System

Abstract

A system is provided.SOLUTION: A system comprising: means for creating a customized curriculum based on a learner's skill, interest, and learning style; means for building a network of national and international experts to provide their knowledge; means for tracking and managing learning progress and providing feedback; means for providing opportunities for learners to actually meet face-to-face and build a learning community; and means for collaborating with local schools, libraries, and municipalities to utilize as an offline teaching platform.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The current education system faces problems such as disparities in educational opportunities between urban and rural areas and an inability to fully address the diverse needs of individual learners. Furthermore, there is a lack of provision of educational content customized to learners' interests and skills, and there are limited opportunities to widely share expert knowledge with learners. As a result, issues of poverty and discrimination arising from educational disparities remain unresolved, and learners are unable to enjoy optimal learning experiences. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system that includes means for generating a customized curriculum based on a learner's skills, interests, and learning style, means for building a network that brings together domestic and international experts and provides their knowledge, means for tracking and managing learning progress and providing feedback, means for building a learning community by providing opportunities for learners to meet in person both online and offline, and means for cooperating with local schools, libraries, and local governments to utilize it as an offline education platform.This system can provide an optimal learning experience for each learner, eliminate educational disparities, and improve the quality of learning through collaboration with experts.

[0006] A "learner" is someone who seeks to acquire knowledge or skills through an educational program.

[0007] "Skill" refers to the ability to execute acquired knowledge and techniques in a particular field.

[0008] "Interest" refers to interest or curiosity in a particular topic or field.

[0009] "Learning style" refers to a learner's individual method or approach to effectively acquiring knowledge.

[0010] "Curriculum" refers to the organized set of educational content and materials provided to learners.

[0011] An "expert" is someone who has advanced knowledge and skills in a particular field.

[0012] A "network" refers to a connection between multiple individuals or organizations to share information and resources.

[0013] "Learning progress" refers to the process and outcome of how much knowledge and skills a learner has acquired through the curriculum.

[0014] "Feedback" refers to the evaluation and suggestions for improvement provided to learners regarding their learning activities and achievements.

[0015] A "community" refers to a group of learners and educators who share a common purpose or interest.

[0016] An "offline education platform" refers to educational activities that do not rely on the internet and are conducted using physical locations and facilities.

[0017] "Generative means" refers to the methods or processes that create something new for a specific purpose.

[0018] "Means of construction" refers to the methods and processes for constructing a system or network.

[0019] "Tracking and management tools" refers to the methods and processes used to record and effectively manage learner activities and data.

[0020] "Means of delivery" refers to the methods or processes used to provide specific resources or services to users.

[0021] "Collaboration means" refers to methods or processes by which multiple individuals or organizations work together.

[0022] "AI algorithm" refers to a computational procedure for performing a specific calculation or analysis using artificial intelligence technology.

[0023] A "database" refers to a collection of data that is systematically organized and made available for efficient management and retrieval.

[0024] "Terminal" means a device through which a User accesses and operates the System. [Brief explanation of the drawings]

[0025] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0026] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0027] First, the terms used in the following description will be explained.

[0028] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0029] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0030] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0031] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0032] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0033] [First embodiment]

[0034] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0035] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0036] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0037] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0038] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0039] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0040] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0041] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0043] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0044] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0045] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0046] This invention is a system that provides learners with a customized educational experience, strengthens connections with experts, and improves the quality of learning through collaboration with the community. The system generates customized curricula based on learners' skills, interests, and learning styles, builds expert networks, tracks and manages learning progress, provides feedback, and creates online and offline learning communities.

[0047] Entering learner information and generating a curriculum

[0048] When users first log in, they enter their learning goals, interests, and skill level, which provides the system with information tailored to their learning style.

[0049] The terminal transmits the input information to the server.

[0050] The server uses AI algorithms to generate a customized learning curriculum based on the received information, which includes content that addresses the user's skills and interests.

[0051] The server stores the generated curriculum in a database and transmits it to the user's terminal.

[0052] Collaboration with experts

[0053] Experts access the system and enter information about themselves, their field of expertise, background, and qualifications, which the system then registers in a database each expert's knowledge and experience.

[0054] Users can enter any questions or concerns they may have while studying and submit their questions.

[0055] The terminal sends a question from the user to the server.

[0056] The server analyzes the question, routes it to the appropriate expert, and then receives the answer from the expert.

[0057] The server sends the received response to the user's terminal and displays it.

[0058] Tracking learning progress and providing feedback

[0059] Users progress through learning activities and progress data is recorded along the way.

[0060] The device sends real-time progress information to the server.

[0061] The server analyzes the learner's performance based on the received progress data and generates feedback.

[0062] The server sends the generated feedback to the user's device and suggests appropriate improvements and next learning steps.

[0063] Building a learning community

[0064] Users have access to online forums and chat rooms to connect with other learners and experts.

[0065] The server monitors community activity data and recommends appropriate forums and chat rooms to users.

[0066] Users receive notifications of offline events provided by the system and decide whether to participate.

[0067] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[0068] Specific examples

[0069] For example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experiences:

[0070] When users first log in, they tell the system that they are interested in data science.

[0071] The server generates a customized data science curriculum based on the received information and sends it to the user's device.

[0072] As the learning process progresses, users ask questions about specific data analysis techniques, which are then routed by the server to the appropriate data science experts.

[0073] The experts answer the questions and the answers are provided to the users via the server.

[0074] As learning progresses, the device sends the user's progress data to the server, which generates feedback based on the analysis results.

[0075] Additionally, the server will notify users of offline data science study groups and events being held in the area, providing them with opportunities to participate.

[0076] This system will provide each learner with the best possible learning experience and eliminate educational disparities through collaboration with experts and local communities.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] A user accesses the system and enters their email address and password on the initial login screen.

[0080] Step 2:

[0081] The terminal sends the input information to the server and requests user authentication.

[0082] Step 3:

[0083] The server compares the received authentication information with a database, generates an authentication token, and sends it to the terminal.

[0084] Step 4:

[0085] After logging in, users are taken to a screen where they can enter their learning goals, interests, and skill level.

[0086] Step 5:

[0087] The terminal transmits the inputted learner information to the server.

[0088] Step 6:

[0089] Based on the learner information received by the server, a customized learning curriculum is generated using an AI algorithm.

[0090] Step 7:

[0091] The server stores the generated curriculum in a database and transmits it to the terminal.

[0092] Step 8:

[0093] Users start learning based on the curriculum, and if they encounter any problems or questions during the learning process, they can enter their questions.

[0094] Step 9:

[0095] The device sends the user's question to the server.

[0096] Step 10:

[0097] The server analyzes the question and routes it to the appropriate expert.

[0098] Step 11:

[0099] The expert enters the answer to the question and sends it to the server.

[0100] Step 12:

[0101] The server receives the answers from the experts and sends them to the user's device.

[0102] Step 13:

[0103] Progress data is recorded as users learn.

[0104] Step 14:

[0105] The device sends progress information to the server in real time.

[0106] Step 15:

[0107] The server analyzes the learner's performance based on the received progress data and generates feedback.

[0108] Step 16:

[0109] The server sends the generated feedback to the user's terminal and displays it to the user.

[0110] Step 17:

[0111] Users have access to online forums and chat rooms where they can interact with other learners and experts.

[0112] Step 18:

[0113] The server monitors community activity data and recommends appropriate forums and chat rooms to users.

[0114] Step 19:

[0115] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[0116] Step 20:

[0117] A user receives notification of an offline event and decides whether to attend.

[0118] Example 1

[0119] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0120] Traditional education systems often provide learners with a uniform curriculum, which does not adequately address individual skills, interests, or learning styles. Furthermore, they face challenges such as a lack of prompt and appropriate feedback on questions that arise during learning, and a lack of collaboration with experts and learning communities. Furthermore, a lack of collaboration with offline educational institutions makes it difficult to improve educational effectiveness through collaboration with local communities.

[0121] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0122] In this invention, the server includes: a means for a learner to input their learning goals, interests, and skill level when they log in for the first time; a means for transmitting the input information to the server; a means for generating a curriculum based on the received information using an artificial intelligence algorithm, storing the curriculum in a database, and transmitting the curriculum to the terminal; a means for the learner to input questions that arise during learning and for routing the questions to appropriate experts; a means for providing the learner with answers from the experts; a means for transmitting learning progress and feedback to the terminal using push notifications; a means for the learner to access online forums and chat rooms to interact with other learners and experts; and a means for collecting information about offline learning events held in the community and notifying appropriate learners of such events. This enables the provision of individually customized learning curricula, appropriate feedback in real time, and collaboration with experts. Furthermore, educational activities in collaboration with the community can provide learners with diverse learning opportunities and significantly improve the quality of education.

[0123] A "learner" is a person who receives education using the system.

[0124] "Skills" are abilities or expertise that a learner already possesses.

[0125] "Interests" refer to areas or topics that a learner is particularly interested in.

[0126] A "learning style" is a method or approach that a learner uses to learn most effectively.

[0127] A "curriculum" is a specific educational program or learning content generated by the system.

[0128] An "expert" is someone who has advanced knowledge and experience in a particular field and who provides guidance and advice to learners.

[0129] A "network" is a structure or system that brings together domestic and international experts through a system to share their knowledge.

[0130] "Learning progress" refers to a learner's progress and achievement in learning activities.

[0131] "Feedback" refers to evaluation of learners and advice for improvement.

[0132] A "learning community" is an online or offline group of learners and professionals who can interact and collaborate.

[0133] "Local educational institutions" refer to schools, libraries, local government and other educational facilities in the area where the learner lives.

[0134] An "offline educational platform" refers to educational activities and learning environments that are conducted without using the Internet.

[0135] "First login" refers to the operation when a learner accesses the system for the first time and enters personal information and learning objectives.

[0136] An "input form" is an interface or screen that a learner uses to enter information.

[0137] An "artificial intelligence algorithm" is an automated computational method used by a computer to generate a curriculum based on learner information.

[0138] "Database" refers to an information structure for systematically managing and storing generated curriculum and other data.

[0139] "Device" refers to a device such as a computer, tablet, or smartphone that a learner uses to access the system.

[0140] "Questions" are questions or things that students have questions about while studying.

[0141] "Routing" refers to the process of sending an incoming question to the appropriate expert.

[0142] "Push notifications" is a function that allows the system to send learning progress, event information, and other information to learners' devices in real time.

[0143] An "online forum" is a bulletin board or community site on the Internet where learners and experts can exchange opinions and share information.

[0144] A "chat room" is an online communication tool for exchanging messages in real time.

[0145] "Offline learning events" are study groups and workshops held locally without internet connectivity.

[0146] "Notifications" are messages or alerts that inform learners of information.

[0147] This invention is a system that provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Specific implementation methods are described below.

[0148] First, when users log in for the first time, they enter their learning goals, interests, and skill level. The input form is designed to allow users to easily select their field of interest and current skill level. For example, options such as "Data Science" and "Beginner Programming" are provided.

[0149] The device sends the entered information to the server using an HTTP request. At this time, the information is encoded in JSON format. For example, the following data may be sent:

[0150] {

[0151] "interest": "data science",

[0152] "skill_level": "Beginner"

[0153] }

[0154] The server then runs an artificial intelligence algorithm (e.g., the TENSORFLOW® model) based on the received information to generate a customized learning curriculum. This algorithm selects the optimal learning resources based on the user's skills and interests, and automatically generates the curriculum.

[0155] The generated curriculum is stored in a MySQL® database by the server and sent to the user's device. The device reads the received curriculum and displays it in a format that is easy for the user to view. This display uses front-end web technologies (e.g., HTML, CSS, JavaScript®).

[0156] Next, the user enters any questions or doubts that arise as they progress through their learning. These questions are then sent to the server in JSON format. For example, the following questions might be entered:

[0157] {

[0158] "question": "How do I set up a neural network?"

[0159] }

[0160] The device sends this question to the server, which analyzes the received question using a natural language processing model (e.g., GPT-4 (registered trademark)) and routes it to the appropriate expert. The expert then answers the question, and the answer is provided to the user via the server.

[0161] As the learning progresses, the device sends the user's progress data in real time to the server, which also encodes the data in JSON format. The server then uses a Python script to analyze the learner's performance and generates feedback using a data analysis tool (e.g., Tableau).

[0162] The generated feedback is sent to the user's device by the server. The feedback includes specific suggestions for improvement and next learning steps. For example, advice such as "The next challenge you should tackle is to understand regression analysis" is displayed.

[0163] Users access online forums and chat rooms by clicking links in the system. The server uses APIs to monitor community activity data and recommend appropriate forums and chat rooms to users. Activity data is collected in real time.

[0164] Finally, the server notifies users of local offline learning events, providing them with the opportunity to participate in local learning groups and workshops.

[0165] In this way, the system provides a personalized learning experience and strengthens collaboration with experts and the local community. Example prompts include:

[0166] A user wants to learn data science. What curriculum will he be offered, how will he connect with experts, how will he receive feedback, and how will he participate in a local learning community?

[0167] This system will make it possible to significantly improve the quality of education and provide a wide variety of learning opportunities.

[0168] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0169] Step 1:

[0170] A user logs in to the system for the first time. After logging in, the user enters their learning goals, interests, and skill level. The data is collected through an on-device input form, which includes text boxes and drop-down menus. Specifically, the user enters information such as "Interest: Data Science" and "Skill Level: Beginner."

[0171] Step 2:

[0172] The terminal encodes the information entered by the user into JSON format and sends it to the server as an HTTP request. The input data will be in JSON format as follows:

[0173] {

[0174] "interest": "data science",

[0175] "skill_level": "Beginner"

[0176] }

[0177] The terminal operates by using an HTTP POST request to send input data to the server.

[0178] Step 3:

[0179] The server generates a curriculum using an artificial intelligence algorithm (e.g., a TensorFlow model) based on the received user information. Specifically, it selects relevant learning materials and activities based on the input "areas of interest" and "skill level." The output is a customized curriculum.

[0180] {

[0181] "course": "Basic Data Science Course",

[0182] "modules": [

[0183] "Data collection and preprocessing",

[0184] "Basic Statistics",

[0185] "Introduction to Machine Learning"

[0186] ]

[0187] }

[0188] Step 4:

[0189] The server saves the generated curriculum in a MySQL database and simultaneously sends the data in JSON format to the terminal, where the curriculum is displayed for the user. As a concrete example, it generates SQL statements to save to the database and saves the curriculum information.

[0190] INSERT INTO curriculum (user_id, course, modules) VALUES ('12345', 'Data Science Fundamentals Course', '["Data Collection and Preprocessing", "Basic Statistics", "Introduction to Machine Learning"]');

[0191] Step 5:

[0192] The user begins learning according to the learning curriculum. If a question arises during the learning process, the user enters the question on the device. For example, they can enter a question such as, "How do I set up a neural network?"

[0193] Step 6:

[0194] The device encodes the question entered by the user into JSON format and sends it to the server as an HTTP request. The data sent looks like this:

[0195] {

[0196] "question": "How do I set up a neural network?"

[0197] }

[0198] The device again sends the data using an HTTP POST request.

[0199] Step 7:

[0200] The server analyzes the received question using a natural language processing model (e.g., GPT-4) and routes the question to the appropriate expert. Specifically, a question about "neural networks" is routed to a machine learning expert. The output is the expert's information and analysis results.

[0201] Step 8:

[0202] The server forwards the routed question to the appropriate expert and waits for the expert's answer. The expert answers the question and the answer is sent to the server. The server receives the answer and encodes it into JSON format.

[0203] Step 9:

[0204] The server then sends the answer it receives to the user's device and displays it, for example, "Here's how to set up the neural network..."

[0205] Step 10:

[0206] As users progress through learning activities, progress data is recorded on the device, for example, when they complete an assignment or finish a particular module.

[0207] Step 11:

[0208] The device sends the progress status to the server in real time. This data is also encoded in JSON format and sent. An example of the data sent is as follows:

[0209] {

[0210] "user_id": "12345",

[0211] "module_completed": "Data Collection and Preprocessing"

[0212] }

[0213] Step 12:

[0214] The server analyzes the learner's performance using Python scripts based on the received progress data and displays the results in a data analysis tool (e.g., Tableau). Performance reports and improvement suggestions are generated as output.

[0215] Step 13:

[0216] The server sends the generated feedback to the user's device via push notification, allowing the user to see appropriate improvement suggestions and next learning steps. For example, a notification might say, "Your next task is to understand regression analysis."

[0217] Step 14:

[0218] Users access online forums and chat rooms to connect with other learners and experts, using dedicated communication apps on their devices.

[0219] Step 15:

[0220] The server monitors community activity data in real time using an API and recommends appropriate forums and chat rooms to users, such as a message like, "We recommend you join a forum that discusses basic statistics."

[0221] Step 16:

[0222] The server collects information about offline learning events held in the area and notifies appropriate users, allowing users to participate in local learning groups and workshops, expanding learning opportunities.

[0223] The above is the specific flow of program processing for this system.

[0224] (Application example 1)

[0225] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0226] In traditional education systems, it was difficult to efficiently provide a curriculum tailored to each learner's skills, interests, and learning style. Furthermore, there was a lack of collaboration with domestic and international experts, progress management, and feedback, which led to problems in improving learners' learning efficiency and maintaining their motivation. Furthermore, there was a lack of offline learning communities and collaboration with local educational institutions, which limited the learning experience.

[0227] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0228] In this invention, the server includes means for receiving learner information and generating a customized learning curriculum using an AI algorithm, means for routing learner questions to appropriate experts using an AI algorithm and providing answers from the experts, means for analyzing learning progress data and generating real-time feedback, and means for collecting and providing local offline event information to learners. This enables learners to have an individually optimized learning experience, strengthening collaboration with experts, improving progress management, and feedback. It also builds online and offline learning communities and promotes collaboration with local educational institutions, thereby improving the learner's overall learning experience.

[0229] A "learner" is an individual or group of people who use a learning system to achieve educational objectives.

[0230] "Interest" refers to the interest or curiosity a learner has in a particular educational field or topic.

[0231] "Learning styles" are the methods or techniques that learners use to learn most effectively.

[0232] A "curriculum" is a set of learning contents and activities, from prerequisites to outcomes, in an educational process.

[0233] An "AI algorithm" is a computational procedure that uses artificial intelligence to automatically perform a specific task.

[0234] A "database" is an information system that efficiently manages large amounts of data and enables searching and updating.

[0235] An "expert" is someone who has advanced knowledge and experience in a particular field and provides this knowledge to learners.

[0236] "Progress data" is information that indicates the progress and achievements of a learner through a learning activity.

[0237] "Feedback" is information that includes an evaluation of a learner's learning activities and suggestions for improvement.

[0238] An "offline event" is a learning-related activity or event that takes place in a physical location without the internet.

[0239] "Local educational institutions" are schools, libraries, municipalities, and other organizations that provide education in the local community.

[0240] A "learning community" is a group or network of learners and professionals who interact with each other and share knowledge and information.

[0241] "Real-time feedback" is information that responds immediately to learners' learning activities and provides evaluations and areas for improvement on the spot.

[0242] "Question routing" is the process of sending questions received from learners to experts to obtain appropriate answers.

[0243] The present invention provides a system for providing learners with a customized educational experience, strengthening collaboration with experts, and improving the quality of learning through collaboration with the local community. This system is configured and provided as follows.

[0244] First, when a user logs in for the first time, they enter their learning goals, interests, and skill level. This provides the system with information that matches the user's learning style. The information entered by the user is sent from the user's device to the server. The server uses an AI algorithm based on the received information to generate a customized learning curriculum. This curriculum includes content that matches the user's skills and interests. The generated curriculum is saved in a database and sent to the user's device.

[0245] Next, collaboration with an expert is attempted. The expert accesses the system and inputs information about themselves, their field of expertise, career history, and qualifications. This allows the system to register each expert's knowledge and experience in a database. The user inputs any questions or doubts that arise during the study and sends them from their device to the server. The server analyzes the content of the question and routes it to the appropriate expert. The server then receives the expert's answer, sends it to the user's device, and displays it.

[0246] Furthermore, learning progress is managed and feedback is provided. As users proceed with their learning activities, they record progress data along the way. The device sends the progress status to the server in real time. The server analyzes the learner's performance based on the received progress data and generates feedback. This feedback includes suggestions for improvement and next learning steps and is sent to the user's device.

[0247] It also creates online and offline learning communities. Users can interact with other learners and experts through online forums and chat rooms. The server monitors community activity data and recommends appropriate forums and chat rooms to users. Furthermore, users can receive notifications from the server about offline study groups and activities being held in their area, allowing them to decide whether or not to participate. The server cooperates with local educational institutions, libraries, and local governments to collect offline event information and provide it to users.

[0248] As a specific example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experience: When the user logs in for the first time, they enter their interest in data science, and a customized data science curriculum is generated and sent to their device. If they ask a question about a specific data analysis method during the learning process, the question is routed to an appropriate data science expert. The expert's answer is provided to the user via the server. As the learning progresses, the device sends the user's progress data to the server, and the server generates feedback based on the analysis results. Furthermore, the server notifies the user of offline data science study groups and events held in the area, offering opportunities to participate.

[0249] Example prompts using a generative AI model:

[0250] "Develop a smartphone application that provides a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Use Python's requests library to send user information to a server and retrieve a customized curriculum generated by an AI algorithm."

[0251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0252] Step 1:

[0253] When a user logs in for the first time, they enter their learning goals, interests, and skill level. The information they enter (e.g., "I'm interested in data science" or "Beginner") is collected via their device and sent to the server.

[0254] Input: Learner's goals, interests, skill level, etc.

[0255] Output: Learner information sent to the server

[0256] Step 2:

[0257] The server uses an AI algorithm to generate a customized learning curriculum based on the received user information. Specifically, the AI ​​algorithm analyzes the learner's interests and skill level, and selects and configures learning modules based on that. The generated curriculum is stored in a database.

[0258] Input: Student information sent to the server

[0259] Output: Customized curriculum stored in a database

[0260] Step 3:

[0261] The server sends the generated curriculum to the user's terminal, which displays the received curriculum and allows the user to start learning.

[0262] Input: Customized curriculum stored in the database

[0263] Output: The curriculum sent to the user's device

[0264] Step 4:

[0265] If a user has a question while studying, the user inputs the question into the terminal, which then sends the input question to the server.

[0266] Input: The question the user types into the terminal

[0267] Output: The question sent to the server

[0268] Step 5:

[0269] The server analyzes the received question and routes it to the expert appropriate for the question. Specifically, the server analyzes the question content using natural language processing and selects the most appropriate expert. The routed question is then sent to the expert.

[0270] Input: The question sent to the server

[0271] Output: Questions routed to experts

[0272] Step 6:

[0273] The expert creates an answer to the received question and sends the answer to the server, which then receives the answer from the expert and sends it to the user's device.

[0274] Input: Expert-generated answers

[0275] Output: The answer sent to the user's terminal

[0276] Step 7:

[0277] The system collects learning progress data while the user is learning. The device sends the learning progress data (e.g., completed modules, unread tutorials, etc.) to the server in real time.

[0278] Input: User's learning progress data

[0279] Output: Learning progress data sent to the server

[0280] Step 8:

[0281] The server analyzes the learning progress data and generates real-time feedback to assess the progress and provide appropriate advice and next steps for learning. The generated feedback is then sent to the user's device.

[0282] Input: Learning progress data sent to the server

[0283] Output: Real-time feedback sent to the user device

[0284] Step 9:

[0285] When users access online forums or chat rooms, the server monitors their activity data and recommends appropriate forums or chat rooms to them. Additionally, the server collects offline event information from local educational institutions, libraries, and local governments and notifies appropriate users.

[0286] Input: Forum and chat room activity data, local offline event information

[0287] Output: User recommended forums, chat rooms and offline event information

[0288] Example prompts using a generative AI model:

[0289] "Develop a smartphone application that provides a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Use Python's requests library to send user information to a server and retrieve a customized curriculum generated by an AI algorithm."

[0290] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0291] The present invention is a system that provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the community, and combines it with an emotion engine that recognizes the user's emotions, allowing it to tailor curriculum, feedback, and communication recommendations based on the learner's emotional state.

[0292] Entering learner information and generating a curriculum

[0293] When users first log in, they enter their email address and password, along with their learning goals, interests, and skill level, and the system uses this information to create a learner profile.

[0294] The terminal transmits the input information to the server.

[0295] The server uses an AI algorithm to generate a customized learning curriculum based on the received information, and also analyzes the user's emotional state using an emotion engine, which then incorporates that information into the curriculum.

[0296] The server stores the generated curriculum in a database and transmits it to the user's terminal.

[0297] Collaboration with experts

[0298] Experts access the system and enter their field of expertise, background, and qualifications, which allows the system to register each expert's knowledge and experience in a database.

[0299] Users can enter any questions or concerns they may have while studying and submit their questions.

[0300] The terminal sends a question from the user to the server.

[0301] The server analyzes the question and routes it to the appropriate expert, taking into account the user's emotional state and recommending an answer in an appropriate tone.

[0302] The expert enters the answer to the question and sends it to the server.

[0303] The server sends the expert's answer to the user's terminal and displays it.

[0304] Tracking learning progress and providing feedback

[0305] As users progress through the learning process, their progress data is recorded, while the emotion engine simultaneously analyzes their emotions from their facial expressions and tone of voice.

[0306] The device transmits progress and emotion data to the server in real time.

[0307] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments, such as lowering the difficulty level if the user is feeling stressed.

[0308] The server sends the generated feedback and adjustments to the user's terminal and displays them to the user.

[0309] Building a learning community

[0310] Users access online forums and chat rooms to interact with other learners and experts, while the emotion engine monitors their emotional state.

[0311] The server monitors community activity data and recommends appropriate forums and chat rooms based on the user's emotional state, as well as providing notifications to encourage active participation within the community.

[0312] Users receive notifications of offline events provided by the system and decide whether to participate. Data from the emotion engine is also taken into consideration at this time, and events suitable for the user are recommended.

[0313] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[0314] Specific examples

[0315] For example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experiences:

[0316] When a user first logs in, they tell the system that they are interested in data science.

[0317] The server generates a customized data science curriculum based on the information received and sends it to the user's device.

[0318] As the learning process progresses, users ask questions about specific data analysis techniques, which are then routed by the server to the appropriate data science experts. An emotion engine detects when the user is frustrated and encourages the experts to respond in a gentler tone.

[0319] Experts answer questions, and the answers are provided to users via a server. As users learn, their progress data and emotional state are recorded and sent to the server in real time. The server analyzes the data and generates appropriate feedback for users. It also recommends participation in appropriate forums and offline events based on the user's emotional state.

[0320] The system provides learners with a highly customized educational experience and addresses their psychological aspects by utilizing an emotional engine, thereby improving the quality of education and enabling learners to achieve optimal learning through collaboration with the local community.

[0321] The processing flow will be explained below.

[0322] Step 1:

[0323] A user accesses the system and enters their email address and password on the initial login screen.

[0324] Step 2:

[0325] The terminal sends the input information to the server and requests user authentication.

[0326] Step 3:

[0327] The server compares the received authentication information with a database, generates an authentication token, and sends it to the terminal.

[0328] Step 4:

[0329] After logging in, the user is directed to a screen where they can enter their learning goals, interests, and skill level. At this point, the camera and microphone are activated, and the emotion engine analyzes the user's facial expressions and voice.

[0330] Step 5:

[0331] The terminal transmits the input learner information and emotion data to the server.

[0332] Step 6:

[0333] The server uses an AI algorithm to generate a customized learning curriculum based on the learner information and emotional data received.

[0334] Step 7:

[0335] The server stores the generated curriculum in a database and sends it to the user's device.

[0336] Step 8:

[0337] Users begin learning based on the curriculum, and if they encounter any problems or questions during the learning process, they can enter them.

[0338] Step 9:

[0339] The device sends the user's question to the server, and the emotion engine also analyzes the user's emotional state at that time and sends the result to the server.

[0340] Step 10:

[0341] The server analyzes the question and emotional data and routes it to the appropriate expert, recommending that the expert respond in an appropriate tone based on the emotional state.

[0342] Step 11:

[0343] The expert enters the answer to the question and sends it to the server.

[0344] Step 12:

[0345] The server receives the answers from the experts and sends them to the user's device.

[0346] Step 13:

[0347] As users learn, their progress is recorded, and an emotion engine analyzes their emotional state.

[0348] Step 14:

[0349] The device transmits progress and emotion data to the server in real time.

[0350] Step 15:

[0351] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments.

[0352] Step 16:

[0353] The server sends the generated feedback and adjustments to the user's device and displays them to the user, adjusting the content and tone of the feedback according to the user's emotional state.

[0354] Step 17:

[0355] As users access online forums and chat rooms and interact with other learners and experts, the emotion engine monitors their emotional state and transmits that data to the server if necessary.

[0356] Step 18:

[0357] The server monitors community activity data and user sentiment data and recommends appropriate forums and chat rooms to users.

[0358] Step 19:

[0359] The server collects information on offline study sessions and activities taking place in the area and sends push notifications to appropriate users based on emotional data.

[0360] Step 20:

[0361] Users receive notifications about offline events and decide whether or not they want to participate. The emotion engine analyzes the user's reactions and provides feedback tailored to their willingness to participate.

[0362] In this way, this system, which combines an emotion engine, also responds to the psychological aspects of learners and provides an optimal learning environment.

[0363] Example 2

[0364] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0365] Traditional educational systems have difficulty customizing to meet individual learners' skills, interests, and learning styles, and generic curricula have been unable to meet individual needs. Furthermore, limited collaboration with experts makes it difficult to respond quickly and appropriately to learners' doubts and questions. Furthermore, the inability to provide feedback or adjust the curriculum to take into account the learner's emotional state means that improvements in learning quality and motivation cannot be expected.

[0366] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0367] In this invention, the server includes means for analyzing the emotional state of the learner and adjusting the curriculum and feedback content, means for analyzing the learner's questions and providing answers in an appropriate tone, and means for collecting information on study sessions and activities taking place in the local area and recommending appropriate offline events based on the learner's emotional state. This makes it possible to provide an educational experience optimized for each learner and to improve the quality of learning and motivation by strengthening collaboration with experts and the local community.

[0368] A "learner" is an individual who engages in a learning activity.

[0369] A "skill" is an ability or technique for effectively performing a particular task or activity.

[0370] "Interests" refer to subjects or topics that interest learners.

[0371] A "learning style" refers to the method or approach that a learner takes in learning.

[0372] A "curriculum" is an educational content or learning program designed to achieve specific learning goals.

[0373] An "expert" is a person who has advanced knowledge or skills in a particular field.

[0374] A "network" is a communication system built to share information and resources.

[0375] "Learning progress" refers to an indicator or state that indicates how far a learner has progressed toward a learning goal.

[0376] "Feedback" refers to information provided about the learning process or results for evaluation and improvement.

[0377] "Online" refers to operations or activities conducted over the Internet.

[0378] "Offline" refers to operations or activities that are not performed via the Internet.

[0379] A "learning community" is a group of learners and experts who exchange information and opinions and support each other's learning.

[0380] An "emotional state" is the emotion or mental state that a learner is feeling at a particular time.

[0381] "Analysis" is the act of examining data or information in detail and clarifying its structure and relationships.

[0382] "Tone" refers to the way one speaks or expresses something, especially its intensity and emotional level.

[0383] "Routing" refers to the procedures and methods used to direct data or information to its proper destination.

[0384] An "offline event" is a learning activity or social gathering that takes place in a physical location.

[0385] The system is designed to provide a customized educational experience that takes into account the learner's skills, interests, and learning style. Key elements include an AI algorithm, an emotion engine, and online and offline learning community functions. The specific implementation of each element is explained below.

[0386] Entering learner information and generating a curriculum

[0387] When a user logs in for the first time, they enter their email address and password, as well as their learning goals, interests, and skill level. This information is sent from the device to the server via an HTTP POST request. The server receives this information and stores it in a database. It then uses an AI algorithm to generate a customized learning curriculum. This AI algorithm selects the most appropriate learning content based on the learner's profile information.

[0388] Furthermore, the server uses an emotion engine to analyze the learner's emotional state. This emotional state is obtained using facial expression analysis technology, tone of voice analysis technology, etc. This makes it possible to reflect emotional information in the curriculum. The generated curriculum is saved in the database again and sent to the terminal. The terminal displays the received curriculum to the user.

[0389] Collaboration with experts

[0390] Experts access the system and enter their field of expertise, background, and qualifications. This information is registered in a database. When a user enters a question or concern during learning, the device sends the question to the server. The server analyzes the question and routes it to the appropriate expert. In doing so, it uses an emotion engine to analyze the user's emotional state and provides the expert with instructions recommending an appropriate tone of voice to respond. The expert enters the answer and sends it to the server, where it is delivered and displayed to the user.

[0391] Tracking learning progress and providing feedback

[0392] As the user progresses through their learning activities, their progress data is recorded. At the same time, an emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and sends this information in real time via the device to the server. The server analyzes the received data and evaluates the learner's performance. Based on this, appropriate feedback and curriculum adjustments are generated, sent to the device, and displayed to the user. For example, if the learner is feeling stressed, the system will make adjustments such as lowering the difficulty of the learning content.

[0393] Building a learning community

[0394] Users can access online forums and chat rooms to interact with other learners and experts. The emotion engine monitors the user's emotional state and recommends appropriate forums and chat rooms. The server also monitors community activity data and sends notifications to encourage active participation.

[0395] The server also collects information about offline study groups and activities taking place in the local area and sends push notifications to appropriate users, providing opportunities for learners to meet in person both online and offline and building a learning community.

[0396] Specific examples

[0397] For example, consider the case where a learner who wants to learn data science enters their interest in data science when logging in for the first time. The server generates a customized data science curriculum based on the received information and sends it to the device. If the user asks a question about a specific data analysis method as they progress through their studies, the question is routed to an appropriate data science expert. At that time, an emotion engine detects the user's frustration and recommends that the expert respond in a gentler tone. The expert's answer is then provided to the user via the server.

[0398] An example of a prompt sentence could be, "Please enter the information needed to customize your data science curriculum. For example, please enter your area of ​​interest, current skill level, and learning goals. Also, please enter your past learning experience and any specific questions you may have." By using this prompt sentence as a concrete example, the system can quickly generate a curriculum optimized for the user's needs.

[0399] Overall, the system aims to improve learning quality and motivation by providing an educational experience tailored to each learner's individual needs and by strengthening collaboration with experts and the local community.

[0400] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0401] Step 1:

[0402] A user enters an email address and password on the login screen. The entered information is sent from the device to the server. Specifically, the data collected in the input form is sent to the server as an HTTP POST request. The input data includes the email address and hashed password.

[0403] Step 2:

[0404] The server compares the received login information with the database and performs authentication. If authentication is successful, the server generates the user's session information and sends the session ID to the terminal. The authentication process checks whether the email address and hashed password match the information in the database.

[0405] Step 3:

[0406] The user enters profile information such as learning objectives, interests, and skill level. The entered information is sent to the server via the terminal. Specifically, the data collected in the form is sent to the server as an HTTP POST request. The input data includes learning objectives, interests, and skill level.

[0407] Step 4:

[0408] The server stores the received profile information in a database and analyzes it using an AI algorithm. As a result of the analysis, a learning curriculum optimal for the learner is generated. Specifically, the received data is input into an AI model to generate a customized curriculum. As an output, the learning curriculum is stored in a database.

[0409] Step 5:

[0410] The server uses an emotion engine to analyze the user's emotional state. Specifically, it receives the user's facial expressions and voice data as input and analyzes them using an emotion analysis model. The output is data indicating the user's emotional state.

[0411] Step 6:

[0412] The server reflects the emotional state in the generated curriculum to complete the final curriculum. Specifically, the content and difficulty of the curriculum are adjusted using the emotional state data. As an output, the curriculum reflecting the emotions is saved again in the database.

[0413] Step 7:

[0414] The server sends the final curriculum to the terminal. Specifically, it sends the generated curriculum to the terminal as an HTTP response. The terminal displays the received curriculum to the user.

[0415] Step 8:

[0416] Experts access the system and enter their field of expertise, background, and qualifications, which are then sent from the terminal to the server and stored in a database.

[0417] Step 9:

[0418] The user inputs questions that arise during learning and sends them from the device to the server. The input data includes the question content. Specifically, the question data collected in the form is sent to the server as an HTTP POST request.

[0419] Step 10:

[0420] The server analyzes the received question and routes it to the appropriate expert. Specifically, it analyzes the question content using natural language processing (NLP) technology and searches a database for the most suitable expert. The output is information about the expert to whom the question will be routed.

[0421] Step 11:

[0422] The server notifies the expert of the question and emotional information. Specifically, the server generates notification data containing the question content and the user's emotional state information and sends it to the expert's terminal.

[0423] Step 12:

[0424] The expert enters the answer to the question and sends it to the server. Specifically, the answer is sent to the server as an HTTP POST request.

[0425] Step 13:

[0426] The server sends the received response to the user's device and displays it. Specifically, it sends the response data to the device as an HTTP response. The device displays the received response to the user.

[0427] Step 14:

[0428] As the user progresses through the learning activity, progress data is recorded. At the same time, the emotion engine analyzes emotional data from facial expressions and tone of voice. This data is sent to the server via the device.

[0429] Step 15:

[0430] The server analyzes the received progress and emotion data and generates feedback. Specifically, the progress and emotion data are input into a machine learning model to generate performance evaluation and optimal feedback. The output is feedback data.

[0431] Step 16:

[0432] The server sends the generated feedback to the terminal and displays it to the user. Specifically, the server sends the feedback data to the terminal as an HTTP response. The terminal then displays the received feedback to the user.

[0433] Step 17:

[0434] A user accesses an online forum or chat room and communicates with the user. The server monitors the user's emotional state using an emotion engine and recommends appropriate forums or chat rooms.

[0435] Step 18:

[0436] The server collects information about offline learning activities taking place in the area and notifies appropriate users. Specifically, it analyzes the collected information data and recommends offline events based on the user's emotional state. The device displays the received event notifications to the user.

[0437] Through this process, the system is able to provide an educational experience that is optimized to the individual needs of each learner.

[0438] (Application example 2)

[0439] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0440] Conventional learning systems lack the ability to customize learning to fit the learner's skills, interests, and emotional state, resulting in poor learning efficiency. Furthermore, in brick-and-mortar stores, they are unable to provide customer service that reflects their emotions, which can lead to lower customer satisfaction. Furthermore, there are challenges in building online and offline learning communities and effectively utilizing expert knowledge.

[0441] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for generating a customized curriculum based on the learner's skills, interests, and learning style; means for bringing together domestic and international experts and building a network to provide their knowledge; means for tracking and managing learning progress and providing feedback; means for providing opportunities for learners to meet in person online and offline and building a learning community; means for collaborating with local schools, libraries, and local governments and utilizing it as an offline education platform; means for analyzing the learner's emotional state using an emotion engine and adjusting the curriculum, feedback, and communication recommendations; and means for realizing a brick-and-mortar store application that analyzes the emotional state of customers in real time and provides customized customer service methods and suggestions. This enables advanced customization according to the individual needs of learners, improving learning efficiency and customer satisfaction.

[0442] "Learner" refers to an individual who uses a learning system to acquire knowledge or skills.

[0443] "Skills" refer to the abilities and techniques that a learner has to accomplish a specific task or work.

[0444] "Interest" refers to the interest or curiosity a learner has in a particular field or topic.

[0445] "Learning style" refers to the methods and procedures by which a learner learns most effectively.

[0446] "Curriculum" refers to an educational plan that defines the content and progression that learners should learn.

[0447] "Domestic and international experts" refers to individuals or institutions with a high level of knowledge and experience in a particular field.

[0448] "Network" refers to a communication network that allows multiple experts and learners to share information and collaborate.

[0449] "Progress" refers to the progress that a learner makes in demonstrating how well they have achieved their learning tasks.

[0450] "Feedback" refers to evaluation and advice provided to learners to improve their learning activities.

[0451] A "community" refers to a group of learners and professionals who share common learning goals and interests.

[0452] "Online" refers to forms of learning and communication delivered via the Internet.

[0453] "Offline" refers to activities and communications that take place in a physical location, not via the internet.

[0454] An "emotion engine" refers to technology that analyzes a user's facial expressions, tone of voice, etc. to determine their emotional state.

[0455] "Customer" means an individual who uses or purchases a particular service or product.

[0456] "Brick and mortar store" refers to a sales or service point located in a physical location.

[0457] "Application" refers to a software program that provides a specific function or service.

[0458] An "AI algorithm" refers to a calculation method for analyzing data and making decisions using artificial intelligence.

[0459] A "database" refers to a digital system that systematically organizes and stores information.

[0460] This system provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Furthermore, by incorporating an emotion engine, the system adjusts curriculum, feedback, and communication recommendations based on the learner's emotional state. This system can also be applied to brick-and-mortar retail applications, where customers' emotional states are analyzed in real time to provide customized customer service methods and suggestions.

[0461] Entering learner information and generating a curriculum

[0462] When logging in for the first time, users enter their email address and password, as well as their learning goals, interests, and skill level. The device then sends the entered information to the server. The server uses an AI algorithm based on the received information to generate a customized learning curriculum, and then analyzes the user's emotional state using an emotion engine and reflects that information in the curriculum. The server then saves the generated curriculum in a database and sends it to the user's device.

[0463] Collaboration with experts

[0464] Experts access the system and register their knowledge and experience in the database by entering their field of expertise, career history, and qualifications. Users enter questions or doubts that arise during their studies and send them from their terminal to the server. The server analyzes the content of the question and routes it to the appropriate expert. The expert enters an answer to the question and sends it to the server. The server sends the answer from the expert to the user's terminal and displays it.

[0465] Tracking learning progress and providing feedback

[0466] As the user progresses through the learning activity, progress data is recorded. At the same time, the emotion engine analyzes the user's emotions from their facial expressions and tone of voice. The device sends the progress and emotion data to the server in real time. The server analyzes the learner's performance based on the received progress and emotion data and generates feedback and adjustments. For example, if the user is feeling stressed, it may lower the difficulty level. The server sends the generated feedback to the user's device and displays it to the user.

[0467] Application in physical stores

[0468] This system can also be applied to improving customer service experiences in brick-and-mortar stores. The device is installed on a smartphone or head-mounted display and uses a camera to capture the customer's facial expressions. The received video data is sent to a server in real time, where an emotion engine analyzes the customer's emotional state. Based on the analysis results, the device displays customer service methods and product suggestions that are appropriate for the customer's emotions.

[0469] For example, when a customer visits a cosmetics counter in a physical store, a staff member's smartphone scans the customer's facial expression and determines that the customer looks a little depressed. The staff member is then shown advice such as, "Today, we'd like to recommend a lip color that will cheer you up a little."

[0470] Prompt Sentence Examples

[0471] The following prompt sentence is used as input to the generative AI model:

[0472] Write a program for a system that recognizes customer emotions and customizes in-store interactions. The hardware used is a smartphone camera, and the software is Python. Include recommendations based on the customer's emotional state.

[0473] This will enable us to provide an educational environment for users and improve the customer service experience in physical stores.

[0474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0475] Step 1:

[0476] When a user logs in for the first time, they enter their email address and password, as well as their learning goals, interests, and skill level. This generates the user's profile information. The entered information is sent to the server by the device. The entered data includes the email address, password, learning goals, interests, and skill level. The device then uploads this data to the server.

[0477] Step 2:

[0478] The server uses an AI algorithm to generate a customized learning curriculum based on the received user information. The learning content is customized based on the user's skills, interests, and learning style. An emotion engine also analyzes the user's emotional state, and the results are reflected in the curriculum. The input here is user information, and the output is a customized learning curriculum.

[0479] Step 3:

[0480] The server stores the generated curriculum in a database and then transmits it to the user's device. The database stored on the server holds a customized educational plan for each learner. The input is curriculum data, and the output is data transmission to the user's device.

[0481] Step 4:

[0482] If a user has any doubts or questions during their studies, they can input them through their device and send them to the server. The input data includes the user's question, and the device uploads it to the server.

[0483] Step 5:

[0484] The server analyzes the received question and routes it to the appropriate expert from a list of experts in the database. The server takes into account the question as well as the user's emotional state, which is analyzed by the emotion engine. The input is the question from the user, and the output is the expert to whom the question is routed.

[0485] Step 6:

[0486] The expert inputs an answer to the question received from the server and sends it to the server. In this process, the answer is generated using the expert's knowledge and experience. The input is the expert's answer, and the output is the response sent to the server.

[0487] Step 7:

[0488] The server sends the expert's answer to the user's device and displays it to the user. In this step, the user can receive an explanation based on expert knowledge. The input is the expert's answer data, and the output is the answer displayed on the user's device.

[0489] Step 8:

[0490] As the user progresses through the learning activity, the progress and emotional data are sent to the server in real time from the device, thereby recording the learning progress and emotional state. The input is progress data and emotional data, and the output is data uploaded to the server.

[0491] Step 9:

[0492] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments. For example, if the user is feeling stressed, the server may lower the difficulty of the learning content. The input is progress and emotion data, and the output is customized feedback.

[0493] Step 10:

[0494] The server sends the generated feedback to the user's terminal and displays it to the user, allowing the user to check areas for improvement in their learning and their next steps. The input is feedback data, and the output is data display on the user's terminal.

[0495] Step 11:

[0496] When a user visits a physical store, the device (smartphone or head-mounted display) uses a camera to capture the customer's facial expressions. The video data is sent to the server in real time. The input is the captured video data, and the output is the video data sent to the server.

[0497] Step 12:

[0498] The server uses an emotion engine to analyze the customer's emotional state and generate customized customer service methods and product suggestions based on the results. The input is video data, and the output is the analysis results and customized suggestions.

[0499] Step 13:

[0500] The server then sends the generated customer service methods and suggestions to the terminal and displays them to the store staff. This allows the staff to provide customer service that is tailored to the customer's emotions. The input is the customized suggestions, and the output is the data displayed on the terminal.

[0501] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0502] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0503] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0504] [Second embodiment]

[0505] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0506] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0507] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0508] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0509] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0510] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0511] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0512] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0513] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0514] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0515] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0516] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0517] This invention is a system that provides learners with a customized educational experience, strengthens connections with experts, and improves the quality of learning through collaboration with the community. The system generates customized curricula based on learners' skills, interests, and learning styles, builds expert networks, tracks and manages learning progress, provides feedback, and creates online and offline learning communities.

[0518] Entering learner information and generating a curriculum

[0519] When users first log in, they enter their learning goals, interests, and skill level, which provides the system with information tailored to their learning style.

[0520] The terminal transmits the input information to the server.

[0521] The server uses AI algorithms to generate a customized learning curriculum based on the received information, which includes content that addresses the user's skills and interests.

[0522] The server stores the generated curriculum in a database and transmits it to the user's terminal.

[0523] Collaboration with experts

[0524] Experts access the system and enter information about themselves, their field of expertise, background, and qualifications, which the system then registers in a database each expert's knowledge and experience.

[0525] Users can enter any questions or concerns they may have while studying and submit their questions.

[0526] The terminal sends a question from the user to the server.

[0527] The server analyzes the question, routes it to the appropriate expert, and then receives the answer from the expert.

[0528] The server sends the received response to the user's terminal and displays it.

[0529] Tracking learning progress and providing feedback

[0530] Users progress through learning activities and progress data is recorded along the way.

[0531] The device sends real-time progress information to the server.

[0532] The server analyzes the learner's performance based on the received progress data and generates feedback.

[0533] The server sends the generated feedback to the user's device and suggests appropriate improvements and next learning steps.

[0534] Building a learning community

[0535] Users have access to online forums and chat rooms to connect with other learners and experts.

[0536] The server monitors community activity data and recommends appropriate forums and chat rooms to users.

[0537] Users receive notifications of offline events provided by the system and decide whether to participate.

[0538] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[0539] Specific examples

[0540] For example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experiences:

[0541] When users first log in, they tell the system that they are interested in data science.

[0542] The server generates a customized data science curriculum based on the received information and sends it to the user's device.

[0543] As the learning process progresses, users ask questions about specific data analysis techniques, which are then routed by the server to the appropriate data science experts.

[0544] The experts answer the questions and the answers are provided to the users via the server.

[0545] As learning progresses, the device sends the user's progress data to the server, which generates feedback based on the analysis results.

[0546] Additionally, the server will notify users of offline data science study groups and events being held in the area, providing them with opportunities to participate.

[0547] This system will provide each learner with the best possible learning experience and eliminate educational disparities through collaboration with experts and local communities.

[0548] The processing flow will be explained below.

[0549] Step 1:

[0550] A user accesses the system and enters their email address and password on the initial login screen.

[0551] Step 2:

[0552] The terminal sends the input information to the server and requests user authentication.

[0553] Step 3:

[0554] The server compares the received authentication information with a database, generates an authentication token, and sends it to the terminal.

[0555] Step 4:

[0556] After logging in, users are taken to a screen where they can enter their learning goals, interests, and skill level.

[0557] Step 5:

[0558] The terminal transmits the inputted learner information to the server.

[0559] Step 6:

[0560] Based on the learner information received by the server, a customized learning curriculum is generated using an AI algorithm.

[0561] Step 7:

[0562] The server stores the generated curriculum in a database and transmits it to the terminal.

[0563] Step 8:

[0564] Users start learning based on the curriculum, and if they encounter any problems or questions during the learning process, they can enter their questions.

[0565] Step 9:

[0566] The device sends the user's question to the server.

[0567] Step 10:

[0568] The server analyzes the question and routes it to the appropriate expert.

[0569] Step 11:

[0570] The expert enters the answer to the question and sends it to the server.

[0571] Step 12:

[0572] The server receives the answers from the experts and sends them to the user's device.

[0573] Step 13:

[0574] Progress data is recorded as users learn.

[0575] Step 14:

[0576] The device sends progress information to the server in real time.

[0577] Step 15:

[0578] The server analyzes the learner's performance based on the received progress data and generates feedback.

[0579] Step 16:

[0580] The server sends the generated feedback to the user's terminal and displays it to the user.

[0581] Step 17:

[0582] Users have access to online forums and chat rooms where they can interact with other learners and experts.

[0583] Step 18:

[0584] The server monitors community activity data and recommends appropriate forums and chat rooms to users.

[0585] Step 19:

[0586] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[0587] Step 20:

[0588] A user receives notification of an offline event and decides whether to attend.

[0589] Example 1

[0590] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0591] Traditional education systems often provide learners with a uniform curriculum, which does not adequately address individual skills, interests, or learning styles. Furthermore, they face challenges such as a lack of prompt and appropriate feedback on questions that arise during learning, and a lack of collaboration with experts and learning communities. Furthermore, a lack of collaboration with offline educational institutions makes it difficult to improve educational effectiveness through collaboration with local communities.

[0592] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0593] In this invention, the server includes: a means for a learner to input their learning goals, interests, and skill level when they log in for the first time; a means for transmitting the input information to the server; a means for generating a curriculum based on the received information using an artificial intelligence algorithm, storing the curriculum in a database, and transmitting the curriculum to the terminal; a means for the learner to input questions that arise during learning and for routing the questions to appropriate experts; a means for providing the learner with answers from the experts; a means for transmitting learning progress and feedback to the terminal using push notifications; a means for the learner to access online forums and chat rooms to interact with other learners and experts; and a means for collecting information about offline learning events held in the community and notifying appropriate learners of such events. This enables the provision of individually customized learning curricula, appropriate feedback in real time, and collaboration with experts. Furthermore, educational activities in collaboration with the community can provide learners with diverse learning opportunities and significantly improve the quality of education.

[0594] A "learner" is a person who receives education using the system.

[0595] "Skills" are abilities or expertise that a learner already possesses.

[0596] "Interests" refer to areas or topics that a learner is particularly interested in.

[0597] A "learning style" is a method or approach that a learner uses to learn most effectively.

[0598] A "curriculum" is a specific educational program or learning content generated by the system.

[0599] An "expert" is someone who has advanced knowledge and experience in a particular field and who provides guidance and advice to learners.

[0600] A "network" is a structure or system that brings together domestic and international experts through a system to share their knowledge.

[0601] "Learning progress" refers to a learner's progress and achievement in learning activities.

[0602] "Feedback" refers to evaluation of learners and advice for improvement.

[0603] A "learning community" is an online or offline group of learners and professionals who can interact and collaborate.

[0604] "Local educational institutions" refer to schools, libraries, local government and other educational facilities in the area where the learner lives.

[0605] An "offline educational platform" refers to educational activities and learning environments that are conducted without using the Internet.

[0606] "First login" refers to the operation when a learner accesses the system for the first time and enters personal information and learning objectives.

[0607] An "input form" is an interface or screen that a learner uses to enter information.

[0608] An "artificial intelligence algorithm" is an automated computational method used by a computer to generate a curriculum based on learner information.

[0609] "Database" refers to an information structure for systematically managing and storing generated curriculum and other data.

[0610] "Device" refers to a device such as a computer, tablet, or smartphone that a learner uses to access the system.

[0611] "Questions" are questions or things that students have questions about while studying.

[0612] "Routing" refers to the process of sending an incoming question to the appropriate expert.

[0613] "Push notifications" is a function that allows the system to send learning progress, event information, and other information to learners' devices in real time.

[0614] An "online forum" is a bulletin board or community site on the Internet where learners and experts can exchange opinions and share information.

[0615] A "chat room" is an online communication tool for exchanging messages in real time.

[0616] "Offline learning events" are study groups and workshops held locally without internet connectivity.

[0617] "Notifications" are messages or alerts that inform learners of information.

[0618] This invention is a system that provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Specific implementation methods are described below.

[0619] First, when users log in for the first time, they enter their learning goals, interests, and skill level. The input form is designed to allow users to easily select their field of interest and current skill level. For example, options such as "Data Science" and "Beginner Programming" are provided.

[0620] The device sends the entered information to the server using an HTTP request. At this time, the information is encoded in JSON format. For example, the following data may be sent:

[0621] {

[0622] "interest": "data science",

[0623] "skill_level": "Beginner"

[0624] }

[0625] The server then runs an artificial intelligence algorithm (e.g., a TensorFlow model) based on the received information to generate a customized learning curriculum. This algorithm selects the optimal learning resources based on the user's skills and interests, and automatically generates the curriculum.

[0626] The generated curriculum is stored in a MySQL database by the server and sent to the user's device. The device reads the received curriculum and displays it in a user-friendly format using front-end web technologies (e.g., HTML, CSS, JavaScript).

[0627] Next, the user enters any questions or doubts that arise as they progress through their learning. These questions are then sent to the server in JSON format. For example, the following questions might be entered:

[0628] {

[0629] "question": "How do I set up a neural network?"

[0630] }

[0631] The device sends this question to the server, which analyzes the received question using a natural language processing model (e.g., GPT-4) and routes it to the appropriate expert. The expert then answers the question, and the answer is provided to the user via the server.

[0632] As the learning progresses, the device sends the user's progress data in real time to the server, which also encodes the data in JSON format. The server then uses a Python script to analyze the learner's performance and generates feedback using a data analysis tool (e.g., Tableau).

[0633] The generated feedback is sent to the user's device by the server. The feedback includes specific suggestions for improvement and next learning steps. For example, advice such as "The next challenge you should tackle is to understand regression analysis" is displayed.

[0634] Users access online forums and chat rooms by clicking links in the system. The server uses APIs to monitor community activity data and recommend appropriate forums and chat rooms to users. Activity data is collected in real time.

[0635] Finally, the server notifies users of local offline learning events, providing them with the opportunity to participate in local learning groups and workshops.

[0636] In this way, the system provides a personalized learning experience and strengthens collaboration with experts and the local community. Example prompts include:

[0637] A user wants to learn data science. What curriculum will he be offered, how will he connect with experts, how will he receive feedback, and how will he participate in a local learning community?

[0638] This system will make it possible to significantly improve the quality of education and provide a wide variety of learning opportunities.

[0639] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0640] Step 1:

[0641] A user logs in to the system for the first time. After logging in, the user enters their learning goals, interests, and skill level. The data is collected through an on-device input form, which includes text boxes and drop-down menus. Specifically, the user enters information such as "Interest: Data Science" and "Skill Level: Beginner."

[0642] Step 2:

[0643] The terminal encodes the information entered by the user into JSON format and sends it to the server as an HTTP request. The input data will be in JSON format as follows:

[0644] {

[0645] "interest": "data science",

[0646] "skill_level": "Beginner"

[0647] }

[0648] The terminal operates by using an HTTP POST request to send input data to the server.

[0649] Step 3:

[0650] The server generates a curriculum using an artificial intelligence algorithm (e.g., a TensorFlow model) based on the received user information. Specifically, it selects relevant learning materials and activities based on the input "areas of interest" and "skill level." The output is a customized curriculum.

[0651] {

[0652] "course": "Basic Data Science Course",

[0653] "modules": [

[0654] "Data collection and preprocessing",

[0655] "Basic Statistics",

[0656] "Introduction to Machine Learning"

[0657] ]

[0658] }

[0659] Step 4:

[0660] The server saves the generated curriculum in a MySQL database and simultaneously sends the data in JSON format to the terminal, where the curriculum is displayed for the user. As a concrete example, it generates SQL statements to save to the database and saves the curriculum information.

[0661] INSERT INTO curriculum (user_id, course, modules) VALUES ('12345', 'Data Science Fundamentals Course', '["Data Collection and Preprocessing", "Basic Statistics", "Introduction to Machine Learning"]');

[0662] Step 5:

[0663] The user begins learning according to the learning curriculum. If a question arises during the learning process, the user enters the question on the device. For example, they can enter a question such as, "How do I set up a neural network?"

[0664] Step 6:

[0665] The device encodes the question entered by the user into JSON format and sends it to the server as an HTTP request. The data sent looks like this:

[0666] {

[0667] "question": "How do I set up a neural network?"

[0668] }

[0669] The device again sends the data using an HTTP POST request.

[0670] Step 7:

[0671] The server analyzes the received question using a natural language processing model (e.g., GPT-4) and routes the question to the appropriate expert. Specifically, a question about "neural networks" is routed to a machine learning expert. The output is the expert's information and analysis results.

[0672] Step 8:

[0673] The server forwards the routed question to the appropriate expert and waits for the expert's answer. The expert answers the question and the answer is sent to the server. The server receives the answer and encodes it into JSON format.

[0674] Step 9:

[0675] The server then sends the answer it receives to the user's device and displays it, for example, "Here's how to set up the neural network..."

[0676] Step 10:

[0677] As users progress through learning activities, progress data is recorded on the device, for example, when they complete an assignment or finish a particular module.

[0678] Step 11:

[0679] The device sends the progress status to the server in real time. This data is also encoded in JSON format and sent. An example of the data sent is as follows:

[0680] {

[0681] "user_id": "12345",

[0682] "module_completed": "Data Collection and Preprocessing"

[0683] }

[0684] Step 12:

[0685] The server analyzes the learner's performance using Python scripts based on the received progress data and displays the results in a data analysis tool (e.g., Tableau). Performance reports and improvement suggestions are generated as output.

[0686] Step 13:

[0687] The server sends the generated feedback to the user's device via push notification, allowing the user to see appropriate improvement suggestions and next learning steps. For example, a notification might say, "Your next task is to understand regression analysis."

[0688] Step 14:

[0689] Users access online forums and chat rooms to connect with other learners and experts, using dedicated communication apps on their devices.

[0690] Step 15:

[0691] The server monitors community activity data in real time using an API and recommends appropriate forums and chat rooms to users, such as a message like, "We recommend you join a forum that discusses basic statistics."

[0692] Step 16:

[0693] The server collects information about offline learning events held in the area and notifies appropriate users, allowing users to participate in local learning groups and workshops, expanding learning opportunities.

[0694] The above is the specific flow of program processing for this system.

[0695] (Application example 1)

[0696] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0697] In traditional education systems, it was difficult to efficiently provide a curriculum tailored to each learner's skills, interests, and learning style. Furthermore, there was a lack of collaboration with domestic and international experts, progress management, and feedback, which led to problems in improving learners' learning efficiency and maintaining their motivation. Furthermore, there was a lack of offline learning communities and collaboration with local educational institutions, which limited the learning experience.

[0698] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0699] In this invention, the server includes means for receiving learner information and generating a customized learning curriculum using an AI algorithm, means for routing learner questions to appropriate experts using an AI algorithm and providing answers from the experts, means for analyzing learning progress data and generating real-time feedback, and means for collecting and providing local offline event information to learners. This enables learners to have an individually optimized learning experience, strengthening collaboration with experts, improving progress management, and feedback. It also builds online and offline learning communities and promotes collaboration with local educational institutions, thereby improving the learner's overall learning experience.

[0700] A "learner" is an individual or group of people who use a learning system to achieve educational objectives.

[0701] "Interest" refers to the interest or curiosity a learner has in a particular educational field or topic.

[0702] "Learning styles" are the methods or techniques that learners use to learn most effectively.

[0703] A "curriculum" is a set of learning contents and activities, from prerequisites to outcomes, in an educational process.

[0704] An "AI algorithm" is a computational procedure that uses artificial intelligence to automatically perform a specific task.

[0705] A "database" is an information system that efficiently manages large amounts of data and enables searching and updating.

[0706] An "expert" is someone who has advanced knowledge and experience in a particular field and provides this knowledge to learners.

[0707] "Progress data" is information that indicates the progress and achievements of a learner through a learning activity.

[0708] "Feedback" is information that includes an evaluation of a learner's learning activities and suggestions for improvement.

[0709] An "offline event" is a learning-related activity or event that takes place in a physical location without the internet.

[0710] "Local educational institutions" are schools, libraries, municipalities, and other organizations that provide education in the local community.

[0711] A "learning community" is a group or network of learners and professionals who interact with each other and share knowledge and information.

[0712] "Real-time feedback" is information that responds immediately to learners' learning activities and provides evaluations and areas for improvement on the spot.

[0713] "Question routing" is the process of sending questions received from learners to experts to obtain appropriate answers.

[0714] The present invention provides a system for providing learners with a customized educational experience, strengthening collaboration with experts, and improving the quality of learning through collaboration with the local community. This system is configured and provided as follows.

[0715] First, when a user logs in for the first time, they enter their learning goals, interests, and skill level. This provides the system with information that matches the user's learning style. The information entered by the user is sent from the user's device to the server. The server uses an AI algorithm based on the received information to generate a customized learning curriculum. This curriculum includes content that matches the user's skills and interests. The generated curriculum is saved in a database and sent to the user's device.

[0716] Next, collaboration with an expert is attempted. The expert accesses the system and inputs information about themselves, their field of expertise, career history, and qualifications. This allows the system to register each expert's knowledge and experience in a database. The user inputs any questions or doubts that arise during the study and sends them from their device to the server. The server analyzes the content of the question and routes it to the appropriate expert. The server then receives the expert's answer, sends it to the user's device, and displays it.

[0717] Furthermore, learning progress is managed and feedback is provided. As users proceed with their learning activities, they record progress data along the way. The device sends the progress status to the server in real time. The server analyzes the learner's performance based on the received progress data and generates feedback. This feedback includes suggestions for improvement and next learning steps and is sent to the user's device.

[0718] It also creates online and offline learning communities. Users can interact with other learners and experts through online forums and chat rooms. The server monitors community activity data and recommends appropriate forums and chat rooms to users. Furthermore, users can receive notifications from the server about offline study groups and activities being held in their area, allowing them to decide whether or not to participate. The server cooperates with local educational institutions, libraries, and local governments to collect offline event information and provide it to users.

[0719] As a specific example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experience: When the user logs in for the first time, they enter their interest in data science, and a customized data science curriculum is generated and sent to their device. If they ask a question about a specific data analysis method during the learning process, the question is routed to an appropriate data science expert. The expert's answer is provided to the user via the server. As the learning progresses, the device sends the user's progress data to the server, and the server generates feedback based on the analysis results. Furthermore, the server notifies the user of offline data science study groups and events held in the area, offering opportunities to participate.

[0720] Example prompts using a generative AI model:

[0721] "Develop a smartphone application that provides a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Use Python's requests library to send user information to a server and retrieve a customized curriculum generated by an AI algorithm."

[0722] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0723] Step 1:

[0724] When a user logs in for the first time, they enter their learning goals, interests, and skill level. The information they enter (e.g., "I'm interested in data science" or "Beginner") is collected via their device and sent to the server.

[0725] Input: Learner's goals, interests, skill level, etc.

[0726] Output: Learner information sent to the server

[0727] Step 2:

[0728] The server uses an AI algorithm to generate a customized learning curriculum based on the received user information. Specifically, the AI ​​algorithm analyzes the learner's interests and skill level, and selects and configures learning modules based on that. The generated curriculum is stored in a database.

[0729] Input: Student information sent to the server

[0730] Output: Customized curriculum stored in a database

[0731] Step 3:

[0732] The server sends the generated curriculum to the user's terminal, which displays the received curriculum and allows the user to start learning.

[0733] Input: Customized curriculum stored in the database

[0734] Output: The curriculum sent to the user's device

[0735] Step 4:

[0736] If a user has a question while studying, the user inputs the question into the terminal, which then sends the input question to the server.

[0737] Input: The question the user types into the terminal

[0738] Output: The question sent to the server

[0739] Step 5:

[0740] The server analyzes the received question and routes it to the expert appropriate for the question. Specifically, the server analyzes the question content using natural language processing and selects the most appropriate expert. The routed question is then sent to the expert.

[0741] Input: The question sent to the server

[0742] Output: Questions routed to experts

[0743] Step 6:

[0744] The expert creates an answer to the received question and sends the answer to the server, which then receives the answer from the expert and sends it to the user's device.

[0745] Input: Expert-generated answers

[0746] Output: The answer sent to the user's terminal

[0747] Step 7:

[0748] The system collects learning progress data while the user is learning. The device sends the learning progress data (e.g., completed modules, unread tutorials, etc.) to the server in real time.

[0749] Input: User's learning progress data

[0750] Output: Learning progress data sent to the server

[0751] Step 8:

[0752] The server analyzes the learning progress data and generates real-time feedback to assess the progress and provide appropriate advice and next steps for learning. The generated feedback is then sent to the user's device.

[0753] Input: Learning progress data sent to the server

[0754] Output: Real-time feedback sent to the user device

[0755] Step 9:

[0756] When users access online forums or chat rooms, the server monitors their activity data and recommends appropriate forums or chat rooms to them. Additionally, the server collects offline event information from local educational institutions, libraries, and local governments and notifies appropriate users.

[0757] Input: Forum and chat room activity data, local offline event information

[0758] Output: User recommended forums, chat rooms and offline event information

[0759] Example prompts using a generative AI model:

[0760] "Develop a smartphone application that provides a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Use Python's requests library to send user information to a server and retrieve a customized curriculum generated by an AI algorithm."

[0761] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0762] The present invention is a system that provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the community, and combines it with an emotion engine that recognizes the user's emotions, allowing it to tailor curriculum, feedback, and communication recommendations based on the learner's emotional state.

[0763] Entering learner information and generating a curriculum

[0764] When users first log in, they enter their email address and password, along with their learning goals, interests, and skill level, and the system uses this information to create a learner profile.

[0765] The terminal transmits the input information to the server.

[0766] The server uses an AI algorithm to generate a customized learning curriculum based on the received information, and also analyzes the user's emotional state using an emotion engine, which then incorporates that information into the curriculum.

[0767] The server stores the generated curriculum in a database and transmits it to the user's terminal.

[0768] Collaboration with experts

[0769] Experts access the system and enter their field of expertise, background, and qualifications, which allows the system to register each expert's knowledge and experience in a database.

[0770] Users can enter any questions or concerns they may have while studying and submit their questions.

[0771] The terminal sends a question from the user to the server.

[0772] The server analyzes the question and routes it to the appropriate expert, taking into account the user's emotional state and recommending an answer in an appropriate tone.

[0773] The expert enters the answer to the question and sends it to the server.

[0774] The server sends the expert's answer to the user's terminal and displays it.

[0775] Tracking learning progress and providing feedback

[0776] As users progress through the learning process, their progress data is recorded, while the emotion engine simultaneously analyzes their emotions from their facial expressions and tone of voice.

[0777] The device transmits progress and emotion data to the server in real time.

[0778] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments, such as lowering the difficulty level if the user is feeling stressed.

[0779] The server sends the generated feedback and adjustments to the user's terminal and displays them to the user.

[0780] Building a learning community

[0781] Users access online forums and chat rooms to interact with other learners and experts, while the emotion engine monitors their emotional state.

[0782] The server monitors community activity data and recommends appropriate forums and chat rooms based on the user's emotional state, as well as providing notifications to encourage active participation within the community.

[0783] Users receive notifications of offline events provided by the system and decide whether to participate. Data from the emotion engine is also taken into consideration at this time, and events suitable for the user are recommended.

[0784] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[0785] Specific examples

[0786] For example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experiences:

[0787] When a user first logs in, they tell the system that they are interested in data science.

[0788] The server generates a customized data science curriculum based on the information received and sends it to the user's device.

[0789] As the learning process progresses, users ask questions about specific data analysis techniques, which are then routed by the server to the appropriate data science experts. An emotion engine detects when the user is frustrated and encourages the experts to respond in a gentler tone.

[0790] Experts answer questions, and the answers are provided to users via a server. As users learn, their progress data and emotional state are recorded and sent to the server in real time. The server analyzes the data and generates appropriate feedback for users. It also recommends participation in appropriate forums and offline events based on the user's emotional state.

[0791] The system provides learners with a highly customized educational experience and addresses their psychological aspects by utilizing an emotional engine, thereby improving the quality of education and enabling learners to achieve optimal learning through collaboration with the local community.

[0792] The processing flow will be explained below.

[0793] Step 1:

[0794] A user accesses the system and enters their email address and password on the initial login screen.

[0795] Step 2:

[0796] The terminal sends the input information to the server and requests user authentication.

[0797] Step 3:

[0798] The server compares the received authentication information with a database, generates an authentication token, and sends it to the terminal.

[0799] Step 4:

[0800] After logging in, the user is directed to a screen where they can enter their learning goals, interests, and skill level. At this point, the camera and microphone are activated, and the emotion engine analyzes the user's facial expressions and voice.

[0801] Step 5:

[0802] The terminal transmits the input learner information and emotion data to the server.

[0803] Step 6:

[0804] The server uses an AI algorithm to generate a customized learning curriculum based on the learner information and emotional data received.

[0805] Step 7:

[0806] The server stores the generated curriculum in a database and sends it to the user's device.

[0807] Step 8:

[0808] Users begin learning based on the curriculum, and if they encounter any problems or questions during the learning process, they can enter them.

[0809] Step 9:

[0810] The device sends the user's question to the server, and the emotion engine also analyzes the user's emotional state at that time and sends the result to the server.

[0811] Step 10:

[0812] The server analyzes the question and emotional data and routes it to the appropriate expert, recommending that the expert respond in an appropriate tone based on the emotional state.

[0813] Step 11:

[0814] The expert enters the answer to the question and sends it to the server.

[0815] Step 12:

[0816] The server receives the answers from the experts and sends them to the user's device.

[0817] Step 13:

[0818] As users learn, their progress is recorded, and an emotion engine analyzes their emotional state.

[0819] Step 14:

[0820] The device transmits progress and emotion data to the server in real time.

[0821] Step 15:

[0822] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments.

[0823] Step 16:

[0824] The server sends the generated feedback and adjustments to the user's device and displays them to the user, adjusting the content and tone of the feedback according to the user's emotional state.

[0825] Step 17:

[0826] As users access online forums and chat rooms and interact with other learners and experts, the emotion engine monitors their emotional state and transmits that data to the server if necessary.

[0827] Step 18:

[0828] The server monitors community activity data and user sentiment data and recommends appropriate forums and chat rooms to users.

[0829] Step 19:

[0830] The server collects information on offline study sessions and activities taking place in the area and sends push notifications to appropriate users based on emotional data.

[0831] Step 20:

[0832] Users receive notifications about offline events and decide whether or not they want to participate. The emotion engine analyzes the user's reactions and provides feedback tailored to their willingness to participate.

[0833] In this way, this system, which combines an emotion engine, also responds to the psychological aspects of learners and provides an optimal learning environment.

[0834] Example 2

[0835] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0836] Traditional educational systems have difficulty customizing to meet individual learners' skills, interests, and learning styles, and generic curricula have been unable to meet individual needs. Furthermore, limited collaboration with experts makes it difficult to respond quickly and appropriately to learners' doubts and questions. Furthermore, the inability to provide feedback or adjust the curriculum to take into account the learner's emotional state means that improvements in learning quality and motivation cannot be expected.

[0837] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0838] In this invention, the server includes means for analyzing the emotional state of the learner and adjusting the curriculum and feedback content, means for analyzing the learner's questions and providing answers in an appropriate tone, and means for collecting information on study sessions and activities taking place in the local area and recommending appropriate offline events based on the learner's emotional state. This makes it possible to provide an educational experience optimized for each learner and to improve the quality of learning and motivation by strengthening collaboration with experts and the local community.

[0839] A "learner" is an individual who engages in a learning activity.

[0840] A "skill" is an ability or technique for effectively performing a particular task or activity.

[0841] "Interests" refer to subjects or topics that interest learners.

[0842] A "learning style" refers to the method or approach that a learner takes in learning.

[0843] A "curriculum" is an educational content or learning program designed to achieve specific learning goals.

[0844] An "expert" is a person who has advanced knowledge or skills in a particular field.

[0845] A "network" is a communication system built to share information and resources.

[0846] "Learning progress" refers to an indicator or state that indicates how far a learner has progressed toward a learning goal.

[0847] "Feedback" refers to information provided about the learning process or results for evaluation and improvement.

[0848] "Online" refers to operations or activities conducted over the Internet.

[0849] "Offline" refers to operations or activities that are not performed via the Internet.

[0850] A "learning community" is a group of learners and experts who exchange information and opinions and support each other's learning.

[0851] An "emotional state" is the emotion or mental state that a learner is feeling at a particular time.

[0852] "Analysis" is the act of examining data or information in detail and clarifying its structure and relationships.

[0853] "Tone" refers to the way one speaks or expresses something, especially its intensity and emotional level.

[0854] "Routing" refers to the procedures and methods used to direct data or information to its proper destination.

[0855] An "offline event" is a learning activity or social gathering that takes place in a physical location.

[0856] The system is designed to provide a customized educational experience that takes into account the learner's skills, interests, and learning style. Key elements include an AI algorithm, an emotion engine, and online and offline learning community functions. The specific implementation of each element is explained below.

[0857] Entering learner information and generating a curriculum

[0858] When a user logs in for the first time, they enter their email address and password, as well as their learning goals, interests, and skill level. This information is sent from the device to the server via an HTTP POST request. The server receives this information and stores it in a database. It then uses an AI algorithm to generate a customized learning curriculum. This AI algorithm selects the most appropriate learning content based on the learner's profile information.

[0859] Furthermore, the server uses an emotion engine to analyze the learner's emotional state. This emotional state is obtained using facial expression analysis technology, tone of voice analysis technology, etc. This makes it possible to reflect emotional information in the curriculum. The generated curriculum is saved in the database again and sent to the terminal. The terminal displays the received curriculum to the user.

[0860] Collaboration with experts

[0861] Experts access the system and enter their field of expertise, background, and qualifications. This information is registered in a database. When a user enters a question or concern during learning, the device sends the question to the server. The server analyzes the question and routes it to the appropriate expert. In doing so, it uses an emotion engine to analyze the user's emotional state and provides the expert with instructions recommending an appropriate tone of voice to respond. The expert enters the answer and sends it to the server, where it is delivered and displayed to the user.

[0862] Tracking learning progress and providing feedback

[0863] As the user progresses through their learning activities, their progress data is recorded. At the same time, an emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and sends this information in real time via the device to the server. The server analyzes the received data and evaluates the learner's performance. Based on this, appropriate feedback and curriculum adjustments are generated, sent to the device, and displayed to the user. For example, if the learner is feeling stressed, the system will make adjustments such as lowering the difficulty of the learning content.

[0864] Building a learning community

[0865] Users can access online forums and chat rooms to interact with other learners and experts. The emotion engine monitors the user's emotional state and recommends appropriate forums and chat rooms. The server also monitors community activity data and sends notifications to encourage active participation.

[0866] The server also collects information about offline study groups and activities taking place in the local area and sends push notifications to appropriate users, providing opportunities for learners to meet in person both online and offline and building a learning community.

[0867] Specific examples

[0868] For example, consider the case where a learner who wants to learn data science enters their interest in data science when logging in for the first time. The server generates a customized data science curriculum based on the received information and sends it to the device. If the user asks a question about a specific data analysis method as they progress through their studies, the question is routed to an appropriate data science expert. At that time, an emotion engine detects the user's frustration and recommends that the expert respond in a gentler tone. The expert's answer is then provided to the user via the server.

[0869] An example of a prompt sentence could be, "Please enter the information needed to customize your data science curriculum. For example, please enter your area of ​​interest, current skill level, and learning goals. Also, please enter your past learning experience and any specific questions you may have." By using this prompt sentence as a concrete example, the system can quickly generate a curriculum optimized for the user's needs.

[0870] Overall, the system aims to improve learning quality and motivation by providing an educational experience tailored to each learner's individual needs and by strengthening collaboration with experts and the local community.

[0871] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0872] Step 1:

[0873] A user enters an email address and password on the login screen. The entered information is sent from the device to the server. Specifically, the data collected in the input form is sent to the server as an HTTP POST request. The input data includes the email address and hashed password.

[0874] Step 2:

[0875] The server compares the received login information with the database and performs authentication. If authentication is successful, the server generates the user's session information and sends the session ID to the terminal. The authentication process checks whether the email address and hashed password match the information in the database.

[0876] Step 3:

[0877] The user enters profile information such as learning objectives, interests, and skill level. The entered information is sent to the server via the terminal. Specifically, the data collected in the form is sent to the server as an HTTP POST request. The input data includes learning objectives, interests, and skill level.

[0878] Step 4:

[0879] The server stores the received profile information in a database and analyzes it using an AI algorithm. As a result of the analysis, a learning curriculum optimal for the learner is generated. Specifically, the received data is input into an AI model to generate a customized curriculum. As an output, the learning curriculum is stored in a database.

[0880] Step 5:

[0881] The server uses an emotion engine to analyze the user's emotional state. Specifically, it receives the user's facial expressions and voice data as input and analyzes them using an emotion analysis model. The output is data indicating the user's emotional state.

[0882] Step 6:

[0883] The server reflects the emotional state in the generated curriculum to complete the final curriculum. Specifically, the content and difficulty of the curriculum are adjusted using the emotional state data. As an output, the curriculum reflecting the emotions is saved again in the database.

[0884] Step 7:

[0885] The server sends the final curriculum to the terminal. Specifically, it sends the generated curriculum to the terminal as an HTTP response. The terminal displays the received curriculum to the user.

[0886] Step 8:

[0887] Experts access the system and enter their field of expertise, background, and qualifications, which are then sent from the terminal to the server and stored in a database.

[0888] Step 9:

[0889] The user inputs questions that arise during learning and sends them from the device to the server. The input data includes the question content. Specifically, the question data collected in the form is sent to the server as an HTTP POST request.

[0890] Step 10:

[0891] The server analyzes the received question and routes it to the appropriate expert. Specifically, it analyzes the question content using natural language processing (NLP) technology and searches a database for the most suitable expert. The output is information about the expert to whom the question will be routed.

[0892] Step 11:

[0893] The server notifies the expert of the question and emotional information. Specifically, the server generates notification data containing the question content and the user's emotional state information and sends it to the expert's terminal.

[0894] Step 12:

[0895] The expert enters the answer to the question and sends it to the server. Specifically, the answer is sent to the server as an HTTP POST request.

[0896] Step 13:

[0897] The server sends the received response to the user's device and displays it. Specifically, it sends the response data to the device as an HTTP response. The device displays the received response to the user.

[0898] Step 14:

[0899] As the user progresses through the learning activity, progress data is recorded. At the same time, the emotion engine analyzes emotional data from facial expressions and tone of voice. This data is sent to the server via the device.

[0900] Step 15:

[0901] The server analyzes the received progress and emotion data and generates feedback. Specifically, the progress and emotion data are input into a machine learning model to generate performance evaluation and optimal feedback. The output is feedback data.

[0902] Step 16:

[0903] The server sends the generated feedback to the terminal and displays it to the user. Specifically, the server sends the feedback data to the terminal as an HTTP response. The terminal then displays the received feedback to the user.

[0904] Step 17:

[0905] A user accesses an online forum or chat room and communicates with the user. The server monitors the user's emotional state using an emotion engine and recommends appropriate forums or chat rooms.

[0906] Step 18:

[0907] The server collects information about offline learning activities taking place in the area and notifies appropriate users. Specifically, it analyzes the collected information data and recommends offline events based on the user's emotional state. The device displays the received event notifications to the user.

[0908] Through this process, the system is able to provide an educational experience that is optimized to the individual needs of each learner.

[0909] (Application example 2)

[0910] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0911] Conventional learning systems lack the ability to customize learning to fit the learner's skills, interests, and emotional state, resulting in poor learning efficiency. Furthermore, in brick-and-mortar stores, they are unable to provide customer service that reflects their emotions, which can lead to lower customer satisfaction. Furthermore, there are challenges in building online and offline learning communities and effectively utilizing expert knowledge.

[0912] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for generating a customized curriculum based on the learner's skills, interests, and learning style; means for bringing together domestic and international experts and building a network to provide their knowledge; means for tracking and managing learning progress and providing feedback; means for providing opportunities for learners to meet in person online and offline and building a learning community; means for collaborating with local schools, libraries, and local governments and utilizing it as an offline education platform; means for analyzing the learner's emotional state using an emotion engine and adjusting the curriculum, feedback, and communication recommendations; and means for realizing a brick-and-mortar store application that analyzes the emotional state of customers in real time and provides customized customer service methods and suggestions. This enables advanced customization according to the individual needs of learners, improving learning efficiency and customer satisfaction.

[0913] "Learner" refers to an individual who uses a learning system to acquire knowledge or skills.

[0914] "Skills" refer to the abilities and techniques that a learner has to accomplish a specific task or work.

[0915] "Interest" refers to the interest or curiosity a learner has in a particular field or topic.

[0916] "Learning style" refers to the methods and procedures by which a learner learns most effectively.

[0917] "Curriculum" refers to an educational plan that defines the content and progression that learners should learn.

[0918] "Domestic and international experts" refers to individuals or institutions with a high level of knowledge and experience in a particular field.

[0919] "Network" refers to a communication network that allows multiple experts and learners to share information and collaborate.

[0920] "Progress" refers to the progress that a learner makes in demonstrating how well they have achieved their learning tasks.

[0921] "Feedback" refers to evaluation and advice provided to learners to improve their learning activities.

[0922] A "community" refers to a group of learners and professionals who share common learning goals and interests.

[0923] "Online" refers to forms of learning and communication delivered via the Internet.

[0924] "Offline" refers to activities and communications that take place in a physical location, not via the internet.

[0925] An "emotion engine" refers to technology that analyzes a user's facial expressions, tone of voice, etc. to determine their emotional state.

[0926] "Customer" means an individual who uses or purchases a particular service or product.

[0927] "Brick and mortar store" refers to a sales or service point located in a physical location.

[0928] "Application" refers to a software program that provides a specific function or service.

[0929] An "AI algorithm" refers to a calculation method for analyzing data and making decisions using artificial intelligence.

[0930] A "database" refers to a digital system that systematically organizes and stores information.

[0931] This system provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Furthermore, by incorporating an emotion engine, the system adjusts curriculum, feedback, and communication recommendations based on the learner's emotional state. This system can also be applied to brick-and-mortar retail applications, where customers' emotional states are analyzed in real time to provide customized customer service methods and suggestions.

[0932] Entering learner information and generating a curriculum

[0933] When logging in for the first time, users enter their email address and password, as well as their learning goals, interests, and skill level. The device then sends the entered information to the server. The server uses an AI algorithm based on the received information to generate a customized learning curriculum, and then analyzes the user's emotional state using an emotion engine and reflects that information in the curriculum. The server then saves the generated curriculum in a database and sends it to the user's device.

[0934] Collaboration with experts

[0935] Experts access the system and register their knowledge and experience in the database by entering their field of expertise, career history, and qualifications. Users enter questions or doubts that arise during their studies and send them from their terminal to the server. The server analyzes the content of the question and routes it to the appropriate expert. The expert enters an answer to the question and sends it to the server. The server sends the answer from the expert to the user's terminal and displays it.

[0936] Tracking learning progress and providing feedback

[0937] As the user progresses through the learning activity, progress data is recorded. At the same time, the emotion engine analyzes the user's emotions from their facial expressions and tone of voice. The device sends the progress and emotion data to the server in real time. The server analyzes the learner's performance based on the received progress and emotion data and generates feedback and adjustments. For example, if the user is feeling stressed, it may lower the difficulty level. The server sends the generated feedback to the user's device and displays it to the user.

[0938] Application in physical stores

[0939] This system can also be applied to improving customer service experiences in brick-and-mortar stores. The device is installed on a smartphone or head-mounted display and uses a camera to capture the customer's facial expressions. The received video data is sent to a server in real time, where an emotion engine analyzes the customer's emotional state. Based on the analysis results, the device displays customer service methods and product suggestions that are appropriate for the customer's emotions.

[0940] For example, when a customer visits a cosmetics counter in a physical store, a staff member's smartphone scans the customer's facial expression and determines that the customer looks a little depressed. The staff member is then shown advice such as, "Today, we'd like to recommend a lip color that will cheer you up a little."

[0941] Prompt Sentence Examples

[0942] The following prompt sentence is used as input to the generative AI model:

[0943] Write a program for a system that recognizes customer emotions and customizes in-store interactions. The hardware used is a smartphone camera, and the software is Python. Include recommendations based on the customer's emotional state.

[0944] This will enable us to provide an educational environment for users and improve the customer service experience in physical stores.

[0945] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0946] Step 1:

[0947] When a user logs in for the first time, they enter their email address and password, as well as their learning goals, interests, and skill level. This generates the user's profile information. The entered information is sent to the server by the device. The entered data includes the email address, password, learning goals, interests, and skill level. The device then uploads this data to the server.

[0948] Step 2:

[0949] The server uses an AI algorithm to generate a customized learning curriculum based on the received user information. The learning content is customized based on the user's skills, interests, and learning style. An emotion engine also analyzes the user's emotional state, and the results are reflected in the curriculum. The input here is user information, and the output is a customized learning curriculum.

[0950] Step 3:

[0951] The server stores the generated curriculum in a database and then transmits it to the user's device. The database stored on the server holds a customized educational plan for each learner. The input is curriculum data, and the output is data transmission to the user's device.

[0952] Step 4:

[0953] If a user has any doubts or questions during their studies, they can input them through their device and send them to the server. The input data includes the user's question, and the device uploads it to the server.

[0954] Step 5:

[0955] The server analyzes the received question and routes it to the appropriate expert from a list of experts in the database. The server takes into account the question as well as the user's emotional state, which is analyzed by the emotion engine. The input is the question from the user, and the output is the expert to whom the question is routed.

[0956] Step 6:

[0957] The expert inputs an answer to the question received from the server and sends it to the server. In this process, the answer is generated using the expert's knowledge and experience. The input is the expert's answer, and the output is the response sent to the server.

[0958] Step 7:

[0959] The server sends the expert's answer to the user's device and displays it to the user. In this step, the user can receive an explanation based on expert knowledge. The input is the expert's answer data, and the output is the answer displayed on the user's device.

[0960] Step 8:

[0961] As the user progresses through the learning activity, the progress and emotional data are sent to the server in real time from the device, thereby recording the learning progress and emotional state. The input is progress data and emotional data, and the output is data uploaded to the server.

[0962] Step 9:

[0963] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments. For example, if the user is feeling stressed, the server may lower the difficulty of the learning content. The input is progress and emotion data, and the output is customized feedback.

[0964] Step 10:

[0965] The server sends the generated feedback to the user's terminal and displays it to the user, allowing the user to check areas for improvement in their learning and their next steps. The input is feedback data, and the output is data display on the user's terminal.

[0966] Step 11:

[0967] When a user visits a physical store, the device (smartphone or head-mounted display) uses a camera to capture the customer's facial expressions. The video data is sent to the server in real time. The input is the captured video data, and the output is the video data sent to the server.

[0968] Step 12:

[0969] The server uses an emotion engine to analyze the customer's emotional state and generate customized customer service methods and product suggestions based on the results. The input is video data, and the output is the analysis results and customized suggestions.

[0970] Step 13:

[0971] The server then sends the generated customer service methods and suggestions to the terminal and displays them to the store staff. This allows the staff to provide customer service that is tailored to the customer's emotions. The input is the customized suggestions, and the output is the data displayed on the terminal.

[0972] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0973] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0974] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0975] [Third embodiment]

[0976] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0977] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0978] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0979] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0980] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0981] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0982] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0983] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0984] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0985] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0986] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0987] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0988] This invention is a system that provides learners with a customized educational experience, strengthens connections with experts, and improves the quality of learning through collaboration with the community. The system generates customized curricula based on learners' skills, interests, and learning styles, builds expert networks, tracks and manages learning progress, provides feedback, and creates online and offline learning communities.

[0989] Entering learner information and generating a curriculum

[0990] When users first log in, they enter their learning goals, interests, and skill level, which provides the system with information tailored to their learning style.

[0991] The terminal transmits the input information to the server.

[0992] The server uses AI algorithms to generate a customized learning curriculum based on the received information, which includes content that addresses the user's skills and interests.

[0993] The server stores the generated curriculum in a database and transmits it to the user's terminal.

[0994] Collaboration with experts

[0995] Experts access the system and enter information about themselves, their field of expertise, background, and qualifications, which the system then registers in a database each expert's knowledge and experience.

[0996] Users can enter any questions or concerns they may have while studying and submit their questions.

[0997] The terminal sends a question from the user to the server.

[0998] The server analyzes the question, routes it to the appropriate expert, and then receives the answer from the expert.

[0999] The server sends the received response to the user's terminal and displays it.

[1000] Tracking learning progress and providing feedback

[1001] Users progress through learning activities and progress data is recorded along the way.

[1002] The device sends real-time progress information to the server.

[1003] The server analyzes the learner's performance based on the received progress data and generates feedback.

[1004] The server sends the generated feedback to the user's device and suggests appropriate improvements and next learning steps.

[1005] Building a learning community

[1006] Users have access to online forums and chat rooms to connect with other learners and experts.

[1007] The server monitors community activity data and recommends appropriate forums and chat rooms to users.

[1008] Users receive notifications of offline events provided by the system and decide whether to participate.

[1009] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[1010] Specific examples

[1011] For example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experiences:

[1012] When users first log in, they tell the system that they are interested in data science.

[1013] The server generates a customized data science curriculum based on the received information and sends it to the user's device.

[1014] As the learning process progresses, users ask questions about specific data analysis techniques, which are then routed by the server to the appropriate data science experts.

[1015] The experts answer the questions and the answers are provided to the users via the server.

[1016] As learning progresses, the device sends the user's progress data to the server, which generates feedback based on the analysis results.

[1017] Additionally, the server will notify users of offline data science study groups and events being held in the area, providing them with opportunities to participate.

[1018] This system will provide each learner with the best possible learning experience and eliminate educational disparities through collaboration with experts and local communities.

[1019] The processing flow will be explained below.

[1020] Step 1:

[1021] A user accesses the system and enters their email address and password on the initial login screen.

[1022] Step 2:

[1023] The terminal sends the input information to the server and requests user authentication.

[1024] Step 3:

[1025] The server compares the received authentication information with a database, generates an authentication token, and sends it to the terminal.

[1026] Step 4:

[1027] After logging in, users are taken to a screen where they can enter their learning goals, interests, and skill level.

[1028] Step 5:

[1029] The terminal transmits the inputted learner information to the server.

[1030] Step 6:

[1031] Based on the learner information received by the server, a customized learning curriculum is generated using an AI algorithm.

[1032] Step 7:

[1033] The server stores the generated curriculum in a database and transmits it to the terminal.

[1034] Step 8:

[1035] Users start learning based on the curriculum, and if they encounter any problems or questions during the learning process, they can enter their questions.

[1036] Step 9:

[1037] The device sends the user's question to the server.

[1038] Step 10:

[1039] The server analyzes the question and routes it to the appropriate expert.

[1040] Step 11:

[1041] The expert enters the answer to the question and sends it to the server.

[1042] Step 12:

[1043] The server receives the answers from the experts and sends them to the user's device.

[1044] Step 13:

[1045] Progress data is recorded as users learn.

[1046] Step 14:

[1047] The device sends progress information to the server in real time.

[1048] Step 15:

[1049] The server analyzes the learner's performance based on the received progress data and generates feedback.

[1050] Step 16:

[1051] The server sends the generated feedback to the user's terminal and displays it to the user.

[1052] Step 17:

[1053] Users have access to online forums and chat rooms where they can interact with other learners and experts.

[1054] Step 18:

[1055] The server monitors community activity data and recommends appropriate forums and chat rooms to users.

[1056] Step 19:

[1057] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[1058] Step 20:

[1059] A user receives notification of an offline event and decides whether to attend.

[1060] Example 1

[1061] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1062] Traditional education systems often provide learners with a uniform curriculum, which does not adequately address individual skills, interests, or learning styles. Furthermore, they face challenges such as a lack of prompt and appropriate feedback on questions that arise during learning, and a lack of collaboration with experts and learning communities. Furthermore, a lack of collaboration with offline educational institutions makes it difficult to improve educational effectiveness through collaboration with local communities.

[1063] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1064] In this invention, the server includes: a means for a learner to input their learning goals, interests, and skill level when they log in for the first time; a means for transmitting the input information to the server; a means for generating a curriculum based on the received information using an artificial intelligence algorithm, storing the curriculum in a database, and transmitting the curriculum to the terminal; a means for the learner to input questions that arise during learning and for routing the questions to appropriate experts; a means for providing the learner with answers from the experts; a means for transmitting learning progress and feedback to the terminal using push notifications; a means for the learner to access online forums and chat rooms to interact with other learners and experts; and a means for collecting information about offline learning events held in the community and notifying appropriate learners of such events. This enables the provision of individually customized learning curricula, appropriate feedback in real time, and collaboration with experts. Furthermore, educational activities in collaboration with the community can provide learners with diverse learning opportunities and significantly improve the quality of education.

[1065] A "learner" is a person who receives education using the system.

[1066] "Skills" are abilities or expertise that a learner already possesses.

[1067] "Interests" refer to areas or topics that a learner is particularly interested in.

[1068] A "learning style" is a method or approach that a learner uses to learn most effectively.

[1069] A "curriculum" is a specific educational program or learning content generated by the system.

[1070] An "expert" is someone who has advanced knowledge and experience in a particular field and who provides guidance and advice to learners.

[1071] A "network" is a structure or system that brings together domestic and international experts through a system to share their knowledge.

[1072] "Learning progress" refers to a learner's progress and achievement in learning activities.

[1073] "Feedback" refers to evaluation of learners and advice for improvement.

[1074] A "learning community" is an online or offline group of learners and professionals who can interact and collaborate.

[1075] "Local educational institutions" refer to schools, libraries, local government and other educational facilities in the area where the learner lives.

[1076] An "offline educational platform" refers to educational activities and learning environments that are conducted without using the Internet.

[1077] "First login" refers to the operation when a learner accesses the system for the first time and enters personal information and learning objectives.

[1078] An "input form" is an interface or screen that a learner uses to enter information.

[1079] An "artificial intelligence algorithm" is an automated computational method used by a computer to generate a curriculum based on learner information.

[1080] "Database" refers to an information structure for systematically managing and storing generated curriculum and other data.

[1081] "Device" refers to a device such as a computer, tablet, or smartphone that a learner uses to access the system.

[1082] "Questions" are questions or things that students have questions about while studying.

[1083] "Routing" refers to the process of sending an incoming question to the appropriate expert.

[1084] "Push notifications" is a function that allows the system to send learning progress, event information, and other information to learners' devices in real time.

[1085] An "online forum" is a bulletin board or community site on the Internet where learners and experts can exchange opinions and share information.

[1086] A "chat room" is an online communication tool for exchanging messages in real time.

[1087] "Offline learning events" are study groups and workshops held locally without internet connectivity.

[1088] "Notifications" are messages or alerts that inform learners of information.

[1089] This invention is a system that provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Specific implementation methods are described below.

[1090] First, when users log in for the first time, they enter their learning goals, interests, and skill level. The input form is designed to allow users to easily select their field of interest and current skill level. For example, options such as "Data Science" and "Beginner Programming" are provided.

[1091] The device sends the entered information to the server using an HTTP request. At this time, the information is encoded in JSON format. For example, the following data may be sent:

[1092] {

[1093] "interest": "data science",

[1094] "skill_level": "Beginner"

[1095] }

[1096] The server then runs an artificial intelligence algorithm (e.g., a TensorFlow model) based on the received information to generate a customized learning curriculum. This algorithm selects the optimal learning resources based on the user's skills and interests, and automatically generates the curriculum.

[1097] The generated curriculum is stored in a MySQL database by the server and sent to the user's device. The device reads the received curriculum and displays it in a user-friendly format using front-end web technologies (e.g., HTML, CSS, JavaScript).

[1098] Next, the user enters any questions or doubts that arise as they progress through their learning. These questions are then sent to the server in JSON format. For example, the following questions might be entered:

[1099] {

[1100] "question": "How do I set up a neural network?"

[1101] }

[1102] The device sends this question to the server, which analyzes the received question using a natural language processing model (e.g., GPT-4) and routes it to the appropriate expert. The expert then answers the question, and the answer is provided to the user via the server.

[1103] As the learning progresses, the device sends the user's progress data in real time to the server, which also encodes the data in JSON format. The server then uses a Python script to analyze the learner's performance and generates feedback using a data analysis tool (e.g., Tableau).

[1104] The generated feedback is sent to the user's device by the server. The feedback includes specific suggestions for improvement and next learning steps. For example, advice such as "The next challenge you should tackle is to understand regression analysis" is displayed.

[1105] Users access online forums and chat rooms by clicking links in the system. The server uses APIs to monitor community activity data and recommend appropriate forums and chat rooms to users. Activity data is collected in real time.

[1106] Finally, the server notifies users of local offline learning events, providing them with the opportunity to participate in local learning groups and workshops.

[1107] In this way, the system provides a personalized learning experience and strengthens collaboration with experts and the local community. Example prompts include:

[1108] A user wants to learn data science. What curriculum will he be offered, how will he connect with experts, how will he receive feedback, and how will he participate in a local learning community?

[1109] This system will make it possible to significantly improve the quality of education and provide a wide variety of learning opportunities.

[1110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1111] Step 1:

[1112] A user logs in to the system for the first time. After logging in, the user enters their learning goals, interests, and skill level. The data is collected through an on-device input form, which includes text boxes and drop-down menus. Specifically, the user enters information such as "Interest: Data Science" and "Skill Level: Beginner."

[1113] Step 2:

[1114] The terminal encodes the information entered by the user into JSON format and sends it to the server as an HTTP request. The input data will be in JSON format as follows:

[1115] {

[1116] "interest": "data science",

[1117] "skill_level": "Beginner"

[1118] }

[1119] The terminal operates by using an HTTP POST request to send input data to the server.

[1120] Step 3:

[1121] The server generates a curriculum using an artificial intelligence algorithm (e.g., a TensorFlow model) based on the received user information. Specifically, it selects relevant learning materials and activities based on the input "areas of interest" and "skill level." The output is a customized curriculum.

[1122] {

[1123] "course": "Basic Data Science Course",

[1124] "modules": [

[1125] "Data collection and preprocessing",

[1126] "Basic Statistics",

[1127] "Introduction to Machine Learning"

[1128] ]

[1129] }

[1130] Step 4:

[1131] The server saves the generated curriculum in a MySQL database and simultaneously sends the data in JSON format to the terminal, where the curriculum is displayed for the user. As a concrete example, it generates SQL statements to save to the database and saves the curriculum information.

[1132] INSERT INTO curriculum (user_id, course, modules) VALUES ('12345', 'Data Science Fundamentals Course', '["Data Collection and Preprocessing", "Basic Statistics", "Introduction to Machine Learning"]');

[1133] Step 5:

[1134] The user begins learning according to the learning curriculum. If a question arises during the learning process, the user enters the question on the device. For example, they can enter a question such as, "How do I set up a neural network?"

[1135] Step 6:

[1136] The device encodes the question entered by the user into JSON format and sends it to the server as an HTTP request. The data sent looks like this:

[1137] {

[1138] "question": "How do I set up a neural network?"

[1139] }

[1140] The device again sends the data using an HTTP POST request.

[1141] Step 7:

[1142] The server analyzes the received question using a natural language processing model (e.g., GPT-4) and routes the question to the appropriate expert. Specifically, a question about "neural networks" is routed to a machine learning expert. The output is the expert's information and analysis results.

[1143] Step 8:

[1144] The server forwards the routed question to the appropriate expert and waits for the expert's answer. The expert answers the question and the answer is sent to the server. The server receives the answer and encodes it into JSON format.

[1145] Step 9:

[1146] The server then sends the answer it receives to the user's device and displays it, for example, "Here's how to set up the neural network..."

[1147] Step 10:

[1148] As users progress through learning activities, progress data is recorded on the device, for example, when they complete an assignment or finish a particular module.

[1149] Step 11:

[1150] The device sends the progress status to the server in real time. This data is also encoded in JSON format and sent. An example of the data sent is as follows:

[1151] {

[1152] "user_id": "12345",

[1153] "module_completed": "Data Collection and Preprocessing"

[1154] }

[1155] Step 12:

[1156] The server analyzes the learner's performance using Python scripts based on the received progress data and displays the results in a data analysis tool (e.g., Tableau). Performance reports and improvement suggestions are generated as output.

[1157] Step 13:

[1158] The server sends the generated feedback to the user's device via push notification, allowing the user to see appropriate improvement suggestions and next learning steps. For example, a notification might say, "Your next task is to understand regression analysis."

[1159] Step 14:

[1160] Users access online forums and chat rooms to connect with other learners and experts, using dedicated communication apps on their devices.

[1161] Step 15:

[1162] The server monitors community activity data in real time using an API and recommends appropriate forums and chat rooms to users, such as a message like, "We recommend you join a forum that discusses basic statistics."

[1163] Step 16:

[1164] The server collects information about offline learning events held in the area and notifies appropriate users, allowing users to participate in local learning groups and workshops, expanding learning opportunities.

[1165] The above is the specific flow of program processing for this system.

[1166] (Application example 1)

[1167] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1168] In traditional education systems, it was difficult to efficiently provide a curriculum tailored to each learner's skills, interests, and learning style. Furthermore, there was a lack of collaboration with domestic and international experts, progress management, and feedback, which led to problems in improving learners' learning efficiency and maintaining their motivation. Furthermore, there was a lack of offline learning communities and collaboration with local educational institutions, which limited the learning experience.

[1169] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1170] In this invention, the server includes means for receiving learner information and generating a customized learning curriculum using an AI algorithm, means for routing learner questions to appropriate experts using an AI algorithm and providing answers from the experts, means for analyzing learning progress data and generating real-time feedback, and means for collecting and providing local offline event information to learners. This enables learners to have an individually optimized learning experience, strengthening collaboration with experts, improving progress management, and feedback. It also builds online and offline learning communities and promotes collaboration with local educational institutions, thereby improving the learner's overall learning experience.

[1171] A "learner" is an individual or group of people who use a learning system to achieve educational objectives.

[1172] "Interest" refers to the interest or curiosity a learner has in a particular educational field or topic.

[1173] "Learning styles" are the methods or techniques that learners use to learn most effectively.

[1174] A "curriculum" is a set of learning contents and activities, from prerequisites to outcomes, in an educational process.

[1175] An "AI algorithm" is a computational procedure that uses artificial intelligence to automatically perform a specific task.

[1176] A "database" is an information system that efficiently manages large amounts of data and enables searching and updating.

[1177] An "expert" is someone who has advanced knowledge and experience in a particular field and provides this knowledge to learners.

[1178] "Progress data" is information that indicates the progress and achievements of a learner through a learning activity.

[1179] "Feedback" is information that includes an evaluation of a learner's learning activities and suggestions for improvement.

[1180] An "offline event" is a learning-related activity or event that takes place in a physical location without the internet.

[1181] "Local educational institutions" are schools, libraries, municipalities, and other organizations that provide education in the local community.

[1182] A "learning community" is a group or network of learners and professionals who interact with each other and share knowledge and information.

[1183] "Real-time feedback" is information that responds immediately to learners' learning activities and provides evaluations and areas for improvement on the spot.

[1184] "Question routing" is the process of sending questions received from learners to experts to obtain appropriate answers.

[1185] The present invention provides a system for providing learners with a customized educational experience, strengthening collaboration with experts, and improving the quality of learning through collaboration with the local community. This system is configured and provided as follows.

[1186] First, when a user logs in for the first time, they enter their learning goals, interests, and skill level. This provides the system with information that matches the user's learning style. The information entered by the user is sent from the user's device to the server. The server uses an AI algorithm based on the received information to generate a customized learning curriculum. This curriculum includes content that matches the user's skills and interests. The generated curriculum is saved in a database and sent to the user's device.

[1187] Next, collaboration with an expert is attempted. The expert accesses the system and inputs information about themselves, their field of expertise, career history, and qualifications. This allows the system to register each expert's knowledge and experience in a database. The user inputs any questions or doubts that arise during the study and sends them from their device to the server. The server analyzes the content of the question and routes it to the appropriate expert. The server then receives the expert's answer, sends it to the user's device, and displays it.

[1188] Furthermore, learning progress is managed and feedback is provided. As users proceed with their learning activities, they record progress data along the way. The device sends the progress status to the server in real time. The server analyzes the learner's performance based on the received progress data and generates feedback. This feedback includes suggestions for improvement and next learning steps and is sent to the user's device.

[1189] It also creates online and offline learning communities. Users can interact with other learners and experts through online forums and chat rooms. The server monitors community activity data and recommends appropriate forums and chat rooms to users. Furthermore, users can receive notifications from the server about offline study groups and activities being held in their area, allowing them to decide whether or not to participate. The server cooperates with local educational institutions, libraries, and local governments to collect offline event information and provide it to users.

[1190] As a specific example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experience: When the user logs in for the first time, they enter their interest in data science, and a customized data science curriculum is generated and sent to their device. If they ask a question about a specific data analysis method during the learning process, the question is routed to an appropriate data science expert. The expert's answer is provided to the user via the server. As the learning progresses, the device sends the user's progress data to the server, and the server generates feedback based on the analysis results. Furthermore, the server notifies the user of offline data science study groups and events held in the area, offering opportunities to participate.

[1191] Example prompts using a generative AI model:

[1192] "Develop a smartphone application that provides a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Use Python's requests library to send user information to a server and retrieve a customized curriculum generated by an AI algorithm."

[1193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1194] Step 1:

[1195] When a user logs in for the first time, they enter their learning goals, interests, and skill level. The information they enter (e.g., "I'm interested in data science" or "Beginner") is collected via their device and sent to the server.

[1196] Input: Learner's goals, interests, skill level, etc.

[1197] Output: Learner information sent to the server

[1198] Step 2:

[1199] The server uses an AI algorithm to generate a customized learning curriculum based on the received user information. Specifically, the AI ​​algorithm analyzes the learner's interests and skill level, and selects and configures learning modules based on that. The generated curriculum is stored in a database.

[1200] Input: Student information sent to the server

[1201] Output: Customized curriculum stored in a database

[1202] Step 3:

[1203] The server sends the generated curriculum to the user's terminal, which displays the received curriculum and allows the user to start learning.

[1204] Input: Customized curriculum stored in the database

[1205] Output: The curriculum sent to the user's device

[1206] Step 4:

[1207] If a user has a question while studying, the user inputs the question into the terminal, which then sends the input question to the server.

[1208] Input: The question the user types into the terminal

[1209] Output: The question sent to the server

[1210] Step 5:

[1211] The server analyzes the received question and routes it to the expert appropriate for the question. Specifically, the server analyzes the question content using natural language processing and selects the most appropriate expert. The routed question is then sent to the expert.

[1212] Input: The question sent to the server

[1213] Output: Questions routed to experts

[1214] Step 6:

[1215] The expert creates an answer to the received question and sends the answer to the server, which then receives the answer from the expert and sends it to the user's device.

[1216] Input: Expert-generated answers

[1217] Output: The answer sent to the user's terminal

[1218] Step 7:

[1219] The system collects learning progress data while the user is learning. The device sends the learning progress data (e.g., completed modules, unread tutorials, etc.) to the server in real time.

[1220] Input: User's learning progress data

[1221] Output: Learning progress data sent to the server

[1222] Step 8:

[1223] The server analyzes the learning progress data and generates real-time feedback to assess the progress and provide appropriate advice and next steps for learning. The generated feedback is then sent to the user's device.

[1224] Input: Learning progress data sent to the server

[1225] Output: Real-time feedback sent to the user device

[1226] Step 9:

[1227] When users access online forums or chat rooms, the server monitors their activity data and recommends appropriate forums or chat rooms to them. Additionally, the server collects offline event information from local educational institutions, libraries, and local governments and notifies appropriate users.

[1228] Input: Forum and chat room activity data, local offline event information

[1229] Output: User recommended forums, chat rooms and offline event information

[1230] Example prompts using a generative AI model:

[1231] "Develop a smartphone application that provides a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Use Python's requests library to send user information to a server and retrieve a customized curriculum generated by an AI algorithm."

[1232] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1233] The present invention is a system that provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the community, and combines it with an emotion engine that recognizes the user's emotions, allowing it to tailor curriculum, feedback, and communication recommendations based on the learner's emotional state.

[1234] Entering learner information and generating a curriculum

[1235] When users first log in, they enter their email address and password, along with their learning goals, interests, and skill level, and the system uses this information to create a learner profile.

[1236] The terminal transmits the input information to the server.

[1237] The server uses an AI algorithm to generate a customized learning curriculum based on the received information, and also analyzes the user's emotional state using an emotion engine, which then incorporates that information into the curriculum.

[1238] The server stores the generated curriculum in a database and transmits it to the user's terminal.

[1239] Collaboration with experts

[1240] Experts access the system and enter their field of expertise, background, and qualifications, which allows the system to register each expert's knowledge and experience in a database.

[1241] Users can enter any questions or concerns they may have while studying and submit their questions.

[1242] The terminal sends a question from the user to the server.

[1243] The server analyzes the question and routes it to the appropriate expert, taking into account the user's emotional state and recommending an answer in an appropriate tone.

[1244] The expert enters the answer to the question and sends it to the server.

[1245] The server sends the expert's answer to the user's terminal and displays it.

[1246] Tracking learning progress and providing feedback

[1247] As users progress through the learning process, their progress data is recorded, while the emotion engine simultaneously analyzes their emotions from their facial expressions and tone of voice.

[1248] The device transmits progress and emotion data to the server in real time.

[1249] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments, such as lowering the difficulty level if the user is feeling stressed.

[1250] The server sends the generated feedback and adjustments to the user's terminal and displays them to the user.

[1251] Building a learning community

[1252] Users access online forums and chat rooms to interact with other learners and experts, while the emotion engine monitors their emotional state.

[1253] The server monitors community activity data and recommends appropriate forums and chat rooms based on the user's emotional state, as well as providing notifications to encourage active participation within the community.

[1254] Users receive notifications of offline events provided by the system and decide whether to participate. Data from the emotion engine is also taken into consideration at this time, and events suitable for the user are recommended.

[1255] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[1256] Specific examples

[1257] For example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experiences:

[1258] When a user first logs in, they tell the system that they are interested in data science.

[1259] The server generates a customized data science curriculum based on the information received and sends it to the user's device.

[1260] As the learning process progresses, users ask questions about specific data analysis techniques, which are then routed by the server to the appropriate data science experts. An emotion engine detects when the user is frustrated and encourages the experts to respond in a gentler tone.

[1261] Experts answer questions, and the answers are provided to users via a server. As users learn, their progress data and emotional state are recorded and sent to the server in real time. The server analyzes the data and generates appropriate feedback for users. It also recommends participation in appropriate forums and offline events based on the user's emotional state.

[1262] The system provides learners with a highly customized educational experience and addresses their psychological aspects by utilizing an emotional engine, thereby improving the quality of education and enabling learners to achieve optimal learning through collaboration with the local community.

[1263] The processing flow will be explained below.

[1264] Step 1:

[1265] A user accesses the system and enters their email address and password on the initial login screen.

[1266] Step 2:

[1267] The terminal sends the input information to the server and requests user authentication.

[1268] Step 3:

[1269] The server compares the received authentication information with a database, generates an authentication token, and sends it to the terminal.

[1270] Step 4:

[1271] After logging in, the user is directed to a screen where they can enter their learning goals, interests, and skill level. At this point, the camera and microphone are activated, and the emotion engine analyzes the user's facial expressions and voice.

[1272] Step 5:

[1273] The terminal transmits the input learner information and emotion data to the server.

[1274] Step 6:

[1275] The server uses an AI algorithm to generate a customized learning curriculum based on the learner information and emotional data received.

[1276] Step 7:

[1277] The server stores the generated curriculum in a database and sends it to the user's device.

[1278] Step 8:

[1279] Users begin learning based on the curriculum, and if they encounter any problems or questions during the learning process, they can enter them.

[1280] Step 9:

[1281] The device sends the user's question to the server, and the emotion engine also analyzes the user's emotional state at that time and sends the result to the server.

[1282] Step 10:

[1283] The server analyzes the question and emotional data and routes it to the appropriate expert, recommending that the expert respond in an appropriate tone based on the emotional state.

[1284] Step 11:

[1285] The expert enters the answer to the question and sends it to the server.

[1286] Step 12:

[1287] The server receives the answers from the experts and sends them to the user's device.

[1288] Step 13:

[1289] As users learn, their progress is recorded, and an emotion engine analyzes their emotional state.

[1290] Step 14:

[1291] The device transmits progress and emotion data to the server in real time.

[1292] Step 15:

[1293] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments.

[1294] Step 16:

[1295] The server sends the generated feedback and adjustments to the user's device and displays them to the user, adjusting the content and tone of the feedback according to the user's emotional state.

[1296] Step 17:

[1297] As users access online forums and chat rooms and interact with other learners and experts, the emotion engine monitors their emotional state and transmits that data to the server if necessary.

[1298] Step 18:

[1299] The server monitors community activity data and user sentiment data and recommends appropriate forums and chat rooms to users.

[1300] Step 19:

[1301] The server collects information on offline study sessions and activities taking place in the area and sends push notifications to appropriate users based on emotional data.

[1302] Step 20:

[1303] Users receive notifications about offline events and decide whether or not they want to participate. The emotion engine analyzes the user's reactions and provides feedback tailored to their willingness to participate.

[1304] In this way, this system, which combines an emotion engine, also responds to the psychological aspects of learners and provides an optimal learning environment.

[1305] Example 2

[1306] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1307] Traditional educational systems have difficulty customizing to meet individual learners' skills, interests, and learning styles, and generic curricula have been unable to meet individual needs. Furthermore, limited collaboration with experts makes it difficult to respond quickly and appropriately to learners' doubts and questions. Furthermore, the inability to provide feedback or adjust the curriculum to take into account the learner's emotional state means that improvements in learning quality and motivation cannot be expected.

[1308] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1309] In this invention, the server includes means for analyzing the emotional state of the learner and adjusting the curriculum and feedback content, means for analyzing the learner's questions and providing answers in an appropriate tone, and means for collecting information on study sessions and activities taking place in the local area and recommending appropriate offline events based on the learner's emotional state. This makes it possible to provide an educational experience optimized for each learner and to improve the quality of learning and motivation by strengthening collaboration with experts and the local community.

[1310] A "learner" is an individual who engages in a learning activity.

[1311] A "skill" is an ability or technique for effectively performing a particular task or activity.

[1312] "Interests" refer to subjects or topics that interest learners.

[1313] A "learning style" refers to the method or approach that a learner takes in learning.

[1314] A "curriculum" is an educational content or learning program designed to achieve specific learning goals.

[1315] An "expert" is a person who has advanced knowledge or skills in a particular field.

[1316] A "network" is a communication system built to share information and resources.

[1317] "Learning progress" refers to an indicator or state that indicates how far a learner has progressed toward a learning goal.

[1318] "Feedback" refers to information provided about the learning process or results for evaluation and improvement.

[1319] "Online" refers to operations or activities conducted over the Internet.

[1320] "Offline" refers to operations or activities that are not performed via the Internet.

[1321] A "learning community" is a group of learners and experts who exchange information and opinions and support each other's learning.

[1322] An "emotional state" is the emotion or mental state that a learner is feeling at a particular time.

[1323] "Analysis" is the act of examining data or information in detail and clarifying its structure and relationships.

[1324] "Tone" refers to the way one speaks or expresses something, especially its intensity and emotional level.

[1325] "Routing" refers to the procedures and methods used to direct data or information to its proper destination.

[1326] An "offline event" is a learning activity or social gathering that takes place in a physical location.

[1327] The system is designed to provide a customized educational experience that takes into account the learner's skills, interests, and learning style. Key elements include an AI algorithm, an emotion engine, and online and offline learning community functions. The specific implementation of each element is explained below.

[1328] Entering learner information and generating a curriculum

[1329] When a user logs in for the first time, they enter their email address and password, as well as their learning goals, interests, and skill level. This information is sent from the device to the server via an HTTP POST request. The server receives this information and stores it in a database. It then uses an AI algorithm to generate a customized learning curriculum. This AI algorithm selects the most appropriate learning content based on the learner's profile information.

[1330] Furthermore, the server uses an emotion engine to analyze the learner's emotional state. This emotional state is obtained using facial expression analysis technology, tone of voice analysis technology, etc. This makes it possible to reflect emotional information in the curriculum. The generated curriculum is saved in the database again and sent to the terminal. The terminal displays the received curriculum to the user.

[1331] Collaboration with experts

[1332] Experts access the system and enter their field of expertise, background, and qualifications. This information is registered in a database. When a user enters a question or concern during learning, the device sends the question to the server. The server analyzes the question and routes it to the appropriate expert. In doing so, it uses an emotion engine to analyze the user's emotional state and provides the expert with instructions recommending an appropriate tone of voice to respond. The expert enters the answer and sends it to the server, where it is delivered and displayed to the user.

[1333] Tracking learning progress and providing feedback

[1334] As the user progresses through their learning activities, their progress data is recorded. At the same time, an emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and sends this information in real time via the device to the server. The server analyzes the received data and evaluates the learner's performance. Based on this, appropriate feedback and curriculum adjustments are generated, sent to the device, and displayed to the user. For example, if the learner is feeling stressed, the system will make adjustments such as lowering the difficulty of the learning content.

[1335] Building a learning community

[1336] Users can access online forums and chat rooms to interact with other learners and experts. The emotion engine monitors the user's emotional state and recommends appropriate forums and chat rooms. The server also monitors community activity data and sends notifications to encourage active participation.

[1337] The server also collects information about offline study groups and activities taking place in the local area and sends push notifications to appropriate users, providing opportunities for learners to meet in person both online and offline and building a learning community.

[1338] Specific examples

[1339] For example, consider the case where a learner who wants to learn data science enters their interest in data science when logging in for the first time. The server generates a customized data science curriculum based on the received information and sends it to the device. If the user asks a question about a specific data analysis method as they progress through their studies, the question is routed to an appropriate data science expert. At that time, an emotion engine detects the user's frustration and recommends that the expert respond in a gentler tone. The expert's answer is then provided to the user via the server.

[1340] An example of a prompt sentence could be, "Please enter the information needed to customize your data science curriculum. For example, please enter your area of ​​interest, current skill level, and learning goals. Also, please enter your past learning experience and any specific questions you may have." By using this prompt sentence as a concrete example, the system can quickly generate a curriculum optimized for the user's needs.

[1341] Overall, the system aims to improve learning quality and motivation by providing an educational experience tailored to each learner's individual needs and by strengthening collaboration with experts and the local community.

[1342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1343] Step 1:

[1344] A user enters an email address and password on the login screen. The entered information is sent from the device to the server. Specifically, the data collected in the input form is sent to the server as an HTTP POST request. The input data includes the email address and hashed password.

[1345] Step 2:

[1346] The server compares the received login information with the database and performs authentication. If authentication is successful, the server generates the user's session information and sends the session ID to the terminal. The authentication process checks whether the email address and hashed password match the information in the database.

[1347] Step 3:

[1348] The user enters profile information such as learning objectives, interests, and skill level. The entered information is sent to the server via the terminal. Specifically, the data collected in the form is sent to the server as an HTTP POST request. The input data includes learning objectives, interests, and skill level.

[1349] Step 4:

[1350] The server stores the received profile information in a database and analyzes it using an AI algorithm. As a result of the analysis, a learning curriculum optimal for the learner is generated. Specifically, the received data is input into an AI model to generate a customized curriculum. As an output, the learning curriculum is stored in a database.

[1351] Step 5:

[1352] The server uses an emotion engine to analyze the user's emotional state. Specifically, it receives the user's facial expressions and voice data as input and analyzes them using an emotion analysis model. The output is data indicating the user's emotional state.

[1353] Step 6:

[1354] The server reflects the emotional state in the generated curriculum to complete the final curriculum. Specifically, the content and difficulty of the curriculum are adjusted using the emotional state data. As an output, the curriculum reflecting the emotions is saved again in the database.

[1355] Step 7:

[1356] The server sends the final curriculum to the terminal. Specifically, it sends the generated curriculum to the terminal as an HTTP response. The terminal displays the received curriculum to the user.

[1357] Step 8:

[1358] Experts access the system and enter their field of expertise, background, and qualifications, which are then sent from the terminal to the server and stored in a database.

[1359] Step 9:

[1360] The user inputs questions that arise during learning and sends them from the device to the server. The input data includes the question content. Specifically, the question data collected in the form is sent to the server as an HTTP POST request.

[1361] Step 10:

[1362] The server analyzes the received question and routes it to the appropriate expert. Specifically, it analyzes the question content using natural language processing (NLP) technology and searches a database for the most suitable expert. The output is information about the expert to whom the question will be routed.

[1363] Step 11:

[1364] The server notifies the expert of the question and emotional information. Specifically, the server generates notification data containing the question content and the user's emotional state information and sends it to the expert's terminal.

[1365] Step 12:

[1366] The expert enters the answer to the question and sends it to the server. Specifically, the answer is sent to the server as an HTTP POST request.

[1367] Step 13:

[1368] The server sends the received response to the user's device and displays it. Specifically, it sends the response data to the device as an HTTP response. The device displays the received response to the user.

[1369] Step 14:

[1370] As the user progresses through the learning activity, progress data is recorded. At the same time, the emotion engine analyzes emotional data from facial expressions and tone of voice. This data is sent to the server via the device.

[1371] Step 15:

[1372] The server analyzes the received progress and emotion data and generates feedback. Specifically, the progress and emotion data are input into a machine learning model to generate performance evaluation and optimal feedback. The output is feedback data.

[1373] Step 16:

[1374] The server sends the generated feedback to the terminal and displays it to the user. Specifically, the server sends the feedback data to the terminal as an HTTP response. The terminal then displays the received feedback to the user.

[1375] Step 17:

[1376] A user accesses an online forum or chat room and communicates with the user. The server monitors the user's emotional state using an emotion engine and recommends appropriate forums or chat rooms.

[1377] Step 18:

[1378] The server collects information about offline learning activities taking place in the area and notifies appropriate users. Specifically, it analyzes the collected information data and recommends offline events based on the user's emotional state. The device displays the received event notifications to the user.

[1379] Through this process, the system is able to provide an educational experience that is optimized to the individual needs of each learner.

[1380] (Application example 2)

[1381] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1382] Conventional learning systems lack the ability to customize learning to fit the learner's skills, interests, and emotional state, resulting in poor learning efficiency. Furthermore, in brick-and-mortar stores, they are unable to provide customer service that reflects their emotions, which can lead to lower customer satisfaction. Furthermore, there are challenges in building online and offline learning communities and effectively utilizing expert knowledge.

[1383] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for generating a customized curriculum based on the learner's skills, interests, and learning style; means for bringing together domestic and international experts and building a network to provide their knowledge; means for tracking and managing learning progress and providing feedback; means for providing opportunities for learners to meet in person online and offline and building a learning community; means for collaborating with local schools, libraries, and local governments and utilizing it as an offline education platform; means for analyzing the learner's emotional state using an emotion engine and adjusting the curriculum, feedback, and communication recommendations; and means for realizing a brick-and-mortar store application that analyzes the emotional state of customers in real time and provides customized customer service methods and suggestions. This enables advanced customization according to the individual needs of learners, improving learning efficiency and customer satisfaction.

[1384] "Learner" refers to an individual who uses a learning system to acquire knowledge or skills.

[1385] "Skills" refer to the abilities and techniques that a learner has to accomplish a specific task or work.

[1386] "Interest" refers to the interest or curiosity a learner has in a particular field or topic.

[1387] "Learning style" refers to the methods and procedures by which a learner learns most effectively.

[1388] "Curriculum" refers to an educational plan that defines the content and progression that learners should learn.

[1389] "Domestic and international experts" refers to individuals or institutions with a high level of knowledge and experience in a particular field.

[1390] "Network" refers to a communication network that allows multiple experts and learners to share information and collaborate.

[1391] "Progress" refers to the progress that a learner makes in demonstrating how well they have achieved their learning tasks.

[1392] "Feedback" refers to evaluation and advice provided to learners to improve their learning activities.

[1393] A "community" refers to a group of learners and professionals who share common learning goals and interests.

[1394] "Online" refers to forms of learning and communication delivered via the Internet.

[1395] "Offline" refers to activities and communications that take place in a physical location, not via the internet.

[1396] An "emotion engine" refers to technology that analyzes a user's facial expressions, tone of voice, etc. to determine their emotional state.

[1397] "Customer" means an individual who uses or purchases a particular service or product.

[1398] "Brick and mortar store" refers to a sales or service point located in a physical location.

[1399] "Application" refers to a software program that provides a specific function or service.

[1400] An "AI algorithm" refers to a calculation method for analyzing data and making decisions using artificial intelligence.

[1401] A "database" refers to a digital system that systematically organizes and stores information.

[1402] This system provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Furthermore, by incorporating an emotion engine, the system adjusts curriculum, feedback, and communication recommendations based on the learner's emotional state. This system can also be applied to brick-and-mortar retail applications, where customers' emotional states are analyzed in real time to provide customized customer service methods and suggestions.

[1403] Entering learner information and generating a curriculum

[1404] When logging in for the first time, users enter their email address and password, as well as their learning goals, interests, and skill level. The device then sends the entered information to the server. The server uses an AI algorithm based on the received information to generate a customized learning curriculum, and then analyzes the user's emotional state using an emotion engine and reflects that information in the curriculum. The server then saves the generated curriculum in a database and sends it to the user's device.

[1405] Collaboration with experts

[1406] Experts access the system and register their knowledge and experience in the database by entering their field of expertise, career history, and qualifications. Users enter questions or doubts that arise during their studies and send them from their terminal to the server. The server analyzes the content of the question and routes it to the appropriate expert. The expert enters an answer to the question and sends it to the server. The server sends the answer from the expert to the user's terminal and displays it.

[1407] Tracking learning progress and providing feedback

[1408] As the user progresses through the learning activity, progress data is recorded. At the same time, the emotion engine analyzes the user's emotions from their facial expressions and tone of voice. The device sends the progress and emotion data to the server in real time. The server analyzes the learner's performance based on the received progress and emotion data and generates feedback and adjustments. For example, if the user is feeling stressed, it may lower the difficulty level. The server sends the generated feedback to the user's device and displays it to the user.

[1409] Application in physical stores

[1410] This system can also be applied to improving customer service experiences in brick-and-mortar stores. The device is installed on a smartphone or head-mounted display and uses a camera to capture the customer's facial expressions. The received video data is sent to a server in real time, where an emotion engine analyzes the customer's emotional state. Based on the analysis results, the device displays customer service methods and product suggestions that are appropriate for the customer's emotions.

[1411] For example, when a customer visits a cosmetics counter in a physical store, a staff member's smartphone scans the customer's facial expression and determines that the customer looks a little depressed. The staff member is then shown advice such as, "Today, we'd like to recommend a lip color that will cheer you up a little."

[1412] Prompt Sentence Examples

[1413] The following prompt sentence is used as input to the generative AI model:

[1414] Write a program for a system that recognizes customer emotions and customizes in-store interactions. The hardware used is a smartphone camera, and the software is Python. Include recommendations based on the customer's emotional state.

[1415] This will enable us to provide an educational environment for users and improve the customer service experience in physical stores.

[1416] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1417] Step 1:

[1418] When a user logs in for the first time, they enter their email address and password, as well as their learning goals, interests, and skill level. This generates the user's profile information. The entered information is sent to the server by the device. The entered data includes the email address, password, learning goals, interests, and skill level. The device then uploads this data to the server.

[1419] Step 2:

[1420] The server uses an AI algorithm to generate a customized learning curriculum based on the received user information. The learning content is customized based on the user's skills, interests, and learning style. An emotion engine also analyzes the user's emotional state, and the results are reflected in the curriculum. The input here is user information, and the output is a customized learning curriculum.

[1421] Step 3:

[1422] The server stores the generated curriculum in a database and then transmits it to the user's device. The database stored on the server holds a customized educational plan for each learner. The input is curriculum data, and the output is data transmission to the user's device.

[1423] Step 4:

[1424] If a user has any doubts or questions during their studies, they can input them through their device and send them to the server. The input data includes the user's question, and the device uploads it to the server.

[1425] Step 5:

[1426] The server analyzes the received question and routes it to the appropriate expert from a list of experts in the database. The server takes into account the question as well as the user's emotional state, which is analyzed by the emotion engine. The input is the question from the user, and the output is the expert to whom the question is routed.

[1427] Step 6:

[1428] The expert inputs an answer to the question received from the server and sends it to the server. In this process, the answer is generated using the expert's knowledge and experience. The input is the expert's answer, and the output is the response sent to the server.

[1429] Step 7:

[1430] The server sends the expert's answer to the user's device and displays it to the user. In this step, the user can receive an explanation based on expert knowledge. The input is the expert's answer data, and the output is the answer displayed on the user's device.

[1431] Step 8:

[1432] As the user progresses through the learning activity, the progress and emotional data are sent to the server in real time from the device, thereby recording the learning progress and emotional state. The input is progress data and emotional data, and the output is data uploaded to the server.

[1433] Step 9:

[1434] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments. For example, if the user is feeling stressed, the server may lower the difficulty of the learning content. The input is progress and emotion data, and the output is customized feedback.

[1435] Step 10:

[1436] The server sends the generated feedback to the user's terminal and displays it to the user, allowing the user to check areas for improvement in their learning and their next steps. The input is feedback data, and the output is data display on the user's terminal.

[1437] Step 11:

[1438] When a user visits a physical store, the device (smartphone or head-mounted display) uses a camera to capture the customer's facial expressions. The video data is sent to the server in real time. The input is the captured video data, and the output is the video data sent to the server.

[1439] Step 12:

[1440] The server uses an emotion engine to analyze the customer's emotional state and generate customized customer service methods and product suggestions based on the results. The input is video data, and the output is the analysis results and customized suggestions.

[1441] Step 13:

[1442] The server then sends the generated customer service methods and suggestions to the terminal and displays them to the store staff. This allows the staff to provide customer service that is tailored to the customer's emotions. The input is the customized suggestions, and the output is the data displayed on the terminal.

[1443] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1444] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1445] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1446] [Fourth embodiment]

[1447] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1448] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1449] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1450] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1451] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1452] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1453] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1454] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1455] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1456] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1457] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1458] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1459] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1460] This invention is a system that provides learners with a customized educational experience, strengthens connections with experts, and improves the quality of learning through collaboration with the community. The system generates customized curricula based on learners' skills, interests, and learning styles, builds expert networks, tracks and manages learning progress, provides feedback, and creates online and offline learning communities.

[1461] Entering learner information and generating a curriculum

[1462] When users first log in, they enter their learning goals, interests, and skill level, which provides the system with information tailored to their learning style.

[1463] The terminal transmits the input information to the server.

[1464] The server uses AI algorithms to generate a customized learning curriculum based on the received information, which includes content that addresses the user's skills and interests.

[1465] The server stores the generated curriculum in a database and transmits it to the user's terminal.

[1466] Collaboration with experts

[1467] Experts access the system and enter information about themselves, their field of expertise, background, and qualifications, which the system then registers in a database each expert's knowledge and experience.

[1468] Users can enter any questions or concerns they may have while studying and submit their questions.

[1469] The terminal sends a question from the user to the server.

[1470] The server analyzes the question, routes it to the appropriate expert, and then receives the answer from the expert.

[1471] The server sends the received response to the user's terminal and displays it.

[1472] Tracking learning progress and providing feedback

[1473] Users progress through learning activities and progress data is recorded along the way.

[1474] The device sends real-time progress information to the server.

[1475] The server analyzes the learner's performance based on the received progress data and generates feedback.

[1476] The server sends the generated feedback to the user's device and suggests appropriate improvements and next learning steps.

[1477] Building a learning community

[1478] Users have access to online forums and chat rooms to connect with other learners and experts.

[1479] The server monitors community activity data and recommends appropriate forums and chat rooms to users.

[1480] Users receive notifications of offline events provided by the system and decide whether to participate.

[1481] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[1482] Specific examples

[1483] For example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experiences:

[1484] When users first log in, they tell the system that they are interested in data science.

[1485] The server generates a customized data science curriculum based on the received information and sends it to the user's device.

[1486] As the learning process progresses, users ask questions about specific data analysis techniques, which are then routed by the server to the appropriate data science experts.

[1487] The experts answer the questions and the answers are provided to the users via the server.

[1488] As learning progresses, the device sends the user's progress data to the server, which generates feedback based on the analysis results.

[1489] Additionally, the server will notify users of offline data science study groups and events being held in the area, providing them with opportunities to participate.

[1490] This system will provide each learner with the best possible learning experience and eliminate educational disparities through collaboration with experts and local communities.

[1491] The processing flow will be explained below.

[1492] Step 1:

[1493] A user accesses the system and enters their email address and password on the initial login screen.

[1494] Step 2:

[1495] The terminal sends the input information to the server and requests user authentication.

[1496] Step 3:

[1497] The server compares the received authentication information with a database, generates an authentication token, and sends it to the terminal.

[1498] Step 4:

[1499] After logging in, users are taken to a screen where they can enter their learning goals, interests, and skill level.

[1500] Step 5:

[1501] The terminal transmits the inputted learner information to the server.

[1502] Step 6:

[1503] Based on the learner information received by the server, a customized learning curriculum is generated using an AI algorithm.

[1504] Step 7:

[1505] The server stores the generated curriculum in a database and transmits it to the terminal.

[1506] Step 8:

[1507] Users start learning based on the curriculum, and if they encounter any problems or questions during the learning process, they can enter their questions.

[1508] Step 9:

[1509] The device sends the user's question to the server.

[1510] Step 10:

[1511] The server analyzes the question and routes it to the appropriate expert.

[1512] Step 11:

[1513] The expert enters the answer to the question and sends it to the server.

[1514] Step 12:

[1515] The server receives the answers from the experts and sends them to the user's device.

[1516] Step 13:

[1517] Progress data is recorded as users learn.

[1518] Step 14:

[1519] The device sends progress information to the server in real time.

[1520] Step 15:

[1521] The server analyzes the learner's performance based on the received progress data and generates feedback.

[1522] Step 16:

[1523] The server sends the generated feedback to the user's terminal and displays it to the user.

[1524] Step 17:

[1525] Users have access to online forums and chat rooms where they can interact with other learners and experts.

[1526] Step 18:

[1527] The server monitors community activity data and recommends appropriate forums and chat rooms to users.

[1528] Step 19:

[1529] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[1530] Step 20:

[1531] A user receives notification of an offline event and decides whether to attend.

[1532] Example 1

[1533] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1534] Traditional education systems often provide learners with a uniform curriculum, which does not adequately address individual skills, interests, or learning styles. Furthermore, they face challenges such as a lack of prompt and appropriate feedback on questions that arise during learning, and a lack of collaboration with experts and learning communities. Furthermore, a lack of collaboration with offline educational institutions makes it difficult to improve educational effectiveness through collaboration with local communities.

[1535] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1536] In this invention, the server includes: a means for a learner to input their learning goals, interests, and skill level when they log in for the first time; a means for transmitting the input information to the server; a means for generating a curriculum based on the received information using an artificial intelligence algorithm, storing the curriculum in a database, and transmitting the curriculum to the terminal; a means for the learner to input questions that arise during learning and for routing the questions to appropriate experts; a means for providing the learner with answers from the experts; a means for transmitting learning progress and feedback to the terminal using push notifications; a means for the learner to access online forums and chat rooms to interact with other learners and experts; and a means for collecting information about offline learning events held in the community and notifying appropriate learners of such events. This enables the provision of individually customized learning curricula, appropriate feedback in real time, and collaboration with experts. Furthermore, educational activities in collaboration with the community can provide learners with diverse learning opportunities and significantly improve the quality of education.

[1537] A "learner" is a person who receives education using the system.

[1538] "Skills" are abilities or expertise that a learner already possesses.

[1539] "Interests" refer to areas or topics that a learner is particularly interested in.

[1540] A "learning style" is a method or approach that a learner uses to learn most effectively.

[1541] A "curriculum" is a specific educational program or learning content generated by the system.

[1542] An "expert" is someone who has advanced knowledge and experience in a particular field and who provides guidance and advice to learners.

[1543] A "network" is a structure or system that brings together domestic and international experts through a system to share their knowledge.

[1544] "Learning progress" refers to a learner's progress and achievement in learning activities.

[1545] "Feedback" refers to evaluation of learners and advice for improvement.

[1546] A "learning community" is an online or offline group of learners and professionals who can interact and collaborate.

[1547] "Local educational institutions" refer to schools, libraries, local government and other educational facilities in the area where the learner lives.

[1548] An "offline educational platform" refers to educational activities and learning environments that are conducted without using the Internet.

[1549] "First login" refers to the operation when a learner accesses the system for the first time and enters personal information and learning objectives.

[1550] An "input form" is an interface or screen that a learner uses to enter information.

[1551] An "artificial intelligence algorithm" is an automated computational method used by a computer to generate a curriculum based on learner information.

[1552] "Database" refers to an information structure for systematically managing and storing generated curriculum and other data.

[1553] "Device" refers to a device such as a computer, tablet, or smartphone that a learner uses to access the system.

[1554] "Questions" are questions or things that students have questions about while studying.

[1555] "Routing" refers to the process of sending an incoming question to the appropriate expert.

[1556] "Push notifications" is a function that allows the system to send learning progress, event information, and other information to learners' devices in real time.

[1557] An "online forum" is a bulletin board or community site on the Internet where learners and experts can exchange opinions and share information.

[1558] A "chat room" is an online communication tool for exchanging messages in real time.

[1559] "Offline learning events" are study groups and workshops held locally without internet connectivity.

[1560] "Notifications" are messages or alerts that inform learners of information.

[1561] This invention is a system that provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Specific implementation methods are described below.

[1562] First, when users log in for the first time, they enter their learning goals, interests, and skill level. The input form is designed to allow users to easily select their field of interest and current skill level. For example, options such as "Data Science" and "Beginner Programming" are provided.

[1563] The device sends the entered information to the server using an HTTP request. At this time, the information is encoded in JSON format. For example, the following data may be sent:

[1564] {

[1565] "interest": "data science",

[1566] "skill_level": "Beginner"

[1567] }

[1568] The server then runs an artificial intelligence algorithm (e.g., a TensorFlow model) based on the received information to generate a customized learning curriculum. This algorithm selects the optimal learning resources based on the user's skills and interests, and automatically generates the curriculum.

[1569] The generated curriculum is stored in a MySQL database by the server and sent to the user's device. The device reads the received curriculum and displays it in a user-friendly format using front-end web technologies (e.g., HTML, CSS, JavaScript).

[1570] Next, the user enters any questions or doubts that arise as they progress through their learning. These questions are then sent to the server in JSON format. For example, the following questions might be entered:

[1571] {

[1572] "question": "How do I set up a neural network?"

[1573] }

[1574] The device sends this question to the server, which analyzes the received question using a natural language processing model (e.g., GPT-4) and routes it to the appropriate expert. The expert then answers the question, and the answer is provided to the user via the server.

[1575] As the learning progresses, the device sends the user's progress data in real time to the server, which also encodes the data in JSON format. The server then uses a Python script to analyze the learner's performance and generates feedback using a data analysis tool (e.g., Tableau).

[1576] The generated feedback is sent to the user's device by the server. The feedback includes specific suggestions for improvement and next learning steps. For example, advice such as "The next challenge you should tackle is to understand regression analysis" is displayed.

[1577] Users access online forums and chat rooms by clicking links in the system. The server uses APIs to monitor community activity data and recommend appropriate forums and chat rooms to users. Activity data is collected in real time.

[1578] Finally, the server notifies users of local offline learning events, providing them with the opportunity to participate in local learning groups and workshops.

[1579] In this way, the system provides a personalized learning experience and strengthens collaboration with experts and the local community. Example prompts include:

[1580] A user wants to learn data science. What curriculum will he be offered, how will he connect with experts, how will he receive feedback, and how will he participate in a local learning community?

[1581] This system will make it possible to significantly improve the quality of education and provide a wide variety of learning opportunities.

[1582] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1583] Step 1:

[1584] A user logs in to the system for the first time. After logging in, the user enters their learning goals, interests, and skill level. The data is collected through an on-device input form, which includes text boxes and drop-down menus. Specifically, the user enters information such as "Interest: Data Science" and "Skill Level: Beginner."

[1585] Step 2:

[1586] The terminal encodes the information entered by the user into JSON format and sends it to the server as an HTTP request. The input data will be in JSON format as follows:

[1587] {

[1588] "interest": "data science",

[1589] "skill_level": "Beginner"

[1590] }

[1591] The terminal operates by using an HTTP POST request to send input data to the server.

[1592] Step 3:

[1593] The server generates a curriculum using an artificial intelligence algorithm (e.g., a TensorFlow model) based on the received user information. Specifically, it selects relevant learning materials and activities based on the input "areas of interest" and "skill level." The output is a customized curriculum.

[1594] {

[1595] "course": "Basic Data Science Course",

[1596] "modules": [

[1597] "Data collection and preprocessing",

[1598] "Basic Statistics",

[1599] "Introduction to Machine Learning"

[1600] ]

[1601] }

[1602] Step 4:

[1603] The server saves the generated curriculum in a MySQL database and simultaneously sends the data in JSON format to the terminal, where the curriculum is displayed for the user. As a concrete example, it generates SQL statements to save to the database and saves the curriculum information.

[1604] INSERT INTO curriculum (user_id, course, modules) VALUES ('12345', 'Data Science Fundamentals Course', '["Data Collection and Preprocessing", "Basic Statistics", "Introduction to Machine Learning"]');

[1605] Step 5:

[1606] The user begins learning according to the learning curriculum. If a question arises during the learning process, the user enters the question on the device. For example, they can enter a question such as, "How do I set up a neural network?"

[1607] Step 6:

[1608] The device encodes the question entered by the user into JSON format and sends it to the server as an HTTP request. The data sent looks like this:

[1609] {

[1610] "question": "How do I set up a neural network?"

[1611] }

[1612] The device again sends the data using an HTTP POST request.

[1613] Step 7:

[1614] The server analyzes the received question using a natural language processing model (e.g., GPT-4) and routes the question to the appropriate expert. Specifically, a question about "neural networks" is routed to a machine learning expert. The output is the expert's information and analysis results.

[1615] Step 8:

[1616] The server forwards the routed question to the appropriate expert and waits for the expert's answer. The expert answers the question and the answer is sent to the server. The server receives the answer and encodes it into JSON format.

[1617] Step 9:

[1618] The server then sends the answer it receives to the user's device and displays it, for example, "Here's how to set up the neural network..."

[1619] Step 10:

[1620] As users progress through learning activities, progress data is recorded on the device, for example, when they complete an assignment or finish a particular module.

[1621] Step 11:

[1622] The device sends the progress status to the server in real time. This data is also encoded in JSON format and sent. An example of the data sent is as follows:

[1623] {

[1624] "user_id": "12345",

[1625] "module_completed": "Data Collection and Preprocessing"

[1626] }

[1627] Step 12:

[1628] The server analyzes the learner's performance using Python scripts based on the received progress data and displays the results in a data analysis tool (e.g., Tableau). Performance reports and improvement suggestions are generated as output.

[1629] Step 13:

[1630] The server sends the generated feedback to the user's device via push notification, allowing the user to see appropriate improvement suggestions and next learning steps. For example, a notification might say, "Your next task is to understand regression analysis."

[1631] Step 14:

[1632] Users access online forums and chat rooms to connect with other learners and experts, using dedicated communication apps on their devices.

[1633] Step 15:

[1634] The server monitors community activity data in real time using an API and recommends appropriate forums and chat rooms to users, such as a message like, "We recommend you join a forum that discusses basic statistics."

[1635] Step 16:

[1636] The server collects information about offline learning events held in the area and notifies appropriate users, allowing users to participate in local learning groups and workshops, expanding learning opportunities.

[1637] The above is the specific flow of program processing for this system.

[1638] (Application example 1)

[1639] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1640] In traditional education systems, it was difficult to efficiently provide a curriculum tailored to each learner's skills, interests, and learning style. Furthermore, there was a lack of collaboration with domestic and international experts, progress management, and feedback, which led to problems in improving learners' learning efficiency and maintaining their motivation. Furthermore, there was a lack of offline learning communities and collaboration with local educational institutions, which limited the learning experience.

[1641] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1642] In this invention, the server includes means for receiving learner information and generating a customized learning curriculum using an AI algorithm, means for routing learner questions to appropriate experts using an AI algorithm and providing answers from the experts, means for analyzing learning progress data and generating real-time feedback, and means for collecting and providing local offline event information to learners. This enables learners to have an individually optimized learning experience, strengthening collaboration with experts, improving progress management, and feedback. It also builds online and offline learning communities and promotes collaboration with local educational institutions, thereby improving the learner's overall learning experience.

[1643] A "learner" is an individual or group of people who use a learning system to achieve educational objectives.

[1644] "Interest" refers to the interest or curiosity a learner has in a particular educational field or topic.

[1645] "Learning styles" are the methods or techniques that learners use to learn most effectively.

[1646] A "curriculum" is a set of learning contents and activities, from prerequisites to outcomes, in an educational process.

[1647] An "AI algorithm" is a computational procedure that uses artificial intelligence to automatically perform a specific task.

[1648] A "database" is an information system that efficiently manages large amounts of data and enables searching and updating.

[1649] An "expert" is someone who has advanced knowledge and experience in a particular field and provides this knowledge to learners.

[1650] "Progress data" is information that indicates the progress and achievements of a learner through a learning activity.

[1651] "Feedback" is information that includes an evaluation of a learner's learning activities and suggestions for improvement.

[1652] An "offline event" is a learning-related activity or event that takes place in a physical location without the internet.

[1653] "Local educational institutions" are schools, libraries, municipalities, and other organizations that provide education in the local community.

[1654] A "learning community" is a group or network of learners and professionals who interact with each other and share knowledge and information.

[1655] "Real-time feedback" is information that responds immediately to learners' learning activities and provides evaluations and areas for improvement on the spot.

[1656] "Question routing" is the process of sending questions received from learners to experts to obtain appropriate answers.

[1657] The present invention provides a system for providing learners with a customized educational experience, strengthening collaboration with experts, and improving the quality of learning through collaboration with the local community. This system is configured and provided as follows.

[1658] First, when a user logs in for the first time, they enter their learning goals, interests, and skill level. This provides the system with information that matches the user's learning style. The information entered by the user is sent from the user's device to the server. The server uses an AI algorithm based on the received information to generate a customized learning curriculum. This curriculum includes content that matches the user's skills and interests. The generated curriculum is saved in a database and sent to the user's device.

[1659] Next, collaboration with an expert is attempted. The expert accesses the system and inputs information about themselves, their field of expertise, career history, and qualifications. This allows the system to register each expert's knowledge and experience in a database. The user inputs any questions or doubts that arise during the study and sends them from their device to the server. The server analyzes the content of the question and routes it to the appropriate expert. The server then receives the expert's answer, sends it to the user's device, and displays it.

[1660] Furthermore, learning progress is managed and feedback is provided. As users proceed with their learning activities, they record progress data along the way. The device sends the progress status to the server in real time. The server analyzes the learner's performance based on the received progress data and generates feedback. This feedback includes suggestions for improvement and next learning steps and is sent to the user's device.

[1661] It also creates online and offline learning communities. Users can interact with other learners and experts through online forums and chat rooms. The server monitors community activity data and recommends appropriate forums and chat rooms to users. Furthermore, users can receive notifications from the server about offline study groups and activities being held in their area, allowing them to decide whether or not to participate. The server cooperates with local educational institutions, libraries, and local governments to collect offline event information and provide it to users.

[1662] As a specific example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experience: When the user logs in for the first time, they enter their interest in data science, and a customized data science curriculum is generated and sent to their device. If they ask a question about a specific data analysis method during the learning process, the question is routed to an appropriate data science expert. The expert's answer is provided to the user via the server. As the learning progresses, the device sends the user's progress data to the server, and the server generates feedback based on the analysis results. Furthermore, the server notifies the user of offline data science study groups and events held in the area, offering opportunities to participate.

[1663] Example prompts using a generative AI model:

[1664] "Develop a smartphone application that provides a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Use Python's requests library to send user information to a server and retrieve a customized curriculum generated by an AI algorithm."

[1665] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1666] Step 1:

[1667] When a user logs in for the first time, they enter their learning goals, interests, and skill level. The information they enter (e.g., "I'm interested in data science" or "Beginner") is collected via their device and sent to the server.

[1668] Input: Learner's goals, interests, skill level, etc.

[1669] Output: Learner information sent to the server

[1670] Step 2:

[1671] The server uses an AI algorithm to generate a customized learning curriculum based on the received user information. Specifically, the AI ​​algorithm analyzes the learner's interests and skill level, and selects and configures learning modules based on that. The generated curriculum is stored in a database.

[1672] Input: Student information sent to the server

[1673] Output: Customized curriculum stored in a database

[1674] Step 3:

[1675] The server sends the generated curriculum to the user's terminal, which displays the received curriculum and allows the user to start learning.

[1676] Input: Customized curriculum stored in the database

[1677] Output: The curriculum sent to the user's device

[1678] Step 4:

[1679] If a user has a question while studying, the user inputs the question into the terminal, which then sends the input question to the server.

[1680] Input: The question the user types into the terminal

[1681] Output: The question sent to the server

[1682] Step 5:

[1683] The server analyzes the received question and routes it to the expert appropriate for the question. Specifically, the server analyzes the question content using natural language processing and selects the most appropriate expert. The routed question is then sent to the expert.

[1684] Input: The question sent to the server

[1685] Output: Questions routed to experts

[1686] Step 6:

[1687] The expert creates an answer to the received question and sends the answer to the server, which then receives the answer from the expert and sends it to the user's device.

[1688] Input: Expert-generated answers

[1689] Output: The answer sent to the user's terminal

[1690] Step 7:

[1691] The system collects learning progress data while the user is learning. The device sends the learning progress data (e.g., completed modules, unread tutorials, etc.) to the server in real time.

[1692] Input: User's learning progress data

[1693] Output: Learning progress data sent to the server

[1694] Step 8:

[1695] The server analyzes the learning progress data and generates real-time feedback to assess the progress and provide appropriate advice and next steps for learning. The generated feedback is then sent to the user's device.

[1696] Input: Learning progress data sent to the server

[1697] Output: Real-time feedback sent to the user device

[1698] Step 9:

[1699] When users access online forums or chat rooms, the server monitors their activity data and recommends appropriate forums or chat rooms to them. Additionally, the server collects offline event information from local educational institutions, libraries, and local governments and notifies appropriate users.

[1700] Input: Forum and chat room activity data, local offline event information

[1701] Output: User recommended forums, chat rooms and offline event information

[1702] Example prompts using a generative AI model:

[1703] "Develop a smartphone application that provides a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Use Python's requests library to send user information to a server and retrieve a customized curriculum generated by an AI algorithm."

[1704] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1705] The present invention is a system that provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the community, and combines it with an emotion engine that recognizes the user's emotions, allowing it to tailor curriculum, feedback, and communication recommendations based on the learner's emotional state.

[1706] Entering learner information and generating a curriculum

[1707] When users first log in, they enter their email address and password, along with their learning goals, interests, and skill level, and the system uses this information to create a learner profile.

[1708] The terminal transmits the input information to the server.

[1709] The server uses an AI algorithm to generate a customized learning curriculum based on the received information, and also analyzes the user's emotional state using an emotion engine, which then incorporates that information into the curriculum.

[1710] The server stores the generated curriculum in a database and transmits it to the user's terminal.

[1711] Collaboration with experts

[1712] Experts access the system and enter their field of expertise, background, and qualifications, which allows the system to register each expert's knowledge and experience in a database.

[1713] Users can enter any questions or concerns they may have while studying and submit their questions.

[1714] The terminal sends a question from the user to the server.

[1715] The server analyzes the question and routes it to the appropriate expert, taking into account the user's emotional state and recommending an answer in an appropriate tone.

[1716] The expert enters the answer to the question and sends it to the server.

[1717] The server sends the expert's answer to the user's terminal and displays it.

[1718] Tracking learning progress and providing feedback

[1719] As users progress through the learning process, their progress data is recorded, while the emotion engine simultaneously analyzes their emotions from their facial expressions and tone of voice.

[1720] The device transmits progress and emotion data to the server in real time.

[1721] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments, such as lowering the difficulty level if the user is feeling stressed.

[1722] The server sends the generated feedback and adjustments to the user's terminal and displays them to the user.

[1723] Building a learning community

[1724] Users access online forums and chat rooms to interact with other learners and experts, while the emotion engine monitors their emotional state.

[1725] The server monitors community activity data and recommends appropriate forums and chat rooms based on the user's emotional state, as well as providing notifications to encourage active participation within the community.

[1726] Users receive notifications of offline events provided by the system and decide whether to participate. Data from the emotion engine is also taken into consideration at this time, and events suitable for the user are recommended.

[1727] The server collects information about offline study sessions and activities taking place in the area and sends push notifications to appropriate users.

[1728] Specific examples

[1729] For example, if a learner living in a rural area wants to learn data science, they can use this system to have the following experiences:

[1730] When a user first logs in, they tell the system that they are interested in data science.

[1731] The server generates a customized data science curriculum based on the information received and sends it to the user's device.

[1732] As the learning process progresses, users ask questions about specific data analysis techniques, which are then routed by the server to the appropriate data science experts. An emotion engine detects when the user is frustrated and encourages the experts to respond in a gentler tone.

[1733] Experts answer questions, and the answers are provided to users via a server. As users learn, their progress data and emotional state are recorded and sent to the server in real time. The server analyzes the data and generates appropriate feedback for users. It also recommends participation in appropriate forums and offline events based on the user's emotional state.

[1734] The system provides learners with a highly customized educational experience and addresses their psychological aspects by utilizing an emotional engine, thereby improving the quality of education and enabling learners to achieve optimal learning through collaboration with the local community.

[1735] The processing flow will be explained below.

[1736] Step 1:

[1737] A user accesses the system and enters their email address and password on the initial login screen.

[1738] Step 2:

[1739] The terminal sends the input information to the server and requests user authentication.

[1740] Step 3:

[1741] The server compares the received authentication information with a database, generates an authentication token, and sends it to the terminal.

[1742] Step 4:

[1743] After logging in, the user is directed to a screen where they can enter their learning goals, interests, and skill level. At this point, the camera and microphone are activated, and the emotion engine analyzes the user's facial expressions and voice.

[1744] Step 5:

[1745] The terminal transmits the input learner information and emotion data to the server.

[1746] Step 6:

[1747] The server uses an AI algorithm to generate a customized learning curriculum based on the learner information and emotional data received.

[1748] Step 7:

[1749] The server stores the generated curriculum in a database and sends it to the user's device.

[1750] Step 8:

[1751] Users begin learning based on the curriculum, and if they encounter any problems or questions during the learning process, they can enter them.

[1752] Step 9:

[1753] The device sends the user's question to the server, and the emotion engine also analyzes the user's emotional state at that time and sends the result to the server.

[1754] Step 10:

[1755] The server analyzes the question and emotional data and routes it to the appropriate expert, recommending that the expert respond in an appropriate tone based on the emotional state.

[1756] Step 11:

[1757] The expert enters the answer to the question and sends it to the server.

[1758] Step 12:

[1759] The server receives the answers from the experts and sends them to the user's device.

[1760] Step 13:

[1761] As users learn, their progress is recorded, and an emotion engine analyzes their emotional state.

[1762] Step 14:

[1763] The device transmits progress and emotion data to the server in real time.

[1764] Step 15:

[1765] The server analyzes the learner's performance based on the received progress and emotion data, and generates feedback and adjustments.

[1766] Step 16:

[1767] The server sends the generated feedback and adjustments to the user's device and displays them to the user, adjusting the content and tone of the feedback according to the user's emotional state.

[1768] Step 17:

[1769] As users access online forums and chat rooms and interact with other learners and experts, the emotion engine monitors their emotional state and transmits that data to the server if necessary.

[1770] Step 18:

[1771] The server monitors community activity data and user sentiment data and recommends appropriate forums and chat rooms to users.

[1772] Step 19:

[1773] The server collects information on offline study sessions and activities taking place in the area and sends push notifications to appropriate users based on emotional data.

[1774] Step 20:

[1775] Users receive notifications about offline events and decide whether or not they want to participate. The emotion engine analyzes the user's reactions and provides feedback tailored to their willingness to participate.

[1776] In this way, this system, which combines an emotion engine, also responds to the psychological aspects of learners and provides an optimal learning environment.

[1777] Example 2

[1778] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1779] Traditional educational systems have difficulty customizing to meet individual learners' skills, interests, and learning styles, and generic curricula have been unable to meet individual needs. Furthermore, limited collaboration with experts makes it difficult to respond quickly and appropriately to learners' doubts and questions. Furthermore, the inability to provide feedback or adjust the curriculum to take into account the learner's emotional state means that improvements in learning quality and motivation cannot be expected.

[1780] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1781] In this invention, the server includes means for analyzing the emotional state of the learner and adjusting the curriculum and feedback content, means for analyzing the learner's questions and providing answers in an appropriate tone, and means for collecting information on study sessions and activities taking place in the local area and recommending appropriate offline events based on the learner's emotional state. This makes it possible to provide an educational experience optimized for each learner and to improve the quality of learning and motivation by strengthening collaboration with experts and the local community.

[1782] A "learner" is an individual who engages in a learning activity.

[1783] A "skill" is an ability or technique for effectively performing a particular task or activity.

[1784] "Interests" refer to subjects or topics that interest learners.

[1785] A "learning style" refers to the method or approach that a learner takes in learning.

[1786] A "curriculum" is an educational content or learning program designed to achieve specific learning goals.

[1787] An "expert" is a person who has advanced knowledge or skills in a particular field.

[1788] A "network" is a communication system built to share information and resources.

[1789] "Learning progress" refers to an indicator or state that indicates how far a learner has progressed toward a learning goal.

[1790] "Feedback" refers to information provided about the learning process or results for evaluation and improvement.

[1791] "Online" refers to operations or activities conducted over the Internet.

[1792] "Offline" refers to operations or activities that are not performed via the Internet.

[1793] A "learning community" is a group of learners and experts who exchange information and opinions and support each other's learning.

[1794] An "emotional state" is the emotion or mental state that a learner is feeling at a particular time.

[1795] "Analysis" is the act of examining data or information in detail and clarifying its structure and relationships.

[1796] "Tone" refers to the way one speaks or expresses something, especially its intensity and emotional level.

[1797] "Routing" refers to the procedures and methods used to direct data or information to its proper destination.

[1798] An "offline event" is a learning activity or social gathering that takes place in a physical location.

[1799] The system is designed to provide a customized educational experience that takes into account the learner's skills, interests, and learning style. Key elements include an AI algorithm, an emotion engine, and online and offline learning community functions. The specific implementation of each element is explained below.

[1800] Entering learner information and generating a curriculum

[1801] When a user logs in for the first time, they enter their email address and password, as well as their learning goals, interests, and skill level. This information is sent from the device to the server via an HTTP POST request. The server receives this information and stores it in a database. It then uses an AI algorithm to generate a customized learning curriculum. This AI algorithm selects the most appropriate learning content based on the learner's profile information.

[1802] Furthermore, the server uses an emotion engine to analyze the learner's emotional state. This emotional state is obtained using facial expression analysis technology, tone of voice analysis technology, etc. This makes it possible to reflect emotional information in the curriculum. The generated curriculum is saved in the database again and sent to the terminal. The terminal displays the received curriculum to the user.

[1803] Collaboration with experts

[1804] Experts access the system and enter their field of expertise, background, and qualifications. This information is registered in a database. When a user enters a question or concern during learning, the device sends the question to the server. The server analyzes the question and routes it to the appropriate expert. In doing so, it uses an emotion engine to analyze the user's emotional state and provides the expert with instructions recommending an appropriate tone of voice to respond. The expert enters the answer and sends it to the server, where it is delivered and displayed to the user.

[1805] Tracking learning progress and providing feedback

[1806] As the user progresses through their learning activities, their progress data is recorded. At the same time, an emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and sends this information in real time via the device to the server. The server analyzes the received data and evaluates the learner's performance. Based on this, appropriate feedback and curriculum adjustments are generated, sent to the device, and displayed to the user. For example, if the learner is feeling stressed, the system will make adjustments such as lowering the difficulty of the learning content.

[1807] Building a learning community

[1808] Users can access online forums and chat rooms to interact with other learners and experts. The emotion engine monitors the user's emotional state and recommends appropriate forums and chat rooms. The server also monitors community activity data and sends notifications to encourage active participation.

[1809] The server also collects information about offline study groups and activities taking place in the local area and sends push notifications to appropriate users, providing opportunities for learners to meet in person both online and offline and building a learning community.

[1810] Specific examples

[1811] For example, consider the case where a learner who wants to learn data science enters their interest in data science when logging in for the first time. The server generates a customized data science curriculum based on the received information and sends it to the device. If the user asks a question about a specific data analysis method as they progress through their studies, the question is routed to an appropriate data science expert. At that time, an emotion engine detects the user's frustration and recommends that the expert respond in a gentler tone. The expert's answer is then provided to the user via the server.

[1812] An example of a prompt sentence could be, "Please enter the information needed to customize your data science curriculum. For example, please enter your area of ​​interest, current skill level, and learning goals. Also, please enter your past learning experience and any specific questions you may have." By using this prompt sentence as a concrete example, the system can quickly generate a curriculum optimized for the user's needs.

[1813] Overall, the system aims to improve learning quality and motivation by providing an educational experience tailored to each learner's individual needs and by strengthening collaboration with experts and the local community.

[1814] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1815] Step 1:

[1816] A user enters an email address and password on the login screen. The entered information is sent from the device to the server. Specifically, the data collected in the input form is sent to the server as an HTTP POST request. The input data includes the email address and hashed password.

[1817] Step 2:

[1818] The server compares the received login information with the database and performs authentication. If authentication is successful, the server generates the user's session information and sends the session ID to the terminal. The authentication process checks whether the email address and hashed password match the information in the database.

[1819] Step 3:

[1820] The user enters profile information such as learning objectives, interests, and skill level. The entered information is sent to the server via the terminal. Specifically, the data collected in the form is sent to the server as an HTTP POST request. The input data includes learning objectives, interests, and skill level.

[1821] Step 4:

[1822] The server stores the received profile information in a database and analyzes it using an AI algorithm. As a result of the analysis, a learning curriculum optimal for the learner is generated. Specifically, the received data is input into an AI model to generate a customized curriculum. As an output, the learning curriculum is stored in a database.

[1823] Step 5:

[1824] The server uses an emotion engine to analyze the user's emotional state. Specifically, it receives the user's facial expressions and voice data as input and analyzes them using an emotion analysis model. The output is data indicating the user's emotional state.

[1825] Step 6:

[1826] The server reflects the emotional state in the generated curriculum to complete the final curriculum. Specifically, the content and difficulty of the curriculum are adjusted using the emotional state data. As an output, the curriculum reflecting the emotions is saved again in the database.

[1827] Step 7:

[1828] The server sends the final curriculum to the terminal. Specifically, it sends the generated curriculum to the terminal as an HTTP response. The terminal displays the received curriculum to the user.

[1829] Step 8:

[1830] Experts access the system and enter their field of expertise, background, and qualifications, which are then sent from the terminal to the server and stored in a database.

[1831] Step 9:

[1832] The user inputs questions that arise during learning and sends them from the device to the server. The input data includes the question content. Specifically, the question data collected in the form is sent to the server as an HTTP POST request.

[1833] Step 10:

[1834] The server analyzes the received question and routes it to the appropriate expert. Specifically, it analyzes the question content using natural language processing (NLP) technology and searches a database for the most suitable expert. The output is information about the expert to whom the question will be routed.

[1835] Step 11:

[1836] The server notifies the expert of the question and emotional information. Specifically, the server generates notification data containing the question content and the user's emotional state information and sends it to the expert's terminal.

[1837] Step 12:

[1838] The expert enters the answer to the question and sends it to the server. Specifically, the answer is sent to the server as an HTTP POST request.

[1839] Step 13:

[1840] The server sends the received response to the user's device and displays it. Specifically, it sends the response data to the device as an HTTP response. The device displays the received response to the user.

[1841] Step 14:

[1842] As the user progresses through the learning activity, progress data is recorded. At the same time, the emotion engine analyzes emotional data from facial expressions and tone of voice. This data is sent to the server via the device.

[1843] Step 15:

[1844] The server analyzes the received progress and emotion data and generates feedback. Specifically, the progress and emotion data are input into a machine learning model to generate performance evaluation and optimal feedback. The output is feedback data.

[1845] Step 16:

[1846] The server sends the generated feedback to the terminal and displays it to the user. Specifically, the server sends the feedback data to the terminal as an HTTP response. The terminal then displays the received feedback to the user.

[1847] Step 17:

[1848] A user accesses an online forum or chat room and communicates with the user. The server monitors the user's emotional state using an emotion engine and recommends appropriate forums or chat rooms.

[1849] Step 18:

[1850] The server collects information about offline learning activities taking place in the area and notifies appropriate users. Specifically, it analyzes the collected information data and recommends offline events based on the user's emotional state. The device displays the received event notifications to the user.

[1851] Through this process, the system is able to provide an educational experience that is optimized to the individual needs of each learner.

[1852] (Application example 2)

[1853] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1854] Conventional learning systems lack the ability to customize learning to fit the learner's skills, interests, and emotional state, resulting in poor learning efficiency. Furthermore, in brick-and-mortar stores, they are unable to provide customer service that reflects their emotions, which can lead to lower customer satisfaction. Furthermore, there are challenges in building online and offline learning communities and effectively utilizing expert knowledge.

[1855] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for generating a customized curriculum based on the learner's skills, interests, and learning style; means for bringing together domestic and international experts and building a network to provide their knowledge; means for tracking and managing learning progress and providing feedback; means for providing opportunities for learners to meet in person online and offline and building a learning community; means for collaborating with local schools, libraries, and local governments and utilizing it as an offline education platform; means for analyzing the learner's emotional state using an emotion engine and adjusting the curriculum, feedback, and communication recommendations; and means for realizing a brick-and-mortar store application that analyzes the emotional state of customers in real time and provides customized customer service methods and suggestions. This enables advanced customization according to the individual needs of learners, improving learning efficiency and customer satisfaction.

[1856] "Learner" refers to an individual who uses a learning system to acquire knowledge or skills.

[1857] "Skills" refer to the abilities and techniques that a learner has to accomplish a specific task or work.

[1858] "Interest" refers to the interest or curiosity a learner has in a particular field or topic.

[1859] "Learning style" refers to the methods and procedures by which a learner learns most effectively.

[1860] "Curriculum" refers to an educational plan that defines the content and progression that learners should learn.

[1861] "Domestic and international experts" refers to individuals or institutions with a high level of knowledge and experience in a particular field.

[1862] "Network" refers to a communication network that allows multiple experts and learners to share information and collaborate.

[1863] "Progress" refers to the progress that a learner makes in demonstrating how well they have achieved their learning tasks.

[1864] "Feedback" refers to evaluation and advice provided to learners to improve their learning activities.

[1865] A "community" refers to a group of learners and professionals who share common learning goals and interests.

[1866] "Online" refers to forms of learning and communication delivered via the Internet.

[1867] "Offline" refers to activities and communications that take place in a physical location, not via the internet.

[1868] An "emotion engine" refers to technology that analyzes a user's facial expressions, tone of voice, etc. to determine their emotional state.

[1869] "Customer" means an individual who uses or purchases a particular service or product.

[1870] "Brick and mortar store" refers to a sales or service point located in a physical location.

[1871] "Application" refers to a software program that provides a specific function or service.

[1872] An "AI algorithm" refers to a calculation method for analyzing data and making decisions using artificial intelligence.

[1873] A "database" refers to a digital system that systematically organizes and stores information.

[1874] This system provides learners with a customized educational experience, strengthens collaboration with experts, and improves the quality of learning through collaboration with the local community. Furthermore, by incorporating an emotion engine, the system adjusts curriculum, feedback, and communication recommendations based on the learner's emotional state. This system can also be applied to brick-and-mortar retail applications, where customers' emotional states are analyzed in real time to provide customized customer service methods and suggestions.

[1875] Entering learner information and generating a curriculum

[1876] When logging in for the first time, users enter their email address and password, as well as their learning goals, interests, and skill level. The device then sends the entered information to the server. The server uses an AI algorithm based on the received information to generate a customized learning curriculum, and then analyzes the user's emotional state using an emotion engine and reflects that information in the curriculum. The server then saves the generated curriculum in a database and sends it to the user's device.

[1877] Collaboration with experts

[1878] Experts access the system and register their knowledge and experience in the database by entering their field of expertise, career history, and qualifications. Users enter questions or doubts that arise during their studies and send them from their terminal to the server. The server analyzes the content of the question and routes it to the appropriate expert. The expert enters an answer to the question and sends it to the server. The server sends the answer from the expert to the user's terminal and displays it.

[1879] Tracking learning progress and providing feedback

[1880] As the user progresses through the learning activity, progress data is recorded. At the same time, the emotion engine analyzes the user's emotions from their facial expressions and tone of voice. The device sends the progress and emotion data to the server in real time. The server analyzes the learner's performance based on the received progress and emotion data and generates feedback and adjustments. For example, if the user is feeling stressed, it may lower the difficulty level. The server sends the generated feedback to the user's device and displays it to the user.

[1881] Application in physical stores

[1882] This system can also be applied to improving customer service experiences in brick-and-mortar stores. The device is installed on a smartphone or head-mounted display and uses a camera to capture the customer's facial expressions. The received video data is sent to a server in real time, where an emotion engine analyzes the customer's emotional state. Based on the analysis results, the device displays customer service methods and product suggestions that are appropriate for the customer's emotions.

[1883] For example, when a customer visits a cosmetics counter in a physical store, a staff member's smartphone scans the customer's facial expression and determines that the customer looks a little depressed. The staff member is then shown advice such as, "Today, we'd like to recommend a lip color that will cheer you up a little."

[1884] Prompt Sentence Examples

[1885] The following prompt sentence is used as input to the generative AI model:

[1886] Write a program for a system that recognizes customer emotions and customizes in-store interactions. The hardware used is a smartphone camera, and the software is Python. Include recommendations based on the customer's emotional state.

[1887] This will enable us to provide an educational environment for users and improve the customer service experience in physical stores.

[1888] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1889] Step 1:

[1890] When a user logs in for the first time, they enter their email address and password, as well as their learning goals, interests, and skill level. This generates the user's profile information. The entered information is sent to the server by the device. The entered data includes the email address, password, learning goals, interests, and skill level. The device then uploads this data to the server.

[1891] Step 2:

[1892] The server uses an AI algorithm to generate a customized learning curriculum based on the received user information. The learning content is customized based on the user's skills, interests, and learning style. An emotion engine also analyzes the user's emotional state, and the results are reflected in the curriculum. The input here is user information, and the output is a customized learning curriculum.

[1893] Step 3:

[1894] The server stores the generated curriculum in a database and then transmits it to the user's device. The database stored on the server holds a customized educational plan for each learner. The input is curriculum data, and the output is data transmission to the user's device.

[1895] Step 4:

[1896] If a user has any doubts or questions during their studies, they can input them through their device and send them to the server. The input data includes the user's question, and the device uploads it to the server.

[1897] Step 5:

[1898] The server analyzes the received question and routes it to the appropriate expert from a list of experts in the database. The server takes into account the question as well as the user's emotional state, which is analyzed by the emotion engine. The input is the question from the user, and the output is the expert to whom the question is routed.

[1899] Step 6:

[1900] The expert inputs an answer to the question received from the server and sends it to the server. In this process, the answer i...

Claims

1. a means of generating customized curriculum based on learners' skills, interests, and learning styles; A means of building a network that brings together domestic and international experts and provides their knowledge; a means to track and manage learning progress and provide feedback; Provide opportunities for learners to meet face-to-face and build learning communities online and offline; We will work with local schools, libraries, and local governments to utilize it as an offline education platform, and A system including:

2. The system according to claim 1, wherein a customized learning curriculum is generated using an AI algorithm based on the received learner information, stored in a database, and transmitted to the terminal.

3. The system of claim 1 , wherein the system routes the received question to an appropriate expert and provides the answer from the expert to the learner.

Images