System

Abstract

A system is provided.SOLUTION: A system, comprising: means for a user to input a learning need through a terminal; means for a server to analyze the user's learning need and store it in a database; means for the server to select optimal learning content based on the analysis result and send it to the terminal; means for the terminal to display the learning content selected by the user; means for recording the user's learning progress and sending it to the server; and means for the server to select new learning content based on the learning progress and send it to the terminal.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] In today's world, the market is flooded with numerous learning materials and services, making it extremely difficult for motivated learners to find the right learning materials and methods. This leads to problems such as reduced learning efficiency and difficulty in maintaining motivation. Furthermore, due to a lack of appropriate learning support tailored to progress, users often get stuck during their studies. Therefore, there is a need for a system that can meet individual learning needs so that users can efficiently improve their skills. [Means for solving the problem]

[0005] This invention solves the above problem with a system that includes a means for a user to input their learning needs via a terminal, a means for a server to analyze the user's learning needs and store them in a database, a means for the server to select optimal learning content based on the analysis results and send it to the terminal, a means for the terminal to display the learning content selected by the user, a means for recording the user's learning progress and sending it to the server, and a means for the server to select new learning content based on the learning progress and send it to the terminal. Furthermore, by including a means for the server to receive questions from the user during learning, search for corresponding answers, and return them to the terminal, and a means for the server to identify the user's learning needs using text analysis and machine learning algorithms, it is possible to respond to individual users' needs and significantly improve learning efficiency.

[0006] "User" refers to an individual who uses the system to obtain learning content and engage in learning activities.

[0007] "Device" refers to a device that allows a user to access the system, input learning needs, view learning content, and submit progress. Examples include smartphones, tablets, and PCs.

[0008] "Server" refers to the central device that manages the entire system, processes data, receives user requests, provides learning content, and analyzes progress data.

[0009] "Learning needs" refers to requirements and desires regarding specific skills and knowledge that a user wants to improve.

[0010] "Database" refers to a system for systematically storing information such as users' learning needs, progress, and appropriate learning content.

[0011] "Analysis" refers to the process of processing and analyzing input data to understand the user's learning needs.

[0012] "Learning content" refers to learning materials provided for users to study, including online courses, specialized books, explanatory pages, and the like.

[0013] "Progress" refers to the results a user has achieved through learning activities and the current state of their learning.

[0014] "Text analysis" refers to technology for analyzing text data entered by a user and interpreting its meaning.

[0015] A "machine learning algorithm" refers to a technology that automatically learns and predicts user behavior patterns and learning needs based on large amounts of data.

[0016] "Answer" refers to explanations or information provided in response to a user's question. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that allows users to select optimal learning content based on their own learning needs and efficiently improve their skills. Next, a specific embodiment for implementing this system will be described.

[0039] 1. User Registration / Login

[0040] A user first accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and sends it to the server. The server checks the received information against a database and performs authentication. If authentication is successful, the user is allowed to access the system.

[0041] 2. Initial Interactive Session

[0042] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their terminals. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions through their terminal, and the terminal sends the answers to the server.

[0043] 3. Data analysis and accumulation

[0044] The server receives the user's response data and analyzes it using text analysis and machine learning algorithms. This analysis identifies the user's individual learning needs and stores the results in a database. For example, if a user responds, "I want to learn Python programming," the server registers that need in the database.

[0045] 4. Learning content suggestions

[0046] The server selects the most appropriate learning content based on the user's learning needs stored in the database. The selected learning content (e.g., online courses or specialized book information) is sent to the terminal and suggested to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" are displayed to the user.

[0047] 5. Learning support

[0048] As the user progresses through the learning process using the suggested learning content, the device records their progress. If the user has a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page."

[0049] 6. Progress management and new proposals

[0050] The device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. It then sends new suggestions to the device. For example, if progress reaches 50%, the server will suggest, "As your next step, we recommend Data Analysis Course C."

[0051] Specific examples

[0052] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," in the database. The server then recommends "online course A for beginners" and "specialized book B for beginners" to the terminal. As the user progresses with these learning materials, if the user sends a question about how to use a function from the terminal to the server, the server will suggest an appropriate explanation page. Furthermore, when the user's progress reaches 50%, the server will suggest "data analysis course C" as the next step.

[0053] This system provides learning support tailored to the individual needs of users, allowing them to improve their skills efficiently.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] A user accesses the system via a terminal. The terminal displays a registration / login screen to the user. Here, the user enters their name, email address, password, etc., and presses the submit button.

[0057] Step 2:

[0058] The terminal sends the entered information to the server. The server checks the received information against the database, and stores the information in the database if it is a new registration, or performs authentication if it is an existing user.

[0059] Step 3:

[0060] The server sends the authentication result to the terminal. If the authentication is successful, the user can access the system and proceed to the next step. If the authentication is unsuccessful, an error message is displayed.

[0061] Step 4:

[0062] The server generates initial questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, the questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to learning?"

[0063] Step 5:

[0064] The user answers questions through the device. For example, they answer "I want to learn Python programming." The device then sends the user's answers to the server.

[0065] Step 6:

[0066] The server analyzes the received response data, uses text analysis and machine learning algorithms to identify the user's learning needs, and stores the results in a database.

[0067] Step 7:

[0068] The server selects the most suitable learning content based on the analysis results. For example, "Online Course A for Beginners" and "Specialized Book B for Beginners" may be selected. The selected learning content is then sent to the device.

[0069] Step 8:

[0070] The device displays the learning content selected by the user, and the user begins learning by viewing the recommended learning content.

[0071] Step 9:

[0072] If a user has a question about their learning as they proceed, they can send it to the server via their device. For example, they might ask, "I don't know how to use a Python function."

[0073] Step 10:

[0074] The server receives the question, searches an internal database or external resources to find the appropriate answer, and sends the answer to the terminal. For example, it sends a response such as "For the basics of Python functions, please see this explanation page."

[0075] Step 11:

[0076] The device periodically records the user's learning progress information and sends it to the server, such as the learning progress status and information on completed assignments.

[0077] Step 12:

[0078] The server analyzes the learning progress data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server may select content such as "We recommend Data Analysis Course C as the next step."

[0079] Step 13:

[0080] The server sends the selected new learning content to the device, which displays it to the user and suggests the next learning step. The user can then use the new learning content to further improve their skills.

[0081] In this way, through a series of processing steps, it is possible to provide optimal learning support tailored to the user's learning needs.

[0082] Example 1

[0083] 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."

[0084] Existing learning systems have difficulty providing optimal learning content that meets individual user needs, making it difficult to efficiently improve skills. They also lack the means to quickly respond to questions that arise during learning, making it impossible to provide appropriate learning support. Furthermore, they lack the flexibility to suggest new content based on learning progress.

[0085] 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.

[0086] In this invention, the server includes: a means for a user to input learning needs via a terminal; a means for identifying learning needs using text analysis or machine learning algorithms and storing them in a database; a means for selecting optimal learning content based on the analysis results and transmitting it to the terminal; a means for the terminal to display the learning content selected by the user; a means for recording the user's learning progress and transmitting it to the server; a means for selecting new learning content based on the user's learning progress and transmitting it to the terminal; a means for the user to input questions via the terminal while learning; a means for receiving questions from the user, searching for corresponding answers from a database or external resources, and returning them to the terminal; a means for using a generative AI model through an initial dialogue session to generate questions to elicit the user's learning needs; and a means for periodically transmitting progress information to the server and analyzing the progress data to select new learning content. This enables the server to provide optimal learning content tailored to the user's individual needs and efficiently improve skills. It also enables the server to quickly respond to questions during learning and provide appropriate learning support. Furthermore, it can flexibly suggest new content according to the user's learning progress.

[0087] "Terminal" refers to the device that a user uses to access and operate the system, such as a smartphone, tablet, or PC.

[0088] "Server" refers to the central computer that manages the entire system and provides learning content and answers to user inputs and requests.

[0089] "Database" refers to a collection of data for storing and managing users' learning needs, progress information, and related learning content.

[0090] "Learning needs" refers to the demands and requirements for knowledge and skills that a user wants to acquire.

[0091] "Text analysis" refers to a method of analyzing input data from a user using natural language processing techniques.

[0092] A "machine learning algorithm" refers to a computational method for learning specific patterns and rules from data and using them to make predictions and classifications.

[0093] "Learning content" refers to the learning materials and resources provided to users for learning, such as online courses and specialized books.

[0094] "Progress Information" refers to data that indicates how much a user has learned and how far they have progressed using the learning content.

[0095] A "generative AI model" refers to an artificial intelligence model that generates appropriate questions and answers based on user input data.

[0096] "Answer" refers to appropriate information or explanation provided in response to a user's question.

[0097] "Questions" refer to questions or things that users want to confirm while studying.

[0098] The present invention is a system that allows users to select optimal learning content based on their own learning needs and efficiently improve their skills. Specific aspects of the system are described below.

[0099] First, a user accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user through the system's website or application. The user enters the required information (name, email address, password, etc.) and sends it to the server.

[0100] The server checks the received information against a database (for example, MySQL or PostgreSQL) and performs authentication. If authentication is successful, the user is allowed to access the system, and the server generates a session ID and sends it to the terminal.

[0101] Next, the server uses the generative AI model to generate a set of questions to elicit learning needs and sends them to the device. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions and sends the answers to the server via the device.

[0102] The server receives the user's response data and analyzes it using text analysis tools (e.g., NLTK or SpaCy) or machine learning algorithms (e.g., Scikit-learn or TensorFlow). This analysis identifies the user's individual learning needs and stores the results in a database. For example, if the user responds, "I want to learn Python programming," the server registers that need in the database.

[0103] Next, the server selects the most suitable learning content based on the user's learning needs stored in the database. For example, information such as "Online Course A" or "Specialized Book B" may be selected. The server then sends these selection results to the terminal, which then displays the selected learning content to the user.

[0104] As the user progresses through the learning process using the suggested learning content, the device records their progress. If a question arises during the learning process, the user enters it via the device, which then sends it to the server. The server receives the question, searches a database or external resources to generate an appropriate answer, and sends it back to the device. For example, in response to a question such as "I don't know how to use a Python function," the server suggests a related explanation page.

[0105] Additionally, the device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. When progress reaches 50%, the server makes suggestions such as recommending "Data Analysis Course C as the next step."

[0106] This invention provides optimal learning content tailored to the individual needs of users, enabling them to efficiently improve their skills. It also responds quickly to questions that arise during learning and provides appropriate learning support. Furthermore, it also makes it possible to flexibly suggest content according to the user's learning progress, making it a very beneficial system for learners.

[0107] Example prompts to input to the generative AI model

[0108] "What online courses would you recommend for beginners who want to learn Python programming?"

[0109] "What learning content would you recommend as the next step for a user who is currently 50% complete?"

[0110] "Please suggest a page that explains how to use Python functions."

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1:

[0113] A user accesses the system using a terminal. The terminal displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and sends it to the server. The server checks the entered information against the database and creates a record in the database if the user is a new user. If the user is already registered, it authenticates the entered password. If authentication is successful, the server generates a session ID and sends it to the terminal. The terminal receives the session ID and displays the main screen.

[0114] Step 2:

[0115] After a user successfully registers or logs in, the server generates a set of questions to start an initial dialogue session. These questions are automatically generated using a generative AI model. For example, they include questions such as, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The server sends these questions to the device, which displays them to the user. The user answers the questions and sends the answers to the server via the device.

[0116] Step 3:

[0117] The server receives the user's response data and analyzes it using text analysis tools (e.g., NLTK or SpaCy) or machine learning algorithms (e.g., Scikit-learn or TensorFlow). The input data for the analysis is the user's response, and the output is the analysis result, which is the user's specific learning needs. For example, if the user's response is "I want to learn Python programming," the server stores that information in a database.

[0118] Step 4:

[0119] The server selects the most suitable learning content based on the user's learning needs stored in the database. In this process, a learning content selection algorithm is used. For example, learning resources such as "Online Course A" or "Specialized Book B" are selected. The selected learning content is sent from the server to the terminal, which then displays it to the user.

[0120] Step 5:

[0121] When a user starts learning using the suggested learning content, the device records the learning progress. The input data is a record of the user's learning activities, and progress information is generated as output data. If the user has any questions while learning, they can input them via the device. The questions are sent to the server, which then receives them.

[0122] Step 6:

[0123] The server analyzes the question sent by the user and searches databases and external resources to find the appropriate answer. Search algorithms and AI models are used to generate the answer. For example, in response to a question such as "I don't know how to use a Python function," the server searches for a relevant explanation page and sends the link to the device. The device then displays the answer to the user.

[0124] Step 7:

[0125] The device periodically sends the user's learning progress information to the server. The server analyzes this progress data and evaluates the current learning situation. Based on the input progress information, an evaluation algorithm is run to select new learning content. For example, when progress reaches 50%, the server recommends "Data Analysis Course C as the next step." The selected new content is sent to the device and displayed to the user as a new suggestion.

[0126] (Application example 1)

[0127] 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."

[0128] Conventional learning systems required a lot of time and effort to respond to individual user needs, and the lack of automation in learning progress and question response made it difficult to improve skills efficiently.Furthermore, while there is a demand for rapid and accurate acquisition of the necessary skills in the operation of factory robots, conventional systems were inadequate in meeting this demand.

[0129] 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.

[0130] In this invention, the server includes: a means for a user to input their learning needs via a terminal; a means for the server to analyze the user's learning needs and store them in a database; a means for the server to select optimal learning content based on the analysis results and send it to the terminal; a means for the terminal to display the learning content selected by the user; a means for recording the user's learning progress and sending it to the server; a means for the server to select new learning content based on the user's learning progress and send it to the terminal; a means for generating optimal answers to questions from the user using a generative AI model and sending them to the terminal; and a means for generating optimal prompt sentences using the generative AI model based on the user's learning needs. This allows users to receive learning content tailored to their individual needs, efficiently manage their learning progress, and quickly respond to questions. It also allows users to efficiently acquire the necessary skills for operating factory robots, contributing to improved productivity.

[0131] "User" refers to a person who uses this system to study.

[0132] A "terminal" is a device used by a user to access the system, such as a smartphone, tablet, or PC.

[0133] "Learning needs" refers to the learning content and goals that users need to learn in order to improve their skills.

[0134] "Server" means a central processing unit for receiving and analyzing data from users and providing appropriate learning content.

[0135] A "database" is a collection of digital data that stores information about a user's learning needs and progress.

[0136] "Analysis" refers to the process of processing data obtained from users using machine learning algorithms and text analysis techniques to identify their learning needs.

[0137] "Learning content" refers to learning materials and resources selected by the server based on the user's learning needs.

[0138] A "generative AI model" is an algorithm or method that uses artificial intelligence to generate optimal answers or prompts to user questions.

[0139] A "prompt" is an instruction or suggestion that is generated by a generative AI model based on the user's learning needs to promote learning.

[0140] "Progress" refers to the learning progress of a user, which indicates how much of the suggested learning content they have completed.

[0141] An "answer" is a response or explanation provided by a server or a generative AI model in response to a user's question.

[0142] The present invention provides a system for enabling users to efficiently advance their learning and improve their skills, particularly in the operation and maintenance of factory robots. The system includes the following components:

[0143] User Registration / Login

[0144] Users first access the system using a device such as a smartphone, tablet, or PC, and then register and log in. Registration requires information such as name, email address, and password, and the server stores this information in a database and performs authentication. If authentication is successful, the user can access the system.

[0145] Initial Interactive Session

[0146] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their devices. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions via their device, and the answers are sent to the server.

[0147] Data analysis and accumulation

[0148] The server receives the user's response data and analyzes it using machine learning algorithms and text analysis. This analysis identifies the user's individual learning needs and stores the results in a database. For example, if a user responds, "I want to learn Python programming," the server registers that need in the database.

[0149] Learning content suggestions

[0150] The server selects the most suitable learning content based on the user's learning needs stored in a database. The selected learning content is sent to the terminal and suggested to the user. For example, "Introductory course on Python programming" or "Specialized books for beginners" are displayed.

[0151] Learning support and questions

[0152] As the user progresses through the learning process using the suggested learning content, the device records their progress. When the user asks a question, the device sends it to the server. The server receives the question, uses a generative AI model to generate the optimal answer, and sends it to the device. For example, in response to a question like "I don't know how to use a Python function," the server might respond with "Please see this explanation page."

[0153] Progress management and new proposals

[0154] The device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. For example, if progress reaches 50%, the server will suggest, "We recommend a data analysis course as your next step."

[0155] Specific examples and prompts for the generation AI

[0156] As a concrete example, imagine a user who has just become an operator of a new factory robot and wants to learn the basic operations. After logging in, the user asks, "Please tell me about an online course on basic robot operations," and the server uses the generative AI model to provide an answer such as, "I recommend this online course."

[0157] Example prompt sentence:

[0158] User: I just became the operator of a new factory robot. I would like to learn the basics of robot operation. What online courses should I take?

[0159] This system allows users to efficiently improve their skills through learning content tailored to their individual needs, and in particular enables them to quickly acquire skills in operating and maintaining factory robots.

[0160] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0161] Step 1:

[0162] A user accesses the system via a terminal and enters the required information (such as name, email address, and password) on the registration or login screen. The entered information is sent to the server, which stores it in a database and performs authentication processing. If successful, the user can access the system.

[0163] Input: User information (name, email address, password)

[0164] Processing: The server stores the user information in a database and performs authentication.

[0165] Output: Authentication success message and access to the system is allowed

[0166] Step 2:

[0167] After a user logs in, the server generates questions to elicit their learning needs and sends them to the device, such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?"

[0168] Input: User login status

[0169] Processing: The server generates questions about learning needs and sends them to the terminal.

[0170] Output: Learning Needs Questionnaire Form

[0171] Step 3:

[0172] Users answer questions about their learning needs through their devices, and the answers are sent from the device to the server. The server receives the answers and analyzes them using machine learning algorithms and text analysis methods. The server identifies the user's learning needs and stores the results in a database.

[0173] Input: User responses regarding learning needs

[0174] Processing: The server analyzes the response data using machine learning algorithms and text analysis methods to identify learning needs and store them in a database.

[0175] Output: Identified learning needs data

[0176] Step 4:

[0177] The server selects the most suitable learning content based on the user's learning needs stored in a database. The selected learning content is sent to the terminal and suggested to the user. For example, "Introductory course on Python programming" or "Specialized books for beginners" are displayed.

[0178] Input: Identified learning needs data

[0179] Processing: The server selects the most appropriate learning content based on the identified needs.

[0180] Output: Suggested learning content

[0181] Step 5:

[0182] As the user progresses through the suggested learning content, the device records their progress. When the user asks a question, the device sends it to the server, which uses a generative AI model to generate the optimal answer and sends it to the device.

[0183] Input: Learning progress information and user questions

[0184] Processing: The server uses the generative AI model to generate the optimal answer to the question and sends it to the device.

[0185] Output: Learning progress information and answers

[0186] Step 6:

[0187] The device periodically sends information about the user's learning progress to the server. The server analyzes this progress data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server will suggest, "We recommend a data analysis course as your next step."

[0188] Input: Learning progress information

[0189] Processing: The server analyzes the progress data and selects new learning content.

[0190] Output: New learning content suggestions

[0191] 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.

[0192] This invention provides a system that allows users to select optimal learning content based on their own learning needs and emotional state, and to efficiently improve their skills. Next, specific embodiments for implementing this system will be described.

[0193] 1. User Registration / Login

[0194] A user first accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and submits it. The server checks the received information against the database, and if it is a new registration, the information is saved in the database, or if it is an existing user, authentication is performed. If authentication is successful, the user is able to access the system.

[0195] 2. Initial Interactive Session

[0196] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their terminals. The terminals display these questions. For example, they include questions such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The users answer these questions through their terminals. The terminals then send the answers to the server.

[0197] 3. Data analysis and accumulation

[0198] The server receives the user's response data and analyzes it using text analysis and machine learning algorithms. This analysis identifies the user's individual learning needs and stores the results in a database. The server also runs an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's audio and video data to identify their current emotional state. The results are also stored in the database.

[0199] 4. Learning content suggestions

[0200] The server selects optimal learning content based on the user's learning needs and emotional state stored in a database. The selected learning content (e.g., information on online courses or specialized books) is sent to the terminal and suggested to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" are displayed to the user. In addition, content and feedback to improve motivation are also provided according to the user's emotional state.

[0201] 5. Learning support

[0202] As the user progresses through the learning process using the suggested learning content, the device records their progress and emotional state, and sends them to the server. If the user asks a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page." In addition, the system analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[0203] 6. Progress management and new proposals

[0204] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes the progress data and emotional data and selects new learning content based on the user's current learning situation. It then sends new suggestions to the device. For example, if progress reaches 50%, the server might suggest, "We recommend Data Analysis Course C as your next step." The server also provides advice on appropriate learning methods based on the user's emotional state.

[0205] Specific examples

[0206] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," as well as the user's emotional state in a database. The server then recommends "Online Course A for Beginners" and "Specialized Book B for Beginners" to the terminal. As the user progresses through their studies using these learning materials, the emotion engine sequentially analyzes the user's emotional state and provides advice to improve motivation as needed. If a question arises, the server suggests an appropriate explanation page. Furthermore, when the user has progressed 50%, it suggests "Data Analysis Course C" as the next step.

[0207] This system provides learning support tailored to the user's needs and emotional state, allowing them to improve their skills efficiently.

[0208] The processing flow will be explained below.

[0209] Step 1:

[0210] A user accesses the system through a terminal. The terminal displays a registration / login screen to the user. The user enters the required information such as name, email address, and password, and presses the submit button.

[0211] Step 2:

[0212] The device sends the entered information to the server, which then checks the received information against the database, saving the information in the database if it is a new registration, or authenticating the user if they are already registered.

[0213] Step 3:

[0214] The server sends the authentication result to the terminal. If the authentication is successful, the user can access the system. If the authentication is unsuccessful, an error message is displayed.

[0215] Step 4:

[0216] The server generates initial questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, the questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to learning?"

[0217] Step 5:

[0218] The user answers questions through the device. For example, they answer "I want to learn Python programming." The device then sends the user's answers to the server.

[0219] Step 6:

[0220] The server analyzes the received response data, uses text analysis and machine learning algorithms to identify the user's learning needs, and stores the results in a database.

[0221] Step 7:

[0222] The server receives the user's audio and video data, analyzes it using an emotion engine, and identifies the user's current emotional state, which is also stored in a database.

[0223] Step 8:

[0224] The server selects the most suitable learning content based on the analysis results. For example, "Online Course A for Beginners" and "Specialized Book B for Beginners" may be selected. The selected learning content is then sent to the device.

[0225] Step 9:

[0226] The device displays the learning content selected by the user. The user then begins learning by viewing the recommended learning content. Motivational content tailored to the user's emotional state is also displayed on the device.

[0227] Step 10:

[0228] If a user has a question about their learning as they proceed, they can send it to the server via their device. For example, they might ask, "I don't know how to use a Python function."

[0229] Step 11:

[0230] The server receives the question, searches an internal database or external resources to find an appropriate answer, and sends the answer to the device. For example, it sends an answer such as "For the basics of Python functions, please see this explanation page." It also provides appropriate feedback based on the user's emotional state along with the answer to the question.

[0231] Step 12:

[0232] The device periodically records the user's learning progress and emotional state and transmits it to the server. Progress data is accumulated throughout the user's learning activities.

[0233] Step 13:

[0234] The server analyzes the progress data and emotional data and selects new learning content based on the user's current learning situation and emotional state. For example, if the progress reaches 50%, the server selects the content, "We recommend Data Analysis Course C as your next step."

[0235] Step 14:

[0236] The server selects new learning content and sends it to the device along with advice on how to study based on the user's emotional state. The device displays this information to the user and suggests the next learning step. The user can then use the new learning content to further improve their skills.

[0237] In this way, through a series of processing steps, optimal learning support can be provided based on the user's learning needs and emotional state.

[0238] Example 2

[0239] 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."

[0240] Conventional learning support systems have difficulty accurately grasping a user's learning needs and emotional state and providing optimal learning content and feedback based on the results. Furthermore, they lack mechanisms for flexibly responding to diverse user needs, such as suggesting new content based on learning progress or providing immediate responses to questions during learning. To address these issues, a system is needed that can analyze a user's learning needs and emotional state in real time and provide optimal learning content and feedback based on that analysis.

[0241] 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.

[0242] In this invention, the server includes means for analyzing the user's learning needs and saving them in a database, means for recording the user's learning progress and emotional state and sending them to the server, and means for selecting new learning content and feedback based on the user's learning progress and emotional state and sending them to the terminal, thereby enabling optimal learning support based on the user's learning needs and emotional state.

[0243] "User" refers to an individual who accesses the system, inputs their learning needs and emotional state, and uses the learning content.

[0244] "Terminal" refers to a device used by a user to access the system, such as a smartphone, tablet, or PC.

[0245] "Server" refers to a central processing unit that analyzes information received from users, stores it in a database, selects learning content, provides feedback, and so on.

[0246] "Learning needs" refers to the skills or areas of knowledge a user wishes to improve and the specific requests and desires associated with them.

[0247] "Emotional state" refers to the user's current psychological and emotional state, which is analyzed based on audio and video data.

[0248] "Database" refers to an information storage system for saving and managing analysis results, such as the user's learning needs and emotional state.

[0249] "Learning content" refers to learning materials and information provided to users for learning purposes, including, for example, online courses and specialized books.

[0250] "Feedback" refers to advice, encouragement, and motivational comments provided based on the user's learning progress and emotional state.

[0251] "Text analysis" refers to the process of analyzing text data entered by a user to identify learning needs.

[0252] A "machine learning algorithm" refers to a computational method for learning from large amounts of data and making predictions and classifications.

[0253] An "emotion engine" refers to software that analyzes a user's audio and video data to identify their emotional state.

[0254] "Progress information" refers to the progress a user makes as they progress through their studies, and includes, for example, the percentage of content that has been studied and the steps that have been achieved.

[0255] MODE FOR CARRYING OUT THE INVENTION

[0256] The present invention provides a system that allows users to select optimal learning content based on their own learning needs and emotional state, thereby improving their skills efficiently. Detailed embodiments of the system will be described below.

[0257] First, a user accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information such as name, email address, and password, and submits it. The server checks the received information against the database. If the user is a new user, the server saves the information in the database, and if the user is an existing user, it performs authentication. If authentication is successful, the user is able to access the system.

[0258] Next, the server generates initial questions for the registered or logged-in user to elicit their learning needs and sends them to the terminal. The terminal displays these questions, and the user answers them. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user's answers are sent from the terminal to the server.

[0259] The server analyzes the user's response data using text analysis and machine learning algorithms, and this analysis identifies the user's individual learning needs. The server also runs an emotion engine that analyzes the user's emotional state based on audio and video data. This emotion engine uses APIs from common cloud services, such as Microsoft and Google APIs. The analysis results are stored in a database.

[0260] The server selects optimal learning content based on the user's learning needs and emotional state, which are stored in a database. The selected learning content (e.g., information on online courses or specialized books) is sent to the terminal and suggested to the user. For example, "Python programming introductory course A" and "beginner-oriented specialized book B" may be selected. Motivational content and feedback are also provided based on the user's emotional state.

[0261] As the user progresses through the learning process using the suggested learning content, the device records their progress and emotional state and sends it to the server. If the user asks a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page." The system also analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[0262] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes the progress data and emotional data, selects new learning content based on the user's current learning situation, and sends new suggestions to the device. For example, if progress reaches 50%, the server will suggest, "We recommend Data Analysis Course C as your next step." It also provides advice on appropriate learning methods based on the user's emotional state.

[0263] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," as well as the user's emotional state, in a database. The server then recommends "online course A for beginners" and "specialized book B for beginners" to the terminal. As the user progresses through their studies using these learning materials, the emotion engine sequentially analyzes the user's emotional state and provides advice to improve motivation as needed. If a question arises, the server suggests an appropriate explanation page. Furthermore, when the user has progressed 50%, it suggests "data analysis course C" as the next step.

[0264] This system provides learning support tailored to the user's needs and emotional state, allowing them to improve their skills efficiently.

[0265] Prompt Sentence Examples

[0266] 1. "Enter your name and email address to create an account."

[0267] 2. "In what areas would you like to improve your skills?"

[0268] 3. "Please describe your current emotional state."

[0269] 4. "I recommend Course A, an introductory course on Python programming, and Book B, a specialized book for beginners."

[0270] 5. "I have a question about Python functions."

[0271] 6. "Why not take Course C in Data Analysis as your next step?"

[0272] In this way, users can receive optimal learning content and feedback based on their own learning progress and emotional state.

[0273] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0274] The flow of this system's program processing

[0275] Step 1: User registration and login

[0276] Input: Name, email address, and password entered by the user on the device

[0277] Output: User authentication result (authentication success / failure)

[0278] Specific description:

[0279] The terminal displays a registration / login screen to the user. The user enters their name, email address, and password and presses the submit button. The terminal sends the entered information to the server via an HTTP POST request. The server checks the received information against its database. If the user is a new user, the server saves the information in the database; if the user is an existing user, the server authenticates them. If authentication is successful, the user is allowed to access the system.

[0280] Specific behavior:

[0281] The terminal displays the form and receives input from the user.

[0282] The terminal transmits the input data to the server.

[0283] The server checks the user information against the database and returns the results to the terminal.

[0284] Step 2: Initial interactive session

[0285] Input: Initial setup questions sent by the server

[0286] Output: User response data

[0287] Specific description:

[0288] The server generates initial setup questions for the logged-in user and sends them to the device. The device displays these questions on the screen, and the user answers them. For example, questions include "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user's answers are sent from the device to the server.

[0289] Specific behavior:

[0290] The server generates question data and sends it to the terminal in JSON format.

[0291] The terminal displays questions and collects answers from the user.

[0292] The terminal transmits the user's answer to the server.

[0293] Step 3: Data analysis and storage

[0294] Input: User response data and emotion data

[0295] Output: Learning needs analysis and emotional state identification

[0296] Specific description:

[0297] The server analyzes the user's response data using text analysis and machine learning algorithms. This analysis identifies the user's learning needs. The server also uses an emotion engine to analyze the user's audio and video data to identify their emotional state. The server then stores the results of these analyses in a database.

[0298] Specific behavior:

[0299] The server analyzes the response data using morphological analysis and machine learning models.

[0300] An emotion engine is used to identify emotional states from audio and video data.

[0301] The analysis results are saved in a database.

[0302] Step 4: Suggest learning content

[0303] Input: Learning needs and emotional states stored in a database

[0304] Output: Selection of optimal learning content

[0305] Specific description:

[0306] The server selects the most appropriate learning content based on the user's learning needs and emotional state, which are stored in a database. The server then sends the selected learning content to the terminal and suggests it to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" may be suggested. Feedback is also provided to improve motivation.

[0307] Specific behavior:

[0308] The server obtains the user's learning needs and emotional state from a database.

[0309] Use an algorithm to select the best learning content.

[0310] The selected content information is sent to the terminal in JSON format.

[0311] The terminal displays the information on the screen.

[0312] Step 5: Learning support

[0313] Input: Learning progress information, emotional state, user questions

[0314] Output: Record of learning progress information, answers to questions

[0315] Specific description:

[0316] As the user progresses through the learning process using the suggested learning content, the device records learning progress information and emotional state and sends them to the server. If the user has a question, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question like "I don't know how to use a Python function," the server responds with "Please see this explanation page." The device also analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[0317] Specific behavior:

[0318] The device periodically transmits learning progress information and emotional state to the server.

[0319] The user enters a question and the terminal sends it to the server.

[0320] The server retrieves the answer and sends it to the terminal, which displays it.

[0321] Step 6: Progress management and new proposals

[0322] Input: Learning progress information, emotional state

[0323] Output: New learning content suggestions

[0324] Specific description:

[0325] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes this data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server will suggest "We recommend Data Analysis Course C as your next step." The server also provides advice on appropriate learning methods based on the user's emotional state.

[0326] Specific behavior:

[0327] The device periodically transmits learning progress data and emotional state to the server.

[0328] The server analyzes this data and selects new learning content.

[0329] The server sends the proposal in JSON format to the device, which displays it on the screen.

[0330] This process allows users to receive optimal learning content and feedback based on their own learning progress and emotional state.

[0331] (Application example 2)

[0332] 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."

[0333] Conventional learning support systems have had difficulty providing learning content that takes into account the user's learning needs as well as their emotional state at any given time. It has also been difficult to provide advice to improve motivation based on the user's emotional state, making it impossible to maximize learning efficiency. Furthermore, it has been insufficient to utilize generative AI models related to dynamic learning content suggestions based on the user's learning needs and emotional state.

[0334] The identification process performed by the identification 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 analyzing the user's learning needs and storing them in a database, means for selecting optimal learning content based on the analysis results and sending it to the terminal, and means for analyzing the user's emotional state and providing advice to improve motivation. This makes it possible to provide optimal learning content based on the user's learning progress and emotional state.

[0335] "User" refers to an individual who uses this system.

[0336] "Device" refers to an electronic device used by a user to access the system and receive learning content, including smartphones, tablets, and personal computers.

[0337] "Learning needs" refers to the skills and knowledge that a user wants to improve, as well as the desires and needs regarding learning content.

[0338] "Server" refers to a computer system that centrally processes data, manages databases, and analyzes users' learning needs and progress information.

[0339] "Analysis" refers to the processing and understanding of the learning needs and emotional state data collected by the server from the user.

[0340] A "database" is an information storage system for storing and managing data such as a user's learning needs, progress information, and emotional state.

[0341] "Learning content" refers to information resources provided to assist users in their learning, including online courses, specialized books, videos, and the like.

[0342] "Emotional state" refers to the user's current psychological and emotional state, including stress level and motivation during learning.

[0343] "Motivational advice" refers to suggestions to encourage and motivate the user to continue learning based on their emotional state.

[0344] "Progress" refers to the degree to which a user has progressed through the learning content.

[0345] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to incorporate algorithms that dynamically generate content suggestions based on the user's learning needs and emotional state.

[0346] "Prompt" refers to the input or instructions used by a generative AI model to generate a desired output.

[0347] A system embodying the present invention provides optimal learning content based on a user's learning needs and emotional state. Specific embodiments of the system will be described below.

[0348] First, a user accesses the system using a device such as a smartphone. The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and submits it. The server stores the received information in a database and performs authentication. If authentication is successful, the user is able to access the system.

[0349] Next, the server generates questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, they include questions such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions through the device. The server receives the answer data and analyzes it. This analysis uses text analysis libraries (e.g., TextBlob) and machine learning algorithms.

[0350] Furthermore, the server runs an emotion engine that analyzes the user's emotional state. The emotion engine analyzes the user's audio and video data to identify the user's current emotional state. This allows the user's learning progress and emotional state to be stored in a database.

[0351] The server uses a generative AI model to suggest optimal learning content based on the user's learning needs and emotional state stored in a database. The generative AI model creates prompts based on the user's needs and selects and provides optimal content based on those prompts. For example, it creates a prompt recommending "Python Programming Introductory Course A" and suggests that course to the user.

[0352] The device displays suggested learning content to the user. As the user uses this learning content to study, the device records learning progress information and sends it to the server. At the same time, the server analyzes the progress data and responds to questions the user may have along the way. The server receives the questions, searches for related learning content or explanation pages, and sends them back to the device.

[0353] The server also periodically analyzes the user's emotional state and learning progress and provides advice to improve motivation, again based on prompts generated by a generative AI model.

[0354] As a concrete example, if a beginner programmer registers the learning need of "I want to learn Python programming," the server analyzes the user's response to the question, "In what field do you want to improve your skills?" If the result of the sentiment analysis is positive, the server will suggest "Python programming introductory course A" and "specialized book B for beginners." If the emotional state is negative, the server will suggest video C to improve motivation.

[0355] An example of a prompt is:

[0356] "Suggest the best learning content for users based on their learning needs:

[0357] Learning Needs: Python Programming, Current Emotional State: Positive"

[0358] This prompt is then fed into a generative AI model to suggest optimal learning content.

[0359] In this way, a system that maximizes the user's learning efficiency is realized.

[0360] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0361] Step 1:

[0362] A user accesses the learning platform using a terminal. The user enters the required information such as name, email address, and password to register or log in. The input data is sent from the terminal to the server, which stores it in a database or authenticates it. If the login is successful, the server allows the user to access the system. The input data is user information (name, email address, password, etc.), and the output is the authentication result (success or failure).

[0363] Step 2:

[0364] The server generates initial questions to elicit the user's learning needs. For example, questions such as "In what areas do you want to improve your skills?" or "How much time can you devote to learning?" are generated and sent to the device. The user answers these questions and sends them back to the server via the device. The input data are the user's answers (learning needs, time available for learning, etc.), and the output is the saved answer data.

[0365] Step 3:

[0366] The server analyzes the response data received from the user using a text analysis library (e.g., TextBlob) and machine learning algorithms to identify learning needs. At the same time, the server runs an emotion engine that analyzes the user's audio and video data to identify their current emotional state. The resulting data, which represent the user's learning needs and emotional state, are stored in a database. The input data are the user's responses and audio / video data, and the output is the analysis results (learning needs and emotional state).

[0367] Step 4:

[0368] The server utilizes a generative AI model to select optimal learning content based on the user's learning needs and emotional state stored in a database. A prompt (e.g., "Please suggest optimal learning content for the user based on the following learning needs: Learning need: Python programming, Current emotional state: Positive") is input to the generative AI model, which then suggests optimal learning content. The output suggestions are then sent to the device. The input data is the prompt, and the output is learning content suggestions made by the generative AI model.

[0369] Step 5:

[0370] The device displays the suggested learning content to the user, who then uses the displayed learning content (e.g., an introductory course A on Python programming or a specialized book B for beginners) to advance their learning. The input data is the suggested learning content, and the output is the content displayed to the user.

[0371] Step 6:

[0372] As the user continues to study, the device records learning progress information and periodically sends it to the server. The learning progress information includes data on how far the user has progressed in their studies. In addition, if the user enters a question while studying, the device sends the question to the server. The input data is the learning progress information and the question content, and the output is data sent to the server.

[0373] Step 7:

[0374] The server receives the user's learning progress information and question content, searches for appropriate answers and explanations, and sends them back to the device. It also analyzes the progress information and emotional state to suggest new learning content and provide advice to improve motivation. Utilizing a generative AI model, it generates optimal advice based on the prompt text. The input data is learning progress, question content, and emotional state, and the output is suggested answers and advice.

[0375] Step 8:

[0376] The terminal displays the answers and advice from the server to the user, who can refer to them and continue learning. The input data are the answers and advice received from the server, and the output is the information displayed to the user.

[0377] This system makes it possible to provide optimal learning support that takes into account the user's learning needs and emotional state.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] [Second embodiment]

[0382] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0383] 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.

[0384] 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).

[0385] 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.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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."

[0394] This invention is a system that allows users to select optimal learning content based on their own learning needs and efficiently improve their skills. Next, a specific embodiment for implementing this system will be described.

[0395] 1. User Registration / Login

[0396] A user first accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and sends it to the server. The server checks the received information against a database and performs authentication. If authentication is successful, the user is allowed to access the system.

[0397] 2. Initial Interactive Session

[0398] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their terminals. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions through their terminal, and the terminal sends the answers to the server.

[0399] 3. Data analysis and accumulation

[0400] The server receives the user's response data and analyzes it using text analysis and machine learning algorithms. This analysis identifies the user's individual learning needs and stores the results in a database. For example, if a user responds, "I want to learn Python programming," the server registers that need in the database.

[0401] 4. Learning content suggestions

[0402] The server selects the most appropriate learning content based on the user's learning needs stored in the database. The selected learning content (e.g., online courses or specialized book information) is sent to the terminal and suggested to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" are displayed to the user.

[0403] 5. Learning support

[0404] As the user progresses through the learning process using the suggested learning content, the device records their progress. If the user has a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page."

[0405] 6. Progress management and new proposals

[0406] The device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. It then sends new suggestions to the device. For example, if progress reaches 50%, the server will suggest, "As your next step, we recommend Data Analysis Course C."

[0407] Specific examples

[0408] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," in the database. The server then recommends "online course A for beginners" and "specialized book B for beginners" to the terminal. As the user progresses with these learning materials, if the user sends a question about how to use a function from the terminal to the server, the server will suggest an appropriate explanation page. Furthermore, when the user's progress reaches 50%, the server will suggest "data analysis course C" as the next step.

[0409] This system provides learning support tailored to the individual needs of users, allowing them to improve their skills efficiently.

[0410] The processing flow will be explained below.

[0411] Step 1:

[0412] A user accesses the system via a terminal. The terminal displays a registration / login screen to the user. Here, the user enters their name, email address, password, etc., and presses the submit button.

[0413] Step 2:

[0414] The terminal sends the entered information to the server. The server checks the received information against the database, and stores the information in the database if it is a new registration, or performs authentication if it is an existing user.

[0415] Step 3:

[0416] The server sends the authentication result to the terminal. If the authentication is successful, the user can access the system and proceed to the next step. If the authentication is unsuccessful, an error message is displayed.

[0417] Step 4:

[0418] The server generates initial questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, the questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to learning?"

[0419] Step 5:

[0420] The user answers questions through the device. For example, they answer "I want to learn Python programming." The device then sends the user's answers to the server.

[0421] Step 6:

[0422] The server analyzes the received response data, uses text analysis and machine learning algorithms to identify the user's learning needs, and stores the results in a database.

[0423] Step 7:

[0424] The server selects the most suitable learning content based on the analysis results. For example, "Online Course A for Beginners" and "Specialized Book B for Beginners" may be selected. The selected learning content is then sent to the device.

[0425] Step 8:

[0426] The device displays the learning content selected by the user, and the user begins learning by viewing the recommended learning content.

[0427] Step 9:

[0428] If a user has a question about their learning as they proceed, they can send it to the server via their device. For example, they might ask, "I don't know how to use a Python function."

[0429] Step 10:

[0430] The server receives the question, searches an internal database or external resources to find the appropriate answer, and sends the answer to the terminal. For example, it sends a response such as "For the basics of Python functions, please see this explanation page."

[0431] Step 11:

[0432] The device periodically records the user's learning progress information and sends it to the server, such as the learning progress status and information on completed assignments.

[0433] Step 12:

[0434] The server analyzes the learning progress data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server may select content such as "We recommend Data Analysis Course C as the next step."

[0435] Step 13:

[0436] The server sends the selected new learning content to the device, which displays it to the user and suggests the next learning step. The user can then use the new learning content to further improve their skills.

[0437] In this way, through a series of processing steps, it is possible to provide optimal learning support tailored to the user's learning needs.

[0438] Example 1

[0439] 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."

[0440] Existing learning systems have difficulty providing optimal learning content that meets individual user needs, making it difficult to efficiently improve skills. They also lack the means to quickly respond to questions that arise during learning, making it impossible to provide appropriate learning support. Furthermore, they lack the flexibility to suggest new content based on learning progress.

[0441] 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.

[0442] In this invention, the server includes: a means for a user to input learning needs via a terminal; a means for identifying learning needs using text analysis or machine learning algorithms and storing them in a database; a means for selecting optimal learning content based on the analysis results and transmitting it to the terminal; a means for the terminal to display the learning content selected by the user; a means for recording the user's learning progress and transmitting it to the server; a means for selecting new learning content based on the user's learning progress and transmitting it to the terminal; a means for the user to input questions via the terminal while learning; a means for receiving questions from the user, searching for corresponding answers from a database or external resources, and returning them to the terminal; a means for using a generative AI model through an initial dialogue session to generate questions to elicit the user's learning needs; and a means for periodically transmitting progress information to the server and analyzing the progress data to select new learning content. This enables the server to provide optimal learning content tailored to the user's individual needs and efficiently improve skills. It also enables the server to quickly respond to questions during learning and provide appropriate learning support. Furthermore, it can flexibly suggest new content according to the user's learning progress.

[0443] "Terminal" refers to the device that a user uses to access and operate the system, such as a smartphone, tablet, or PC.

[0444] "Server" refers to the central computer that manages the entire system and provides learning content and answers to user inputs and requests.

[0445] "Database" refers to a collection of data for storing and managing users' learning needs, progress information, and related learning content.

[0446] "Learning needs" refers to the demands and requirements for knowledge and skills that a user wants to acquire.

[0447] "Text analysis" refers to a method of analyzing input data from a user using natural language processing techniques.

[0448] A "machine learning algorithm" refers to a computational method for learning specific patterns and rules from data and using them to make predictions and classifications.

[0449] "Learning content" refers to the learning materials and resources provided to users for learning, such as online courses and specialized books.

[0450] "Progress Information" refers to data that indicates how much a user has learned and how far they have progressed using the learning content.

[0451] A "generative AI model" refers to an artificial intelligence model that generates appropriate questions and answers based on user input data.

[0452] "Answer" refers to appropriate information or explanation provided in response to a user's question.

[0453] "Questions" refer to questions or things that users want to confirm while studying.

[0454] The present invention is a system that allows users to select optimal learning content based on their own learning needs and efficiently improve their skills. Specific aspects of the system are described below.

[0455] First, a user accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user through the system's website or application. The user enters the required information (name, email address, password, etc.) and sends it to the server.

[0456] The server checks the received information against a database (for example, MySQL or PostgreSQL) and performs authentication. If authentication is successful, the user is allowed to access the system, and the server generates a session ID and sends it to the terminal.

[0457] Next, the server uses the generative AI model to generate a set of questions to elicit learning needs and sends them to the device. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions and sends the answers to the server via the device.

[0458] The server receives the user's response data and analyzes it using text analysis tools (e.g., NLTK or SpaCy) or machine learning algorithms (e.g., Scikit-learn or TensorFlow). This analysis identifies the user's individual learning needs and stores the results in a database. For example, if the user responds, "I want to learn Python programming," the server registers that need in the database.

[0459] Next, the server selects the most suitable learning content based on the user's learning needs stored in the database. For example, information such as "Online Course A" or "Specialized Book B" may be selected. The server then sends these selection results to the terminal, which then displays the selected learning content to the user.

[0460] As the user progresses through the learning process using the suggested learning content, the device records their progress. If a question arises during the learning process, the user enters it via the device, which then sends it to the server. The server receives the question, searches a database or external resources to generate an appropriate answer, and sends it back to the device. For example, in response to a question such as "I don't know how to use a Python function," the server suggests a related explanation page.

[0461] Additionally, the device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. When progress reaches 50%, the server makes suggestions such as recommending "Data Analysis Course C as the next step."

[0462] This invention provides optimal learning content tailored to the individual needs of users, enabling them to efficiently improve their skills. It also responds quickly to questions that arise during learning and provides appropriate learning support. Furthermore, it also makes it possible to flexibly suggest content according to the user's learning progress, making it a very beneficial system for learners.

[0463] Example prompts to input to the generative AI model

[0464] "What online courses would you recommend for beginners who want to learn Python programming?"

[0465] "What learning content would you recommend as the next step for a user who is currently 50% complete?"

[0466] "Please suggest a page that explains how to use Python functions."

[0467] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0468] Step 1:

[0469] A user accesses the system using a terminal. The terminal displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and sends it to the server. The server checks the entered information against the database and creates a record in the database if the user is a new user. If the user is already registered, it authenticates the entered password. If authentication is successful, the server generates a session ID and sends it to the terminal. The terminal receives the session ID and displays the main screen.

[0470] Step 2:

[0471] After a user successfully registers or logs in, the server generates a set of questions to start an initial dialogue session. These questions are automatically generated using a generative AI model. For example, they include questions such as, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The server sends these questions to the device, which displays them to the user. The user answers the questions and sends the answers to the server via the device.

[0472] Step 3:

[0473] The server receives the user's response data and analyzes it using text analysis tools (e.g., NLTK or SpaCy) or machine learning algorithms (e.g., Scikit-learn or TensorFlow). The input data for the analysis is the user's response, and the output is the analysis result, which is the user's specific learning needs. For example, if the user's response is "I want to learn Python programming," the server stores that information in a database.

[0474] Step 4:

[0475] The server selects the most suitable learning content based on the user's learning needs stored in the database. In this process, a learning content selection algorithm is used. For example, learning resources such as "Online Course A" or "Specialized Book B" are selected. The selected learning content is sent from the server to the terminal, which then displays it to the user.

[0476] Step 5:

[0477] When a user starts learning using the suggested learning content, the device records the learning progress. The input data is a record of the user's learning activities, and progress information is generated as output data. If the user has any questions while learning, they can input them via the device. The questions are sent to the server, which then receives them.

[0478] Step 6:

[0479] The server analyzes the question sent by the user and searches databases and external resources to find the appropriate answer. Search algorithms and AI models are used to generate the answer. For example, in response to a question such as "I don't know how to use a Python function," the server searches for a relevant explanation page and sends the link to the device. The device then displays the answer to the user.

[0480] Step 7:

[0481] The device periodically sends the user's learning progress information to the server. The server analyzes this progress data and evaluates the current learning situation. Based on the input progress information, an evaluation algorithm is run to select new learning content. For example, when progress reaches 50%, the server recommends "Data Analysis Course C as the next step." The selected new content is sent to the device and displayed to the user as a new suggestion.

[0482] (Application example 1)

[0483] 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."

[0484] Conventional learning systems required a lot of time and effort to respond to individual user needs, and the lack of automation in learning progress and question response made it difficult to improve skills efficiently.Furthermore, while there is a demand for rapid and accurate acquisition of the necessary skills in the operation of factory robots, conventional systems were inadequate in meeting this demand.

[0485] 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.

[0486] In this invention, the server includes: a means for a user to input their learning needs via a terminal; a means for the server to analyze the user's learning needs and store them in a database; a means for the server to select optimal learning content based on the analysis results and send it to the terminal; a means for the terminal to display the learning content selected by the user; a means for recording the user's learning progress and sending it to the server; a means for the server to select new learning content based on the user's learning progress and send it to the terminal; a means for generating optimal answers to questions from the user using a generative AI model and sending them to the terminal; and a means for generating optimal prompt sentences using the generative AI model based on the user's learning needs. This allows users to receive learning content tailored to their individual needs, efficiently manage their learning progress, and quickly respond to questions. It also allows users to efficiently acquire the necessary skills for operating factory robots, contributing to improved productivity.

[0487] "User" refers to a person who uses this system to study.

[0488] A "terminal" is a device used by a user to access the system, such as a smartphone, tablet, or PC.

[0489] "Learning needs" refers to the learning content and goals that users need to learn in order to improve their skills.

[0490] "Server" means a central processing unit for receiving and analyzing data from users and providing appropriate learning content.

[0491] A "database" is a collection of digital data that stores information about a user's learning needs and progress.

[0492] "Analysis" refers to the process of processing data obtained from users using machine learning algorithms and text analysis techniques to identify their learning needs.

[0493] "Learning content" refers to learning materials and resources selected by the server based on the user's learning needs.

[0494] A "generative AI model" is an algorithm or method that uses artificial intelligence to generate optimal answers or prompts to user questions.

[0495] A "prompt" is an instruction or suggestion that is generated by a generative AI model based on the user's learning needs to promote learning.

[0496] "Progress" refers to the learning progress of a user, which indicates how much of the suggested learning content they have completed.

[0497] An "answer" is a response or explanation provided by a server or a generative AI model in response to a user's question.

[0498] The present invention provides a system for enabling users to efficiently advance their learning and improve their skills, particularly in the operation and maintenance of factory robots. The system includes the following components:

[0499] User Registration / Login

[0500] Users first access the system using a device such as a smartphone, tablet, or PC, and then register and log in. Registration requires information such as name, email address, and password, and the server stores this information in a database and performs authentication. If authentication is successful, the user can access the system.

[0501] Initial Interactive Session

[0502] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their devices. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions via their device, and the answers are sent to the server.

[0503] Data analysis and accumulation

[0504] The server receives the user's response data and analyzes it using machine learning algorithms and text analysis. This analysis identifies the user's individual learning needs and stores the results in a database. For example, if a user responds, "I want to learn Python programming," the server registers that need in the database.

[0505] Learning content suggestions

[0506] The server selects the most suitable learning content based on the user's learning needs stored in a database. The selected learning content is sent to the terminal and suggested to the user. For example, "Introductory course on Python programming" or "Specialized books for beginners" are displayed.

[0507] Learning support and questions

[0508] As the user progresses through the learning process using the suggested learning content, the device records their progress. When the user asks a question, the device sends it to the server. The server receives the question, uses a generative AI model to generate the optimal answer, and sends it to the device. For example, in response to a question like "I don't know how to use a Python function," the server might respond with "Please see this explanation page."

[0509] Progress management and new proposals

[0510] The device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. For example, if progress reaches 50%, the server will suggest, "We recommend a data analysis course as your next step."

[0511] Specific examples and prompts for the generation AI

[0512] As a concrete example, imagine a user who has just become an operator of a new factory robot and wants to learn the basic operations. After logging in, the user asks, "Please tell me about an online course on basic robot operations," and the server uses the generative AI model to provide an answer such as, "I recommend this online course."

[0513] Example prompt sentence:

[0514] User: I just became the operator of a new factory robot. I would like to learn the basics of robot operation. What online courses should I take?

[0515] This system allows users to efficiently improve their skills through learning content tailored to their individual needs, and in particular enables them to quickly acquire skills in operating and maintaining factory robots.

[0516] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0517] Step 1:

[0518] A user accesses the system via a terminal and enters the required information (such as name, email address, and password) on the registration or login screen. The entered information is sent to the server, which stores it in a database and performs authentication processing. If successful, the user can access the system.

[0519] Input: User information (name, email address, password)

[0520] Processing: The server stores the user information in a database and performs authentication.

[0521] Output: Authentication success message and access to the system is allowed

[0522] Step 2:

[0523] After a user logs in, the server generates questions to elicit their learning needs and sends them to the device, such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?"

[0524] Input: User login status

[0525] Processing: The server generates questions about learning needs and sends them to the terminal.

[0526] Output: Learning Needs Questionnaire Form

[0527] Step 3:

[0528] Users answer questions about their learning needs through their devices, and the answers are sent from the device to the server. The server receives the answers and analyzes them using machine learning algorithms and text analysis methods. The server identifies the user's learning needs and stores the results in a database.

[0529] Input: User responses regarding learning needs

[0530] Processing: The server analyzes the response data using machine learning algorithms and text analysis methods to identify learning needs and store them in a database.

[0531] Output: Identified learning needs data

[0532] Step 4:

[0533] The server selects the most suitable learning content based on the user's learning needs stored in a database. The selected learning content is sent to the terminal and suggested to the user. For example, "Introductory course on Python programming" or "Specialized books for beginners" are displayed.

[0534] Input: Identified learning needs data

[0535] Processing: The server selects the most appropriate learning content based on the identified needs.

[0536] Output: Suggested learning content

[0537] Step 5:

[0538] As the user progresses through the suggested learning content, the device records their progress. When the user asks a question, the device sends it to the server, which uses a generative AI model to generate the optimal answer and sends it to the device.

[0539] Input: Learning progress information and user questions

[0540] Processing: The server uses the generative AI model to generate the optimal answer to the question and sends it to the device.

[0541] Output: Learning progress information and answers

[0542] Step 6:

[0543] The device periodically sends information about the user's learning progress to the server. The server analyzes this progress data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server will suggest, "We recommend a data analysis course as your next step."

[0544] Input: Learning progress information

[0545] Processing: The server analyzes the progress data and selects new learning content.

[0546] Output: New learning content suggestions

[0547] 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.

[0548] This invention provides a system that allows users to select optimal learning content based on their own learning needs and emotional state, and to efficiently improve their skills. Next, specific embodiments for implementing this system will be described.

[0549] 1. User Registration / Login

[0550] A user first accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and submits it. The server checks the received information against the database, and if it is a new registration, the information is saved in the database, or if it is an existing user, authentication is performed. If authentication is successful, the user is able to access the system.

[0551] 2. Initial Interactive Session

[0552] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their terminals. The terminals display these questions. For example, they include questions such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The users answer these questions through their terminals. The terminals then send the answers to the server.

[0553] 3. Data analysis and accumulation

[0554] The server receives the user's response data and analyzes it using text analysis and machine learning algorithms. This analysis identifies the user's individual learning needs and stores the results in a database. The server also runs an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's audio and video data to identify their current emotional state. The results are also stored in the database.

[0555] 4. Learning content suggestions

[0556] The server selects optimal learning content based on the user's learning needs and emotional state stored in a database. The selected learning content (e.g., information on online courses or specialized books) is sent to the terminal and suggested to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" are displayed to the user. In addition, content and feedback to improve motivation are also provided according to the user's emotional state.

[0557] 5. Learning support

[0558] As the user progresses through the learning process using the suggested learning content, the device records their progress and emotional state, and sends them to the server. If the user asks a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page." In addition, the system analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[0559] 6. Progress management and new proposals

[0560] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes the progress data and emotional data and selects new learning content based on the user's current learning situation. It then sends new suggestions to the device. For example, if progress reaches 50%, the server might suggest, "We recommend Data Analysis Course C as your next step." The server also provides advice on appropriate learning methods based on the user's emotional state.

[0561] Specific examples

[0562] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," as well as the user's emotional state in a database. The server then recommends "Online Course A for Beginners" and "Specialized Book B for Beginners" to the terminal. As the user progresses through their studies using these learning materials, the emotion engine sequentially analyzes the user's emotional state and provides advice to improve motivation as needed. If a question arises, the server suggests an appropriate explanation page. Furthermore, when the user has progressed 50%, it suggests "Data Analysis Course C" as the next step.

[0563] This system provides learning support tailored to the user's needs and emotional state, allowing them to improve their skills efficiently.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] A user accesses the system through a terminal. The terminal displays a registration / login screen to the user. The user enters the required information such as name, email address, and password, and presses the submit button.

[0567] Step 2:

[0568] The device sends the entered information to the server, which then checks the received information against the database, saving the information in the database if it is a new registration, or authenticating the user if they are already registered.

[0569] Step 3:

[0570] The server sends the authentication result to the terminal. If the authentication is successful, the user can access the system. If the authentication is unsuccessful, an error message is displayed.

[0571] Step 4:

[0572] The server generates initial questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, the questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to learning?"

[0573] Step 5:

[0574] The user answers questions through the device. For example, they answer "I want to learn Python programming." The device then sends the user's answers to the server.

[0575] Step 6:

[0576] The server analyzes the received response data, uses text analysis and machine learning algorithms to identify the user's learning needs, and stores the results in a database.

[0577] Step 7:

[0578] The server receives the user's audio and video data, analyzes it using an emotion engine, and identifies the user's current emotional state, which is also stored in a database.

[0579] Step 8:

[0580] The server selects the most suitable learning content based on the analysis results. For example, "Online Course A for Beginners" and "Specialized Book B for Beginners" may be selected. The selected learning content is then sent to the device.

[0581] Step 9:

[0582] The device displays the learning content selected by the user. The user then begins learning by viewing the recommended learning content. Motivational content tailored to the user's emotional state is also displayed on the device.

[0583] Step 10:

[0584] If a user has a question about their learning as they proceed, they can send it to the server via their device. For example, they might ask, "I don't know how to use a Python function."

[0585] Step 11:

[0586] The server receives the question, searches an internal database or external resources to find an appropriate answer, and sends the answer to the device. For example, it sends an answer such as "For the basics of Python functions, please see this explanation page." It also provides appropriate feedback based on the user's emotional state along with the answer to the question.

[0587] Step 12:

[0588] The device periodically records the user's learning progress and emotional state and transmits it to the server. Progress data is accumulated throughout the user's learning activities.

[0589] Step 13:

[0590] The server analyzes the progress data and emotional data and selects new learning content based on the user's current learning situation and emotional state. For example, if the progress reaches 50%, the server selects the content, "We recommend Data Analysis Course C as your next step."

[0591] Step 14:

[0592] The server selects new learning content and sends it to the device along with advice on how to study based on the user's emotional state. The device displays this information to the user and suggests the next learning step. The user can then use the new learning content to further improve their skills.

[0593] In this way, through a series of processing steps, optimal learning support can be provided based on the user's learning needs and emotional state.

[0594] Example 2

[0595] 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."

[0596] Conventional learning support systems have difficulty accurately grasping a user's learning needs and emotional state and providing optimal learning content and feedback based on the results. Furthermore, they lack mechanisms for flexibly responding to diverse user needs, such as suggesting new content based on learning progress or providing immediate responses to questions during learning. To address these issues, a system is needed that can analyze a user's learning needs and emotional state in real time and provide optimal learning content and feedback based on that analysis.

[0597] 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.

[0598] In this invention, the server includes means for analyzing the user's learning needs and saving them in a database, means for recording the user's learning progress and emotional state and sending them to the server, and means for selecting new learning content and feedback based on the user's learning progress and emotional state and sending them to the terminal, thereby enabling optimal learning support based on the user's learning needs and emotional state.

[0599] "User" refers to an individual who accesses the system, inputs their learning needs and emotional state, and uses the learning content.

[0600] "Terminal" refers to a device used by a user to access the system, such as a smartphone, tablet, or PC.

[0601] "Server" refers to a central processing unit that analyzes information received from users, stores it in a database, selects learning content, provides feedback, and so on.

[0602] "Learning needs" refers to the skills or areas of knowledge a user wishes to improve and the specific requests and desires associated with them.

[0603] "Emotional state" refers to the user's current psychological and emotional state, which is analyzed based on audio and video data.

[0604] "Database" refers to an information storage system for saving and managing analysis results, such as the user's learning needs and emotional state.

[0605] "Learning content" refers to learning materials and information provided to users for learning purposes, including, for example, online courses and specialized books.

[0606] "Feedback" refers to advice, encouragement, and motivational comments provided based on the user's learning progress and emotional state.

[0607] "Text analysis" refers to the process of analyzing text data entered by a user to identify learning needs.

[0608] A "machine learning algorithm" refers to a computational method for learning from large amounts of data and making predictions and classifications.

[0609] An "emotion engine" refers to software that analyzes a user's audio and video data to identify their emotional state.

[0610] "Progress information" refers to the progress a user makes as they progress through their studies, and includes, for example, the percentage of content that has been studied and the steps that have been achieved.

[0611] MODE FOR CARRYING OUT THE INVENTION

[0612] The present invention provides a system that allows users to select optimal learning content based on their own learning needs and emotional state, thereby improving their skills efficiently. Detailed embodiments of the system will be described below.

[0613] First, a user accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information such as name, email address, and password, and submits it. The server checks the received information against the database. If the user is a new user, the server saves the information in the database, and if the user is an existing user, it performs authentication. If authentication is successful, the user is able to access the system.

[0614] Next, the server generates initial questions for the registered or logged-in user to elicit their learning needs and sends them to the terminal. The terminal displays these questions, and the user answers them. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user's answers are sent from the terminal to the server.

[0615] The server analyzes the user's response data using text analysis and machine learning algorithms, and this analysis identifies the user's individual learning needs. The server also runs an emotion engine that analyzes the user's emotional state based on audio and video data. This emotion engine uses APIs from common cloud services, such as Microsoft and Google APIs. The analysis results are stored in a database.

[0616] The server selects optimal learning content based on the user's learning needs and emotional state, which are stored in a database. The selected learning content (e.g., information on online courses or specialized books) is sent to the terminal and suggested to the user. For example, "Python programming introductory course A" and "beginner-oriented specialized book B" may be selected. Motivational content and feedback are also provided based on the user's emotional state.

[0617] As the user progresses through the learning process using the suggested learning content, the device records their progress and emotional state and sends it to the server. If the user asks a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page." The system also analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[0618] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes the progress data and emotional data, selects new learning content based on the user's current learning situation, and sends new suggestions to the device. For example, if progress reaches 50%, the server will suggest, "We recommend Data Analysis Course C as your next step." It also provides advice on appropriate learning methods based on the user's emotional state.

[0619] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," as well as the user's emotional state, in a database. The server then recommends "online course A for beginners" and "specialized book B for beginners" to the terminal. As the user progresses through their studies using these learning materials, the emotion engine sequentially analyzes the user's emotional state and provides advice to improve motivation as needed. If a question arises, the server suggests an appropriate explanation page. Furthermore, when the user has progressed 50%, it suggests "data analysis course C" as the next step.

[0620] This system provides learning support tailored to the user's needs and emotional state, allowing them to improve their skills efficiently.

[0621] Prompt Sentence Examples

[0622] 1. "Enter your name and email address to create an account."

[0623] 2. "In what areas would you like to improve your skills?"

[0624] 3. "Please describe your current emotional state."

[0625] 4. "I recommend Course A, an introductory course on Python programming, and Book B, a specialized book for beginners."

[0626] 5. "I have a question about Python functions."

[0627] 6. "Why not take Course C in Data Analysis as your next step?"

[0628] In this way, users can receive optimal learning content and feedback based on their own learning progress and emotional state.

[0629] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0630] The flow of this system's program processing

[0631] Step 1: User registration and login

[0632] Input: Name, email address, and password entered by the user on the device

[0633] Output: User authentication result (authentication success / failure)

[0634] Specific description:

[0635] The terminal displays a registration / login screen to the user. The user enters their name, email address, and password and presses the submit button. The terminal sends the entered information to the server via an HTTP POST request. The server checks the received information against its database. If the user is a new user, the server saves the information in the database; if the user is an existing user, the server authenticates them. If authentication is successful, the user is allowed to access the system.

[0636] Specific behavior:

[0637] The terminal displays the form and receives input from the user.

[0638] The terminal transmits the input data to the server.

[0639] The server checks the user information against the database and returns the results to the terminal.

[0640] Step 2: Initial interactive session

[0641] Input: Initial setup questions sent by the server

[0642] Output: User response data

[0643] Specific description:

[0644] The server generates initial setup questions for the logged-in user and sends them to the device. The device displays these questions on the screen, and the user answers them. For example, questions include "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user's answers are sent from the device to the server.

[0645] Specific behavior:

[0646] The server generates question data and sends it to the terminal in JSON format.

[0647] The terminal displays questions and collects answers from the user.

[0648] The terminal transmits the user's answer to the server.

[0649] Step 3: Data analysis and storage

[0650] Input: User response data and emotion data

[0651] Output: Learning needs analysis and emotional state identification

[0652] Specific description:

[0653] The server analyzes the user's response data using text analysis and machine learning algorithms. This analysis identifies the user's learning needs. The server also uses an emotion engine to analyze the user's audio and video data to identify their emotional state. The server then stores the results of these analyses in a database.

[0654] Specific behavior:

[0655] The server analyzes the response data using morphological analysis and machine learning models.

[0656] An emotion engine is used to identify emotional states from audio and video data.

[0657] The analysis results are saved in a database.

[0658] Step 4: Suggest learning content

[0659] Input: Learning needs and emotional states stored in a database

[0660] Output: Selection of optimal learning content

[0661] Specific description:

[0662] The server selects the most appropriate learning content based on the user's learning needs and emotional state, which are stored in a database. The server then sends the selected learning content to the terminal and suggests it to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" may be suggested. Feedback is also provided to improve motivation.

[0663] Specific behavior:

[0664] The server obtains the user's learning needs and emotional state from a database.

[0665] Use an algorithm to select the best learning content.

[0666] The selected content information is sent to the terminal in JSON format.

[0667] The terminal displays the information on the screen.

[0668] Step 5: Learning support

[0669] Input: Learning progress information, emotional state, user questions

[0670] Output: Record of learning progress information, answers to questions

[0671] Specific description:

[0672] As the user progresses through the learning process using the suggested learning content, the device records learning progress information and emotional state and sends them to the server. If the user has a question, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question like "I don't know how to use a Python function," the server responds with "Please see this explanation page." The device also analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[0673] Specific behavior:

[0674] The device periodically transmits learning progress information and emotional state to the server.

[0675] The user enters a question and the terminal sends it to the server.

[0676] The server retrieves the answer and sends it to the terminal, which displays it.

[0677] Step 6: Progress management and new proposals

[0678] Input: Learning progress information, emotional state

[0679] Output: New learning content suggestions

[0680] Specific description:

[0681] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes this data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server will suggest "We recommend Data Analysis Course C as your next step." The server also provides advice on appropriate learning methods based on the user's emotional state.

[0682] Specific behavior:

[0683] The device periodically transmits learning progress data and emotional state to the server.

[0684] The server analyzes this data and selects new learning content.

[0685] The server sends the proposal in JSON format to the device, which displays it on the screen.

[0686] This process allows users to receive optimal learning content and feedback based on their own learning progress and emotional state.

[0687] (Application example 2)

[0688] 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."

[0689] Conventional learning support systems have had difficulty providing learning content that takes into account the user's learning needs as well as their emotional state at any given time. It has also been difficult to provide advice to improve motivation based on the user's emotional state, making it impossible to maximize learning efficiency. Furthermore, it has been insufficient to utilize generative AI models related to dynamic learning content suggestions based on the user's learning needs and emotional state.

[0690] The identification process performed by the identification 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 analyzing the user's learning needs and storing them in a database, means for selecting optimal learning content based on the analysis results and sending it to the terminal, and means for analyzing the user's emotional state and providing advice to improve motivation. This makes it possible to provide optimal learning content based on the user's learning progress and emotional state.

[0691] "User" refers to an individual who uses this system.

[0692] "Device" refers to an electronic device used by a user to access the system and receive learning content, including smartphones, tablets, and personal computers.

[0693] "Learning needs" refers to the skills and knowledge that a user wants to improve, as well as the desires and needs regarding learning content.

[0694] "Server" refers to a computer system that centrally processes data, manages databases, and analyzes users' learning needs and progress information.

[0695] "Analysis" refers to the processing and understanding of the learning needs and emotional state data collected by the server from the user.

[0696] A "database" is an information storage system for storing and managing data such as a user's learning needs, progress information, and emotional state.

[0697] "Learning content" refers to information resources provided to assist users in their learning, including online courses, specialized books, videos, and the like.

[0698] "Emotional state" refers to the user's current psychological and emotional state, including stress level and motivation during learning.

[0699] "Motivational advice" refers to suggestions to encourage and motivate the user to continue learning based on their emotional state.

[0700] "Progress" refers to the degree to which a user has progressed through the learning content.

[0701] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to incorporate algorithms that dynamically generate content suggestions based on the user's learning needs and emotional state.

[0702] "Prompt" refers to the input or instructions used by a generative AI model to generate a desired output.

[0703] A system embodying the present invention provides optimal learning content based on a user's learning needs and emotional state. Specific embodiments of the system will be described below.

[0704] First, a user accesses the system using a device such as a smartphone. The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and submits it. The server stores the received information in a database and performs authentication. If authentication is successful, the user is able to access the system.

[0705] Next, the server generates questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, they include questions such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions through the device. The server receives the answer data and analyzes it. This analysis uses text analysis libraries (e.g., TextBlob) and machine learning algorithms.

[0706] Furthermore, the server runs an emotion engine that analyzes the user's emotional state. The emotion engine analyzes the user's audio and video data to identify the user's current emotional state. This allows the user's learning progress and emotional state to be stored in a database.

[0707] The server uses a generative AI model to suggest optimal learning content based on the user's learning needs and emotional state stored in a database. The generative AI model creates prompts based on the user's needs and selects and provides optimal content based on those prompts. For example, it creates a prompt recommending "Python Programming Introductory Course A" and suggests that course to the user.

[0708] The device displays suggested learning content to the user. As the user uses this learning content to study, the device records learning progress information and sends it to the server. At the same time, the server analyzes the progress data and responds to questions the user may have along the way. The server receives the questions, searches for related learning content or explanation pages, and sends them back to the device.

[0709] The server also periodically analyzes the user's emotional state and learning progress and provides advice to improve motivation, again based on prompts generated by a generative AI model.

[0710] As a concrete example, if a beginner programmer registers the learning need of "I want to learn Python programming," the server analyzes the user's response to the question, "In what field do you want to improve your skills?" If the result of the sentiment analysis is positive, the server will suggest "Python programming introductory course A" and "specialized book B for beginners." If the emotional state is negative, the server will suggest video C to improve motivation.

[0711] An example of a prompt is:

[0712] "Suggest the best learning content for users based on their learning needs:

[0713] Learning Needs: Python Programming, Current Emotional State: Positive"

[0714] This prompt is then fed into a generative AI model to suggest optimal learning content.

[0715] In this way, a system that maximizes the user's learning efficiency is realized.

[0716] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0717] Step 1:

[0718] A user accesses the learning platform using a terminal. The user enters the required information such as name, email address, and password to register or log in. The input data is sent from the terminal to the server, which stores it in a database or authenticates it. If the login is successful, the server allows the user to access the system. The input data is user information (name, email address, password, etc.), and the output is the authentication result (success or failure).

[0719] Step 2:

[0720] The server generates initial questions to elicit the user's learning needs. For example, questions such as "In what areas do you want to improve your skills?" or "How much time can you devote to learning?" are generated and sent to the device. The user answers these questions and sends them back to the server via the device. The input data are the user's answers (learning needs, time available for learning, etc.), and the output is the saved answer data.

[0721] Step 3:

[0722] The server analyzes the response data received from the user using a text analysis library (e.g., TextBlob) and machine learning algorithms to identify learning needs. At the same time, the server runs an emotion engine that analyzes the user's audio and video data to identify their current emotional state. The resulting data, which represent the user's learning needs and emotional state, are stored in a database. The input data are the user's responses and audio / video data, and the output is the analysis results (learning needs and emotional state).

[0723] Step 4:

[0724] The server utilizes a generative AI model to select optimal learning content based on the user's learning needs and emotional state stored in a database. A prompt (e.g., "Please suggest optimal learning content for the user based on the following learning needs: Learning need: Python programming, Current emotional state: Positive") is input to the generative AI model, which then suggests optimal learning content. The output suggestions are then sent to the device. The input data is the prompt, and the output is learning content suggestions made by the generative AI model.

[0725] Step 5:

[0726] The device displays the suggested learning content to the user, who then uses the displayed learning content (e.g., an introductory course A on Python programming or a specialized book B for beginners) to advance their learning. The input data is the suggested learning content, and the output is the content displayed to the user.

[0727] Step 6:

[0728] As the user continues to study, the device records learning progress information and periodically sends it to the server. The learning progress information includes data on how far the user has progressed in their studies. In addition, if the user enters a question while studying, the device sends the question to the server. The input data is the learning progress information and the question content, and the output is data sent to the server.

[0729] Step 7:

[0730] The server receives the user's learning progress information and question content, searches for appropriate answers and explanations, and sends them back to the device. It also analyzes the progress information and emotional state to suggest new learning content and provide advice to improve motivation. Utilizing a generative AI model, it generates optimal advice based on the prompt text. The input data is learning progress, question content, and emotional state, and the output is suggested answers and advice.

[0731] Step 8:

[0732] The terminal displays the answers and advice from the server to the user, who can refer to them and continue learning. The input data are the answers and advice received from the server, and the output is the information displayed to the user.

[0733] This system makes it possible to provide optimal learning support that takes into account the user's learning needs and emotional state.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] [Third embodiment]

[0738] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0739] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0740] 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).

[0741] 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.

[0742] 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.

[0743] 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).

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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."

[0750] This invention is a system that allows users to select optimal learning content based on their own learning needs and efficiently improve their skills. Next, a specific embodiment for implementing this system will be described.

[0751] 1. User Registration / Login

[0752] A user first accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and sends it to the server. The server checks the received information against a database and performs authentication. If authentication is successful, the user is allowed to access the system.

[0753] 2. Initial Interactive Session

[0754] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their terminals. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions through their terminal, and the terminal sends the answers to the server.

[0755] 3. Data analysis and accumulation

[0756] The server receives the user's response data and analyzes it using text analysis and machine learning algorithms. This analysis identifies the user's individual learning needs and stores the results in a database. For example, if a user responds, "I want to learn Python programming," the server registers that need in the database.

[0757] 4. Learning content suggestions

[0758] The server selects the most appropriate learning content based on the user's learning needs stored in the database. The selected learning content (e.g., online courses or specialized book information) is sent to the terminal and suggested to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" are displayed to the user.

[0759] 5. Learning support

[0760] As the user progresses through the learning process using the suggested learning content, the device records their progress. If the user has a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page."

[0761] 6. Progress management and new proposals

[0762] The device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. It then sends new suggestions to the device. For example, if progress reaches 50%, the server will suggest, "As your next step, we recommend Data Analysis Course C."

[0763] Specific examples

[0764] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," in the database. The server then recommends "online course A for beginners" and "specialized book B for beginners" to the terminal. As the user progresses with these learning materials, if the user sends a question about how to use a function from the terminal to the server, the server will suggest an appropriate explanation page. Furthermore, when the user's progress reaches 50%, the server will suggest "data analysis course C" as the next step.

[0765] This system provides learning support tailored to the individual needs of users, allowing them to improve their skills efficiently.

[0766] The processing flow will be explained below.

[0767] Step 1:

[0768] A user accesses the system via a terminal. The terminal displays a registration / login screen to the user. Here, the user enters their name, email address, password, etc., and presses the submit button.

[0769] Step 2:

[0770] The terminal sends the entered information to the server. The server checks the received information against the database, and stores the information in the database if it is a new registration, or performs authentication if it is an existing user.

[0771] Step 3:

[0772] The server sends the authentication result to the terminal. If the authentication is successful, the user can access the system and proceed to the next step. If the authentication is unsuccessful, an error message is displayed.

[0773] Step 4:

[0774] The server generates initial questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, the questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to learning?"

[0775] Step 5:

[0776] The user answers questions through the device. For example, they answer "I want to learn Python programming." The device then sends the user's answers to the server.

[0777] Step 6:

[0778] The server analyzes the received response data, uses text analysis and machine learning algorithms to identify the user's learning needs, and stores the results in a database.

[0779] Step 7:

[0780] The server selects the most suitable learning content based on the analysis results. For example, "Online Course A for Beginners" and "Specialized Book B for Beginners" may be selected. The selected learning content is then sent to the device.

[0781] Step 8:

[0782] The device displays the learning content selected by the user, and the user begins learning by viewing the recommended learning content.

[0783] Step 9:

[0784] If a user has a question about their learning as they proceed, they can send it to the server via their device. For example, they might ask, "I don't know how to use a Python function."

[0785] Step 10:

[0786] The server receives the question, searches an internal database or external resources to find the appropriate answer, and sends the answer to the terminal. For example, it sends a response such as "For the basics of Python functions, please see this explanation page."

[0787] Step 11:

[0788] The device periodically records the user's learning progress information and sends it to the server, such as the learning progress status and information on completed assignments.

[0789] Step 12:

[0790] The server analyzes the learning progress data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server may select content such as "We recommend Data Analysis Course C as the next step."

[0791] Step 13:

[0792] The server sends the selected new learning content to the device, which displays it to the user and suggests the next learning step. The user can then use the new learning content to further improve their skills.

[0793] In this way, through a series of processing steps, it is possible to provide optimal learning support tailored to the user's learning needs.

[0794] Example 1

[0795] 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."

[0796] Existing learning systems have difficulty providing optimal learning content that meets individual user needs, making it difficult to efficiently improve skills. They also lack the means to quickly respond to questions that arise during learning, making it impossible to provide appropriate learning support. Furthermore, they lack the flexibility to suggest new content based on learning progress.

[0797] 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.

[0798] In this invention, the server includes: a means for a user to input learning needs via a terminal; a means for identifying learning needs using text analysis or machine learning algorithms and storing them in a database; a means for selecting optimal learning content based on the analysis results and transmitting it to the terminal; a means for the terminal to display the learning content selected by the user; a means for recording the user's learning progress and transmitting it to the server; a means for selecting new learning content based on the user's learning progress and transmitting it to the terminal; a means for the user to input questions via the terminal while learning; a means for receiving questions from the user, searching for corresponding answers from a database or external resources, and returning them to the terminal; a means for using a generative AI model through an initial dialogue session to generate questions to elicit the user's learning needs; and a means for periodically transmitting progress information to the server and analyzing the progress data to select new learning content. This enables the server to provide optimal learning content tailored to the user's individual needs and efficiently improve skills. It also enables the server to quickly respond to questions during learning and provide appropriate learning support. Furthermore, it can flexibly suggest new content according to the user's learning progress.

[0799] "Terminal" refers to the device that a user uses to access and operate the system, such as a smartphone, tablet, or PC.

[0800] "Server" refers to the central computer that manages the entire system and provides learning content and answers to user inputs and requests.

[0801] "Database" refers to a collection of data for storing and managing users' learning needs, progress information, and related learning content.

[0802] "Learning needs" refers to the demands and requirements for knowledge and skills that a user wants to acquire.

[0803] "Text analysis" refers to a method of analyzing input data from a user using natural language processing techniques.

[0804] A "machine learning algorithm" refers to a computational method for learning specific patterns and rules from data and using them to make predictions and classifications.

[0805] "Learning content" refers to the learning materials and resources provided to users for learning, such as online courses and specialized books.

[0806] "Progress Information" refers to data that indicates how much a user has learned and how far they have progressed using the learning content.

[0807] A "generative AI model" refers to an artificial intelligence model that generates appropriate questions and answers based on user input data.

[0808] "Answer" refers to appropriate information or explanation provided in response to a user's question.

[0809] "Questions" refer to questions or things that users want to confirm while studying.

[0810] The present invention is a system that allows users to select optimal learning content based on their own learning needs and efficiently improve their skills. Specific aspects of the system are described below.

[0811] First, a user accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user through the system's website or application. The user enters the required information (name, email address, password, etc.) and sends it to the server.

[0812] The server checks the received information against a database (for example, MySQL or PostgreSQL) and performs authentication. If authentication is successful, the user is allowed to access the system, and the server generates a session ID and sends it to the terminal.

[0813] Next, the server uses the generative AI model to generate a set of questions to elicit learning needs and sends them to the device. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions and sends the answers to the server via the device.

[0814] The server receives the user's response data and analyzes it using text analysis tools (e.g., NLTK or SpaCy) or machine learning algorithms (e.g., Scikit-learn or TensorFlow). This analysis identifies the user's individual learning needs and stores the results in a database. For example, if the user responds, "I want to learn Python programming," the server registers that need in the database.

[0815] Next, the server selects the most suitable learning content based on the user's learning needs stored in the database. For example, information such as "Online Course A" or "Specialized Book B" may be selected. The server then sends these selection results to the terminal, which then displays the selected learning content to the user.

[0816] As the user progresses through the learning process using the suggested learning content, the device records their progress. If a question arises during the learning process, the user enters it via the device, which then sends it to the server. The server receives the question, searches a database or external resources to generate an appropriate answer, and sends it back to the device. For example, in response to a question such as "I don't know how to use a Python function," the server suggests a related explanation page.

[0817] Additionally, the device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. When progress reaches 50%, the server makes suggestions such as recommending "Data Analysis Course C as the next step."

[0818] This invention provides optimal learning content tailored to the individual needs of users, enabling them to efficiently improve their skills. It also responds quickly to questions that arise during learning and provides appropriate learning support. Furthermore, it also makes it possible to flexibly suggest content according to the user's learning progress, making it a very beneficial system for learners.

[0819] Example prompts to input to the generative AI model

[0820] "What online courses would you recommend for beginners who want to learn Python programming?"

[0821] "What learning content would you recommend as the next step for a user who is currently 50% complete?"

[0822] "Please suggest a page that explains how to use Python functions."

[0823] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0824] Step 1:

[0825] A user accesses the system using a terminal. The terminal displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and sends it to the server. The server checks the entered information against the database and creates a record in the database if the user is a new user. If the user is already registered, it authenticates the entered password. If authentication is successful, the server generates a session ID and sends it to the terminal. The terminal receives the session ID and displays the main screen.

[0826] Step 2:

[0827] After a user successfully registers or logs in, the server generates a set of questions to start an initial dialogue session. These questions are automatically generated using a generative AI model. For example, they include questions such as, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The server sends these questions to the device, which displays them to the user. The user answers the questions and sends the answers to the server via the device.

[0828] Step 3:

[0829] The server receives the user's response data and analyzes it using text analysis tools (e.g., NLTK or SpaCy) or machine learning algorithms (e.g., Scikit-learn or TensorFlow). The input data for the analysis is the user's response, and the output is the analysis result, which is the user's specific learning needs. For example, if the user's response is "I want to learn Python programming," the server stores that information in a database.

[0830] Step 4:

[0831] The server selects the most suitable learning content based on the user's learning needs stored in the database. In this process, a learning content selection algorithm is used. For example, learning resources such as "Online Course A" or "Specialized Book B" are selected. The selected learning content is sent from the server to the terminal, which then displays it to the user.

[0832] Step 5:

[0833] When a user starts learning using the suggested learning content, the device records the learning progress. The input data is a record of the user's learning activities, and progress information is generated as output data. If the user has any questions while learning, they can input them via the device. The questions are sent to the server, which then receives them.

[0834] Step 6:

[0835] The server analyzes the question sent by the user and searches databases and external resources to find the appropriate answer. Search algorithms and AI models are used to generate the answer. For example, in response to a question such as "I don't know how to use a Python function," the server searches for a relevant explanation page and sends the link to the device. The device then displays the answer to the user.

[0836] Step 7:

[0837] The device periodically sends the user's learning progress information to the server. The server analyzes this progress data and evaluates the current learning situation. Based on the input progress information, an evaluation algorithm is run to select new learning content. For example, when progress reaches 50%, the server recommends "Data Analysis Course C as the next step." The selected new content is sent to the device and displayed to the user as a new suggestion.

[0838] (Application example 1)

[0839] 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."

[0840] Conventional learning systems required a lot of time and effort to respond to individual user needs, and the lack of automation in learning progress and question response made it difficult to improve skills efficiently.Furthermore, while there is a demand for rapid and accurate acquisition of the necessary skills in the operation of factory robots, conventional systems were inadequate in meeting this demand.

[0841] 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.

[0842] In this invention, the server includes: a means for a user to input their learning needs via a terminal; a means for the server to analyze the user's learning needs and store them in a database; a means for the server to select optimal learning content based on the analysis results and send it to the terminal; a means for the terminal to display the learning content selected by the user; a means for recording the user's learning progress and sending it to the server; a means for the server to select new learning content based on the user's learning progress and send it to the terminal; a means for generating optimal answers to questions from the user using a generative AI model and sending them to the terminal; and a means for generating optimal prompt sentences using the generative AI model based on the user's learning needs. This allows users to receive learning content tailored to their individual needs, efficiently manage their learning progress, and quickly respond to questions. It also allows users to efficiently acquire the necessary skills for operating factory robots, contributing to improved productivity.

[0843] "User" refers to a person who uses this system to study.

[0844] A "terminal" is a device used by a user to access the system, such as a smartphone, tablet, or PC.

[0845] "Learning needs" refers to the learning content and goals that users need to learn in order to improve their skills.

[0846] "Server" means a central processing unit for receiving and analyzing data from users and providing appropriate learning content.

[0847] A "database" is a collection of digital data that stores information about a user's learning needs and progress.

[0848] "Analysis" refers to the process of processing data obtained from users using machine learning algorithms and text analysis techniques to identify their learning needs.

[0849] "Learning content" refers to learning materials and resources selected by the server based on the user's learning needs.

[0850] A "generative AI model" is an algorithm or method that uses artificial intelligence to generate optimal answers or prompts to user questions.

[0851] A "prompt" is an instruction or suggestion that is generated by a generative AI model based on the user's learning needs to promote learning.

[0852] "Progress" refers to the learning progress of a user, which indicates how much of the suggested learning content they have completed.

[0853] An "answer" is a response or explanation provided by a server or a generative AI model in response to a user's question.

[0854] The present invention provides a system for enabling users to efficiently advance their learning and improve their skills, particularly in the operation and maintenance of factory robots. The system includes the following components:

[0855] User Registration / Login

[0856] Users first access the system using a device such as a smartphone, tablet, or PC, and then register and log in. Registration requires information such as name, email address, and password, and the server stores this information in a database and performs authentication. If authentication is successful, the user can access the system.

[0857] Initial Interactive Session

[0858] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their devices. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions via their device, and the answers are sent to the server.

[0859] Data analysis and accumulation

[0860] The server receives the user's response data and analyzes it using machine learning algorithms and text analysis. This analysis identifies the user's individual learning needs and stores the results in a database. For example, if a user responds, "I want to learn Python programming," the server registers that need in the database.

[0861] Learning content suggestions

[0862] The server selects the most suitable learning content based on the user's learning needs stored in a database. The selected learning content is sent to the terminal and suggested to the user. For example, "Introductory course on Python programming" or "Specialized books for beginners" are displayed.

[0863] Learning support and questions

[0864] As the user progresses through the learning process using the suggested learning content, the device records their progress. When the user asks a question, the device sends it to the server. The server receives the question, uses a generative AI model to generate the optimal answer, and sends it to the device. For example, in response to a question like "I don't know how to use a Python function," the server might respond with "Please see this explanation page."

[0865] Progress management and new proposals

[0866] The device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. For example, if progress reaches 50%, the server will suggest, "We recommend a data analysis course as your next step."

[0867] Specific examples and prompts for the generation AI

[0868] As a concrete example, imagine a user who has just become an operator of a new factory robot and wants to learn the basic operations. After logging in, the user asks, "Please tell me about an online course on basic robot operations," and the server uses the generative AI model to provide an answer such as, "I recommend this online course."

[0869] Example prompt sentence:

[0870] User: I just became the operator of a new factory robot. I would like to learn the basics of robot operation. What online courses should I take?

[0871] This system allows users to efficiently improve their skills through learning content tailored to their individual needs, and in particular enables them to quickly acquire skills in operating and maintaining factory robots.

[0872] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0873] Step 1:

[0874] A user accesses the system via a terminal and enters the required information (such as name, email address, and password) on the registration or login screen. The entered information is sent to the server, which stores it in a database and performs authentication processing. If successful, the user can access the system.

[0875] Input: User information (name, email address, password)

[0876] Processing: The server stores the user information in a database and performs authentication.

[0877] Output: Authentication success message and access to the system is allowed

[0878] Step 2:

[0879] After a user logs in, the server generates questions to elicit their learning needs and sends them to the device, such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?"

[0880] Input: User login status

[0881] Processing: The server generates questions about learning needs and sends them to the terminal.

[0882] Output: Learning Needs Questionnaire Form

[0883] Step 3:

[0884] Users answer questions about their learning needs through their devices, and the answers are sent from the device to the server. The server receives the answers and analyzes them using machine learning algorithms and text analysis methods. The server identifies the user's learning needs and stores the results in a database.

[0885] Input: User responses regarding learning needs

[0886] Processing: The server analyzes the response data using machine learning algorithms and text analysis methods to identify learning needs and store them in a database.

[0887] Output: Identified learning needs data

[0888] Step 4:

[0889] The server selects the most suitable learning content based on the user's learning needs stored in a database. The selected learning content is sent to the terminal and suggested to the user. For example, "Introductory course on Python programming" or "Specialized books for beginners" are displayed.

[0890] Input: Identified learning needs data

[0891] Processing: The server selects the most appropriate learning content based on the identified needs.

[0892] Output: Suggested learning content

[0893] Step 5:

[0894] As the user progresses through the suggested learning content, the device records their progress. When the user asks a question, the device sends it to the server, which uses a generative AI model to generate the optimal answer and sends it to the device.

[0895] Input: Learning progress information and user questions

[0896] Processing: The server uses the generative AI model to generate the optimal answer to the question and sends it to the device.

[0897] Output: Learning progress information and answers

[0898] Step 6:

[0899] The device periodically sends information about the user's learning progress to the server. The server analyzes this progress data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server will suggest, "We recommend a data analysis course as your next step."

[0900] Input: Learning progress information

[0901] Processing: The server analyzes the progress data and selects new learning content.

[0902] Output: New learning content suggestions

[0903] 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.

[0904] This invention provides a system that allows users to select optimal learning content based on their own learning needs and emotional state, and to efficiently improve their skills. Next, specific embodiments for implementing this system will be described.

[0905] 1. User Registration / Login

[0906] A user first accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and submits it. The server checks the received information against the database, and if it is a new registration, the information is saved in the database, or if it is an existing user, authentication is performed. If authentication is successful, the user is able to access the system.

[0907] 2. Initial Interactive Session

[0908] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their terminals. The terminals display these questions. For example, they include questions such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The users answer these questions through their terminals. The terminals then send the answers to the server.

[0909] 3. Data analysis and accumulation

[0910] The server receives the user's response data and analyzes it using text analysis and machine learning algorithms. This analysis identifies the user's individual learning needs and stores the results in a database. The server also runs an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's audio and video data to identify their current emotional state. The results are also stored in the database.

[0911] 4. Learning content suggestions

[0912] The server selects optimal learning content based on the user's learning needs and emotional state stored in a database. The selected learning content (e.g., information on online courses or specialized books) is sent to the terminal and suggested to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" are displayed to the user. In addition, content and feedback to improve motivation are also provided according to the user's emotional state.

[0913] 5. Learning support

[0914] As the user progresses through the learning process using the suggested learning content, the device records their progress and emotional state, and sends them to the server. If the user asks a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page." In addition, the system analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[0915] 6. Progress management and new proposals

[0916] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes the progress data and emotional data and selects new learning content based on the user's current learning situation. It then sends new suggestions to the device. For example, if progress reaches 50%, the server might suggest, "We recommend Data Analysis Course C as your next step." The server also provides advice on appropriate learning methods based on the user's emotional state.

[0917] Specific examples

[0918] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," as well as the user's emotional state in a database. The server then recommends "Online Course A for Beginners" and "Specialized Book B for Beginners" to the terminal. As the user progresses through their studies using these learning materials, the emotion engine sequentially analyzes the user's emotional state and provides advice to improve motivation as needed. If a question arises, the server suggests an appropriate explanation page. Furthermore, when the user has progressed 50%, it suggests "Data Analysis Course C" as the next step.

[0919] This system provides learning support tailored to the user's needs and emotional state, allowing them to improve their skills efficiently.

[0920] The processing flow will be explained below.

[0921] Step 1:

[0922] A user accesses the system through a terminal. The terminal displays a registration / login screen to the user. The user enters the required information such as name, email address, and password, and presses the submit button.

[0923] Step 2:

[0924] The device sends the entered information to the server, which then checks the received information against the database, saving the information in the database if it is a new registration, or authenticating the user if they are already registered.

[0925] Step 3:

[0926] The server sends the authentication result to the terminal. If the authentication is successful, the user can access the system. If the authentication is unsuccessful, an error message is displayed.

[0927] Step 4:

[0928] The server generates initial questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, the questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to learning?"

[0929] Step 5:

[0930] The user answers questions through the device. For example, they answer "I want to learn Python programming." The device then sends the user's answers to the server.

[0931] Step 6:

[0932] The server analyzes the received response data, uses text analysis and machine learning algorithms to identify the user's learning needs, and stores the results in a database.

[0933] Step 7:

[0934] The server receives the user's audio and video data, analyzes it using an emotion engine, and identifies the user's current emotional state, which is also stored in a database.

[0935] Step 8:

[0936] The server selects the most suitable learning content based on the analysis results. For example, "Online Course A for Beginners" and "Specialized Book B for Beginners" may be selected. The selected learning content is then sent to the device.

[0937] Step 9:

[0938] The device displays the learning content selected by the user. The user then begins learning by viewing the recommended learning content. Motivational content tailored to the user's emotional state is also displayed on the device.

[0939] Step 10:

[0940] If a user has a question about their learning as they proceed, they can send it to the server via their device. For example, they might ask, "I don't know how to use a Python function."

[0941] Step 11:

[0942] The server receives the question, searches an internal database or external resources to find an appropriate answer, and sends the answer to the device. For example, it sends an answer such as "For the basics of Python functions, please see this explanation page." It also provides appropriate feedback based on the user's emotional state along with the answer to the question.

[0943] Step 12:

[0944] The device periodically records the user's learning progress and emotional state and transmits it to the server. Progress data is accumulated throughout the user's learning activities.

[0945] Step 13:

[0946] The server analyzes the progress data and emotional data and selects new learning content based on the user's current learning situation and emotional state. For example, if the progress reaches 50%, the server selects the content, "We recommend Data Analysis Course C as your next step."

[0947] Step 14:

[0948] The server selects new learning content and sends it to the device along with advice on how to study based on the user's emotional state. The device displays this information to the user and suggests the next learning step. The user can then use the new learning content to further improve their skills.

[0949] In this way, through a series of processing steps, optimal learning support can be provided based on the user's learning needs and emotional state.

[0950] Example 2

[0951] 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."

[0952] Conventional learning support systems have difficulty accurately grasping a user's learning needs and emotional state and providing optimal learning content and feedback based on the results. Furthermore, they lack mechanisms for flexibly responding to diverse user needs, such as suggesting new content based on learning progress or providing immediate responses to questions during learning. To address these issues, a system is needed that can analyze a user's learning needs and emotional state in real time and provide optimal learning content and feedback based on that analysis.

[0953] 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.

[0954] In this invention, the server includes means for analyzing the user's learning needs and saving them in a database, means for recording the user's learning progress and emotional state and sending them to the server, and means for selecting new learning content and feedback based on the user's learning progress and emotional state and sending them to the terminal, thereby enabling optimal learning support based on the user's learning needs and emotional state.

[0955] "User" refers to an individual who accesses the system, inputs their learning needs and emotional state, and uses the learning content.

[0956] "Terminal" refers to a device used by a user to access the system, such as a smartphone, tablet, or PC.

[0957] "Server" refers to a central processing unit that analyzes information received from users, stores it in a database, selects learning content, provides feedback, and so on.

[0958] "Learning needs" refers to the skills or areas of knowledge a user wishes to improve and the specific requests and desires associated with them.

[0959] "Emotional state" refers to the user's current psychological and emotional state, which is analyzed based on audio and video data.

[0960] "Database" refers to an information storage system for saving and managing analysis results, such as the user's learning needs and emotional state.

[0961] "Learning content" refers to learning materials and information provided to users for learning purposes, including, for example, online courses and specialized books.

[0962] "Feedback" refers to advice, encouragement, and motivational comments provided based on the user's learning progress and emotional state.

[0963] "Text analysis" refers to the process of analyzing text data entered by a user to identify learning needs.

[0964] A "machine learning algorithm" refers to a computational method for learning from large amounts of data and making predictions and classifications.

[0965] An "emotion engine" refers to software that analyzes a user's audio and video data to identify their emotional state.

[0966] "Progress information" refers to the progress a user makes as they progress through their studies, and includes, for example, the percentage of content that has been studied and the steps that have been achieved.

[0967] MODE FOR CARRYING OUT THE INVENTION

[0968] The present invention provides a system that allows users to select optimal learning content based on their own learning needs and emotional state, thereby improving their skills efficiently. Detailed embodiments of the system will be described below.

[0969] First, a user accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information such as name, email address, and password, and submits it. The server checks the received information against the database. If the user is a new user, the server saves the information in the database, and if the user is an existing user, it performs authentication. If authentication is successful, the user is able to access the system.

[0970] Next, the server generates initial questions for the registered or logged-in user to elicit their learning needs and sends them to the terminal. The terminal displays these questions, and the user answers them. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user's answers are sent from the terminal to the server.

[0971] The server analyzes the user's response data using text analysis and machine learning algorithms, and this analysis identifies the user's individual learning needs. The server also runs an emotion engine that analyzes the user's emotional state based on audio and video data. This emotion engine uses APIs from common cloud services, such as Microsoft and Google APIs. The analysis results are stored in a database.

[0972] The server selects optimal learning content based on the user's learning needs and emotional state, which are stored in a database. The selected learning content (e.g., information on online courses or specialized books) is sent to the terminal and suggested to the user. For example, "Python programming introductory course A" and "beginner-oriented specialized book B" may be selected. Motivational content and feedback are also provided based on the user's emotional state.

[0973] As the user progresses through the learning process using the suggested learning content, the device records their progress and emotional state and sends it to the server. If the user asks a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page." The system also analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[0974] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes the progress data and emotional data, selects new learning content based on the user's current learning situation, and sends new suggestions to the device. For example, if progress reaches 50%, the server will suggest, "We recommend Data Analysis Course C as your next step." It also provides advice on appropriate learning methods based on the user's emotional state.

[0975] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," as well as the user's emotional state, in a database. The server then recommends "online course A for beginners" and "specialized book B for beginners" to the terminal. As the user progresses through their studies using these learning materials, the emotion engine sequentially analyzes the user's emotional state and provides advice to improve motivation as needed. If a question arises, the server suggests an appropriate explanation page. Furthermore, when the user has progressed 50%, it suggests "data analysis course C" as the next step.

[0976] This system provides learning support tailored to the user's needs and emotional state, allowing them to improve their skills efficiently.

[0977] Prompt Sentence Examples

[0978] 1. "Enter your name and email address to create an account."

[0979] 2. "In what areas would you like to improve your skills?"

[0980] 3. "Please describe your current emotional state."

[0981] 4. "I recommend Course A, an introductory course on Python programming, and Book B, a specialized book for beginners."

[0982] 5. "I have a question about Python functions."

[0983] 6. "Why not take Course C in Data Analysis as your next step?"

[0984] In this way, users can receive optimal learning content and feedback based on their own learning progress and emotional state.

[0985] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0986] The flow of this system's program processing

[0987] Step 1: User registration and login

[0988] Input: Name, email address, and password entered by the user on the device

[0989] Output: User authentication result (authentication success / failure)

[0990] Specific description:

[0991] The terminal displays a registration / login screen to the user. The user enters their name, email address, and password and presses the submit button. The terminal sends the entered information to the server via an HTTP POST request. The server checks the received information against its database. If the user is a new user, the server saves the information in the database; if the user is an existing user, the server authenticates them. If authentication is successful, the user is allowed to access the system.

[0992] Specific behavior:

[0993] The terminal displays the form and receives input from the user.

[0994] The terminal transmits the input data to the server.

[0995] The server checks the user information against the database and returns the results to the terminal.

[0996] Step 2: Initial interactive session

[0997] Input: Initial setup questions sent by the server

[0998] Output: User response data

[0999] Specific description:

[1000] The server generates initial setup questions for the logged-in user and sends them to the device. The device displays these questions on the screen, and the user answers them. For example, questions include "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user's answers are sent from the device to the server.

[1001] Specific behavior:

[1002] The server generates question data and sends it to the terminal in JSON format.

[1003] The terminal displays questions and collects answers from the user.

[1004] The terminal transmits the user's answer to the server.

[1005] Step 3: Data analysis and storage

[1006] Input: User response data and emotion data

[1007] Output: Learning needs analysis and emotional state identification

[1008] Specific description:

[1009] The server analyzes the user's response data using text analysis and machine learning algorithms. This analysis identifies the user's learning needs. The server also uses an emotion engine to analyze the user's audio and video data to identify their emotional state. The server then stores the results of these analyses in a database.

[1010] Specific behavior:

[1011] The server analyzes the response data using morphological analysis and machine learning models.

[1012] An emotion engine is used to identify emotional states from audio and video data.

[1013] The analysis results are saved in a database.

[1014] Step 4: Suggest learning content

[1015] Input: Learning needs and emotional states stored in a database

[1016] Output: Selection of optimal learning content

[1017] Specific description:

[1018] The server selects the most appropriate learning content based on the user's learning needs and emotional state, which are stored in a database. The server then sends the selected learning content to the terminal and suggests it to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" may be suggested. Feedback is also provided to improve motivation.

[1019] Specific behavior:

[1020] The server obtains the user's learning needs and emotional state from a database.

[1021] Use an algorithm to select the best learning content.

[1022] The selected content information is sent to the terminal in JSON format.

[1023] The terminal displays the information on the screen.

[1024] Step 5: Learning support

[1025] Input: Learning progress information, emotional state, user questions

[1026] Output: Record of learning progress information, answers to questions

[1027] Specific description:

[1028] As the user progresses through the learning process using the suggested learning content, the device records learning progress information and emotional state and sends them to the server. If the user has a question, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question like "I don't know how to use a Python function," the server responds with "Please see this explanation page." The device also analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[1029] Specific behavior:

[1030] The device periodically transmits learning progress information and emotional state to the server.

[1031] The user enters a question and the terminal sends it to the server.

[1032] The server retrieves the answer and sends it to the terminal, which displays it.

[1033] Step 6: Progress management and new proposals

[1034] Input: Learning progress information, emotional state

[1035] Output: New learning content suggestions

[1036] Specific description:

[1037] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes this data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server will suggest "We recommend Data Analysis Course C as your next step." The server also provides advice on appropriate learning methods based on the user's emotional state.

[1038] Specific behavior:

[1039] The device periodically transmits learning progress data and emotional state to the server.

[1040] The server analyzes this data and selects new learning content.

[1041] The server sends the proposal in JSON format to the device, which displays it on the screen.

[1042] This process allows users to receive optimal learning content and feedback based on their own learning progress and emotional state.

[1043] (Application example 2)

[1044] 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."

[1045] Conventional learning support systems have had difficulty providing learning content that takes into account the user's learning needs as well as their emotional state at any given time. It has also been difficult to provide advice to improve motivation based on the user's emotional state, making it impossible to maximize learning efficiency. Furthermore, it has been insufficient to utilize generative AI models related to dynamic learning content suggestions based on the user's learning needs and emotional state.

[1046] The identification process performed by the identification 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 analyzing the user's learning needs and storing them in a database, means for selecting optimal learning content based on the analysis results and sending it to the terminal, and means for analyzing the user's emotional state and providing advice to improve motivation. This makes it possible to provide optimal learning content based on the user's learning progress and emotional state.

[1047] "User" refers to an individual who uses this system.

[1048] "Device" refers to an electronic device used by a user to access the system and receive learning content, including smartphones, tablets, and personal computers.

[1049] "Learning needs" refers to the skills and knowledge that a user wants to improve, as well as the desires and needs regarding learning content.

[1050] "Server" refers to a computer system that centrally processes data, manages databases, and analyzes users' learning needs and progress information.

[1051] "Analysis" refers to the processing and understanding of the learning needs and emotional state data collected by the server from the user.

[1052] A "database" is an information storage system for storing and managing data such as a user's learning needs, progress information, and emotional state.

[1053] "Learning content" refers to information resources provided to assist users in their learning, including online courses, specialized books, videos, and the like.

[1054] "Emotional state" refers to the user's current psychological and emotional state, including stress level and motivation during learning.

[1055] "Motivational advice" refers to suggestions to encourage and motivate the user to continue learning based on their emotional state.

[1056] "Progress" refers to the degree to which a user has progressed through the learning content.

[1057] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to incorporate algorithms that dynamically generate content suggestions based on the user's learning needs and emotional state.

[1058] "Prompt" refers to the input or instructions used by a generative AI model to generate a desired output.

[1059] A system embodying the present invention provides optimal learning content based on a user's learning needs and emotional state. Specific embodiments of the system will be described below.

[1060] First, a user accesses the system using a device such as a smartphone. The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and submits it. The server stores the received information in a database and performs authentication. If authentication is successful, the user is able to access the system.

[1061] Next, the server generates questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, they include questions such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions through the device. The server receives the answer data and analyzes it. This analysis uses text analysis libraries (e.g., TextBlob) and machine learning algorithms.

[1062] Furthermore, the server runs an emotion engine that analyzes the user's emotional state. The emotion engine analyzes the user's audio and video data to identify the user's current emotional state. This allows the user's learning progress and emotional state to be stored in a database.

[1063] The server uses a generative AI model to suggest optimal learning content based on the user's learning needs and emotional state stored in a database. The generative AI model creates prompts based on the user's needs and selects and provides optimal content based on those prompts. For example, it creates a prompt recommending "Python Programming Introductory Course A" and suggests that course to the user.

[1064] The device displays suggested learning content to the user. As the user uses this learning content to study, the device records learning progress information and sends it to the server. At the same time, the server analyzes the progress data and responds to questions the user may have along the way. The server receives the questions, searches for related learning content or explanation pages, and sends them back to the device.

[1065] The server also periodically analyzes the user's emotional state and learning progress and provides advice to improve motivation, again based on prompts generated by a generative AI model.

[1066] As a concrete example, if a beginner programmer registers the learning need of "I want to learn Python programming," the server analyzes the user's response to the question, "In what field do you want to improve your skills?" If the result of the sentiment analysis is positive, the server will suggest "Python programming introductory course A" and "specialized book B for beginners." If the emotional state is negative, the server will suggest video C to improve motivation.

[1067] An example of a prompt is:

[1068] "Suggest the best learning content for users based on their learning needs:

[1069] Learning Needs: Python Programming, Current Emotional State: Positive"

[1070] This prompt is then fed into a generative AI model to suggest optimal learning content.

[1071] In this way, a system that maximizes the user's learning efficiency is realized.

[1072] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1073] Step 1:

[1074] A user accesses the learning platform using a terminal. The user enters the required information such as name, email address, and password to register or log in. The input data is sent from the terminal to the server, which stores it in a database or authenticates it. If the login is successful, the server allows the user to access the system. The input data is user information (name, email address, password, etc.), and the output is the authentication result (success or failure).

[1075] Step 2:

[1076] The server generates initial questions to elicit the user's learning needs. For example, questions such as "In what areas do you want to improve your skills?" or "How much time can you devote to learning?" are generated and sent to the device. The user answers these questions and sends them back to the server via the device. The input data are the user's answers (learning needs, time available for learning, etc.), and the output is the saved answer data.

[1077] Step 3:

[1078] The server analyzes the response data received from the user using a text analysis library (e.g., TextBlob) and machine learning algorithms to identify learning needs. At the same time, the server runs an emotion engine that analyzes the user's audio and video data to identify their current emotional state. The resulting data, which represent the user's learning needs and emotional state, are stored in a database. The input data are the user's responses and audio / video data, and the output is the analysis results (learning needs and emotional state).

[1079] Step 4:

[1080] The server utilizes a generative AI model to select optimal learning content based on the user's learning needs and emotional state stored in a database. A prompt (e.g., "Please suggest optimal learning content for the user based on the following learning needs: Learning need: Python programming, Current emotional state: Positive") is input to the generative AI model, which then suggests optimal learning content. The output suggestions are then sent to the device. The input data is the prompt, and the output is learning content suggestions made by the generative AI model.

[1081] Step 5:

[1082] The device displays the suggested learning content to the user, who then uses the displayed learning content (e.g., an introductory course A on Python programming or a specialized book B for beginners) to advance their learning. The input data is the suggested learning content, and the output is the content displayed to the user.

[1083] Step 6:

[1084] As the user continues to study, the device records learning progress information and periodically sends it to the server. The learning progress information includes data on how far the user has progressed in their studies. In addition, if the user enters a question while studying, the device sends the question to the server. The input data is the learning progress information and the question content, and the output is data sent to the server.

[1085] Step 7:

[1086] The server receives the user's learning progress information and question content, searches for appropriate answers and explanations, and sends them back to the device. It also analyzes the progress information and emotional state to suggest new learning content and provide advice to improve motivation. Utilizing a generative AI model, it generates optimal advice based on the prompt text. The input data is learning progress, question content, and emotional state, and the output is suggested answers and advice.

[1087] Step 8:

[1088] The terminal displays the answers and advice from the server to the user, who can refer to them and continue learning. The input data are the answers and advice received from the server, and the output is the information displayed to the user.

[1089] This system makes it possible to provide optimal learning support that takes into account the user's learning needs and emotional state.

[1090] 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.

[1091] 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.

[1092] 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.

[1093] [Fourth embodiment]

[1094] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1095] 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.

[1096] 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).

[1097] 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.

[1098] 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.

[1099] 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).

[1100] 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.

[1101] 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.

[1102] 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.

[1103] 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.

[1104] 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.

[1105] 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.

[1106] 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."

[1107] This invention is a system that allows users to select optimal learning content based on their own learning needs and efficiently improve their skills. Next, a specific embodiment for implementing this system will be described.

[1108] 1. User Registration / Login

[1109] A user first accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and sends it to the server. The server checks the received information against a database and performs authentication. If authentication is successful, the user is allowed to access the system.

[1110] 2. Initial Interactive Session

[1111] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their terminals. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions through their terminal, and the terminal sends the answers to the server.

[1112] 3. Data analysis and accumulation

[1113] The server receives the user's response data and analyzes it using text analysis and machine learning algorithms. This analysis identifies the user's individual learning needs and stores the results in a database. For example, if a user responds, "I want to learn Python programming," the server registers that need in the database.

[1114] 4. Learning content suggestions

[1115] The server selects the most appropriate learning content based on the user's learning needs stored in the database. The selected learning content (e.g., online courses or specialized book information) is sent to the terminal and suggested to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" are displayed to the user.

[1116] 5. Learning support

[1117] As the user progresses through the learning process using the suggested learning content, the device records their progress. If the user has a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page."

[1118] 6. Progress management and new proposals

[1119] The device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. It then sends new suggestions to the device. For example, if progress reaches 50%, the server will suggest, "As your next step, we recommend Data Analysis Course C."

[1120] Specific examples

[1121] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," in the database. The server then recommends "online course A for beginners" and "specialized book B for beginners" to the terminal. As the user progresses with these learning materials, if the user sends a question about how to use a function from the terminal to the server, the server will suggest an appropriate explanation page. Furthermore, when the user's progress reaches 50%, the server will suggest "data analysis course C" as the next step.

[1122] This system provides learning support tailored to the individual needs of users, allowing them to improve their skills efficiently.

[1123] The processing flow will be explained below.

[1124] Step 1:

[1125] A user accesses the system via a terminal. The terminal displays a registration / login screen to the user. Here, the user enters their name, email address, password, etc., and presses the submit button.

[1126] Step 2:

[1127] The terminal sends the entered information to the server. The server checks the received information against the database, and stores the information in the database if it is a new registration, or performs authentication if it is an existing user.

[1128] Step 3:

[1129] The server sends the authentication result to the terminal. If the authentication is successful, the user can access the system and proceed to the next step. If the authentication is unsuccessful, an error message is displayed.

[1130] Step 4:

[1131] The server generates initial questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, the questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to learning?"

[1132] Step 5:

[1133] The user answers questions through the device. For example, they answer "I want to learn Python programming." The device then sends the user's answers to the server.

[1134] Step 6:

[1135] The server analyzes the received response data, uses text analysis and machine learning algorithms to identify the user's learning needs, and stores the results in a database.

[1136] Step 7:

[1137] The server selects the most suitable learning content based on the analysis results. For example, "Online Course A for Beginners" and "Specialized Book B for Beginners" may be selected. The selected learning content is then sent to the device.

[1138] Step 8:

[1139] The device displays the learning content selected by the user, and the user begins learning by viewing the recommended learning content.

[1140] Step 9:

[1141] If a user has a question about their learning as they proceed, they can send it to the server via their device. For example, they might ask, "I don't know how to use a Python function."

[1142] Step 10:

[1143] The server receives the question, searches an internal database or external resources to find the appropriate answer, and sends the answer to the terminal. For example, it sends a response such as "For the basics of Python functions, please see this explanation page."

[1144] Step 11:

[1145] The device periodically records the user's learning progress information and sends it to the server, such as the learning progress status and information on completed assignments.

[1146] Step 12:

[1147] The server analyzes the learning progress data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server may select content such as "We recommend Data Analysis Course C as the next step."

[1148] Step 13:

[1149] The server sends the selected new learning content to the device, which displays it to the user and suggests the next learning step. The user can then use the new learning content to further improve their skills.

[1150] In this way, through a series of processing steps, it is possible to provide optimal learning support tailored to the user's learning needs.

[1151] Example 1

[1152] 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."

[1153] Existing learning systems have difficulty providing optimal learning content that meets individual user needs, making it difficult to efficiently improve skills. They also lack the means to quickly respond to questions that arise during learning, making it impossible to provide appropriate learning support. Furthermore, they lack the flexibility to suggest new content based on learning progress.

[1154] 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.

[1155] In this invention, the server includes: a means for a user to input learning needs via a terminal; a means for identifying learning needs using text analysis or machine learning algorithms and storing them in a database; a means for selecting optimal learning content based on the analysis results and transmitting it to the terminal; a means for the terminal to display the learning content selected by the user; a means for recording the user's learning progress and transmitting it to the server; a means for selecting new learning content based on the user's learning progress and transmitting it to the terminal; a means for the user to input questions via the terminal while learning; a means for receiving questions from the user, searching for corresponding answers from a database or external resources, and returning them to the terminal; a means for using a generative AI model through an initial dialogue session to generate questions to elicit the user's learning needs; and a means for periodically transmitting progress information to the server and analyzing the progress data to select new learning content. This enables the server to provide optimal learning content tailored to the user's individual needs and efficiently improve skills. It also enables the server to quickly respond to questions during learning and provide appropriate learning support. Furthermore, it can flexibly suggest new content according to the user's learning progress.

[1156] "Terminal" refers to the device that a user uses to access and operate the system, such as a smartphone, tablet, or PC.

[1157] "Server" refers to the central computer that manages the entire system and provides learning content and answers to user inputs and requests.

[1158] "Database" refers to a collection of data for storing and managing users' learning needs, progress information, and related learning content.

[1159] "Learning needs" refers to the demands and requirements for knowledge and skills that a user wants to acquire.

[1160] "Text analysis" refers to a method of analyzing input data from a user using natural language processing techniques.

[1161] A "machine learning algorithm" refers to a computational method for learning specific patterns and rules from data and using them to make predictions and classifications.

[1162] "Learning content" refers to the learning materials and resources provided to users for learning, such as online courses and specialized books.

[1163] "Progress Information" refers to data that indicates how much a user has learned and how far they have progressed using the learning content.

[1164] A "generative AI model" refers to an artificial intelligence model that generates appropriate questions and answers based on user input data.

[1165] "Answer" refers to appropriate information or explanation provided in response to a user's question.

[1166] "Questions" refer to questions or things that users want to confirm while studying.

[1167] The present invention is a system that allows users to select optimal learning content based on their own learning needs and efficiently improve their skills. Specific aspects of the system are described below.

[1168] First, a user accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user through the system's website or application. The user enters the required information (name, email address, password, etc.) and sends it to the server.

[1169] The server checks the received information against a database (for example, MySQL or PostgreSQL) and performs authentication. If authentication is successful, the user is allowed to access the system, and the server generates a session ID and sends it to the terminal.

[1170] Next, the server uses the generative AI model to generate a set of questions to elicit learning needs and sends them to the device. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions and sends the answers to the server via the device.

[1171] The server receives the user's response data and analyzes it using text analysis tools (e.g., NLTK or SpaCy) or machine learning algorithms (e.g., Scikit-learn or TensorFlow). This analysis identifies the user's individual learning needs and stores the results in a database. For example, if the user responds, "I want to learn Python programming," the server registers that need in the database.

[1172] Next, the server selects the most suitable learning content based on the user's learning needs stored in the database. For example, information such as "Online Course A" or "Specialized Book B" may be selected. The server then sends these selection results to the terminal, which then displays the selected learning content to the user.

[1173] As the user progresses through the learning process using the suggested learning content, the device records their progress. If a question arises during the learning process, the user enters it via the device, which then sends it to the server. The server receives the question, searches a database or external resources to generate an appropriate answer, and sends it back to the device. For example, in response to a question such as "I don't know how to use a Python function," the server suggests a related explanation page.

[1174] Additionally, the device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. When progress reaches 50%, the server makes suggestions such as recommending "Data Analysis Course C as the next step."

[1175] This invention provides optimal learning content tailored to the individual needs of users, enabling them to efficiently improve their skills. It also responds quickly to questions that arise during learning and provides appropriate learning support. Furthermore, it also makes it possible to flexibly suggest content according to the user's learning progress, making it a very beneficial system for learners.

[1176] Example prompts to input to the generative AI model

[1177] "What online courses would you recommend for beginners who want to learn Python programming?"

[1178] "What learning content would you recommend as the next step for a user who is currently 50% complete?"

[1179] "Please suggest a page that explains how to use Python functions."

[1180] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1181] Step 1:

[1182] A user accesses the system using a terminal. The terminal displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and sends it to the server. The server checks the entered information against the database and creates a record in the database if the user is a new user. If the user is already registered, it authenticates the entered password. If authentication is successful, the server generates a session ID and sends it to the terminal. The terminal receives the session ID and displays the main screen.

[1183] Step 2:

[1184] After a user successfully registers or logs in, the server generates a set of questions to start an initial dialogue session. These questions are automatically generated using a generative AI model. For example, they include questions such as, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The server sends these questions to the device, which displays them to the user. The user answers the questions and sends the answers to the server via the device.

[1185] Step 3:

[1186] The server receives the user's response data and analyzes it using text analysis tools (e.g., NLTK or SpaCy) or machine learning algorithms (e.g., Scikit-learn or TensorFlow). The input data for the analysis is the user's response, and the output is the analysis result, which is the user's specific learning needs. For example, if the user's response is "I want to learn Python programming," the server stores that information in a database.

[1187] Step 4:

[1188] The server selects the most suitable learning content based on the user's learning needs stored in the database. In this process, a learning content selection algorithm is used. For example, learning resources such as "Online Course A" or "Specialized Book B" are selected. The selected learning content is sent from the server to the terminal, which then displays it to the user.

[1189] Step 5:

[1190] When a user starts learning using the suggested learning content, the device records the learning progress. The input data is a record of the user's learning activities, and progress information is generated as output data. If the user has any questions while learning, they can input them via the device. The questions are sent to the server, which then receives them.

[1191] Step 6:

[1192] The server analyzes the question sent by the user and searches databases and external resources to find the appropriate answer. Search algorithms and AI models are used to generate the answer. For example, in response to a question such as "I don't know how to use a Python function," the server searches for a relevant explanation page and sends the link to the device. The device then displays the answer to the user.

[1193] Step 7:

[1194] The device periodically sends the user's learning progress information to the server. The server analyzes this progress data and evaluates the current learning situation. Based on the input progress information, an evaluation algorithm is run to select new learning content. For example, when progress reaches 50%, the server recommends "Data Analysis Course C as the next step." The selected new content is sent to the device and displayed to the user as a new suggestion.

[1195] (Application example 1)

[1196] 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."

[1197] Conventional learning systems required a lot of time and effort to respond to individual user needs, and the lack of automation in learning progress and question response made it difficult to improve skills efficiently.Furthermore, while there is a demand for rapid and accurate acquisition of the necessary skills in the operation of factory robots, conventional systems were inadequate in meeting this demand.

[1198] 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.

[1199] In this invention, the server includes: a means for a user to input their learning needs via a terminal; a means for the server to analyze the user's learning needs and store them in a database; a means for the server to select optimal learning content based on the analysis results and send it to the terminal; a means for the terminal to display the learning content selected by the user; a means for recording the user's learning progress and sending it to the server; a means for the server to select new learning content based on the user's learning progress and send it to the terminal; a means for generating optimal answers to questions from the user using a generative AI model and sending them to the terminal; and a means for generating optimal prompt sentences using the generative AI model based on the user's learning needs. This allows users to receive learning content tailored to their individual needs, efficiently manage their learning progress, and quickly respond to questions. It also allows users to efficiently acquire the necessary skills for operating factory robots, contributing to improved productivity.

[1200] "User" refers to a person who uses this system to study.

[1201] A "terminal" is a device used by a user to access the system, such as a smartphone, tablet, or PC.

[1202] "Learning needs" refers to the learning content and goals that users need to learn in order to improve their skills.

[1203] "Server" means a central processing unit for receiving and analyzing data from users and providing appropriate learning content.

[1204] A "database" is a collection of digital data that stores information about a user's learning needs and progress.

[1205] "Analysis" refers to the process of processing data obtained from users using machine learning algorithms and text analysis techniques to identify their learning needs.

[1206] "Learning content" refers to learning materials and resources selected by the server based on the user's learning needs.

[1207] A "generative AI model" is an algorithm or method that uses artificial intelligence to generate optimal answers or prompts to user questions.

[1208] A "prompt" is an instruction or suggestion that is generated by a generative AI model based on the user's learning needs to promote learning.

[1209] "Progress" refers to the learning progress of a user, which indicates how much of the suggested learning content they have completed.

[1210] An "answer" is a response or explanation provided by a server or a generative AI model in response to a user's question.

[1211] The present invention provides a system for enabling users to efficiently advance their learning and improve their skills, particularly in the operation and maintenance of factory robots. The system includes the following components:

[1212] User Registration / Login

[1213] Users first access the system using a device such as a smartphone, tablet, or PC, and then register and log in. Registration requires information such as name, email address, and password, and the server stores this information in a database and performs authentication. If authentication is successful, the user can access the system.

[1214] Initial Interactive Session

[1215] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their devices. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions via their device, and the answers are sent to the server.

[1216] Data analysis and accumulation

[1217] The server receives the user's response data and analyzes it using machine learning algorithms and text analysis. This analysis identifies the user's individual learning needs and stores the results in a database. For example, if a user responds, "I want to learn Python programming," the server registers that need in the database.

[1218] Learning content suggestions

[1219] The server selects the most suitable learning content based on the user's learning needs stored in a database. The selected learning content is sent to the terminal and suggested to the user. For example, "Introductory course on Python programming" or "Specialized books for beginners" are displayed.

[1220] Learning support and questions

[1221] As the user progresses through the learning process using the suggested learning content, the device records their progress. When the user asks a question, the device sends it to the server. The server receives the question, uses a generative AI model to generate the optimal answer, and sends it to the device. For example, in response to a question like "I don't know how to use a Python function," the server might respond with "Please see this explanation page."

[1222] Progress management and new proposals

[1223] The device periodically sends information about the user's learning progress to the server. The server analyzes the progress data and selects new learning content based on the user's current learning situation. For example, if progress reaches 50%, the server will suggest, "We recommend a data analysis course as your next step."

[1224] Specific examples and prompts for the generation AI

[1225] As a concrete example, imagine a user who has just become an operator of a new factory robot and wants to learn the basic operations. After logging in, the user asks, "Please tell me about an online course on basic robot operations," and the server uses the generative AI model to provide an answer such as, "I recommend this online course."

[1226] Example prompt sentence:

[1227] User: I just became the operator of a new factory robot. I would like to learn the basics of robot operation. What online courses should I take?

[1228] This system allows users to efficiently improve their skills through learning content tailored to their individual needs, and in particular enables them to quickly acquire skills in operating and maintaining factory robots.

[1229] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1230] Step 1:

[1231] A user accesses the system via a terminal and enters the required information (such as name, email address, and password) on the registration or login screen. The entered information is sent to the server, which stores it in a database and performs authentication processing. If successful, the user can access the system.

[1232] Input: User information (name, email address, password)

[1233] Processing: The server stores the user information in a database and performs authentication.

[1234] Output: Authentication success message and access to the system is allowed

[1235] Step 2:

[1236] After a user logs in, the server generates questions to elicit their learning needs and sends them to the device, such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?"

[1237] Input: User login status

[1238] Processing: The server generates questions about learning needs and sends them to the terminal.

[1239] Output: Learning Needs Questionnaire Form

[1240] Step 3:

[1241] Users answer questions about their learning needs through their devices, and the answers are sent from the device to the server. The server receives the answers and analyzes them using machine learning algorithms and text analysis methods. The server identifies the user's learning needs and stores the results in a database.

[1242] Input: User responses regarding learning needs

[1243] Processing: The server analyzes the response data using machine learning algorithms and text analysis methods to identify learning needs and store them in a database.

[1244] Output: Identified learning needs data

[1245] Step 4:

[1246] The server selects the most suitable learning content based on the user's learning needs stored in a database. The selected learning content is sent to the terminal and suggested to the user. For example, "Introductory course on Python programming" or "Specialized books for beginners" are displayed.

[1247] Input: Identified learning needs data

[1248] Processing: The server selects the most appropriate learning content based on the identified needs.

[1249] Output: Suggested learning content

[1250] Step 5:

[1251] As the user progresses through the suggested learning content, the device records their progress. When the user asks a question, the device sends it to the server, which uses a generative AI model to generate the optimal answer and sends it to the device.

[1252] Input: Learning progress information and user questions

[1253] Processing: The server uses the generative AI model to generate the optimal answer to the question and sends it to the device.

[1254] Output: Learning progress information and answers

[1255] Step 6:

[1256] The device periodically sends information about the user's learning progress to the server. The server analyzes this progress data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server will suggest, "We recommend a data analysis course as your next step."

[1257] Input: Learning progress information

[1258] Processing: The server analyzes the progress data and selects new learning content.

[1259] Output: New learning content suggestions

[1260] 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.

[1261] This invention provides a system that allows users to select optimal learning content based on their own learning needs and emotional state, and to efficiently improve their skills. Next, specific embodiments for implementing this system will be described.

[1262] 1. User Registration / Login

[1263] A user first accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and submits it. The server checks the received information against the database, and if it is a new registration, the information is saved in the database, or if it is an existing user, authentication is performed. If authentication is successful, the user is able to access the system.

[1264] 2. Initial Interactive Session

[1265] The server generates questions for registered or logged-in users to elicit their learning needs and sends them to their terminals. The terminals display these questions. For example, they include questions such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The users answer these questions through their terminals. The terminals then send the answers to the server.

[1266] 3. Data analysis and accumulation

[1267] The server receives the user's response data and analyzes it using text analysis and machine learning algorithms. This analysis identifies the user's individual learning needs and stores the results in a database. The server also runs an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's audio and video data to identify their current emotional state. The results are also stored in the database.

[1268] 4. Learning content suggestions

[1269] The server selects optimal learning content based on the user's learning needs and emotional state stored in a database. The selected learning content (e.g., information on online courses or specialized books) is sent to the terminal and suggested to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" are displayed to the user. In addition, content and feedback to improve motivation are also provided according to the user's emotional state.

[1270] 5. Learning support

[1271] As the user progresses through the learning process using the suggested learning content, the device records their progress and emotional state, and sends them to the server. If the user asks a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page." In addition, the system analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[1272] 6. Progress management and new proposals

[1273] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes the progress data and emotional data and selects new learning content based on the user's current learning situation. It then sends new suggestions to the device. For example, if progress reaches 50%, the server might suggest, "We recommend Data Analysis Course C as your next step." The server also provides advice on appropriate learning methods based on the user's emotional state.

[1274] Specific examples

[1275] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," as well as the user's emotional state in a database. The server then recommends "Online Course A for Beginners" and "Specialized Book B for Beginners" to the terminal. As the user progresses through their studies using these learning materials, the emotion engine sequentially analyzes the user's emotional state and provides advice to improve motivation as needed. If a question arises, the server suggests an appropriate explanation page. Furthermore, when the user has progressed 50%, it suggests "Data Analysis Course C" as the next step.

[1276] This system provides learning support tailored to the user's needs and emotional state, allowing them to improve their skills efficiently.

[1277] The processing flow will be explained below.

[1278] Step 1:

[1279] A user accesses the system through a terminal. The terminal displays a registration / login screen to the user. The user enters the required information such as name, email address, and password, and presses the submit button.

[1280] Step 2:

[1281] The device sends the entered information to the server, which then checks the received information against the database, saving the information in the database if it is a new registration, or authenticating the user if they are already registered.

[1282] Step 3:

[1283] The server sends the authentication result to the terminal. If the authentication is successful, the user can access the system. If the authentication is unsuccessful, an error message is displayed.

[1284] Step 4:

[1285] The server generates initial questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, the questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to learning?"

[1286] Step 5:

[1287] The user answers questions through the device. For example, they answer "I want to learn Python programming." The device then sends the user's answers to the server.

[1288] Step 6:

[1289] The server analyzes the received response data, uses text analysis and machine learning algorithms to identify the user's learning needs, and stores the results in a database.

[1290] Step 7:

[1291] The server receives the user's audio and video data, analyzes it using an emotion engine, and identifies the user's current emotional state, which is also stored in a database.

[1292] Step 8:

[1293] The server selects the most suitable learning content based on the analysis results. For example, "Online Course A for Beginners" and "Specialized Book B for Beginners" may be selected. The selected learning content is then sent to the device.

[1294] Step 9:

[1295] The device displays the learning content selected by the user. The user then begins learning by viewing the recommended learning content. Motivational content tailored to the user's emotional state is also displayed on the device.

[1296] Step 10:

[1297] If a user has a question about their learning as they proceed, they can send it to the server via their device. For example, they might ask, "I don't know how to use a Python function."

[1298] Step 11:

[1299] The server receives the question, searches an internal database or external resources to find an appropriate answer, and sends the answer to the device. For example, it sends an answer such as "For the basics of Python functions, please see this explanation page." It also provides appropriate feedback based on the user's emotional state along with the answer to the question.

[1300] Step 12:

[1301] The device periodically records the user's learning progress and emotional state and transmits it to the server. Progress data is accumulated throughout the user's learning activities.

[1302] Step 13:

[1303] The server analyzes the progress data and emotional data and selects new learning content based on the user's current learning situation and emotional state. For example, if the progress reaches 50%, the server selects the content, "We recommend Data Analysis Course C as your next step."

[1304] Step 14:

[1305] The server selects new learning content and sends it to the device along with advice on how to study based on the user's emotional state. The device displays this information to the user and suggests the next learning step. The user can then use the new learning content to further improve their skills.

[1306] In this way, through a series of processing steps, optimal learning support can be provided based on the user's learning needs and emotional state.

[1307] Example 2

[1308] 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."

[1309] Conventional learning support systems have difficulty accurately grasping a user's learning needs and emotional state and providing optimal learning content and feedback based on the results. Furthermore, they lack mechanisms for flexibly responding to diverse user needs, such as suggesting new content based on learning progress or providing immediate responses to questions during learning. To address these issues, a system is needed that can analyze a user's learning needs and emotional state in real time and provide optimal learning content and feedback based on that analysis.

[1310] 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.

[1311] In this invention, the server includes means for analyzing the user's learning needs and saving them in a database, means for recording the user's learning progress and emotional state and sending them to the server, and means for selecting new learning content and feedback based on the user's learning progress and emotional state and sending them to the terminal, thereby enabling optimal learning support based on the user's learning needs and emotional state.

[1312] "User" refers to an individual who accesses the system, inputs their learning needs and emotional state, and uses the learning content.

[1313] "Terminal" refers to a device used by a user to access the system, such as a smartphone, tablet, or PC.

[1314] "Server" refers to a central processing unit that analyzes information received from users, stores it in a database, selects learning content, provides feedback, and so on.

[1315] "Learning needs" refers to the skills or areas of knowledge a user wishes to improve and the specific requests and desires associated with them.

[1316] "Emotional state" refers to the user's current psychological and emotional state, which is analyzed based on audio and video data.

[1317] "Database" refers to an information storage system for saving and managing analysis results, such as the user's learning needs and emotional state.

[1318] "Learning content" refers to learning materials and information provided to users for learning purposes, including, for example, online courses and specialized books.

[1319] "Feedback" refers to advice, encouragement, and motivational comments provided based on the user's learning progress and emotional state.

[1320] "Text analysis" refers to the process of analyzing text data entered by a user to identify learning needs.

[1321] A "machine learning algorithm" refers to a computational method for learning from large amounts of data and making predictions and classifications.

[1322] An "emotion engine" refers to software that analyzes a user's audio and video data to identify their emotional state.

[1323] "Progress information" refers to the progress a user makes as they progress through their studies, and includes, for example, the percentage of content that has been studied and the steps that have been achieved.

[1324] MODE FOR CARRYING OUT THE INVENTION

[1325] The present invention provides a system that allows users to select optimal learning content based on their own learning needs and emotional state, thereby improving their skills efficiently. Detailed embodiments of the system will be described below.

[1326] First, a user accesses the system using a device (smartphone, tablet, PC, etc.). The device displays a registration / login screen to the user. The user enters the required information such as name, email address, and password, and submits it. The server checks the received information against the database. If the user is a new user, the server saves the information in the database, and if the user is an existing user, it performs authentication. If authentication is successful, the user is able to access the system.

[1327] Next, the server generates initial questions for the registered or logged-in user to elicit their learning needs and sends them to the terminal. The terminal displays these questions, and the user answers them. For example, questions include, "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user's answers are sent from the terminal to the server.

[1328] The server analyzes the user's response data using text analysis and machine learning algorithms, and this analysis identifies the user's individual learning needs. The server also runs an emotion engine that analyzes the user's emotional state based on audio and video data. This emotion engine uses APIs from common cloud services, such as Microsoft and Google APIs. The analysis results are stored in a database.

[1329] The server selects optimal learning content based on the user's learning needs and emotional state, which are stored in a database. The selected learning content (e.g., information on online courses or specialized books) is sent to the terminal and suggested to the user. For example, "Python programming introductory course A" and "beginner-oriented specialized book B" may be selected. Motivational content and feedback are also provided based on the user's emotional state.

[1330] As the user progresses through the learning process using the suggested learning content, the device records their progress and emotional state and sends it to the server. If the user asks a question while learning, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question such as "I don't know how to use a Python function," the server responds with "Please see this explanation page." The system also analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[1331] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes the progress data and emotional data, selects new learning content based on the user's current learning situation, and sends new suggestions to the device. For example, if progress reaches 50%, the server will suggest, "We recommend Data Analysis Course C as your next step." It also provides advice on appropriate learning methods based on the user's emotional state.

[1332] As a concrete example, consider the case where a user wants to learn Python programming. The user accesses the system using a terminal and logs in. The server stores the user's learning need, "I want to learn Python programming," as well as the user's emotional state, in a database. The server then recommends "online course A for beginners" and "specialized book B for beginners" to the terminal. As the user progresses through their studies using these learning materials, the emotion engine sequentially analyzes the user's emotional state and provides advice to improve motivation as needed. If a question arises, the server suggests an appropriate explanation page. Furthermore, when the user has progressed 50%, it suggests "data analysis course C" as the next step.

[1333] This system provides learning support tailored to the user's needs and emotional state, allowing them to improve their skills efficiently.

[1334] Prompt Sentence Examples

[1335] 1. "Enter your name and email address to create an account."

[1336] 2. "In what areas would you like to improve your skills?"

[1337] 3. "Please describe your current emotional state."

[1338] 4. "I recommend Course A, an introductory course on Python programming, and Book B, a specialized book for beginners."

[1339] 5. "I have a question about Python functions."

[1340] 6. "Why not take Course C in Data Analysis as your next step?"

[1341] In this way, users can receive optimal learning content and feedback based on their own learning progress and emotional state.

[1342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1343] The flow of this system's program processing

[1344] Step 1: User registration and login

[1345] Input: Name, email address, and password entered by the user on the device

[1346] Output: User authentication result (authentication success / failure)

[1347] Specific description:

[1348] The terminal displays a registration / login screen to the user. The user enters their name, email address, and password and presses the submit button. The terminal sends the entered information to the server via an HTTP POST request. The server checks the received information against its database. If the user is a new user, the server saves the information in the database; if the user is an existing user, the server authenticates them. If authentication is successful, the user is allowed to access the system.

[1349] Specific behavior:

[1350] The terminal displays the form and receives input from the user.

[1351] The terminal transmits the input data to the server.

[1352] The server checks the user information against the database and returns the results to the terminal.

[1353] Step 2: Initial interactive session

[1354] Input: Initial setup questions sent by the server

[1355] Output: User response data

[1356] Specific description:

[1357] The server generates initial setup questions for the logged-in user and sends them to the device. The device displays these questions on the screen, and the user answers them. For example, questions include "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user's answers are sent from the device to the server.

[1358] Specific behavior:

[1359] The server generates question data and sends it to the terminal in JSON format.

[1360] The terminal displays questions and collects answers from the user.

[1361] The terminal transmits the user's answer to the server.

[1362] Step 3: Data analysis and storage

[1363] Input: User response data and emotion data

[1364] Output: Learning needs analysis and emotional state identification

[1365] Specific description:

[1366] The server analyzes the user's response data using text analysis and machine learning algorithms. This analysis identifies the user's learning needs. The server also uses an emotion engine to analyze the user's audio and video data to identify their emotional state. The server then stores the results of these analyses in a database.

[1367] Specific behavior:

[1368] The server analyzes the response data using morphological analysis and machine learning models.

[1369] An emotion engine is used to identify emotional states from audio and video data.

[1370] The analysis results are saved in a database.

[1371] Step 4: Suggest learning content

[1372] Input: Learning needs and emotional states stored in a database

[1373] Output: Selection of optimal learning content

[1374] Specific description:

[1375] The server selects the most appropriate learning content based on the user's learning needs and emotional state, which are stored in a database. The server then sends the selected learning content to the terminal and suggests it to the user. For example, "Python Programming Introductory Course A" and "Beginner's Specialized Book B" may be suggested. Feedback is also provided to improve motivation.

[1376] Specific behavior:

[1377] The server obtains the user's learning needs and emotional state from a database.

[1378] Use an algorithm to select the best learning content.

[1379] The selected content information is sent to the terminal in JSON format.

[1380] The terminal displays the information on the screen.

[1381] Step 5: Learning support

[1382] Input: Learning progress information, emotional state, user questions

[1383] Output: Record of learning progress information, answers to questions

[1384] Specific description:

[1385] As the user progresses through the learning process using the suggested learning content, the device records learning progress information and emotional state and sends them to the server. If the user has a question, the device sends the question to the server. The server receives the question, searches for the corresponding answer, and sends it to the device. For example, in response to a question like "I don't know how to use a Python function," the server responds with "Please see this explanation page." The device also analyzes the user's emotional state at the time of the question and provides appropriate feedback.

[1386] Specific behavior:

[1387] The device periodically transmits learning progress information and emotional state to the server.

[1388] The user enters a question and the terminal sends it to the server.

[1389] The server retrieves the answer and sends it to the terminal, which displays it.

[1390] Step 6: Progress management and new proposals

[1391] Input: Learning progress information, emotional state

[1392] Output: New learning content suggestions

[1393] Specific description:

[1394] The device periodically sends the user's learning progress information and emotional state to the server. The server analyzes this data and selects new learning content based on the user's current learning situation. For example, if the user's progress reaches 50%, the server will suggest "We recommend Data Analysis Course C as your next step." The server also provides advice on appropriate learning methods based on the user's emotional state.

[1395] Specific behavior:

[1396] The device periodically transmits learning progress data and emotional state to the server.

[1397] The server analyzes this data and selects new learning content.

[1398] The server sends the proposal in JSON format to the device, which displays it on the screen.

[1399] This process allows users to receive optimal learning content and feedback based on their own learning progress and emotional state.

[1400] (Application example 2)

[1401] 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."

[1402] Conventional learning support systems have had difficulty providing learning content that takes into account the user's learning needs as well as their emotional state at any given time. It has also been difficult to provide advice to improve motivation based on the user's emotional state, making it impossible to maximize learning efficiency. Furthermore, it has been insufficient to utilize generative AI models related to dynamic learning content suggestions based on the user's learning needs and emotional state.

[1403] The identification process performed by the identification 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 analyzing the user's learning needs and storing them in a database, means for selecting optimal learning content based on the analysis results and sending it to the terminal, and means for analyzing the user's emotional state and providing advice to improve motivation. This makes it possible to provide optimal learning content based on the user's learning progress and emotional state.

[1404] "User" refers to an individual who uses this system.

[1405] "Device" refers to an electronic device used by a user to access the system and receive learning content, including smartphones, tablets, and personal computers.

[1406] "Learning needs" refers to the skills and knowledge that a user wants to improve, as well as the desires and needs regarding learning content.

[1407] "Server" refers to a computer system that centrally processes data, manages databases, and analyzes users' learning needs and progress information.

[1408] "Analysis" refers to the processing and understanding of the learning needs and emotional state data collected by the server from the user.

[1409] A "database" is an information storage system for storing and managing data such as a user's learning needs, progress information, and emotional state.

[1410] "Learning content" refers to information resources provided to assist users in their learning, including online courses, specialized books, videos, and the like.

[1411] "Emotional state" refers to the user's current psychological and emotional state, including stress level and motivation during learning.

[1412] "Motivational advice" refers to suggestions to encourage and motivate the user to continue learning based on their emotional state.

[1413] "Progress" refers to the degree to which a user has progressed through the learning content.

[1414] A "generative AI model" refers to an artificial intelligence model that uses machine learning technology to incorporate algorithms that dynamically generate content suggestions based on the user's learning needs and emotional state.

[1415] "Prompt" refers to the input or instructions used by a generative AI model to generate a desired output.

[1416] A system embodying the present invention provides optimal learning content based on a user's learning needs and emotional state. Specific embodiments of the system will be described below.

[1417] First, a user accesses the system using a device such as a smartphone. The device displays a registration / login screen to the user. The user enters the required information (name, email address, password, etc.) and submits it. The server stores the received information in a database and performs authentication. If authentication is successful, the user is able to access the system.

[1418] Next, the server generates questions to elicit the user's learning needs and sends them to the device. The device displays these questions. For example, they include questions such as "In what areas do you want to improve your skills?" and "How much time can you devote to studying?" The user answers these questions through the device. The server receives the answer data and analyzes it. This analysis uses text analysis libraries (e.g., TextBlob) and machine learning algorithms.

[1419] Furthermore, the server runs an emotion engine that analyzes the user's emotional state. The emotion engine analyzes the user's audio and video data to identify the user's current emotional state. This allows the user's learning progress and emotional state to be stored in a database.

[1420] The server uses a generative AI model to suggest optimal learning content based on the user's learning needs and emotional state stored in a database. The generative AI model creates prompts based on the user's needs and selects and provides optimal content based on those prompts. For example, it creates a prompt recommending "Python Programming Introductory Course A" and suggests that course to the user.

[1421] The device displays suggested learning content to the user. As the user uses this learning content to study, the device records learning progress information and sends it to the server. At the same time, the server analyzes the progress data and responds to questions the user may have along the way. The server receives the questions, searches for related learning content or explanation pages, and sends them back to the device.

[1422] The server also periodically analyzes the user's emotional state and learning progress and provides advice to improve motivation, again based on prompts generated by a generative AI model.

[1423] As a concrete example, if a beginner programmer registers the learning need of "I want to learn Python programming," the server analyzes the user's response to the question, "In what field do you want to improve your skills?" If the result of the sentiment analysis is positive, the server will suggest "Python programming introductory course A" and "specialized book B for beginners." If the emotional state is negative, the server will suggest video C to improve motivation.

[1424] An example of a prompt is:

[1425] "Suggest the best learning content for users based on their learning needs:

[1426] Learning Needs: Python Programming, Current Emotional State: Positive"

[1427] This prompt is then fed into a generative AI model to suggest optimal learning content.

[1428] In this way, a system that maximizes the user's learning efficiency is realized.

[1429] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1430] Step 1:

[1431] A user accesses the learning platform using a terminal. The user enters the required information such as name, email address, and password to register or log in. The input data is sent from the terminal to the server, which stores it in a database or authenticates it. If the login is successful, the server allows the user to access the system. The input data is user information (name, email address, password, etc.), and the output is the authentication result (success or failure).

[1432] Step 2:

[1433] The server generates initial questions to elicit the user's learning needs. For example, questions such as "In what areas do you want to improve your skills?" or "How much time can you devote to learning?" are generated and sent to the device. The user answers these questions and sends them back to the server via the device. The input data are the user's answers (learning needs, time available for learning, etc.), and the output is the saved answer data.

[1434] Step 3:

[1435] The server analyzes the response data received from the user using a text analysis library (e.g., TextBlob) and machine learning algorithms to identify learning needs. At the same time, the server runs an emotion engine that analyzes the user's audio and video data to identify their current emotional state. The resulting data, which represent the user's learning needs and emotional state, are stored in a database. The input data are the user's responses and audio / video data, and the output is the analysis results (learning needs and emotional state).

[1436] Step 4:

[1437] The server utilizes a generative AI model to select optimal learning content based on the user's learning needs and emotional state stored in a database. A prompt (e.g., "Please suggest optimal learning content for the user based on the following learning needs: Learning need: Python programming, Current emotional state: Positive") is input to the generative AI model, which then suggests optimal learning content. The output suggestions are then sent to the device. The input data is the prompt, and the output is learning content suggestions made by the generative AI model.

[1438] Step 5:

[1439] The device displays the suggested learning content to the user, who then uses the displayed learning content (e.g., an introductory course A on Python programming or a specialized book B for beginners) to advance their learning. The input data is the suggested learning content, and the output is the content displayed to the user.

[1440] Step 6:

[1441] As the user continues to study, the device records learning progress information and periodically sends it to the server. The learning progress information includes data on how far the user has progressed in their studies. In addition, if the user enters a question while studying, the device sends the question to the server. The input data is the learning progress information and the question content, and the output is data sent to the server.

[1442] Step 7:

[1443] The server receives the user's learning progress information and question content, searches for appropriate answers and explanations, and sends them back to the device. It also analyzes the progress information and emotional state to suggest new learning content and provide advice to improve motivation. Utilizing a generative AI model, it generates optimal advice based on the prompt text. The input data is learning progress, question content, and emotional state, and the output is suggested answers and advice.

[1444] Step 8:

[1445] The terminal displays the answers and advice from the server to the user, who can refer to them and continue learning. The input data are the answers and advice received from the server, and the output is the information displayed to the user.

[1446] This system makes it possible to provide optimal learning support that takes into account the user's learning needs and emotional state.

[1447] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1448] 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.

[1449] 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 robot 414.

[1450] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1451] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1452] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1453] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1454] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1455] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1456] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1457] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1458] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1459] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1460] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1461] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1462] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1463] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1464] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1465] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1466] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1467] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1468] The following is further disclosed regarding the above embodiment.

[1469] (Claim 1)

[1470] A means for a user to input learning needs via a terminal;

[1471] A means for the server to analyze the user's learning needs and store them in a database;

[1472] A means for the server to select the most suitable learning content based on the analysis results and send it to the device;

[1473] a means for displaying learning content selected by a user on the terminal;

[1474] a means for recording the user's learning progress and transmitting the recording to a server;

[1475] A means for the server to select new learning content based on the learning progress and transmit the content to the terminal;

[1476] A system including:

[1477] (Claim 2)

[1478] 2. The system according to claim 1, wherein the server includes means for receiving a question from a user during learning, searching for a corresponding answer, and returning the answer to the terminal.

[1479] (Claim 3)

[1480] 10. The system of claim 1, wherein the server includes means for identifying the user's learning needs using text analysis and machine learning algorithms.

[1481] "Example 1"

[1482] (Claim 1)

[1483] A means for a user to input learning needs via a terminal;

[1484] A means for the server to identify the user's learning needs using text analysis and machine learning algorithms and store the identified needs in a database;

[1485] A means for the server to select the most suitable learning content based on the analysis results and send it to the device;

[1486] a means for displaying learning content selected by a user on the terminal;

[1487] a means for recording the user's learning progress and transmitting the recording to a server;

[1488] A means for the server to select new learning content based on the learning progress and transmit the content to the terminal;

[1489] a means for a user to input questions via a terminal during learning;

[1490] A means for the server to receive a question from a user, search for a corresponding answer from a database or an external resource, and return the answer to the terminal;

[1491] A system including:

[1492] (Claim 2)

[1493] 10. The system of claim 1, wherein the server includes means for using the generative AI model through an initial interaction session to generate questions for the user to elicit learning needs.

[1494] (Claim 3) ...

Claims

1. A means for a user to input learning needs via a terminal; A means for the server to analyze the user's learning needs and store them in a database; A means for the server to select the most suitable learning content based on the analysis results and send it to the device; a means for displaying learning content selected by a user on the terminal; a means for recording the user's learning progress and transmitting the recording to a server; A means for the server to select new learning content based on the learning progress and transmit the content to the terminal; A system including:

2. 2. The system according to claim 1, wherein the server includes means for receiving questions from the user during learning, retrieving corresponding answers, and returning the answers to the terminal.

3. 10. The system of claim 1, wherein the server includes means for identifying the user's learning needs using text analysis and machine learning algorithms.

Images