword: 'machine learning for beginners'."

[0115] As described above, the implementation of this invention enables learners to utilize learning materials efficiently and individually.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The user enters learning keywords using a communication terminal. The entered keywords are temporarily stored on the terminal and prepared for transmission to the server. Once the user has finished entering the keywords, the data is formatted for transmission.

[0119] Step 2:

[0120] The terminal packets the entered keywords and sends them to the server via the internet. The output here is packet data of the learned keywords converted into a format that the server can process.

[0121] Step 3:

[0122] The server analyzes the received keywords and searches for relevant online information sources. In this process, Python is used to retrieve educational materials related to the keywords through APIs and web scraping techniques. The input is the keyword, and the output is a list of potential educational materials.

[0123] Step 4:

[0124] The server analyzes the collected educational materials and sorts them based on the learner's knowledge level and learning history. The data processing here involves matching the acquired information with the user profile to select materials of appropriate difficulty.

[0125] Step 5:

[0126] The selected learning materials are organized into a list format and sent to the device. The input in this process is the selected educational materials, and the output is a list of materials that can be displayed to the user.

[0127] Step 6:

[0128] The device displays the received list on the user interface. The user can intuitively browse this list and select learning materials of interest as needed. The selected information is temporarily recorded for future recommendations.

[0129] Step 7:

[0130] The server records the user's learning history and updates the learner profile. The updated information is used to recommend learning materials for future sessions. In this step, the input is the user's selection history, and the output is the updated learner profile.

[0131] 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.

[0132] This invention provides a system that offers relevant learning materials based on keywords entered by the learner, and also provides a personalized learning experience that takes into account the user's emotional state. This system operates in combination with a server, terminal, and emotion engine, and aims to improve the user's learning efficiency and motivation.

[0133] The user first enters keywords related to the learning content via their device. This information is sent from the device to the server. The server uses the received keywords to retrieve relevant learning materials from online sources. Web scraping techniques and public APIs are used to quickly collect diverse educational content.

[0134] After collecting training material, the server uses an emotion engine to recognize the user's current emotional state. The emotion engine generates emotional data based on the user's facial expressions, keyboard input speed, voice tone, etc., and analyzes the results. Based on this data, the server filters the training material to match the user's emotional state and selects the most suitable resources.

[0135] The filtered learning materials are presented to the user in a way that is adjusted according to their emotional state, taking into account their learning level and history. For example, if the emotion engine determines that the user is stressed, visually appealing content with a relaxing effect will be selected. Conversely, if the user is highly motivated, materials containing challenging problems may be presented.

[0136] Furthermore, the server records the user's learning history and emotional data, and refers to this data during subsequent use to provide more deeply personalized learning support. In this way, users can always receive a learning experience that is suited to their current state, enabling them to learn effectively.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The user enters keywords related to the learning content into their device and performs a search. The device then sends this information to the server.

[0140] Step 2:

[0141] The server analyzes the learning keywords received from the terminal and searches for relevant online information sources. The server uses web scraping techniques and public APIs to collect appropriate learning materials.

[0142] Step 3:

[0143] The server collects training material while simultaneously activating an emotion engine to analyze the user's emotions. Using the device's camera and microphone, it detects the user's facial expressions, voice, and behavioral patterns to generate emotion data.

[0144] Step 4:

[0145] The server analyzes the user's emotional data and re-evaluates the collected training material. The server filters the training material to match the user's current emotional state and updates the list accordingly.

[0146] Step 5:

[0147] The server formats the filtered learning materials and, taking into account the user's learning level and past history, sends an optimized content list to the device.

[0148] Step 6:

[0149] The device displays a list of received learning materials on the user interface, and the user selects from the list to begin learning.

[0150] Step 7:

[0151] The learning process progresses based on the content of the learning materials selected by the user. Simultaneously, the server records the user's selection history and changes in their emotions during learning in a database.

[0152] Step 8:

[0153] The server analyzes recorded historical data and emotional information to update the user profile to the latest content, which will then be used to improve learning support in the future.

[0154] (Example 2)

[0155] 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".

[0156] In modern education systems, personalized learning tailored to each learner's level of understanding and emotional state is often insufficient. This leads to problems such as decreased learning efficiency and difficulty maintaining motivation. Furthermore, while the amount of online learning material is vast, selecting the appropriate content is difficult. Therefore, there is a need to provide learners with necessary information quickly and effectively, and to optimize the learning experience according to their emotional state.

[0157] 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.

[0158] In this invention, the server includes means for receiving learning themes entered by the learner, means for obtaining relevant educational materials from online information sources, and means for analyzing the learner's emotional state. This enables the rapid selection and presentation of educational materials tailored to the learner's specific emotional state and learning level.

[0159] A "learning theme" refers to a specific topic or subject that a learner is interested in and wishes to learn about.

[0160] "Educational materials" is a general term for information sources and content provided to support learners' learning.

[0161] "Online information sources" refer to digital content and databases that are accessible via the internet.

[0162] "Data extraction technology" refers to methods for automatically collecting necessary information from specific websites or databases.

[0163] A "public program interface" refers to a standardized connection point that is made public for exchanging data between applications.

[0164] An "emotion analysis engine" refers to the technology and algorithms used to analyze a user's emotional state based on external input data.

[0165] "Filtering" refers to the process of selecting data or content based on specific criteria or conditions.

[0166] "Learning level" refers to the degree of knowledge and skills that a learner currently possesses.

[0167] "Learning history" refers to a record of learning activities and educational materials used by learners in the past.

[0168] In the specific implementation of this system, a server, terminal, and sentiment analysis engine work together. The user uses the terminal to input the topic they wish to learn about. This information is transmitted to the server via an internet connection. Based on the received topic, the server retrieves relevant educational materials from various online sources. This process utilizes data extraction techniques and a publicly accessible programming interface to gather information quickly and efficiently.

[0169] The server is equipped with an emotion analysis engine to analyze the user's emotional state. Using input data provided by the device's camera and microphone, it analyzes the user's facial expressions and voice to quantify their emotional state.

[0170] The server filters the acquired educational materials based on the user's emotional state, learning level, and past history. This filtering presents the optimal learning experience tailored to the user's state, thereby improving learning efficiency.

[0171] For example, if a user enters "data science" as their topic, the server will retrieve relevant online courses and articles. If the sentiment analysis engine detects the user's level of concentration, it can provide content that includes challenging exercises.

[0172] An example of a prompt might be, "How can I provide personalized educational materials based on emotional states?" This allows the generative AI model to generate responses tailored to the user's needs.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The user enters keywords related to the topic they wish to learn about through their device. This input information is sent to the server in text data format. The server receives this input and stores it in a database in preparation for the next processing step.

[0176] Step 2:

[0177] The server collects relevant educational materials from online sources based on the entered keywords. This process utilizes data extraction techniques and a publicly available program interface. The input is keywords, and the output is a list of relevant educational materials, which are stored in a database.

[0178] Step 3:

[0179] The server uses an emotion analysis engine to analyze the user's emotional state. Camera video and audio data acquired from the terminal are used as input, and this data is analyzed to generate an emotion score. The output is numerical data indicating the user's emotional state.

[0180] Step 4:

[0181] The server filters the acquired educational materials based on the user's emotional state and learning history. The inputs are a list of educational materials, emotional scores, and learning history, while the output is user-optimized and filtered educational materials. These results are then added to the database.

[0182] Step 5:

[0183] The terminal receives filtered educational materials from the server and presents them to the user. When displayed, the materials are provided in an interactive format and with a visually appealing layout, allowing the user to gain a learning experience. The input to this process is filtered educational materials, and the output is information that is visually understandable to the user.

[0184] Step 6:

[0185] The server records the user's choices, learning history, and sentiment data at the end of each session. This data is used to enhance personalization on subsequent accesses and is securely stored in a database. In this process, the collected data is the input, and the output is an updated learner profile.

[0186] (Application Example 2)

[0187] 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."

[0188] In today's world, learners can access learning materials from a variety of online sources, but it is extremely difficult for them to receive the optimal learning experience tailored to their individual learning situation and emotions. Furthermore, providing uniform materials without considering emotional states can lead to decreased learning efficiency. Therefore, accurately understanding learners' emotional states and providing individually optimized learning experiences is essential.

[0189] 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.

[0190] In this invention, the server includes means for receiving learning content keywords entered by the learner, means for obtaining relevant learning materials from online information sources based on the learning content keywords, means for filtering the obtained learning materials according to the learner's learning level and history, means for analyzing the learner's emotional state using sensors incorporated in the device, and means for adjusting and presenting the learning materials based on the emotional state. This enables a more personalized learning experience that takes into account the learner's emotional state.

[0191] "Learning content keywords" are input information that represents the topics or themes that learners want to study.

[0192] "Online information sources" refer to various information platforms and databases that exist on the internet.

[0193] "Learning materials" refer to content such as texts, videos, and quizzes that help learners acquire knowledge.

[0194] "Learner's learning level" is an indicator that shows the stage of knowledge and skills that a learner has currently attained.

[0195] "Learner history" refers to records of past learning activities, choices, and achievements.

[0196] "Filtering" is the process of selecting learning materials in the format and content that is most suitable for the learner.

[0197] A "sensor" is an electronic detection device used to analyze the emotional state of a learner.

[0198] "Emotional state" refers to data that indicates the learner's psychological state and changes in their emotions.

[0199] "Adjustment" refers to the act of appropriately changing learning materials according to the learner's emotional state and other factors.

[0200] "Presentation" refers to the act of ultimately displaying information or content to learners on a screen or other means.

[0201] The system for realizing this invention consists of a terminal used by the learner, a server for information processing, and sensors built into the device. This system receives learning content keywords entered by the user from the terminal and sends that information to the server. Based on the received keywords, the server retrieves relevant learning materials from online information sources using web scraping technology and public APIs.

[0202] The server then filters the acquired learning materials according to the learner's learning level and history. This filtering is based on what materials the learner has used in the past and what results they have achieved.

[0203] Furthermore, the emotion engine analyzes the user's current emotional state using data from sensors built into the user's device (e.g., camera and microphone). Existing technologies such as "Face API" and "Azure® Emotion API" are used for this analysis. Based on this emotional data, the server adjusts and presents the training material in a way that is appropriate for the user's emotions.

[0204] For example, if a user inputs that they want to learn "linear algebra" and the server detects that they are excited, the server will select and present materials that include challenging quizzes and advanced problems. On the other hand, if the same user is feeling fatigued, the server will provide videos and animations that are visually relaxing.

[0205] For example, if a user who wants to learn the basics of project management enters the prompt message, "Please recommend content that allows me to learn the fundamental knowledge necessary for project management in a relaxed manner," the system can provide appropriate learning materials.

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The user enters keywords related to the learning content using a terminal. The entered keywords become input data for the system, and the terminal sends this information to the server.

[0209] Step 2:

[0210] The server retrieves relevant learning materials from online sources based on the received keywords. It collects data using web scraping techniques and public APIs, and compiles the results into learning materials. This becomes the initial output from the server.

[0211] Step 3:

[0212] The server receives the learner's learning level and past history as input and filters the retrieved learning materials. This process uses database queries and algorithms to select the most suitable materials for the learner and generates output to pass on to the next step.

[0213] Step 4:

[0214] Sensors embedded in the user's device capture the user's facial expressions and voice data. This data is passed as input to an emotion engine, which analyzes the user's current emotional state. The emotion engine then uses machine learning algorithms to output emotional data.

[0215] Step 5:

[0216] The server receives emotional state data from the emotion engine and further refines the filtered training material. Here, the emotional data is used to change the content and difficulty level of the training material, and the training material to be presented as the final output is determined.

[0217] Step 6:

[0218] The server sends the tailored learning materials to the device and presents them to the user. The user can access these personalized learning materials via the device and progress through their learning. The device outputs its display, providing the user with information in a visual or auditory form.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] This invention is an online learning support system that meets the needs of learners and efficiently provides optimal learning materials based on learner input. This system is realized through the interaction of a server, a terminal, and a user.

[0236] Users enter learning keywords via their device. This information is sent from the device to the server. The server uses the received keywords to search for relevant learning materials from various online sources on the web. Specifically, it quickly collects diverse educational content using web scraping techniques and APIs.

[0237] Next, the server analyzes the collected learning materials and filters them, taking into account the user's learning level and history. This process extracts only the information best suited to the learner. The filtered results are sent to the terminal as an organized list and displayed on the interface for easy selection by the user.

[0238] Furthermore, the server records the user's selections and learning history, updating the learner profile to provide more precisely personalized suggestions for future use. In this way, users can quickly access the learning content they need and obtain appropriate learning resources.

[0239] For example, if a user enters "basics of differential and integral calculus," the server will find relevant introductory videos and problem sets and present them according to the user's learning level. It can also suggest additional resources within the same difficulty range based on previously learned content. This allows users to expand their knowledge seamlessly and effectively.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The user enters learning content keywords on their device and presses the search button. The device collects this input data and sends it to the server as an HTTP request.

[0243] Step 2:

[0244] The server analyzes the learning content keywords received from the terminal. Based on these keywords, the server initiates appropriate API calls or web scraping procedures to collect relevant learning materials.

[0245] Step 3:

[0246] The server retrieves data from relevant sources on the internet. Specifically, it retrieves video data from YouTube and other educational platforms via APIs, and collects practice questions from open websites.

[0247] Step 4:

[0248] The server analyzes the acquired data and filters it based on the learner's profile information and past learning history. This filtering selects the most suitable learning materials according to the learner's level.

[0249] Step 5:

[0250] The server formats the filtered learning materials and converts them into a user-friendly format. This includes a list containing the title, link, brief description, and recommended level of the learning material.

[0251] Step 6:

[0252] The server sends a list of organized learning materials to the device.

[0253] Step 7:

[0254] The list of materials received by the device is displayed on the user interface and presented to the user in a selectable format. The user can then choose materials that match their interests.

[0255] Step 8:

[0256] When a user selects specific learning material, that selection information is sent from the device to the server. The server uses this information to record the user's learning history in a database.

[0257] Step 9:

[0258] The server updates this historical data to prepare for providing more personalized learning materials in future searches.

[0259] (Example 1)

[0260] 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 glasses 214 will be referred to as the "terminal."

[0261] Traditional online learning support systems struggle to efficiently provide optimal educational materials tailored to each learner's individual needs and level. This results in learners spending considerable time and effort finding materials that match their learning progress. Furthermore, providing a personalized experience based on learning history is also difficult.

[0262] 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.

[0263] In this invention, the server includes means for receiving educational content keywords entered by the learner, means for obtaining relevant educational materials from electronic information sources, and means for selecting the obtained educational materials according to the learner's educational level and history. This makes it possible to quickly provide educational materials that are suitable for the individual needs of the learner and to realize a personalized learning experience.

[0264] A "learner" refers to an individual whose purpose is to acquire knowledge through educational materials.

[0265] "Educational content keywords" refer to words or phrases that learners enter to express specific themes or topics they want to learn about.

[0266] "Electronic information sources" refer to various education-related databases and platforms provided on the internet or in digital format.

[0267] "Educational materials" refer to content such as textbooks, videos, and workbooks used by learners for educational purposes.

[0268] "Educational level" refers to a measure that indicates a learner's current level of knowledge and progress in learning.

[0269] "History" refers to a record of what a learner has studied in the past and the educational materials they have selected.

[0270] "Selection" refers to the filtering process of choosing educational materials that are suitable for the learner from the materials that have been acquired.

[0271] "Learner characteristics" refer to an individual learning profile of a learner, constructed based on their past learning history and selected educational materials.

[0272] An "application program interface" refers to an interface used to link functions and data between different software programs.

[0273] This system is an online learning support system that provides individually optimized educational materials based on educational content keywords entered by learners. The system is built on the interaction between the server, terminal, and user.

[0274] First, the user enters educational keywords indicating the topic they want to learn about via their device. For example, they might enter the keyword "Fundamentals of Differential and Integral Calculus" into their device. The device then sends this information to the server. The server analyzes this data and uses web scraping techniques and publicly available application programming interfaces to search for corresponding educational materials. Specifically, it utilizes Python libraries such as Beautiful Soup and APIs provided by various educational platforms.

[0275] The server uses the acquired educational materials to select appropriate materials, taking into account the learner's current educational level and past history. This filtering process utilizes machine learning techniques based on learner characteristics. Specifically, it performs analysis using machine learning libraries such as Scikit-learn.

[0276] Next, the server sends the selection results to the terminal and displays them in a format that the user can easily view on the interface. The user's selected materials and their learning history are also recorded on the server and updated in the database as learner characteristics. This allows the system to provide even more refined personalized support the next time the user uses it.

[0277] A concrete example of a prompt is, "Please suggest the best learning materials for the user to learn the basics of differential and integral calculus." This prompt is sent to a generative AI model, which helps learners efficiently deepen their knowledge by suggesting the most suitable educational materials.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The user enters educational content keywords into the device that indicate what they want to learn. The entered data is treated as keywords and prepared to be sent to the server. Specifically, a simple UI is displayed on the device, and when the user enters keywords and presses the send button, the entered data is converted into a format that can be sent to the server.

[0281] Step 2:

[0282] The terminal sends the keyword entered by the user to the server. The server receives the transmitted keyword, decodes it, and prepares for the next processing step. It receives the keyword sent from the terminal as input data and uses it in the next data retrieval process.

[0283] Step 3:

[0284] The server searches for and collects relevant educational materials from electronic information sources based on the received keywords. This is done using web scraping technology and publicly available application programming interfaces. The input is the keyword to be processed, and the output is a list of relevant educational materials. At this time, the web page is parsed using the Beautiful Soup library in Python, and the necessary data is pulled using the public API.

[0285] Step 4:

[0286] The server sorts the collected educational materials based on the learner's educational level and history. Machine learning technology is used here to select the optimal materials. The input is the educational materials collected in the previous step, and the output is the sorted educational materials. Specifically, the Scikit-learn library is used to select materials based on the prediction model.

[0287] Step 5:

[0288] The server sends the sorted educational materials to the terminal. The terminal neatly displays the received materials on the user interface. The input is the sorted educational materials from the server, and the output is the display of the materials in a format that is easy for the user to select. On the terminal side, the display is in a list or card format, providing intuitive access for the user.

[0289] Step 6:

[0290] The server records the materials selected by the learner and the learning history in the database and updates the learner characteristics. This enables further optimization of future learning support. The input is the materials selected by the user and the operation history, and the output is the updated learner profile. The database update process is incorporated into a specific learning management system to reflect the learning history.

[0291] (Application Example 1)

[0292] 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."

[0293] With the spread of online education, it is not easy for learners to find suitable learning materials from the vast amount of information available. Furthermore, there is a need for material recommendations tailored to each learner's knowledge level and past learning history, but existing systems are insufficient to address this. Additionally, providing an interface that displays filtered information in an intuitive and easily understandable way is another challenge.

[0294] 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.

[0295] In this invention, the server includes means for receiving learning content keywords entered by the learner, means for obtaining relevant information from online information sources based on the learning content keywords, and means for selecting the obtained information according to the learner's knowledge level and history. This makes it possible for learners to easily find learning materials optimized for them.

[0296] "Learning content keywords entered by the learner" are words or phrases that express the content the learner wants to learn.

[0297] "Online information sources" refer to a collection of digital information accessible via the internet.

[0298] "Related information" refers to educational materials that are deemed to be related to the learning content keywords.

[0299] "Knowledge level" is an indicator that represents a learner's current level of understanding and ability.

[0300] "History" refers to a record of what a learner has studied in the past and the materials they have selected.

[0301] "To select" refers to the act of selecting information that matches the needs of the learner.

[0302] "Device" refers to an electronic device for displaying or operating the presented information.

[0303] "Communication terminal" refers to a device used for transmitting and receiving information.

[0304] "Digital interface" refers to the screen and operation method for the user to interact with the computer system.

[0305] "Data analysis technology" refers to the methods and techniques for extracting meaningful information based on the collected data.

[0306] "Published application interface technology" refers to a protocol that defines the method for an external system to utilize a specific function.

[0307] The embodiments for implementing the present invention are mainly configured based on the interaction among the server, the terminal, and the user.

[0308] First, the user uses a communication terminal to input learning content keywords. The terminal is an electronic device such as a smartphone or a tablet, and has the function of transmitting data to the server via the Internet. This input keyword is a phrase that accurately reflects the content required by the learner.

[0309] Next, based on the received keywords, the server collects relevant information from online information sources. In the server, data analysis technology using Python and published application interface technology are utilized to efficiently collect information. Also, web scraping technology using BeautifulSoup or the like may be adopted.

[0310] The collected information is filtered according to the learner's knowledge level and past history. The server refers to past learning history data to identify the most suitable learning materials for the learner and provides personalized recommendations as needed. The filtered information is sent to the user's device as an organized list.

[0311] For example, if a user enters the keyword "machine learning for beginners" using a communication device, the server uses that information to select and present appropriate tutorials and explanatory videos to the user. The user can then proceed with their learning based on the presented information.

[0312] Furthermore, the server can continuously record the learning history in the learner program, making it possible to provide more precise information in subsequent sessions.

[0313] A concrete example of a prompt would be, "Suggest online learning resources related to the following keyword: 'machine learning for beginners'."

[0314] As described above, the implementation of this invention enables learners to utilize learning materials efficiently and individually.

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The user enters learning keywords using a communication terminal. The entered keywords are temporarily stored on the terminal and prepared for transmission to the server. Once the user has finished entering the keywords, the data is formatted for transmission.

[0318] Step 2:

[0319] The terminal packets the entered keywords and sends them to the server via the internet. The output here is packet data of the learned keywords converted into a format that the server can process.

[0320] Step 3:

[0321] The server analyzes the received keywords and searches for relevant online information sources. In this process, Python is used to retrieve educational materials related to the keywords through APIs and web scraping techniques. The input is the keyword, and the output is a list of potential educational materials.

[0322] Step 4:

[0323] The server analyzes the collected educational materials and sorts them based on the learner's knowledge level and learning history. The data processing here involves matching the acquired information with the user profile to select materials of appropriate difficulty.

[0324] Step 5:

[0325] The selected learning materials are organized into a list format and sent to the device. The input in this process is the selected educational materials, and the output is a list of materials that can be displayed to the user.

[0326] Step 6:

[0327] The device displays the received list on the user interface. The user can intuitively browse this list and select learning materials of interest as needed. The selected information is temporarily recorded for future recommendations.

[0328] Step 7:

[0329] The server records the user's learning history and updates the learner profile. The updated information is used to recommend learning materials for future sessions. In this step, the input is the user's selection history, and the output is the updated learner profile.

[0330] 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.

[0331] This invention provides a system that offers relevant learning materials based on keywords entered by the learner, and also provides a personalized learning experience that takes into account the user's emotional state. This system operates in combination with a server, terminal, and emotion engine, and aims to improve the user's learning efficiency and motivation.

[0332] The user first enters keywords related to the learning content via their device. This information is sent from the device to the server. The server uses the received keywords to retrieve relevant learning materials from online sources. Web scraping techniques and public APIs are used to quickly collect diverse educational content.

[0333] After collecting training material, the server uses an emotion engine to recognize the user's current emotional state. The emotion engine generates emotional data based on the user's facial expressions, keyboard input speed, voice tone, etc., and analyzes the results. Based on this data, the server filters the training material to match the user's emotional state and selects the most suitable resources.

[0334] The filtered learning materials are presented to the user in a way that is adjusted according to their emotional state, taking into account their learning level and history. For example, if the emotion engine determines that the user is stressed, visually appealing content with a relaxing effect will be selected. Conversely, if the user is highly motivated, materials containing challenging problems may be presented.

[0335] Furthermore, the server records the user's learning history and emotional data, and refers to this data during subsequent use to provide more deeply personalized learning support. In this way, users can always receive a learning experience that is suited to their current state, enabling them to learn effectively.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] The user enters keywords related to the learning content into their device and performs a search. The device then sends this information to the server.

[0339] Step 2:

[0340] The server analyzes the learning keywords received from the terminal and searches for relevant online information sources. The server uses web scraping techniques and public APIs to collect appropriate learning materials.

[0341] Step 3:

[0342] The server collects training material while simultaneously activating an emotion engine to analyze the user's emotions. Using the device's camera and microphone, it detects the user's facial expressions, voice, and behavioral patterns to generate emotion data.

[0343] Step 4:

[0344] The server analyzes the user's emotional data and re-evaluates the collected training material. The server filters the training material to match the user's current emotional state and updates the list accordingly.

[0345] Step 5:

[0346] The server formats the filtered learning materials and, taking into account the user's learning level and past history, sends an optimized content list to the device.

[0347] Step 6:

[0348] The device displays a list of received learning materials on the user interface, and the user selects from the list to begin learning.

[0349] Step 7:

[0350] The learning process progresses based on the content of the learning materials selected by the user. Simultaneously, the server records the user's selection history and changes in their emotions during learning in a database.

[0351] Step 8:

[0352] The server analyzes recorded historical data and emotional information to update the user profile to the latest content, which will then be used to improve learning support in the future.

[0353] (Example 2)

[0354] 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".

[0355] In modern education systems, personalized learning tailored to each learner's level of understanding and emotional state is often insufficient. This leads to problems such as decreased learning efficiency and difficulty maintaining motivation. Furthermore, while the amount of online learning material is vast, selecting the appropriate content is difficult. Therefore, there is a need to provide learners with necessary information quickly and effectively, and to optimize the learning experience according to their emotional state.

[0356] 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.

[0357] In this invention, the server includes means for receiving learning themes entered by the learner, means for obtaining relevant educational materials from online information sources, and means for analyzing the learner's emotional state. This enables the rapid selection and presentation of educational materials tailored to the learner's specific emotional state and learning level.

[0358] A "learning theme" refers to a specific topic or subject that a learner is interested in and wishes to learn about.

[0359] "Educational materials" is a general term for information sources and content provided to support learners' learning.

[0360] "Online information sources" refer to digital content and databases that are accessible via the internet.

[0361] "Data extraction technology" refers to methods for automatically collecting necessary information from specific websites or databases.

[0362] A "public program interface" refers to a standardized connection point that is made public for exchanging data between applications.

[0363] An "emotion analysis engine" refers to the technology and algorithms used to analyze a user's emotional state based on external input data.

[0364] "Filtering" refers to the process of selecting data or content based on specific criteria or conditions.

[0365] "Learning level" refers to the degree of knowledge and skills that a learner currently possesses.

[0366] "Learning history" refers to a record of learning activities and educational materials used by learners in the past.

[0367] In the specific implementation of this system, a server, terminal, and sentiment analysis engine work together. The user uses the terminal to input the topic they wish to learn about. This information is transmitted to the server via an internet connection. Based on the received topic, the server retrieves relevant educational materials from various online sources. This process utilizes data extraction techniques and a publicly accessible programming interface to gather information quickly and efficiently.

[0368] The server is equipped with an emotion analysis engine to analyze the user's emotional state. Using input data provided by the device's camera and microphone, it analyzes the user's facial expressions and voice to quantify their emotional state.

[0369] The server filters the acquired educational materials based on the user's emotional state, learning level, and past history. This filtering presents the optimal learning experience tailored to the user's state, thereby improving learning efficiency.

[0370] For example, if a user enters "data science" as their topic, the server will retrieve relevant online courses and articles. If the sentiment analysis engine detects the user's level of concentration, it can provide content that includes challenging exercises.

[0371] An example of a prompt might be, "How can I provide personalized educational materials based on emotional states?" This allows the generative AI model to generate responses tailored to the user's needs.

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] The user enters keywords related to the topic they wish to learn about through their device. This input information is sent to the server in text data format. The server receives this input and stores it in a database in preparation for the next processing step.

[0375] Step 2:

[0376] The server collects relevant educational materials from online sources based on the entered keywords. This process utilizes data extraction techniques and a publicly available program interface. The input is keywords, and the output is a list of relevant educational materials, which are stored in a database.

[0377] Step 3:

[0378] The server uses an emotion analysis engine to analyze the user's emotional state. Camera video and audio data acquired from the terminal are used as input, and this data is analyzed to generate an emotion score. The output is numerical data indicating the user's emotional state.

[0379] Step 4:

[0380] The server filters the acquired educational materials based on the user's emotional state and learning history. The inputs are a list of educational materials, emotional scores, and learning history, while the output is user-optimized and filtered educational materials. These results are then added to the database.

[0381] Step 5:

[0382] The terminal receives filtered educational materials from the server and presents them to the user. When displayed, the materials are provided in an interactive format and with a visually appealing layout, allowing the user to gain a learning experience. The input to this process is filtered educational materials, and the output is information that is visually understandable to the user.

[0383] Step 6:

[0384] The server records the user's choices, learning history, and sentiment data at the end of each session. This data is used to enhance personalization on subsequent accesses and is securely stored in a database. In this process, the collected data is the input, and the output is an updated learner profile.

[0385] (Application Example 2)

[0386] 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 as the "terminal".

[0387] In today's world, learners can access learning materials from a variety of online sources, but it is extremely difficult for them to receive the optimal learning experience tailored to their individual learning situation and emotions. Furthermore, providing uniform materials without considering emotional states can lead to decreased learning efficiency. Therefore, accurately understanding learners' emotional states and providing individually optimized learning experiences is essential.

[0388] 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.

[0389] In this invention, the server includes means for receiving learning content keywords entered by the learner, means for obtaining relevant learning materials from online information sources based on the learning content keywords, means for filtering the obtained learning materials according to the learner's learning level and history, means for analyzing the learner's emotional state using sensors incorporated in the device, and means for adjusting and presenting the learning materials based on the emotional state. This enables a more personalized learning experience that takes into account the learner's emotional state.

[0390] "Learning content keywords" are input information that represents the topics or themes that learners want to study.

[0391] "Online information sources" refer to various information platforms and databases that exist on the internet.

[0392] "Learning materials" refer to content such as texts, videos, and quizzes that help learners acquire knowledge.

[0393] "Learner's learning level" is an indicator that shows the stage of knowledge and skills that a learner has currently attained.

[0394] "Learner history" refers to records of past learning activities, choices, and achievements.

[0395] "Filtering" is the process of selecting learning materials in the format and content that is most suitable for the learner.

[0396] A "sensor" is an electronic detection device used to analyze the emotional state of a learner.

[0397] "Emotional state" refers to data that indicates the learner's psychological state and changes in their emotions.

[0398] "Adjustment" refers to the act of appropriately changing learning materials according to the learner's emotional state and other factors.

[0399] "Presentation" refers to the act of ultimately displaying information or content to learners on a screen or other means.

[0400] The system for realizing this invention consists of a terminal used by the learner, a server for information processing, and sensors built into the device. This system receives learning content keywords entered by the user from the terminal and sends that information to the server. Based on the received keywords, the server retrieves relevant learning materials from online information sources using web scraping technology and public APIs.

[0401] The server then filters the acquired learning materials according to the learner's learning level and history. This filtering is based on what materials the learner has used in the past and what results they have achieved.

[0402] Furthermore, the emotion engine analyzes the user's current emotional state using data from sensors built into the user's device (e.g., camera and microphone). Existing technologies such as "Face API" and "Azure Emotion API" are used for this analysis. Based on this emotional data, the server adjusts and presents the training material in a way that is appropriate for the user's emotions.

[0403] For example, if a user inputs that they want to learn "linear algebra" and the server detects that they are excited, the server will select and present materials that include challenging quizzes and advanced problems. On the other hand, if the same user is feeling fatigued, the server will provide videos and animations that are visually relaxing.

[0404] For example, if a user who wants to learn the basics of project management enters the prompt message, "Please recommend content that allows me to learn the fundamental knowledge necessary for project management in a relaxed manner," the system can provide appropriate learning materials.

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The user enters keywords related to the learning content using a terminal. The entered keywords become input data for the system, and the terminal sends this information to the server.

[0408] Step 2:

[0409] The server retrieves relevant learning materials from online sources based on the received keywords. It collects data using web scraping techniques and public APIs, and compiles the results into learning materials. This becomes the initial output from the server.

[0410] Step 3:

[0411] The server receives the learner's learning level and past history as input and filters the retrieved learning materials. This process uses database queries and algorithms to select the most suitable materials for the learner and generates output to pass on to the next step.

[0412] Step 4:

[0413] Sensors embedded in the user's device capture the user's facial expressions and voice data. This data is passed as input to an emotion engine, which analyzes the user's current emotional state. The emotion engine then uses machine learning algorithms to output emotional data.

[0414] Step 5:

[0415] The server receives emotional state data from the emotion engine and further refines the filtered training material. Here, the emotional data is used to change the content and difficulty level of the training material, and the training material to be presented as the final output is determined.

[0416] Step 6:

[0417] The server sends the tailored learning materials to the device and presents them to the user. The user can access these personalized learning materials via the device and progress through their learning. The device outputs its display, providing the user with information in a visual or auditory form.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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".

[0434] This invention is an online learning support system that meets the needs of learners and efficiently provides optimal learning materials based on learner input. This system is realized through the interaction of a server, a terminal, and a user.

[0435] Users enter learning keywords via their device. This information is sent from the device to the server. The server uses the received keywords to search for relevant learning materials from various online sources on the web. Specifically, it quickly collects diverse educational content using web scraping techniques and APIs.

[0436] Next, the server analyzes the collected learning materials and filters them, taking into account the user's learning level and history. This process extracts only the information best suited to the learner. The filtered results are sent to the terminal as an organized list and displayed on the interface for easy selection by the user.

[0437] Furthermore, the server records the user's selections and learning history, updating the learner profile to provide more precisely personalized suggestions for future use. In this way, users can quickly access the learning content they need and obtain appropriate learning resources.

[0438] For example, if a user enters "basics of differential and integral calculus," the server will find relevant introductory videos and problem sets and present them according to the user's learning level. It can also suggest additional resources within the same difficulty range based on previously learned content. This allows users to expand their knowledge seamlessly and effectively.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] The user enters learning content keywords on their device and presses the search button. The device collects this input data and sends it to the server as an HTTP request.

[0442] Step 2:

[0443] The server analyzes the learning content keywords received from the terminal. Based on these keywords, the server initiates appropriate API calls or web scraping procedures to collect relevant learning materials.

[0444] Step 3:

[0445] The server retrieves data from relevant sources on the internet. Specifically, it retrieves video data from YouTube and other educational platforms via APIs, and collects practice questions from open websites.

[0446] Step 4:

[0447] The server analyzes the acquired data and filters it based on the learner's profile information and past learning history. This filtering selects the most suitable learning materials according to the learner's level.

[0448] Step 5:

[0449] The server formats the filtered learning materials and converts them into a user-friendly format. This includes a list containing the title, link, brief description, and recommended level of the learning material.

[0450] Step 6:

[0451] The server sends a list of organized learning materials to the device.

[0452] Step 7:

[0453] The list of materials received by the device is displayed on the user interface and presented to the user in a selectable format. The user can then choose materials that match their interests.

[0454] Step 8:

[0455] When a user selects specific learning material, that selection information is sent from the device to the server. The server uses this information to record the user's learning history in a database.

[0456] Step 9:

[0457] The server updates this historical data to prepare for providing more personalized learning materials in future searches.

[0458] (Example 1)

[0459] 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."

[0460] Traditional online learning support systems struggle to efficiently provide optimal educational materials tailored to each learner's individual needs and level. This results in learners spending considerable time and effort finding materials that match their learning progress. Furthermore, providing a personalized experience based on learning history is also difficult.

[0461] 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.

[0462] In this invention, the server includes means for receiving educational content keywords entered by the learner, means for obtaining relevant educational materials from electronic information sources, and means for selecting the obtained educational materials according to the learner's educational level and history. This makes it possible to quickly provide educational materials that are suitable for the individual needs of the learner and to realize a personalized learning experience.

[0463] A "learner" refers to an individual whose purpose is to acquire knowledge through educational materials.

[0464] "Educational content keywords" refer to words or phrases that learners enter to express specific themes or topics they want to learn about.

[0465] "Electronic information sources" refer to various education-related databases and platforms provided on the internet or in digital format.

[0466] "Educational materials" refer to content such as textbooks, videos, and workbooks used by learners for educational purposes.

[0467] "Educational level" refers to a measure that indicates a learner's current level of knowledge and progress in learning.

[0468] "History" refers to a record of what a learner has studied in the past and the educational materials they have selected.

[0469] "Selection" refers to the filtering process of choosing educational materials that are suitable for the learner from the materials that have been acquired.

[0470] "Learner characteristics" refer to an individual learning profile of a learner, constructed based on their past learning history and selected educational materials.

[0471] An "application program interface" refers to an interface used to link functions and data between different software programs.

[0472] This system is an online learning support system that provides individually optimized educational materials based on educational content keywords entered by learners. The system is built on the interaction between the server, terminal, and user.

[0473] First, the user enters educational keywords indicating the topic they want to learn about via their device. For example, they might enter the keyword "Fundamentals of Differential and Integral Calculus" into their device. The device then sends this information to the server. The server analyzes this data and uses web scraping techniques and publicly available application programming interfaces to search for corresponding educational materials. Specifically, it utilizes Python libraries such as Beautiful Soup and APIs provided by various educational platforms.

[0474] The server uses the acquired educational materials to select appropriate materials, taking into account the learner's current educational level and past history. This filtering process utilizes machine learning techniques based on learner characteristics. Specifically, it performs analysis using machine learning libraries such as Scikit-learn.

[0475] Next, the server sends the selection results to the terminal and displays them in a format that the user can easily view on the interface. The user's selected materials and their learning history are also recorded on the server and updated in the database as learner characteristics. This allows the system to provide even more refined personalized support the next time the user uses it.

[0476] A concrete example of a prompt is, "Please suggest the best learning materials for the user to learn the basics of differential and integral calculus." This prompt is sent to a generative AI model, which helps learners efficiently deepen their knowledge by suggesting the most suitable educational materials.

[0477] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0478] Step 1:

[0479] The user enters educational content keywords into the device that indicate what they want to learn. The entered data is treated as keywords and prepared to be sent to the server. Specifically, a simple UI is displayed on the device, and when the user enters keywords and presses the send button, the entered data is converted into a format that can be sent to the server.

[0480] Step 2:

[0481] The terminal sends the keyword entered by the user to the server. The server receives the transmitted keyword, decodes it, and prepares for the next processing step. It receives the keyword sent from the terminal as input data and uses it in the next data retrieval process.

[0482] Step 3:

[0483] The server searches for and collects relevant educational materials from electronic sources based on the received keywords. This is done using web scraping techniques and a publicly available application programming interface. The input is the keywords to be processed, and the output is a list of relevant educational materials. In this process, the Python library Beautiful Soup is used to parse web pages, and the necessary data is pulled using a public API.

[0484] Step 4:

[0485] The server sorts the collected educational materials based on the learner's educational level and history. Machine learning techniques are used here to select the most suitable materials. The input is the educational materials collected in the previous step, and the output is the sorted educational materials. Specifically, the Scikit-learn library is used to select materials based on a predictive model.

[0486] Step 5:

[0487] The server sends selected educational materials to the terminal. The terminal displays the received materials in an organized manner on its user interface. The input is the selected educational materials from the server, and the output is a display of materials in a user-friendly format. On the terminal side, materials are displayed in list or card format, providing the user with intuitive access.

[0488] Step 6:

[0489] The server records the learner's selected materials and learning history in a database and updates the learner profile. This allows for further optimization of future learning support. The input is the user's selected materials and operation history, and the output is the updated learner profile. The database update process is integrated into a specific learning management system to reflect the learning history.

[0490] (Application Example 1)

[0491] 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."

[0492] With the spread of online education, it is not easy for learners to find suitable learning materials from the vast amount of information available. Furthermore, there is a need for material recommendations tailored to each learner's knowledge level and past learning history, but existing systems are insufficient to address this. Additionally, providing an interface that displays filtered information in an intuitive and easily understandable way is another challenge.

[0493] 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.

[0494] In this invention, the server includes means for receiving learning content keywords entered by the learner, means for obtaining relevant information from online information sources based on the learning content keywords, and means for selecting the obtained information according to the learner's knowledge level and history. This makes it possible for learners to easily find learning materials optimized for them.

[0495] "Learning content keywords entered by the learner" are words or phrases that express the content the learner wants to learn.

[0496] "Online information sources" refer to a collection of digital information accessible via the internet.

[0497] "Related information" refers to educational materials that are deemed to be related to the learning content keywords.

[0498] "Knowledge level" is an indicator that represents a learner's current level of understanding and ability.

[0499] "History" refers to a record of what a learner has studied in the past and the materials they have selected.

[0500] "Selecting" refers to the act of choosing information that is suitable for the learner's needs.

[0501] A "device" is an electronic device used to display or manipulate presented information.

[0502] A "communication terminal" is a device used to send and receive information.

[0503] A "digital interface" refers to the screens and operating methods that users use to interact with a computer system.

[0504] "Data analysis technology" refers to methods and techniques for extracting meaningful information based on collected data.

[0505] "Open Application Interface Technology" refers to a protocol that defines how external systems can utilize specific functions.

[0506] The embodiments for carrying out the present invention are mainly based on the interaction between a server, a terminal, and a user.

[0507] First, the user uses a communication device to input learning content keywords. These devices, such as smartphones and tablets, are electronic devices capable of transmitting data to a server via the internet. The entered keywords accurately reflect the content the learner is seeking.

[0508] Next, the server collects relevant information from online sources based on the received keywords. The server utilizes data analysis techniques using Python and publicly available application interface technologies to efficiently gather information. Web scraping techniques using tools like BeautifulSoup may also be employed.

[0509] The collected information is filtered according to the learner's knowledge level and past history. The server refers to past learning history data to identify the most suitable learning materials for the learner and provides personalized recommendations as needed. The filtered information is sent to the user's device as an organized list.

[0510] For example, if a user enters the keyword "machine learning for beginners" using a communication device, the server uses that information to select and present appropriate tutorials and explanatory videos to the user. The user can then proceed with their learning based on the presented information.

[0511] Furthermore, the server can continuously record the learning history in the learner program, making it possible to provide more precise information in subsequent sessions.

[0512] A concrete example of a prompt would be, "Suggest online learning resources related to the following keyword: 'machine learning for beginners'."

[0513] As described above, the implementation of this invention enables learners to utilize learning materials efficiently and individually.

[0514] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0515] Step 1:

[0516] The user enters learning keywords using a communication terminal. The entered keywords are temporarily stored on the terminal and prepared for transmission to the server. Once the user has finished entering the keywords, the data is formatted for transmission.

[0517] Step 2:

[0518] The terminal packets the entered keywords and sends them to the server via the internet. The output here is packet data of the learned keywords converted into a format that the server can process.

[0519] Step 3:

[0520] The server analyzes the received keywords and searches for relevant online information sources. In this process, Python is used to retrieve educational materials related to the keywords through APIs and web scraping techniques. The input is the keyword, and the output is a list of potential educational materials.

[0521] Step 4:

[0522] The server analyzes the collected educational materials and sorts them based on the learner's knowledge level and learning history. The data processing here involves matching the acquired information with the user profile to select materials of appropriate difficulty.

[0523] Step 5:

[0524] The selected learning materials are organized into a list format and sent to the device. The input in this process is the selected educational materials, and the output is a list of materials that can be displayed to the user.

[0525] Step 6:

[0526] The device displays the received list on the user interface. The user can intuitively browse this list and select learning materials of interest as needed. The selected information is temporarily recorded for future recommendations.

[0527] Step 7:

[0528] The server records the user's learning history and updates the learner profile. The updated information is used to recommend learning materials for future sessions. In this step, the input is the user's selection history, and the output is the updated learner profile.

[0529] 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.

[0530] This invention provides a system that offers relevant learning materials based on keywords entered by the learner, and also provides a personalized learning experience that takes into account the user's emotional state. This system operates in combination with a server, terminal, and emotion engine, and aims to improve the user's learning efficiency and motivation.

[0531] The user first enters keywords related to the learning content via their device. This information is sent from the device to the server. The server uses the received keywords to retrieve relevant learning materials from online sources. Web scraping techniques and public APIs are used to quickly collect diverse educational content.

[0532] After collecting training material, the server uses an emotion engine to recognize the user's current emotional state. The emotion engine generates emotional data based on the user's facial expressions, keyboard input speed, voice tone, etc., and analyzes the results. Based on this data, the server filters the training material to match the user's emotional state and selects the most suitable resources.

[0533] The filtered learning materials are presented to the user in a way that is adjusted according to their emotional state, taking into account their learning level and history. For example, if the emotion engine determines that the user is stressed, visually appealing content with a relaxing effect will be selected. Conversely, if the user is highly motivated, materials containing challenging problems may be presented.

[0534] Furthermore, the server records the user's learning history and emotional data, and refers to this data during subsequent use to provide more deeply personalized learning support. In this way, users can always receive a learning experience that is suited to their current state, enabling them to learn effectively.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The user enters keywords related to the learning content into their device and performs a search. The device then sends this information to the server.

[0538] Step 2:

[0539] The server analyzes the learning keywords received from the terminal and searches for relevant online information sources. The server uses web scraping techniques and public APIs to collect appropriate learning materials.

[0540] Step 3:

[0541] The server collects training material while simultaneously activating an emotion engine to analyze the user's emotions. Using the device's camera and microphone, it detects the user's facial expressions, voice, and behavioral patterns to generate emotion data.

[0542] Step 4:

[0543] The server analyzes the user's emotional data and re-evaluates the collected training material. The server filters the training material to match the user's current emotional state and updates the list accordingly.

[0544] Step 5:

[0545] The server formats the filtered learning materials and, taking into account the user's learning level and past history, sends an optimized content list to the device.

[0546] Step 6:

[0547] The device displays a list of received learning materials on the user interface, and the user selects from the list to begin learning.

[0548] Step 7:

[0549] The learning process progresses based on the content of the learning materials selected by the user. Simultaneously, the server records the user's selection history and changes in their emotions during learning in a database.

[0550] Step 8:

[0551] The server analyzes recorded historical data and emotional information to update the user profile to the latest content, which will then be used to improve learning support in the future.

[0552] (Example 2)

[0553] 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."

[0554] In modern education systems, personalized learning tailored to each learner's level of understanding and emotional state is often insufficient. This leads to problems such as decreased learning efficiency and difficulty maintaining motivation. Furthermore, while the amount of online learning material is vast, selecting the appropriate content is difficult. Therefore, there is a need to provide learners with necessary information quickly and effectively, and to optimize the learning experience according to their emotional state.

[0555] 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.

[0556] In this invention, the server includes means for receiving learning themes entered by the learner, means for obtaining relevant educational materials from online information sources, and means for analyzing the learner's emotional state. This enables the rapid selection and presentation of educational materials tailored to the learner's specific emotional state and learning level.

[0557] A "learning theme" refers to a specific topic or subject that a learner is interested in and wishes to learn about.

[0558] "Educational materials" is a general term for information sources and content provided to support learners' learning.

[0559] "Online information sources" refer to digital content and databases that are accessible via the internet.

[0560] "Data extraction technology" refers to methods for automatically collecting necessary information from specific websites or databases.

[0561] A "public program interface" refers to a standardized connection point that is made public for exchanging data between applications.

[0562] An "emotion analysis engine" refers to the technology and algorithms used to analyze a user's emotional state based on external input data.

[0563] "Filtering" refers to the process of selecting data or content based on specific criteria or conditions.

[0564] "Learning level" refers to the degree of knowledge and skills that a learner currently possesses.

[0565] "Learning history" refers to a record of learning activities and educational materials used by learners in the past.

[0566] In the specific implementation of this system, a server, terminal, and sentiment analysis engine work together. The user uses the terminal to input the topic they wish to learn about. This information is transmitted to the server via an internet connection. Based on the received topic, the server retrieves relevant educational materials from various online sources. This process utilizes data extraction techniques and a publicly accessible programming interface to gather information quickly and efficiently.

[0567] The server is equipped with an emotion analysis engine to analyze the user's emotional state. Using input data provided by the device's camera and microphone, it analyzes the user's facial expressions and voice to quantify their emotional state.

[0568] The server filters the acquired educational materials based on the user's emotional state, learning level, and past history. This filtering presents the optimal learning experience tailored to the user's state, thereby improving learning efficiency.

[0569] For example, if a user enters "data science" as their topic, the server will retrieve relevant online courses and articles. If the sentiment analysis engine detects the user's level of concentration, it can provide content that includes challenging exercises.

[0570] An example of a prompt might be, "How can I provide personalized educational materials based on emotional states?" This allows the generative AI model to generate responses tailored to the user's needs.

[0571] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0572] Step 1:

[0573] The user enters keywords related to the topic they wish to learn about through their device. This input information is sent to the server in text data format. The server receives this input and stores it in a database in preparation for the next processing step.

[0574] Step 2:

[0575] The server collects relevant educational materials from online sources based on the entered keywords. This process utilizes data extraction techniques and a publicly available program interface. The input is keywords, and the output is a list of relevant educational materials, which are stored in a database.

[0576] Step 3:

[0577] The server uses an emotion analysis engine to analyze the user's emotional state. Camera video and audio data acquired from the terminal are used as input, and this data is analyzed to generate an emotion score. The output is numerical data indicating the user's emotional state.

[0578] Step 4:

[0579] The server filters the acquired educational materials based on the user's emotional state and learning history. The inputs are a list of educational materials, emotional scores, and learning history, while the output is user-optimized and filtered educational materials. These results are then added to the database.

[0580] Step 5:

[0581] The terminal receives filtered educational materials from the server and presents them to the user. When displayed, the materials are provided in an interactive format and with a visually appealing layout, allowing the user to gain a learning experience. The input to this process is filtered educational materials, and the output is information that is visually understandable to the user.

[0582] Step 6:

[0583] The server records the user's choices, learning history, and sentiment data at the end of each session. This data is used to enhance personalization on subsequent accesses and is securely stored in a database. In this process, the collected data is the input, and the output is an updated learner profile.

[0584] (Application Example 2)

[0585] 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."

[0586] In today's world, learners can access learning materials from a variety of online sources, but it is extremely difficult for them to receive the optimal learning experience tailored to their individual learning situation and emotions. Furthermore, providing uniform materials without considering emotional states can lead to decreased learning efficiency. Therefore, accurately understanding learners' emotional states and providing individually optimized learning experiences is essential.

[0587] 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.

[0588] In this invention, the server includes means for receiving learning content keywords entered by the learner, means for obtaining relevant learning materials from online information sources based on the learning content keywords, means for filtering the obtained learning materials according to the learner's learning level and history, means for analyzing the learner's emotional state using sensors incorporated in the device, and means for adjusting and presenting the learning materials based on the emotional state. This enables a more personalized learning experience that takes into account the learner's emotional state.

[0589] "Learning content keywords" are input information that represents the topics or themes that learners want to study.

[0590] "Online information sources" refer to various information platforms and databases that exist on the internet.

[0591] "Learning materials" refer to content such as texts, videos, and quizzes that help learners acquire knowledge.

[0592] "Learner's learning level" is an indicator that shows the stage of knowledge and skills that a learner has currently attained.

[0593] "Learner history" refers to records of past learning activities, choices, and achievements.

[0594] "Filtering" is the process of selecting learning materials in the format and content that is most suitable for the learner.

[0595] A "sensor" is an electronic detection device used to analyze the emotional state of a learner.

[0596] "Emotional state" refers to data that indicates the learner's psychological state and changes in their emotions.

[0597] "Adjustment" refers to the act of appropriately changing learning materials according to the learner's emotional state and other factors.

[0598] "Presentation" refers to the act of ultimately displaying information or content to learners on a screen or other means.

[0599] The system for realizing this invention consists of a terminal used by the learner, a server for information processing, and sensors built into the device. This system receives learning content keywords entered by the user from the terminal and sends that information to the server. Based on the received keywords, the server retrieves relevant learning materials from online information sources using web scraping technology and public APIs.

[0600] The server then filters the acquired learning materials according to the learner's learning level and history. This filtering is based on what materials the learner has used in the past and what results they have achieved.

[0601] Furthermore, the emotion engine analyzes the user's current emotional state using data from sensors built into the user's device (e.g., camera and microphone). Existing technologies such as "Face API" and "Azure Emotion API" are used for this analysis. Based on this emotional data, the server adjusts and presents the training material in a way that is appropriate for the user's emotions.

[0602] For example, if a user inputs that they want to learn "linear algebra" and the server detects that they are excited, the server will select and present materials that include challenging quizzes and advanced problems. On the other hand, if the same user is feeling fatigued, the server will provide videos and animations that are visually relaxing.

[0603] For example, if a user who wants to learn the basics of project management enters the prompt message, "Please recommend content that allows me to learn the fundamental knowledge necessary for project management in a relaxed manner," the system can provide appropriate learning materials.

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The user enters keywords related to the learning content using a terminal. The entered keywords become input data for the system, and the terminal sends this information to the server.

[0607] Step 2:

[0608] The server retrieves relevant learning materials from online sources based on the received keywords. It collects data using web scraping techniques and public APIs, and compiles the results into learning materials. This becomes the initial output from the server.

[0609] Step 3:

[0610] The server receives the learner's learning level and past history as input and filters the retrieved learning materials. This process uses database queries and algorithms to select the most suitable materials for the learner and generates output to pass on to the next step.

[0611] Step 4:

[0612] Sensors embedded in the user's device capture the user's facial expressions and voice data. This data is passed as input to an emotion engine, which analyzes the user's current emotional state. The emotion engine then uses machine learning algorithms to output emotional data.

[0613] Step 5:

[0614] The server receives emotional state data from the emotion engine and further refines the filtered training material. Here, the emotional data is used to change the content and difficulty level of the training material, and the training material to be presented as the final output is determined.

[0615] Step 6:

[0616] The server sends the tailored learning materials to the device and presents them to the user. The user can access these personalized learning materials via the device and progress through their learning. The device outputs its display, providing the user with information in a visual or auditory form.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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".

[0634] This invention is an online learning support system that meets the needs of learners and efficiently provides optimal learning materials based on learner input. This system is realized through the interaction of a server, a terminal, and a user.

[0635] Users enter learning keywords via their device. This information is sent from the device to the server. The server uses the received keywords to search for relevant learning materials from various online sources on the web. Specifically, it quickly collects diverse educational content using web scraping techniques and APIs.

[0636] Next, the server analyzes the collected learning materials and filters them, taking into account the user's learning level and history. This process extracts only the information best suited to the learner. The filtered results are sent to the terminal as an organized list and displayed on the interface for easy selection by the user.

[0637] Furthermore, the server records the user's selections and learning history, updating the learner profile to provide more precisely personalized suggestions for future use. In this way, users can quickly access the learning content they need and obtain appropriate learning resources.

[0638] For example, if a user enters "basics of differential and integral calculus," the server will find relevant introductory videos and problem sets and present them according to the user's learning level. It can also suggest additional resources within the same difficulty range based on previously learned content. This allows users to expand their knowledge seamlessly and effectively.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] The user enters learning content keywords on their device and presses the search button. The device collects this input data and sends it to the server as an HTTP request.

[0642] Step 2:

[0643] The server analyzes the learning content keywords received from the terminal. Based on these keywords, the server initiates appropriate API calls or web scraping procedures to collect relevant learning materials.

[0644] Step 3:

[0645] The server retrieves data from relevant sources on the internet. Specifically, it retrieves video data from YouTube and other educational platforms via APIs, and collects practice questions from open websites.

[0646] Step 4:

[0647] The server analyzes the acquired data and filters it based on the learner's profile information and past learning history. This filtering selects the most suitable learning materials according to the learner's level.

[0648] Step 5:

[0649] The server formats the filtered learning materials and converts them into a user-friendly format. This includes a list containing the title, link, brief description, and recommended level of the learning material.

[0650] Step 6:

[0651] The server sends a list of organized learning materials to the device.

[0652] Step 7:

[0653] The list of materials received by the device is displayed on the user interface and presented to the user in a selectable format. The user can then choose materials that match their interests.

[0654] Step 8:

[0655] When a user selects specific learning material, that selection information is sent from the device to the server. The server uses this information to record the user's learning history in a database.

[0656] Step 9:

[0657] The server updates this historical data to prepare for providing more personalized learning materials in future searches.

[0658] (Example 1)

[0659] 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".

[0660] Traditional online learning support systems struggle to efficiently provide optimal educational materials tailored to each learner's individual needs and level. This results in learners spending considerable time and effort finding materials that match their learning progress. Furthermore, providing a personalized experience based on learning history is also difficult.

[0661] 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.

[0662] In this invention, the server includes means for receiving educational content keywords entered by the learner, means for obtaining relevant educational materials from electronic information sources, and means for selecting the obtained educational materials according to the learner's educational level and history. This makes it possible to quickly provide educational materials that are suitable for the individual needs of the learner and to realize a personalized learning experience.

[0663] A "learner" refers to an individual whose purpose is to acquire knowledge through educational materials.

[0664] "Educational content keywords" refer to words or phrases that learners enter to express specific themes or topics they want to learn about.

[0665] "Electronic information sources" refer to various education-related databases and platforms provided on the internet or in digital format.

[0666] "Educational materials" refer to content such as textbooks, videos, and workbooks used by learners for educational purposes.

[0667] "Educational level" refers to a measure that indicates a learner's current level of knowledge and progress in learning.

[0668] "History" refers to a record of what a learner has studied in the past and the educational materials they have selected.

[0669] "Selection" refers to the filtering process of choosing educational materials that are suitable for the learner from the materials that have been acquired.

[0670] "Learner characteristics" refer to an individual learning profile of a learner, constructed based on their past learning history and selected educational materials.

[0671] An "application program interface" refers to an interface used to link functions and data between different software programs.

[0672] This system is an online learning support system that provides individually optimized educational materials based on educational content keywords entered by learners. The system is built on the interaction between the server, terminal, and user.

[0673] First, the user enters educational keywords indicating the topic they want to learn about via their device. For example, they might enter the keyword "Fundamentals of Differential and Integral Calculus" into their device. The device then sends this information to the server. The server analyzes this data and uses web scraping techniques and publicly available application programming interfaces to search for corresponding educational materials. Specifically, it utilizes Python libraries such as Beautiful Soup and APIs provided by various educational platforms.

[0674] The server uses the acquired educational materials to select appropriate materials, taking into account the learner's current educational level and past history. This filtering process utilizes machine learning techniques based on learner characteristics. Specifically, it performs analysis using machine learning libraries such as Scikit-learn.

[0675] Next, the server sends the selection results to the terminal and displays them in a format that the user can easily view on the interface. The user's selected materials and their learning history are also recorded on the server and updated in the database as learner characteristics. This allows the system to provide even more refined personalized support the next time the user uses it.

[0676] A concrete example of a prompt is, "Please suggest the best learning materials for the user to learn the basics of differential and integral calculus." This prompt is sent to a generative AI model, which helps learners efficiently deepen their knowledge by suggesting the most suitable educational materials.

[0677] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0678] Step 1:

[0679] The user enters educational content keywords into the device that indicate what they want to learn. The entered data is treated as keywords and prepared to be sent to the server. Specifically, a simple UI is displayed on the device, and when the user enters keywords and presses the send button, the entered data is converted into a format that can be sent to the server.

[0680] Step 2:

[0681] The terminal sends the keyword entered by the user to the server. The server receives the transmitted keyword, decodes it, and prepares for the next processing step. It receives the keyword sent from the terminal as input data and uses it in the next data retrieval process.

[0682] Step 3:

[0683] The server searches for and collects relevant educational materials from electronic sources based on the received keywords. This is done using web scraping techniques and a publicly available application programming interface. The input is the keywords to be processed, and the output is a list of relevant educational materials. In this process, the Python library Beautiful Soup is used to parse web pages, and the necessary data is pulled using a public API.

[0684] Step 4:

[0685] The server sorts the collected educational materials based on the learner's educational level and history. Machine learning techniques are used here to select the most suitable materials. The input is the educational materials collected in the previous step, and the output is the sorted educational materials. Specifically, the Scikit-learn library is used to select materials based on a predictive model.

[0686] Step 5:

[0687] The server sends selected educational materials to the terminal. The terminal displays the received materials in an organized manner on its user interface. The input is the selected educational materials from the server, and the output is a display of materials in a user-friendly format. On the terminal side, materials are displayed in list or card format, providing the user with intuitive access.

[0688] Step 6:

[0689] The server records the learner's selected materials and learning history in a database and updates the learner profile. This allows for further optimization of future learning support. The input is the user's selected materials and operation history, and the output is the updated learner profile. The database update process is integrated into a specific learning management system to reflect the learning history.

[0690] (Application Example 1)

[0691] 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".

[0692] With the spread of online education, it is not easy for learners to find suitable learning materials from the vast amount of information available. Furthermore, there is a need for material recommendations tailored to each learner's knowledge level and past learning history, but existing systems are insufficient to address this. Additionally, providing an interface that displays filtered information in an intuitive and easily understandable way is another challenge.

[0693] 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.

[0694] In this invention, the server includes means for receiving learning content keywords entered by the learner, means for obtaining relevant information from online information sources based on the learning content keywords, and means for selecting the obtained information according to the learner's knowledge level and history. This makes it possible for learners to easily find learning materials optimized for them.

[0695] "Learning content keywords entered by the learner" are words or phrases that express the content the learner wants to learn.

[0696] "Online information sources" refer to a collection of digital information accessible via the internet.

[0697] "Related information" refers to educational materials that are deemed to be related to the learning content keywords.

[0698] "Knowledge level" is an indicator that represents a learner's current level of understanding and ability.

[0699] "History" refers to a record of what a learner has studied in the past and the materials they have selected.

[0700] "Selecting" refers to the act of choosing information that is suitable for the learner's needs.

[0701] A "device" is an electronic device used to display or manipulate presented information.

[0702] A "communication terminal" is a device used to send and receive information.

[0703] A "digital interface" refers to the screens and operating methods that users use to interact with a computer system.

[0704] "Data analysis technology" refers to methods and techniques for extracting meaningful information based on collected data.

[0705] "Open Application Interface Technology" refers to a protocol that defines how external systems can utilize specific functions.

[0706] The embodiments for carrying out the present invention are mainly based on the interaction between a server, a terminal, and a user.

[0707] First, the user uses a communication device to input learning content keywords. These devices, such as smartphones and tablets, are electronic devices capable of transmitting data to a server via the internet. The entered keywords accurately reflect the content the learner is seeking.

[0708] Next, the server collects relevant information from online sources based on the received keywords. The server utilizes data analysis techniques using Python and publicly available application interface technologies to efficiently gather information. Web scraping techniques using tools like BeautifulSoup may also be employed.

[0709] The collected information is filtered according to the learner's knowledge level and past history. The server refers to past learning history data to identify the most suitable learning materials for the learner and provides personalized recommendations as needed. The filtered information is sent to the user's device as an organized list.

[0710] For example, if a user enters the keyword "machine learning for beginners" using a communication device, the server uses that information to select and present appropriate tutorials and explanatory videos to the user. The user can then proceed with their learning based on the presented information.

[0711] Furthermore, the server can continuously record the learning history in the learner program, making it possible to provide more precise information in subsequent sessions.

[0712] A concrete example of a prompt would be, "Suggest online learning resources related to the following keyword: 'machine learning for beginners'."

[0713] As described above, the implementation of this invention enables learners to utilize learning materials efficiently and individually.

[0714] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0715] Step 1:

[0716] The user enters learning keywords using a communication terminal. The entered keywords are temporarily stored on the terminal and prepared for transmission to the server. Once the user has finished entering the keywords, the data is formatted for transmission.

[0717] Step 2:

[0718] The terminal packets the entered keywords and sends them to the server via the internet. The output here is packet data of the learned keywords converted into a format that the server can process.

[0719] Step 3:

[0720] The server analyzes the received keywords and searches for relevant online information sources. In this process, Python is used to retrieve educational materials related to the keywords through APIs and web scraping techniques. The input is the keyword, and the output is a list of potential educational materials.

[0721] Step 4:

[0722] The server analyzes the collected educational materials and sorts them based on the learner's knowledge level and learning history. The data processing here involves matching the acquired information with the user profile to select materials of appropriate difficulty.

[0723] Step 5:

[0724] The selected learning materials are organized into a list format and sent to the device. The input in this process is the selected educational materials, and the output is a list of materials that can be displayed to the user.

[0725] Step 6:

[0726] The device displays the received list on the user interface. The user can intuitively browse this list and select learning materials of interest as needed. The selected information is temporarily recorded for future recommendations.

[0727] Step 7:

[0728] The server records the user's learning history and updates the learner profile. The updated information is used to recommend learning materials for future sessions. In this step, the input is the user's selection history, and the output is the updated learner profile.

[0729] 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.

[0730] This invention provides a system that offers relevant learning materials based on keywords entered by the learner, and also provides a personalized learning experience that takes into account the user's emotional state. This system operates in combination with a server, terminal, and emotion engine, and aims to improve the user's learning efficiency and motivation.

[0731] The user first enters keywords related to the learning content via their device. This information is sent from the device to the server. The server uses the received keywords to retrieve relevant learning materials from online sources. Web scraping techniques and public APIs are used to quickly collect diverse educational content.

[0732] After collecting training material, the server uses an emotion engine to recognize the user's current emotional state. The emotion engine generates emotional data based on the user's facial expressions, keyboard input speed, voice tone, etc., and analyzes the results. Based on this data, the server filters the training material to match the user's emotional state and selects the most suitable resources.

[0733] The filtered learning materials are presented to the user in a way that is adjusted according to their emotional state, taking into account their learning level and history. For example, if the emotion engine determines that the user is stressed, visually appealing content with a relaxing effect will be selected. Conversely, if the user is highly motivated, materials containing challenging problems may be presented.

[0734] Furthermore, the server records the user's learning history and emotional data, and refers to this data during subsequent use to provide more deeply personalized learning support. In this way, users can always receive a learning experience that is suited to their current state, enabling them to learn effectively.

[0735] The following describes the processing flow.

[0736] Step 1:

[0737] The user enters keywords related to the learning content into their device and performs a search. The device then sends this information to the server.

[0738] Step 2:

[0739] The server analyzes the learning keywords received from the terminal and searches for relevant online information sources. The server uses web scraping techniques and public APIs to collect appropriate learning materials.

[0740] Step 3:

[0741] The server collects training material while simultaneously activating an emotion engine to analyze the user's emotions. Using the device's camera and microphone, it detects the user's facial expressions, voice, and behavioral patterns to generate emotion data.

[0742] Step 4:

[0743] The server analyzes the user's emotional data and re-evaluates the collected training material. The server filters the training material to match the user's current emotional state and updates the list accordingly.

[0744] Step 5:

[0745] The server formats the filtered learning materials and, taking into account the user's learning level and past history, sends an optimized content list to the device.

[0746] Step 6:

[0747] The device displays a list of received learning materials on the user interface, and the user selects from the list to begin learning.

[0748] Step 7:

[0749] The learning process progresses based on the content of the learning materials selected by the user. Simultaneously, the server records the user's selection history and changes in their emotions during learning in a database.

[0750] Step 8:

[0751] The server analyzes recorded historical data and emotional information to update the user profile to the latest content, which will then be used to improve learning support in the future.

[0752] (Example 2)

[0753] 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".

[0754] In modern education systems, personalized learning tailored to each learner's level of understanding and emotional state is often insufficient. This leads to problems such as decreased learning efficiency and difficulty maintaining motivation. Furthermore, while the amount of online learning material is vast, selecting the appropriate content is difficult. Therefore, there is a need to provide learners with necessary information quickly and effectively, and to optimize the learning experience according to their emotional state.

[0755] 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.

[0756] In this invention, the server includes means for receiving learning themes entered by the learner, means for obtaining relevant educational materials from online information sources, and means for analyzing the learner's emotional state. This enables the rapid selection and presentation of educational materials tailored to the learner's specific emotional state and learning level.

[0757] A "learning theme" refers to a specific topic or subject that a learner is interested in and wishes to learn about.

[0758] "Educational materials" is a general term for information sources and content provided to support learners' learning.

[0759] "Online information sources" refer to digital content and databases that are accessible via the internet.

[0760] "Data extraction technology" refers to methods for automatically collecting necessary information from specific websites or databases.

[0761] A "public program interface" refers to a standardized connection point that is made public for exchanging data between applications.

[0762] An "emotion analysis engine" refers to the technology and algorithms used to analyze a user's emotional state based on external input data.

[0763] "Filtering" refers to the process of selecting data or content based on specific criteria or conditions.

[0764] "Learning level" refers to the degree of knowledge and skills that a learner currently possesses.

[0765] "Learning history" refers to a record of learning activities and educational materials used by learners in the past.

[0766] In the specific implementation of this system, a server, terminal, and sentiment analysis engine work together. The user uses the terminal to input the topic they wish to learn about. This information is transmitted to the server via an internet connection. Based on the received topic, the server retrieves relevant educational materials from various online sources. This process utilizes data extraction techniques and a publicly accessible programming interface to gather information quickly and efficiently.

[0767] The server is equipped with an emotion analysis engine to analyze the user's emotional state. Using input data provided by the device's camera and microphone, it analyzes the user's facial expressions and voice to quantify their emotional state.

[0768] The server filters the acquired educational materials based on the user's emotional state, learning level, and past history. This filtering presents the optimal learning experience tailored to the user's state, thereby improving learning efficiency.

[0769] For example, if a user enters "data science" as their topic, the server will retrieve relevant online courses and articles. If the sentiment analysis engine detects the user's level of concentration, it can provide content that includes challenging exercises.

[0770] An example of a prompt might be, "How can I provide personalized educational materials based on emotional states?" This allows the generative AI model to generate responses tailored to the user's needs.

[0771] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0772] Step 1:

[0773] The user enters keywords related to the topic they wish to learn about through their device. This input information is sent to the server in text data format. The server receives this input and stores it in a database in preparation for the next processing step.

[0774] Step 2:

[0775] The server collects relevant educational materials from online sources based on the entered keywords. This process utilizes data extraction techniques and a publicly available program interface. The input is keywords, and the output is a list of relevant educational materials, which are stored in a database.

[0776] Step 3:

[0777] The server uses an emotion analysis engine to analyze the user's emotional state. Camera video and audio data acquired from the terminal are used as input, and this data is analyzed to generate an emotion score. The output is numerical data indicating the user's emotional state.

[0778] Step 4:

[0779] The server filters the acquired educational materials based on the user's emotional state and learning history. The inputs are a list of educational materials, emotional scores, and learning history, while the output is user-optimized and filtered educational materials. These results are then added to the database.

[0780] Step 5:

[0781] The terminal receives filtered educational materials from the server and presents them to the user. When displayed, the materials are provided in an interactive format and with a visually appealing layout, allowing the user to gain a learning experience. The input to this process is filtered educational materials, and the output is information that is visually understandable to the user.

[0782] Step 6:

[0783] The server records the user's choices, learning history, and sentiment data at the end of each session. This data is used to enhance personalization on subsequent accesses and is securely stored in a database. In this process, the collected data is the input, and the output is an updated learner profile.

[0784] (Application Example 2)

[0785] 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".

[0786] In today's world, learners can access learning materials from a variety of online sources, but it is extremely difficult for them to receive the optimal learning experience tailored to their individual learning situation and emotions. Furthermore, providing uniform materials without considering emotional states can lead to decreased learning efficiency. Therefore, accurately understanding learners' emotional states and providing individually optimized learning experiences is essential.

[0787] 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.

[0788] In this invention, the server includes means for receiving learning content keywords entered by the learner, means for obtaining relevant learning materials from online information sources based on the learning content keywords, means for filtering the obtained learning materials according to the learner's learning level and history, means for analyzing the learner's emotional state using sensors incorporated in the device, and means for adjusting and presenting the learning materials based on the emotional state. This enables a more personalized learning experience that takes into account the learner's emotional state.

[0789] "Learning content keywords" are input information that represents the topics or themes that learners want to study.

[0790] "Online information sources" refer to various information platforms and databases that exist on the internet.

[0791] "Learning materials" refer to content such as texts, videos, and quizzes that help learners acquire knowledge.

[0792] "Learner's learning level" is an indicator that shows the stage of knowledge and skills that a learner has currently attained.

[0793] "Learner history" refers to records of past learning activities, choices, and achievements.

[0794] "Filtering" is the process of selecting learning materials in the format and content that is most suitable for the learner.

[0795] A "sensor" is an electronic detection device used to analyze the emotional state of a learner.

[0796] "Emotional state" refers to data that indicates the learner's psychological state and changes in their emotions.

[0797] "Adjustment" refers to the act of appropriately changing learning materials according to the learner's emotional state and other factors.

[0798] "Presentation" refers to the act of ultimately displaying information or content to learners on a screen or other means.

[0799] The system for realizing this invention consists of a terminal used by the learner, a server for information processing, and sensors built into the device. This system receives learning content keywords entered by the user from the terminal and sends that information to the server. Based on the received keywords, the server retrieves relevant learning materials from online information sources using web scraping technology and public APIs.

[0800] The server then filters the acquired learning materials according to the learner's learning level and history. This filtering is based on what materials the learner has used in the past and what results they have achieved.

[0801] Furthermore, the emotion engine analyzes the user's current emotional state using data from sensors built into the user's device (e.g., camera and microphone). Existing technologies such as "Face API" and "Azure Emotion API" are used for this analysis. Based on this emotional data, the server adjusts and presents the training material in a way that is appropriate for the user's emotions.

[0802] For example, if a user inputs that they want to learn "linear algebra" and the server detects that they are excited, the server will select and present materials that include challenging quizzes and advanced problems. On the other hand, if the same user is feeling fatigued, the server will provide videos and animations that are visually relaxing.

[0803] For example, if a user who wants to learn the basics of project management enters the prompt message, "Please recommend content that allows me to learn the fundamental knowledge necessary for project management in a relaxed manner," the system can provide appropriate learning materials.

[0804] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0805] Step 1:

[0806] The user enters keywords related to the learning content using a terminal. The entered keywords become input data for the system, and the terminal sends this information to the server.

[0807] Step 2:

[0808] The server retrieves relevant learning materials from online sources based on the received keywords. It collects data using web scraping techniques and public APIs, and compiles the results into learning materials. This becomes the initial output from the server.

[0809] Step 3:

[0810] The server receives the learner's learning level and past history as input and filters the retrieved learning materials. This process uses database queries and algorithms to select the most suitable materials for the learner and generates output to pass on to the next step.

[0811] Step 4:

[0812] Sensors embedded in the user's device capture the user's facial expressions and voice data. This data is passed as input to an emotion engine, which analyzes the user's current emotional state. The emotion engine then uses machine learning algorithms to output emotional data.

[0813] Step 5:

[0814] The server receives emotional state data from the emotion engine and further refines the filtered training material. Here, the emotional data is used to change the content and difficulty level of the training material, and the training material to be presented as the final output is determined.

[0815] Step 6:

[0816] The server sends the tailored learning materials to the device and presents them to the user. The user can access these personalized learning materials via the device and progress through their learning. The device outputs its display, providing the user with information in a visual or auditory form.

[0817] 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.

[0818] 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.

[0819] 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 robot 414.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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."

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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 as being incorporated by reference.

[0838] The following is further disclosed regarding the embodiments described above.

[0839] (Claim 1)

[0840] A means of receiving learning content keywords entered by learners,

[0841] A means of obtaining relevant learning materials from online information sources based on the aforementioned learning content keywords,

[0842] A means for filtering the acquired learning materials according to the learner's learning level and history,

[0843] A means for presenting the filtered learning material to the learner,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, which includes means for recording learner selections and history information and using that information to provide future learning materials.

[0847] (Claim 3)

[0848] The system according to claim 1, comprising means of using web scraping technology and a public application programming interface in obtaining the aforementioned learning materials.

[0849] "Example 1"

[0850] (Claim 1)

[0851] A means of receiving educational content keywords entered by learners,

[0852] A means of obtaining relevant educational materials from electronic information sources based on the aforementioned educational content keywords,

[0853] A means for selecting the aforementioned acquired educational materials according to the learner's educational level and background,

[0854] A means for presenting the selected educational materials to learners,

[0855] A means of recording the educational materials and learning history selected by learners, and updating learner characteristics,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, which uses digital information analysis technology and a publicly available application program interface in acquiring the aforementioned educational materials.

[0859] (Claim 3)

[0860] The system according to claim 1, which includes means for accumulating learner selection and attribute information and utilizing it to provide future educational materials.

[0861] "Application Example 1"

[0862] (Claim 1)

[0863] A means of receiving learning content keywords entered by learners,

[0864] A means for obtaining relevant information from online information sources based on the aforementioned learning content keywords,

[0865] A means for selecting the acquired information according to the learner's knowledge level and history,

[0866] A device for presenting the selected information to the learner,

[0867] A means having a digital interface for displaying selected information on a communication terminal,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, which includes means for recording learners' choices and history and using them to provide information in the future.

[0871] (Claim 3)

[0872] The system according to claim 1, comprising means for utilizing data analysis techniques and publicly available application interface techniques in acquiring the aforementioned information.

[0873] "Example 2 of combining an emotion engine"

[0874] (Claim 1)

[0875] A means of receiving learning themes entered by learners,

[0876] A means of obtaining relevant educational materials from online sources based on the aforementioned learning theme,

[0877] Means for using data extraction techniques and public program interfaces when acquiring the aforementioned educational materials,

[0878] A means of analyzing the emotional state of learners,

[0879] A means for filtering the aforementioned educational materials according to the learner's emotional state, learning level, and history,

[0880] A means for presenting the filtered educational materials to the learner,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, which includes means for recording learner selections, history information, and emotional data, and for using this information to provide future educational materials.

[0884] (Claim 3)

[0885] The system according to claim 1, which includes means for using an emotion analysis engine to analyze the aforementioned emotional state, and using the user's input speed and facial expression data.

[0886] "Application example 2 of combining emotional engines"

[0887] (Claim 1)

[0888] A means of receiving learning content keywords entered by learners,

[0889] A means of obtaining relevant learning materials from online information sources based on the aforementioned learning content keywords,

[0890] A means for filtering the acquired learning materials according to the learner's learning level and history,

[0891] A means of analyzing the emotional state of learners using sensors embedded in a device,

[0892] A means for adjusting and presenting learning materials based on the aforementioned emotional state,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, which includes means for recording learner selections, history information, and emotional data, and for using this information to provide future learning materials.

[0896] (Claim 3)

[0897] The system according to claim 1, comprising means for using an information acquisition method and a public interface in acquiring the aforementioned learning materials. [Explanation of Symbols]

[0898] 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. A means of receiving learning content keywords entered by learners, A means of obtaining relevant learning materials from online information sources based on the aforementioned learning content keywords, A means for filtering the acquired learning materials according to the learner's learning level and history, A means for presenting the filtered learning material to the learner, A system that includes this.

2. The system according to claim 1, which includes means for recording learner selections and history information and using that information to provide future learning materials.

3. The system according to claim 1, comprising means of using web scraping technology and a public application programming interface in obtaining the aforementioned learning materials.

Images