system

Abstract

Provide a system. A means for collecting a user's learning history and progress; means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user; A means of assessing the user's learning progress and suggesting areas for enhancement or improvement; A means including a generative model that generates specific explanations and examples for difficult content; A means for generating and providing messages to maintain motivation according to the user's learning progress; A system including:

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] To study effectively, an optimal learning plan tailored to each individual's goals and level is necessary, but many people are unsure of the learning method that best suits them, making it difficult for them to continue their studies. Furthermore, the domestic education market is large, and awareness of lifelong learning is growing, leading to an increase in the number of people seeking new learning opportunities. However, it is difficult to provide appropriate support based on each individual's learning progress and level of understanding, and typical learning methods are unable to fully meet individual needs. This reduces the effectiveness of learning and creates obstacles that make it difficult to maintain motivation. [Means for solving the problem]

[0005] To solve this problem, the present invention provides an artificial intelligence engine that collects a user's learning history and progress, analyzes the collected data, and generates an optimal learning plan for the user. The system further includes a means for evaluating the user's learning progress and suggesting areas for strengthening or improvement. It also includes a means including a generative model that generates specific explanations and examples for difficult content. Furthermore, the system provides a means for generating and providing messages to maintain motivation according to the user's learning progress, making it easier for users to continue learning. Furthermore, the generative model generates specific explanations and examples based on the user's questions, thereby deepening the user's understanding. This makes it possible to provide optimal support according to each user's learning progress and improve learning effectiveness. Furthermore, the system customizes messages to maintain motivation according to the user's learning progress, thereby maintaining the user's motivation to learn.

[0006] "User" refers to an individual who uses this system to learn.

[0007] "Study history" refers to a record of the user's past learning content, time, grades, etc.

[0008] "Progress" refers to the learning content that the user is currently working on and the degree of progress.

[0009] "Artificial Intelligence Engine" refers to the artificial intelligence technology used to analyze user data and generate an optimal learning plan.

[0010] "Data analysis" refers to the process of analyzing users' learning patterns and level of understanding based on collected data.

[0011] A "study plan" refers to a guideline for planning the optimal learning materials, study content, and study time allocation for a user.

[0012] "Improvement points" refer to areas or content where users should further strengthen their learning.

[0013] "Areas for improvement" refers to areas or content that the user does not understand or needs to review.

[0014] A "generative model" refers to a model that generates specific explanations and examples based on the user's questions and progress.

[0015] "Maintaining motivation" refers to the process of increasing and maintaining users' motivation to continue learning.

[0016] "Messages" refer to encouraging and instructive sentences generated by the AI ​​engine based on the user's learning progress. [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 describes an AI-based learning personal assistant system to personalize and effectively assist users in their learning.

[0039] This system includes a server, a user terminal, and an artificial intelligence engine. The system operates as follows.

[0040] User data collection

[0041] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[0042] Analyzing data and creating a learning plan

[0043] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[0044] Learning progress assessment and suggestions

[0045] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[0046] Explaining difficult topics and providing examples

[0047] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0048] Support for maintaining motivation

[0049] The server generates encouraging messages and achievements based on the user's learning progress. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[0050] Specific examples

[0051] For example, let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user's device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to an artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. If the user encounters difficulties during learning, the user's device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. Additionally, depending on the user's progress, the server generates encouraging messages, which the user's device notifies, helping them continue their learning.

[0052] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user logs in to the system, enters the authentication information to log in, and presses the submit button.

[0056] Step 2:

[0057] The terminal receives the user's login information and sends it to the server, which includes the user ID and password.

[0058] Step 3:

[0059] After verifying that the user has entered the correct authentication information, the server retrieves the user's learning history and progress data from the database, including past learning content, study time, test results, etc.

[0060] Step 4:

[0061] The server sends the acquired user data to an AI engine, which analyzes the user's learning history and progress and generates an optimal learning plan.

[0062] Step 5:

[0063] Based on the analysis results, the AI ​​engine generates an optimal study plan for the user, which includes recommended learning materials, study time allocation, and study order.

[0064] Step 6:

[0065] The server sends the generated learning plan to the terminal, which displays the learning plan to the user.

[0066] Step 7:

[0067] The user performs the learning activity. The user uses the learning material according to the learning content, and if the user has any questions or encounters difficult content, the user inputs the questions into the system.

[0068] Step 8:

[0069] The device sends the user's question to the server, which then passes the question to an artificial intelligence engine, requesting it to generate appropriate explanations and examples.

[0070] Step 9:

[0071] The AI ​​engine generates explanations and examples based on the user's question and sends them to the server, which then sends them to the device, which displays them to the user.

[0072] Step 10:

[0073] The device records the user's learning activities in real time and transmits the progress data to the server, which periodically evaluates the learning progress and has the AI ​​engine analyze the progress data.

[0074] Step 11:

[0075] Based on the analysis results, the server will suggest areas for improvement and strengthen the user, and will also send motivational messages, including encouraging messages generated by the AI ​​engine, to the device.

[0076] Step 12:

[0077] The device displays encouraging messages and notifications of areas for improvement to the user, helping them to stay motivated to continue learning.

[0078] Example 1

[0079] 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."

[0080] Conventional learning support systems have not provided sufficient personalized learning support that takes into account each user's progress and learning history. Furthermore, when users encounter difficult content during learning, it is difficult to provide specific explanations and examples at the appropriate time. As a result, users' learning efficiency and motivation can decline.

[0081] 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.

[0082] In this invention, the server includes: means for collecting a user's learning history and progress; means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user; means for evaluating the user's learning progress and suggesting areas for strengthening or improvement; means including a generative model that generates specific explanations and examples based on questions entered by the user for specific problems or difficult content; means for generating and providing messages to maintain motivation according to the user's learning progress; and means for generating encouraging messages according to the user's learning plan and progress and notifying the user terminal. This makes it possible to provide learning support and maintain motivation that is optimized for each individual user.

[0083] A "user" is an individual who uses the system to carry out learning activities.

[0084] "Learning history" is a record of the learning activities that a user has undertaken to date.

[0085] "Progress" refers to the user's current achievement or progress in learning.

[0086] "Means of collection" refers to the functions and mechanisms for inputting and storing a user's learning history and progress into the system.

[0087] "Analyzing data" means organizing information based on collected learning data and extracting useful insights.

[0088] An "artificial intelligence engine" refers to the entire algorithm or system that analyzes a user's learning data and generates the optimal learning plan.

[0089] A "study plan" is a plan that includes the study materials to be used, study time, study order, etc., to enable the user to study efficiently.

[0090] "Means of evaluation" are functions and mechanisms for regularly checking users' learning progress and measuring the results.

[0091] "Improvements" are areas where users should learn more.

[0092] "Areas for improvement" are areas that users don't understand or items that need to be corrected to improve efficiency.

[0093] A "generative model" is a computational model that can generate appropriate explanations and concrete examples in response to questions that users have.

[0094] Maintaining "motivation" involves activities that include actions and messages that motivate users to continue learning.

[0095] "Means for generating and providing messages" refers to a function or mechanism for creating messages according to the user's progress and informing the user of these messages.

[0096] "Encouraging messages" are positive words or notifications that motivate users to continue learning.

[0097] A "user terminal" is a device (smartphone, tablet, PC, etc.) that a user uses to access the system and carry out learning activities.

[0098] The present invention describes a learning personal assistant system that utilizes artificial intelligence to personalize and effectively assist users in their learning. The system includes a server, a user terminal, and an artificial intelligence engine.

[0099] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from a database (e.g., MySQL (registered trademark)) and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[0100] The server sends the collected data to an artificial intelligence engine (for example, OpenAI's GPT-3 (registered trademark)), which analyzes the user's learning data. The artificial intelligence engine analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time should be spent, and the order in which the learning should be done.

[0101] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine. The artificial intelligence engine analyzes the evaluation results and identifies areas for strengthening and improvement. The server receives feedback from the artificial intelligence engine and sends it to the user's device. The user can then receive feedback on which areas need strengthening or improvement based on their own progress.

[0102] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0103] The server generates encouraging messages and achievements based on the user's learning progress. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, keeping the user motivated to continue learning.

[0104] Specific examples

[0105] Let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user's device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to an artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. If the user encounters difficulties during learning, the user's device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. Additionally, depending on the user's progress, the server generates encouraging messages, which the user's device notifies the user of, supporting them in continuing their learning.

[0106] Example prompts for generative AI models

[0107] "User ID: 001 is having trouble with the basics of programming. Please provide an explanation and concrete examples based on the user's learning history."

[0108] "Generate an encouraging message based on the progress of user ID: 001."

[0109] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1:

[0112] A user logs in to the system.

[0113] Specific behavior:

[0114] The user launches the learning app, enters their user ID and password on the login screen, and presses the "Login" button. This causes the user device to send the entered login information to the server.

[0115] input:

[0116] User ID and password

[0117] output:

[0118] The login information is sent to the server.

[0119] Step 2:

[0120] The server retrieves the user's learning history and progress from the database.

[0121] Specific behavior:

[0122] The server receives the login information, searches for and retrieves the user's learning history and progress from a database (e.g., MySQL) based on the user ID, and stores the retrieved data in temporary memory (e.g., Redis).

[0123] input:

[0124] User ID

[0125] output:

[0126] Learning history and progress data is stored in temporary memory.

[0127] Step 3:

[0128] The server sends the collected data to an artificial intelligence engine.

[0129] Specific behavior:

[0130] The server sends the user's learning data stored in temporary memory to an artificial intelligence engine (e.g., GPT-3).

[0131] input:

[0132] User learning history and progress data

[0133] output:

[0134] The data is sent to an artificial intelligence engine.

[0135] Step 4:

[0136] The artificial intelligence engine analyzes the user's learning data and generates the optimal learning plan.

[0137] Specific behavior:

[0138] The AI ​​engine analyzes the received learning data, analysing the user's learning patterns and level of understanding. Based on the results, it generates an optimal learning plan, including the learning materials to be used, study time, and learning order, and returns it to the server.

[0139] input:

[0140] User learning data

[0141] output:

[0142] The best study plan

[0143] Step 5:

[0144] The server sends the learning plan to the user's device.

[0145] Specific behavior:

[0146] The server receives the optimal learning plan from the AI ​​engine and sends it to the user's device, which displays it to the user and tells them what to study next.

[0147] input:

[0148] The best study plan

[0149] output:

[0150] The learning plan will be displayed on the user's device.

[0151] Step 6:

[0152] The user's device records the user's learning progress in real time and transmits it to the server.

[0153] Specific behavior:

[0154] As the user progresses through their studies, the user's device records the progress of the study, including the start time, end time, and study items, in real time, and sends this information to the server at regular intervals (e.g., every 30 minutes).

[0155] input:

[0156] Learning progress data

[0157] output:

[0158] Progress data is sent to the server.

[0159] Step 7:

[0160] The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine.

[0161] Specific behavior:

[0162] The server evaluates the user's progress based on the received learning progress data and sends the results to the AI ​​engine, which analyzes the evaluation data and identifies areas for improvement.

[0163] input:

[0164] Learning progress data

[0165] output:

[0166] The evaluation results are sent to an artificial intelligence engine.

[0167] Step 8:

[0168] The artificial intelligence engine analyzes the evaluation results and identifies areas for strengthening and improvement.

[0169] Specific behavior:

[0170] The AI ​​engine analyzes the evaluation data, identifies areas where the user needs to improve and provides feedback to the server.

[0171] input:

[0172] Evaluation results

[0173] output:

[0174] Feedback on enhancements and improvements

[0175] Step 9:

[0176] The server sends feedback on enhancements and improvements to the user's device.

[0177] Specific behavior:

[0178] The server receives feedback from the AI ​​engine and sends it to the user's device, which displays the feedback to the user and provides advice based on their progress.

[0179] input:

[0180] feedback

[0181] output:

[0182] Feedback is displayed on the user's device.

[0183] Step 10:

[0184] The user types a question.

[0185] Specific behavior:

[0186] If a user encounters a problem while learning, they enter a question into the question input field within the learning app and press the "Submit" button.

[0187] input:

[0188] Question

[0189] output:

[0190] A question is sent from the user terminal to the server.

[0191] Step 11:

[0192] The server sends the question to the artificial intelligence engine.

[0193] Specific behavior:

[0194] The server passes the question sent from the user's device to the artificial intelligence engine, requesting it to generate an explanation and specific examples.

[0195] input:

[0196] Question

[0197] output:

[0198] The question is sent to an artificial intelligence engine.

[0199] Step 12:

[0200] The artificial intelligence engine generates explanations and examples based on the question.

[0201] Specific behavior:

[0202] The AI ​​engine analyzes the question and generates appropriate explanations and examples, which are then sent to the server.

[0203] input:

[0204] Question

[0205] output:

[0206] Explanation and examples

[0207] Step 13:

[0208] The server sends explanations and examples to the user's terminal.

[0209] Specific behavior:

[0210] The server sends the explanations and concrete examples received from the artificial intelligence engine to the user terminal, which then displays them to the user.

[0211] input:

[0212] Explanation and examples

[0213] output:

[0214] Explanations and examples are displayed on the user's device.

[0215] Step 14:

[0216] The server generates encouraging messages based on the user's progress.

[0217] Specific behavior:

[0218] The server analyzes the user's learning progress data and automatically generates encouraging messages and achievements, which are customized based on the user's progress and goal achievements.

[0219] input:

[0220] Learning progress data

[0221] output:

[0222] Encouraging messages and achievements

[0223] Step 15:

[0224] The server sends encouraging messages to the user terminal.

[0225] Specific behavior:

[0226] The server transmits the generated encouraging message to the user terminal, and the user terminal notifies the user of the message.

[0227] input:

[0228] Messages of encouragement

[0229] output:

[0230] The message is sent to the user terminal.

[0231] Through these steps, the system can personalize and effectively support users' learning activities.

[0232] (Application example 1)

[0233] 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."

[0234] The problem that this invention aims to solve is to individually optimize a user's learning, provide effective learning support, provide real-time explanations for stumbling blocks and questions during learning, and maintain the user's motivation. Furthermore, by realizing this across multiple devices, it aims to improve the user's learning experience.

[0235] 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.

[0236] In this invention, the server includes means for collecting a user's learning history and progress, means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user, means for evaluating the user's learning progress and suggesting areas for strengthening or improvement, means including a generative model that generates specific explanations and examples for difficult content, means for generating and providing messages to maintain motivation according to the user's learning progress, means for providing a personalized learning plan on multiple devices, and means for generating explanations in real time in response to the user's questions. This makes it possible to comprehensively support the user's learning experience and achieve individually optimized learning.

[0237] "Means for collecting a user's learning history and progress" refers to devices or software that record what a user has learned in the past and their progress at that time, and consolidate this information into a system.

[0238] "Means including an artificial intelligence engine that analyzes collected data and generates optimal learning plans for users" refers to devices or software that use AI to analyze collected user learning data and create optimal learning plans for each user based on that data.

[0239] "Means for assessing a user's learning progress and suggesting areas for reinforcement or improvement" refers to devices or software that periodically check a user's learning status and suggest areas that need reinforcement or improvement in order to support effective learning.

[0240] "Means including a generative model that generates specific explanations and examples for difficult content" refers to devices or software that use a generative model to automatically generate specific, easy-to-understand explanations and examples for content that users find difficult to understand while studying.

[0241] "Means for generating and providing messages to maintain motivation according to the user's learning progress" refers to devices or software that generate encouraging and supportive messages according to the user's learning progress, motivating the user to continue learning.

[0242] "Means for providing personalized learning plans on multiple devices" refers to devices or software that make learning plans customized for each user available on multiple devices, such as smartphones, tablets, and smart glasses.

[0243] "Means for generating explanations in real time in response to user questions" refers to devices or software that instantly generate and provide appropriate explanations in response to questions that users have while studying.

[0244] To realize the system of the present invention, a server, a user terminal, and an artificial intelligence engine (AI engine) are required. This system provides learning support to users through the following specific process.

[0245] Major hardware and software configurations

[0246] Hardware:

[0247] Server: AWS (registered trademark) (Amazon Web Services) or Google (registered trademark) Cloud

[0248] User devices: smartphones, tablets, smart glasses

[0249] software:

[0250] Database: MySQL

[0251] Artificial intelligence engine: Google Cloud AI, OpenAI GPT

[0252] System Operation Overview

[0253] 1. User data collection:

[0254] Users log in to the system from their devices. The login information is sent to the server, which retrieves past learning history and progress from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be aggregated on the server.

[0255] 2. Analyze the data and generate a learning plan:

[0256] The server sends the collected data to an AI engine, which analyzes the data, analyzes the user's learning patterns and level of understanding, and generates an optimal learning plan, including specific learning material recommendations and study time allocations.

[0257] 3. Learning progress assessment and suggestions:

[0258] The user's device records the learning progress in real time and sends it to the server, which periodically evaluates it and sends it to the AI ​​engine to identify areas that need strengthening or improvement, and the user can receive feedback based on this.

[0259] 4. Explanation of difficult content:

[0260] When a user inputs a question during learning, the question is sent to the server, which passes it to the AI ​​engine to generate an explanation and concrete examples. The generated content is then sent to the device and provided to the user.

[0261] 5. Motivation support:

[0262] The server generates encouraging messages and achievements based on learning progress, which the device notifies the user and motivates them to continue learning.

[0263] 6. Multi-device compatibility:

[0264] Learning plans, feedback and explanations are available across multiple devices including smartphones, tablets and smart glasses.

[0265] Specific examples

[0266] For example, let's say a user (user ID: 001) wants to learn the basics of programming. The user logs into the system using their smartphone. The server collects user 001's learning history and progress from the database and sends it to the AI ​​engine. The AI ​​engine analyzes the data and generates an optimal learning plan including the next learning step. If the user gets stuck while learning, they can input a question, and the server will generate explanations and concrete examples and provide them to the user. The server also generates encouraging messages according to the user's learning progress and notifies them to keep the user motivated.

[0267] Prompt Sentence Examples

[0268] Users find it difficult to understand the basic programming concept of "loop structure." Please provide a detailed explanation with concrete examples.

[0269] In this way, the system of the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[0270] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0271] Step 1: Collect user data

[0272] A user logs into the system from their device. The login information is sent to the server. The server retrieves past learning history and progress from the database and temporarily stores it. The aggregated data includes the user's past learning content, study time, test results, etc.

[0273] Input: User login information

[0274] Data processing / calculation: Obtaining learning history and progress from the database

[0275] Output: Captured learning history and progress data

[0276] Step 2: Analyze the data and generate a learning plan

[0277] The server sends the collected data to an AI engine, which analyzes the data and analyzes the user's learning patterns and level of understanding. Based on the analysis results, an optimal learning plan is generated for the user. This plan includes which learning materials to use, how much time to spend on them, and the order in which they should be studied.

[0278] Input: Learning history and progress data

[0279] Data processing / calculation: Data analysis and plan generation using an AI engine

[0280] Output: Optimal study plan

[0281] Step 3: Assessment and recommendations for learning progress

[0282] The user's device records the learning progress in real time and sends it to the server, which then periodically sends it to the AI ​​engine to evaluate the user's progress. Based on the evaluation, suggestions for improvements and enhancements are made.

[0283] Input: Real-time learning progress data

[0284] Data processing / calculation: Progress evaluation and proposal generation using an AI engine

[0285] Output: Enhancements and Improvements

[0286] Step 4: Explaining the complexities

[0287] When a user inputs a question during learning, the question is sent to the server, which passes it to the AI ​​engine to generate an explanation and concrete examples. The generated content is then sent to the device and provided to the user.

[0288] Input: User's question

[0289] Data processing / calculation: Explanations and concrete examples generated by AI engine

[0290] Output: Generated explanations and examples

[0291] Step 5: Support to maintain motivation

[0292] The server generates encouraging messages and achievements based on the user's learning progress. Messages are customized according to the user's progress and sent to the user's device.

[0293] Input: User's learning progress data

[0294] Data processing / calculation: Server-generated encouragement messages and achievements

[0295] Output: Generated encouragement message and achievement

[0296] Step 6: Multi-device compatibility

[0297] The learning plans, feedback, and explanations are available on multiple devices, including smartphones, tablets, and smart glasses, with the data being sent from the server to each device in an appropriate format.

[0298] Input: Generated lesson plans, explanations, and feedback data

[0299] Data processing / calculation: Device-compatible format generation and data transmission

[0300] Output: Data converted into a format that can be used by each device

[0301] 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.

[0302] This invention is a learning personal assistant system that utilizes AI to personalize and effectively support users' learning. It combines an emotion engine to recognize the user's emotions and, based on those emotions, more effectively creates learning plans and maintains motivation.

[0303] This system includes a server, a user terminal, an artificial intelligence engine, and an emotion engine. The system operates as follows.

[0304] User data collection

[0305] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[0306] Analyzing data and creating a learning plan

[0307] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[0308] Emotion recognition by emotion engine

[0309] While studying, the user's device collects emotional data from the user's facial expressions and voice and sends it to the server. The emotion engine recognizes the user's emotions based on the received emotional data and uses this information to adjust the study plan and encouraging messages.

[0310] Learning progress assessment and suggestions

[0311] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[0312] Explaining difficult topics and providing examples

[0313] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0314] Support for maintaining motivation

[0315] The server generates encouraging messages and achievements based on the user's learning progress and emotional data. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[0316] Specific examples

[0317] For example, let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to the artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. The user device sends the user's facial expressions and voice to the emotion engine while learning, and if the user is confused, it adjusts the learning pace and provides additional explanations. If the user stumbles while learning, the user device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. The server also generates encouraging messages based on the user's progress and emotions, and the user device notifies the user of this, helping them continue their learning.

[0318] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[0319] The processing flow will be explained below.

[0320] Step 1:

[0321] The user logs in to the system, enters the authentication information to log in, and presses the submit button.

[0322] Step 2:

[0323] The terminal receives the user's login information and sends it to the server. This login information includes the user ID and password.

[0324] Step 3:

[0325] The server verifies the user's authentication information and, if correct, retrieves the user's learning history and progress data from a database, including past learning content, study time, test results, etc.

[0326] Step 4:

[0327] The server sends the acquired user data to an AI engine, which analyzes the learning data. The AI ​​engine analyzes the user's learning patterns and level of understanding and generates an optimal learning plan. This learning plan includes which learning materials to use, how much time to spend on each, and the learning order.

[0328] Step 5:

[0329] The server transmits the generated study plan to the terminal, which displays it to the user, who then begins studying according to the study plan.

[0330] Step 6:

[0331] Emotion data is generated using facial expressions and voice during training. For example, facial expression and voice analysis is performed using a camera and microphone.

[0332] Step 7:

[0333] The terminal collects the user's emotion data in real time and transmits it to the server.

[0334] Step 8:

[0335] The server uses an emotion engine to analyze the received emotion data and recognize the user's emotional state (e.g., confusion, satisfaction, fatigue, etc.).

[0336] Step 9:

[0337] The server determines if the lesson plan needs to be adjusted based on the perceived emotional state, for example, adjusting the lesson plan to slow down the pace or provide additional explanation if the user is confused.

[0338] Step 10:

[0339] The server sends the adjusted learning plan and additional explanations to the terminal, which displays them to the user.

[0340] Step 11:

[0341] If a user encounters a problem while studying, they can enter a question and submit it to the system.

[0342] Step 12:

[0343] The device sends the user's question to the server, which then passes the question to an artificial intelligence engine, requesting it to generate appropriate explanations and examples.

[0344] Step 13:

[0345] The AI ​​engine generates explanations and examples based on the user's question and sends them to the server, which then sends them to the device, which displays them to the user.

[0346] Step 14:

[0347] The device records the user's learning activities in real time and transmits the progress data to the server, which periodically evaluates the learning progress and has the AI ​​engine analyze the progress data.

[0348] Step 15:

[0349] Based on the analysis results, the server suggests areas for improvement to the user. It also sends messages to the device to maintain motivation, including encouraging messages, based on the evaluation results generated by the emotion engine.

[0350] Step 16:

[0351] The device displays encouraging messages and notifications of areas for improvement to the user, helping them to stay motivated to continue learning.

[0352] Example 2

[0353] 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."

[0354] Conventional learning support systems collect users' learning history and progress and provide learning plans based on that information. However, they are unable to provide support that takes into account the user's emotional state. Therefore, there is a need for a method to effectively support users in maintaining their motivation and understanding difficult content. Furthermore, there is a need for a method to generate personalized encouraging messages in real time according to the user's learning progress and deliver them at the appropriate time.

[0355] 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.

[0356] In this invention, the server includes a means for collecting the user's learning history and progress, a means including an artificial intelligence engine for analyzing the collected data to generate an optimal learning plan for the user, and a means including an emotion engine for collecting and analyzing the user's emotion data, thereby making it possible to effectively analyze the user's learning pattern and level of understanding and adjust the learning plan and encouraging messages.

[0357] "User's learning history" refers to a record of all learning activities that a user has performed in the past, including information such as learning content, study time, and test results.

[0358] "Progress" is data that indicates the user's learning progress, and includes information such as the current learning stage, level of achievement, and level of understanding.

[0359] An "artificial intelligence engine" refers to an algorithm or program that analyzes collected data and generates the optimal learning plan for the user.

[0360] An "emotion engine" refers to an algorithm or program that collects and analyzes emotional data such as a user's facial expressions and voice.

[0361] A "study plan" is a specific instruction plan for a user to effectively progress through their studies, and includes the learning materials to be used, study time, study order, etc.

[0362] "Encouragement messages" refer to encouraging text or audio messages generated to motivate users to learn.

[0363] "Difficult content" refers to specific issues or concepts that users find difficult to understand while learning.

[0364] A "generative model" refers to an algorithm or program that automatically generates specific explanations and examples based on a user's questions or requests.

[0365] "Areas for reinforcement or improvement" indicates areas that need further reinforcement or improvement as a result of evaluating the user's learning situation.

[0366] "Motivational messages" refer to personalized messages of encouragement designed to maintain or increase a user's motivation to learn.

[0367] The present invention relates to a personal learning assistant system that individually optimizes a user's learning and improves learning efficiency. The system collects the user's learning history and progress and provides an appropriate learning plan based on that. It also uses an emotion engine to recognize the user's emotional state and adjusts the learning plan and encouraging messages accordingly, thereby maintaining the user's motivation.

[0368] Explanation of program processing

[0369] This system is composed of a server, a user terminal, an AI engine, and an emotion engine. The specific operation of each component is as follows:

[0370] User data collection

[0371] When a user logs in to the system, the device sends the login information to the server. The server retrieves the user's past learning history and progress from the database based on the user ID and temporarily stores it. This allows the server to store the user's learning content, study time, and test results.

[0372] Analyzing data and creating a learning plan

[0373] The server sends the temporarily stored data to an AI engine. The AI ​​engine analyzes the user's learning data, analyzing their learning patterns and level of understanding. Based on the analysis results, it generates an optimal learning plan and returns it to the server. This learning plan includes the learning materials to be used, the study time, and the study order.

[0374] Emotion recognition by emotion engine

[0375] While studying, the device uses a camera and microphone to collect the user's facial expressions and voice. The collected emotional data is sent to a server, which then transmits it to an emotion engine. The emotion engine analyzes the emotional data and recognizes the user's emotional state. Based on the analysis results, the server adjusts the study plan and encouraging messages.

[0376] Learning progress assessment and suggestions

[0377] The device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to the AI ​​engine. Based on the feedback from the AI ​​engine, the server makes appropriate suggestions to the user.

[0378] Explaining difficult content and providing concrete examples

[0379] When a user enters a question, the device sends it to the server, which passes the question to an artificial intelligence engine and uses a generative AI model to generate appropriate explanations and examples. The generated explanations and examples are then returned from the server to the device and displayed to the user.

[0380] Support for maintaining motivation

[0381] The server generates encouraging messages and achievements based on the user's learning progress and emotional data, and the device notifies the user of the messages received from the server, thus maintaining the user's motivation to continue learning.

[0382] Specific examples

[0383] For example, let us consider a case where a user (user ID: 001) wishes to learn the basics of programming.

[0384] 1. The user terminal sends User 001's login information to the system, and the server collects User 001's learning history and progress from the database. The collected data is sent to an artificial intelligence engine, which generates an optimal learning plan.

[0385] 2. The user device collects the user's facial expressions and voice during learning and sends them to the emotion engine. If the user is confused, the learning pace will be adjusted and additional explanations will be provided.

[0386] 3. If the user encounters a problem while studying, the user device sends the question to the server, and the server generates an explanation and concrete examples and provides them to the user.

[0387] 4. The server generates encouraging messages based on the user's progress and emotions, and the user's device notifies the user of these messages to help them continue their studies.

[0388] Prompt Sentence Examples

[0389] Generate the following learning plan based on the user's learning progress and past history: The user wants to learn the basics of programming.

[0390] In this way, the learning personal assistant system of the present invention provides flexible support tailored to the individual needs of the user, and realizes effective learning and continuous learning that takes into account the user's emotional state.

[0391] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0392] Step 1:

[0393] User login and data collection

[0394] When a user logs in to the system, the terminal sends the user's login information to the server.

[0395] Input: User ID and password

[0396] Processing: The server uses the user ID to retrieve the past learning history and progress from the database.

[0397] Output: User learning history and progress data

[0398] Specific operation: The terminal displays a login form and sends the ID and password entered by the user to the server. The server receives this and executes a database query. The result is temporarily saved.

[0399] Step 2:

[0400] Analyzing data and creating a learning plan

[0401] The server sends the temporarily stored user learning data to the artificial intelligence engine.

[0402] Input: User learning history and progress data

[0403] Processing: The artificial intelligence engine analyzes the data and analyzes the user's learning patterns and comprehension.

[0404] Output: Optimal study plan

[0405] How it works: The server sends the data to the AI ​​engine, which uses an analytical algorithm to generate a learning plan, which is then returned to the server in JSON format.

[0406] Step 3:

[0407] Emotion Recognition and Regulation

[0408] During learning, the device collects the user's facial expressions and voice using a camera and microphone and sends them to the server.

[0409] Input: User's facial expression data and voice data

[0410] Processing: The emotion engine analyzes these data and recognizes the user's emotional state.

[0411] Output: Feedback based on emotional state

[0412] Specific operation: The device activates the camera and microphone to collect data in real time. The collected data is sent to the server, which then relays it to the emotion engine. The analysis results are reflected as feedback in the form of learning plans and encouraging messages.

[0413] Step 4:

[0414] Learning progress assessment and suggestions

[0415] The device records the user's learning progress in real time and transmits it to the server.

[0416] Input: User's learning progress data

[0417] Processing: The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine.

[0418] Output: Suggested improvements and enhancements

[0419] How it works: The device records which page or learning material the user is currently studying and sends this to the server. The server uses a "progress assessment algorithm" to evaluate the data and sends the results to the AI ​​engine, which then provides feedback.

[0420] Step 5:

[0421] Explaining difficult content and providing concrete examples

[0422] The user enters a question and the terminal sends the question to the server.

[0423] Input: User's question

[0424] Processing: The server sends the question to an artificial intelligence engine, which uses a generative AI model to generate explanations and examples.

[0425] Output: Explanation and Examples

[0426] Specific operation: During learning, the user types "I don't understand the loop syntax." The device sends this question to the server, which then sends a request to the generative AI model to "provide a specific explanation." The generative AI model generates an explanation and a specific example and returns it to the server. The server then displays this to the user.

[0427] Step 6:

[0428] Support for maintaining motivation

[0429] The server generates encouraging messages and achievements based on the user's learning progress and emotional data.

[0430] Input: Learning progress data and emotion data

[0431] Processing: The server generates an encouraging message based on the data and sends it to the device.

[0432] Output: An encouraging message

[0433] Specific operation: The server periodically evaluates the "learning progress" and "emotional data" and generates encouraging messages such as "Keep up the good work!" The device notifies the user of this and displays it via voice or a pop-up.

[0434] Through these steps, the system is able to personalize and effectively support users' learning.

[0435] (Application example 2)

[0436] 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."

[0437] Conventional learning support systems provide learning plans based on the user's learning progress and history, and while they are effective to a certain extent, they do not adequately take into account the user's emotional state. As a result, they are unable to effectively address frustration and loss of motivation that users experience while learning, leaving issues with learning continuity. Furthermore, in brick-and-mortar learning support services, it is often difficult for users to immediately obtain the information they need, resulting in a poor quality learning experience.

[0438] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting a user's learning history and progress, means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user, means for evaluating the user's learning progress and suggesting areas for strengthening or improvement, means including a generative model that generates specific explanations and examples for difficult content, means for generating and providing messages to maintain motivation according to the user's learning progress, means including an emotion engine that recognizes the user's emotional state and adjusts the learning plan, means for recording the user's learning progress in real time, and means for providing learning support for the user to study specific information in a store. This enables effective learning support that comprehensively takes into account the user's emotional state and learning progress, and the quality of the learning experience can be improved by providing immediate and appropriate information in a physical store.

[0439] "User" refers to an individual who uses the system to advance their learning.

[0440] "Learning history" refers to a record of a user's past learning activities.

[0441] "Progress" refers to data that shows how far a user has progressed in their learning.

[0442] An "artificial intelligence engine" refers to software or hardware that analyzes collected data and generates optimal learning plans for users.

[0443] "Points of improvement" refers to areas of user learning that require particular reinforcement.

[0444] "Areas for improvement" refers to areas that particularly need improvement in user learning.

[0445] A "generative model" refers to an algorithm or software that generates explanations or examples under certain conditions.

[0446] "Messages to maintain motivation" refers to messages that motivate users to continue learning.

[0447] An "emotion engine" refers to software or hardware that recognizes emotions from a user's facial expressions, voice, etc.

[0448] "Real-time" refers to a state in which processing and analysis are carried out immediately at the present time.

[0449] "Study Progress" refers to data that indicates how far a user has progressed in their current study plan.

[0450] "In-store learning support" refers to providing support to users in physical stores to learn about products and services.

[0451] This invention is a learning personal assistant system that utilizes AI to personalize and effectively support users' learning. It combines an emotion engine to recognize the user's emotions and, based on those emotions, more effectively creates learning plans and maintains motivation.

[0452] The system includes a server, a user terminal, an artificial intelligence engine, and an emotion engine. Each of these components is described in detail below.

[0453] How we collect your data

[0454] The server receives login information from the user's device and retrieves the user's learning history and progress data from the database, allowing information such as the user's past learning content, study time, and test results to be stored on the server.

[0455] How to generate a lesson plan

[0456] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[0457] emotion recognition means

[0458] While studying, the user's device collects emotional data from the user's facial expressions and voice and sends it to the server. The emotion engine recognizes the user's emotions based on the received emotional data and uses this information to adjust the study plan and encouraging messages.

[0459] Learning progress assessment and suggestion tools

[0460] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[0461] A means of generating explanations and examples of difficult content

[0462] If a user encounters difficulty understanding a particular problem or complex content during learning, they can send a question from their device to the server. The server then passes the user's question to the generative model, which generates appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0463] Motivational message generation method

[0464] The server generates encouraging messages and achievements based on the user's learning progress and emotional data. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[0465] In-store learning support methods

[0466] When users learn about products or services in a physical store, they can learn specific information using their own devices or tablets installed in the store. The system instantly provides details and instructions on specific products, allowing users to obtain the information they want in a timely manner. The system also improves the quality of the learning experience by providing appropriate support and encouraging messages based on the user's learning progress and emotional state.

[0467] Specific examples

[0468] As a concrete example, let's consider the case where a user wants to learn how to use a new rice cooker at an electronics store. The user's device sends login information to the server, which then collects the user's past usage history. The artificial intelligence engine analyzes this and generates an optimal learning plan for how to use the rice cooker. The user's device uses the store's camera to send the user's facial expressions to the emotion engine, which recognizes the user's emotional state. The server then generates appropriate explanations and examples to answer the question, resolving the user's doubts. By providing messages to maintain motivation, the user's learning experience is optimized.

[0469] Prompt Sentence Examples

[0470] "I want to learn how to use new appliances. Can you tell me the next step for the appliances I currently use?"

[0471] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[0472] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0473] Step 1:

[0474] User data collection

[0475] When a user logs in from their device, the server receives the login information and retrieves the user's learning history and progress data from the database. This input data includes past learning content, study time, and test results, and uses this information to create an individual user profile. As output, the user's learning history and progress are temporarily stored on the server.

[0476] Step 2:

[0477] Generate a learning plan

[0478] The server sends the collected user data to an AI engine, which analyzes the user's learning data. Using learning history and progress as input data, the AI ​​engine analyzes the user's learning patterns and level of understanding. This generates an optimal learning plan. As an output, the optimal learning plan, which includes learning materials, study time, and study order, is stored on the server.

[0479] Step 3:

[0480] emotion recognition

[0481] During learning, the user device collects emotion data from the user's facial expressions and voice and sends it to the server. Images of the user's facial expressions and recorded voice data are used as input data. The emotion engine analyzes this data and recognizes the user's emotional state. As output, data on the user's emotions (e.g., satisfaction, confusion, impatience) is generated and stored on the server.

[0482] Step 4:

[0483] Assessment and recommendations for learning progress

[0484] The server receives learning progress data sent from the user's device in real time. The input data includes the current progress. The server periodically evaluates this data and sends it to an artificial intelligence engine to identify areas for improvement and strengthening. This generates appropriate feedback for the user. As an output, progress evaluation results and feedback are generated and stored on the server.

[0485] Step 5:

[0486] Explaining complex content and generating examples

[0487] When a user inputs a question during learning, the question is sent from the user's device to the server. The input data includes the user's question. The server passes this data to a generative model, which generates appropriate explanations and concrete examples. As output, explanations and concrete examples of difficult content are generated and provided to the user.

[0488] Step 6:

[0489] Generate motivational messages

[0490] The server generates encouraging messages and achievements based on learning progress and emotional data. Input data includes progress assessment results and emotional states. The generated messages are customized according to the progress and goal achievement status. As output, the customized encouraging messages are stored in the server and sent to the user's device.

[0491] Step 7:

[0492] In-store learning support

[0493] When a user learns about a product or service in a physical store, they learn specific information using their device or a tablet device in the store. The input data includes information about the product or service the user wants to learn about. The server immediately provides details about the specific product and how to use it, allowing the user to obtain the information they want to learn in a timely manner. The output provides detailed information about the product or service, as well as messages of support and encouragement.

[0494] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[0495] 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.

[0496] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0497] 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.

[0498] [Second embodiment]

[0499] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0500] 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.

[0501] 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).

[0502] 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.

[0503] 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.

[0504] 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).

[0505] 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.

[0506] 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.

[0507] 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.

[0508] 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.

[0509] 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.

[0510] 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."

[0511] This invention describes an AI-based learning personal assistant system to personalize and effectively assist users in their learning.

[0512] This system includes a server, a user terminal, and an artificial intelligence engine. The system operates as follows.

[0513] User data collection

[0514] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[0515] Analyzing data and creating a learning plan

[0516] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[0517] Learning progress assessment and suggestions

[0518] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[0519] Explaining difficult topics and providing examples

[0520] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0521] Support for maintaining motivation

[0522] The server generates encouraging messages and achievements based on the user's learning progress. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[0523] Specific examples

[0524] For example, let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user's device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to an artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. If the user encounters difficulties during learning, the user's device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. Additionally, depending on the user's progress, the server generates encouraging messages, which the user's device notifies, helping them continue their learning.

[0525] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[0526] The processing flow will be explained below.

[0527] Step 1:

[0528] The user logs in to the system, enters the authentication information to log in, and presses the submit button.

[0529] Step 2:

[0530] The terminal receives the user's login information and sends it to the server, which includes the user ID and password.

[0531] Step 3:

[0532] After verifying that the user has entered the correct authentication information, the server retrieves the user's learning history and progress data from the database, including past learning content, study time, test results, etc.

[0533] Step 4:

[0534] The server sends the acquired user data to an AI engine, which analyzes the user's learning history and progress and generates an optimal learning plan.

[0535] Step 5:

[0536] Based on the analysis results, the AI ​​engine generates an optimal study plan for the user, which includes recommended learning materials, study time allocation, and study order.

[0537] Step 6:

[0538] The server sends the generated learning plan to the terminal, which displays the learning plan to the user.

[0539] Step 7:

[0540] The user performs the learning activity. The user uses the learning material according to the learning content, and if the user has any questions or encounters difficult content, the user inputs the questions into the system.

[0541] Step 8:

[0542] The device sends the user's question to the server, which then passes the question to an artificial intelligence engine, requesting it to generate appropriate explanations and examples.

[0543] Step 9:

[0544] The AI ​​engine generates explanations and examples based on the user's question and sends them to the server, which then sends them to the device, which displays them to the user.

[0545] Step 10:

[0546] The device records the user's learning activities in real time and transmits the progress data to the server, which periodically evaluates the learning progress and has the AI ​​engine analyze the progress data.

[0547] Step 11:

[0548] Based on the analysis results, the server will suggest areas for improvement and strengthen the user, and will also send motivational messages, including encouraging messages generated by the AI ​​engine, to the device.

[0549] Step 12:

[0550] The device displays encouraging messages and notifications of areas for improvement to the user, helping them to stay motivated to continue learning.

[0551] Example 1

[0552] 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."

[0553] Conventional learning support systems have not provided sufficient personalized learning support that takes into account each user's progress and learning history. Furthermore, when users encounter difficult content during learning, it is difficult to provide specific explanations and examples at the appropriate time. As a result, users' learning efficiency and motivation can decline.

[0554] 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.

[0555] In this invention, the server includes: means for collecting a user's learning history and progress; means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user; means for evaluating the user's learning progress and suggesting areas for strengthening or improvement; means including a generative model that generates specific explanations and examples based on questions entered by the user for specific problems or difficult content; means for generating and providing messages to maintain motivation according to the user's learning progress; and means for generating encouraging messages according to the user's learning plan and progress and notifying the user terminal. This makes it possible to provide learning support and maintain motivation that is optimized for each individual user.

[0556] A "user" is an individual who uses the system to carry out learning activities.

[0557] "Learning history" is a record of the learning activities that a user has undertaken to date.

[0558] "Progress" refers to the user's current achievement or progress in learning.

[0559] "Means of collection" refers to the functions and mechanisms for inputting and storing a user's learning history and progress into the system.

[0560] "Analyzing data" means organizing information based on collected learning data and extracting useful insights.

[0561] An "artificial intelligence engine" refers to the entire algorithm or system that analyzes a user's learning data and generates the optimal learning plan.

[0562] A "study plan" is a plan that includes the study materials to be used, study time, study order, etc., to enable the user to study efficiently.

[0563] "Means of evaluation" are functions and mechanisms for regularly checking users' learning progress and measuring the results.

[0564] "Improvements" are areas where users should learn more.

[0565] "Areas for improvement" are areas that users don't understand or items that need to be corrected to improve efficiency.

[0566] A "generative model" is a computational model that can generate appropriate explanations and concrete examples in response to questions that users have.

[0567] Maintaining "motivation" involves activities that include actions and messages that motivate users to continue learning.

[0568] "Means for generating and providing messages" refers to a function or mechanism for creating messages according to the user's progress and informing the user of these messages.

[0569] "Encouraging messages" are positive words or notifications that motivate users to continue learning.

[0570] A "user terminal" is a device (smartphone, tablet, PC, etc.) that a user uses to access the system and carry out learning activities.

[0571] The present invention describes a learning personal assistant system that utilizes artificial intelligence to personalize and effectively assist users in their learning. The system includes a server, a user terminal, and an artificial intelligence engine.

[0572] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from a database (e.g., MySQL) and temporarily stores it. This allows the server to accumulate information such as the user's past learning content, study time, and test results.

[0573] The server sends the collected data to an artificial intelligence engine (for example, OpenAI's GPT-3), which analyzes the user's learning data. The artificial intelligence engine analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes which learning materials to use, how much time to spend on them, and the order in which they should be studied.

[0574] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine. The artificial intelligence engine analyzes the evaluation results and identifies areas for strengthening and improvement. The server receives feedback from the artificial intelligence engine and sends it to the user's device. The user can then receive feedback on which areas need strengthening or improvement based on their own progress.

[0575] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0576] The server generates encouraging messages and achievements based on the user's learning progress. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, keeping the user motivated to continue learning.

[0577] Specific examples

[0578] Let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user's device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to an artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. If the user encounters difficulties during learning, the user's device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. Additionally, depending on the user's progress, the server generates encouraging messages, which the user's device notifies the user of, supporting them in continuing their learning.

[0579] Example prompts for generative AI models

[0580] "User ID: 001 is having trouble with the basics of programming. Please provide an explanation and concrete examples based on the user's learning history."

[0581] "Generate an encouraging message based on the progress of user ID: 001."

[0582] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[0583] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0584] Step 1:

[0585] A user logs in to the system.

[0586] Specific behavior:

[0587] The user launches the learning app, enters their user ID and password on the login screen, and presses the "Login" button. This causes the user device to send the entered login information to the server.

[0588] input:

[0589] User ID and password

[0590] output:

[0591] The login information is sent to the server.

[0592] Step 2:

[0593] The server retrieves the user's learning history and progress from the database.

[0594] Specific behavior:

[0595] The server receives the login information, searches for and retrieves the user's learning history and progress from a database (e.g., MySQL) based on the user ID, and stores the retrieved data in temporary memory (e.g., Redis).

[0596] input:

[0597] User ID

[0598] output:

[0599] Learning history and progress data is stored in temporary memory.

[0600] Step 3:

[0601] The server sends the collected data to an artificial intelligence engine.

[0602] Specific behavior:

[0603] The server sends the user's learning data stored in temporary memory to an artificial intelligence engine (e.g., GPT-3).

[0604] input:

[0605] User learning history and progress data

[0606] output:

[0607] The data is sent to an artificial intelligence engine.

[0608] Step 4:

[0609] The artificial intelligence engine analyzes the user's learning data and generates the optimal learning plan.

[0610] Specific behavior:

[0611] The AI ​​engine analyzes the received learning data, analysing the user's learning patterns and level of understanding. Based on the results, it generates an optimal learning plan, including the learning materials to be used, study time, and learning order, and returns it to the server.

[0612] input:

[0613] User learning data

[0614] output:

[0615] The best study plan

[0616] Step 5:

[0617] The server sends the learning plan to the user's device.

[0618] Specific behavior:

[0619] The server receives the optimal learning plan from the AI ​​engine and sends it to the user's device, which displays it to the user and tells them what to study next.

[0620] input:

[0621] The best study plan

[0622] output:

[0623] The learning plan will be displayed on the user's device.

[0624] Step 6:

[0625] The user's device records the user's learning progress in real time and transmits it to the server.

[0626] Specific behavior:

[0627] As the user progresses through their studies, the user's device records the progress of the study, including the start time, end time, and study items, in real time, and sends this information to the server at regular intervals (e.g., every 30 minutes).

[0628] input:

[0629] Learning progress data

[0630] output:

[0631] Progress data is sent to the server.

[0632] Step 7:

[0633] The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine.

[0634] Specific behavior:

[0635] The server evaluates the user's progress based on the received learning progress data and sends the results to the AI ​​engine, which analyzes the evaluation data and identifies areas for improvement.

[0636] input:

[0637] Learning progress data

[0638] output:

[0639] The evaluation results are sent to an artificial intelligence engine.

[0640] Step 8:

[0641] The artificial intelligence engine analyzes the evaluation results and identifies areas for strengthening and improvement.

[0642] Specific behavior:

[0643] The AI ​​engine analyzes the evaluation data, identifies areas where the user needs to improve and provides feedback to the server.

[0644] input:

[0645] Evaluation results

[0646] output:

[0647] Feedback on enhancements and improvements

[0648] Step 9:

[0649] The server sends feedback on enhancements and improvements to the user's device.

[0650] Specific behavior:

[0651] The server receives feedback from the AI ​​engine and sends it to the user's device, which displays the feedback to the user and provides advice based on their progress.

[0652] input:

[0653] feedback

[0654] output:

[0655] Feedback is displayed on the user's device.

[0656] Step 10:

[0657] The user types a question.

[0658] Specific behavior:

[0659] If a user encounters a problem while learning, they enter a question into the question input field within the learning app and press the "Submit" button.

[0660] input:

[0661] Question

[0662] output:

[0663] A question is sent from the user terminal to the server.

[0664] Step 11:

[0665] The server sends the question to the artificial intelligence engine.

[0666] Specific behavior:

[0667] The server passes the question sent from the user's device to the artificial intelligence engine, requesting it to generate an explanation and specific examples.

[0668] input:

[0669] Question

[0670] output:

[0671] The question is sent to an artificial intelligence engine.

[0672] Step 12:

[0673] The artificial intelligence engine generates explanations and examples based on the question.

[0674] Specific behavior:

[0675] The AI ​​engine analyzes the question and generates appropriate explanations and examples, which are then sent to the server.

[0676] input:

[0677] Question

[0678] output:

[0679] Explanation and examples

[0680] Step 13:

[0681] The server sends explanations and examples to the user's terminal.

[0682] Specific behavior:

[0683] The server sends the explanations and concrete examples received from the artificial intelligence engine to the user terminal, which then displays them to the user.

[0684] input:

[0685] Explanation and examples

[0686] output:

[0687] Explanations and examples are displayed on the user's device.

[0688] Step 14:

[0689] The server generates encouraging messages based on the user's progress.

[0690] Specific behavior:

[0691] The server analyzes the user's learning progress data and automatically generates encouraging messages and achievements, which are customized based on the user's progress and goal achievements.

[0692] input:

[0693] Learning progress data

[0694] output:

[0695] Encouraging messages and achievements

[0696] Step 15:

[0697] The server sends encouraging messages to the user terminal.

[0698] Specific behavior:

[0699] The server transmits the generated encouraging message to the user terminal, and the user terminal notifies the user of the message.

[0700] input:

[0701] Messages of encouragement

[0702] output:

[0703] The message is sent to the user terminal.

[0704] Through these steps, the system can personalize and effectively support users' learning activities.

[0705] (Application example 1)

[0706] 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."

[0707] The problem that this invention aims to solve is to individually optimize a user's learning, provide effective learning support, provide real-time explanations for stumbling blocks and questions during learning, and maintain the user's motivation. Furthermore, by realizing this across multiple devices, it aims to improve the user's learning experience.

[0708] 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.

[0709] In this invention, the server includes means for collecting a user's learning history and progress, means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user, means for evaluating the user's learning progress and suggesting areas for strengthening or improvement, means including a generative model that generates specific explanations and examples for difficult content, means for generating and providing messages to maintain motivation according to the user's learning progress, means for providing a personalized learning plan on multiple devices, and means for generating explanations in real time in response to the user's questions. This makes it possible to comprehensively support the user's learning experience and achieve individually optimized learning.

[0710] "Means for collecting a user's learning history and progress" refers to devices or software that record what a user has learned in the past and their progress at that time, and consolidate this information into a system.

[0711] "Means including an artificial intelligence engine that analyzes collected data and generates optimal learning plans for users" refers to devices or software that use AI to analyze collected user learning data and create optimal learning plans for each user based on that data.

[0712] "Means for assessing a user's learning progress and suggesting areas for reinforcement or improvement" refers to devices or software that periodically check a user's learning status and suggest areas that need reinforcement or improvement in order to support effective learning.

[0713] "Means including a generative model that generates specific explanations and examples for difficult content" refers to devices or software that use a generative model to automatically generate specific, easy-to-understand explanations and examples for content that users find difficult to understand while studying.

[0714] "Means for generating and providing messages to maintain motivation according to the user's learning progress" refers to devices or software that generate encouraging and supportive messages according to the user's learning progress, motivating the user to continue learning.

[0715] "Means for providing personalized learning plans on multiple devices" refers to devices or software that make learning plans customized for each user available on multiple devices, such as smartphones, tablets, and smart glasses.

[0716] "Means for generating explanations in real time in response to user questions" refers to devices or software that instantly generate and provide appropriate explanations in response to questions that users have while studying.

[0717] To realize the system of the present invention, a server, a user terminal, and an artificial intelligence engine (AI engine) are required. This system provides learning support to users through the following specific process.

[0718] Major hardware and software configurations

[0719] Hardware:

[0720] Server: AWS (Amazon Web Services) or Google Cloud

[0721] User devices: smartphones, tablets, smart glasses

[0722] software:

[0723] Database: MySQL

[0724] Artificial intelligence engine: Google Cloud AI, OpenAI GPT

[0725] System Operation Overview

[0726] 1. User data collection:

[0727] Users log in to the system from their devices. The login information is sent to the server, which retrieves past learning history and progress from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be aggregated on the server.

[0728] 2. Analyze the data and generate a learning plan:

[0729] The server sends the collected data to an AI engine, which analyzes the data, analyzes the user's learning patterns and level of understanding, and generates an optimal learning plan, including specific learning material recommendations and study time allocations.

[0730] 3. Learning progress assessment and suggestions:

[0731] The user's device records the learning progress in real time and sends it to the server, which periodically evaluates it and sends it to the AI ​​engine to identify areas that need strengthening or improvement, and the user can receive feedback based on this.

[0732] 4. Explanation of difficult content:

[0733] When a user inputs a question during learning, the question is sent to the server, which passes it to the AI ​​engine to generate an explanation and concrete examples. The generated content is then sent to the device and provided to the user.

[0734] 5. Motivation support:

[0735] The server generates encouraging messages and achievements based on learning progress, which the device notifies the user and motivates them to continue learning.

[0736] 6. Multi-device compatibility:

[0737] Learning plans, feedback and explanations are available across multiple devices including smartphones, tablets and smart glasses.

[0738] Specific examples

[0739] For example, let's say a user (user ID: 001) wants to learn the basics of programming. The user logs into the system using their smartphone. The server collects user 001's learning history and progress from the database and sends it to the AI ​​engine. The AI ​​engine analyzes the data and generates an optimal learning plan including the next learning step. If the user gets stuck while learning, they can input a question, and the server will generate explanations and concrete examples and provide them to the user. The server also generates encouraging messages according to the user's learning progress and notifies them to keep the user motivated.

[0740] Prompt Sentence Examples

[0741] Users find it difficult to understand the basic programming concept of "loop structure." Please provide a detailed explanation with concrete examples.

[0742] In this way, the system of the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[0743] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0744] Step 1: Collect user data

[0745] A user logs into the system from their device. The login information is sent to the server. The server retrieves past learning history and progress from the database and temporarily stores it. The aggregated data includes the user's past learning content, study time, test results, etc.

[0746] Input: User login information

[0747] Data processing / calculation: Obtaining learning history and progress from the database

[0748] Output: Captured learning history and progress data

[0749] Step 2: Analyze the data and generate a learning plan

[0750] The server sends the collected data to an AI engine, which analyzes the data and analyzes the user's learning patterns and level of understanding. Based on the analysis results, an optimal learning plan is generated for the user. This plan includes which learning materials to use, how much time to spend on them, and the order in which they should be studied.

[0751] Input: Learning history and progress data

[0752] Data processing / calculation: Data analysis and plan generation using an AI engine

[0753] Output: Optimal study plan

[0754] Step 3: Assessment and recommendations for learning progress

[0755] The user's device records the learning progress in real time and sends it to the server, which then periodically sends it to the AI ​​engine to evaluate the user's progress. Based on the evaluation, suggestions for improvements and enhancements are made.

[0756] Input: Real-time learning progress data

[0757] Data processing / calculation: Progress evaluation and proposal generation using an AI engine

[0758] Output: Enhancements and Improvements

[0759] Step 4: Explaining the complexities

[0760] When a user inputs a question during learning, the question is sent to the server, which passes it to the AI ​​engine to generate an explanation and concrete examples. The generated content is then sent to the device and provided to the user.

[0761] Input: User's question

[0762] Data processing / calculation: Explanations and concrete examples generated by AI engine

[0763] Output: Generated explanations and examples

[0764] Step 5: Support to maintain motivation

[0765] The server generates encouraging messages and achievements based on the user's learning progress. Messages are customized according to the user's progress and sent to the user's device.

[0766] Input: User's learning progress data

[0767] Data processing / calculation: Server-generated encouragement messages and achievements

[0768] Output: Generated encouragement message and achievement

[0769] Step 6: Multi-device compatibility

[0770] The learning plans, feedback, and explanations are available on multiple devices, including smartphones, tablets, and smart glasses, with the data being sent from the server to each device in an appropriate format.

[0771] Input: Generated lesson plans, explanations, and feedback data

[0772] Data processing / calculation: Device-compatible format generation and data transmission

[0773] Output: Data converted into a format that can be used by each device

[0774] 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.

[0775] This invention is a learning personal assistant system that utilizes AI to personalize and effectively support users' learning. It combines an emotion engine to recognize the user's emotions and, based on those emotions, more effectively creates learning plans and maintains motivation.

[0776] This system includes a server, a user terminal, an artificial intelligence engine, and an emotion engine. The system operates as follows.

[0777] User data collection

[0778] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[0779] Analyzing data and creating a learning plan

[0780] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[0781] Emotion recognition by emotion engine

[0782] While studying, the user's device collects emotional data from the user's facial expressions and voice and sends it to the server. The emotion engine recognizes the user's emotions based on the received emotional data and uses this information to adjust the study plan and encouraging messages.

[0783] Learning progress assessment and suggestions

[0784] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[0785] Explaining difficult topics and providing examples

[0786] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0787] Support for maintaining motivation

[0788] The server generates encouraging messages and achievements based on the user's learning progress and emotional data. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[0789] Specific examples

[0790] For example, let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to the artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. The user device sends the user's facial expressions and voice to the emotion engine while learning, and if the user is confused, it adjusts the learning pace and provides additional explanations. If the user stumbles while learning, the user device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. The server also generates encouraging messages based on the user's progress and emotions, and the user device notifies the user of this, helping them continue their learning.

[0791] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[0792] The processing flow will be explained below.

[0793] Step 1:

[0794] The user logs in to the system, enters the authentication information to log in, and presses the submit button.

[0795] Step 2:

[0796] The terminal receives the user's login information and sends it to the server. This login information includes the user ID and password.

[0797] Step 3:

[0798] The server verifies the user's authentication information and, if correct, retrieves the user's learning history and progress data from a database, including past learning content, study time, test results, etc.

[0799] Step 4:

[0800] The server sends the acquired user data to an AI engine, which analyzes the learning data. The AI ​​engine analyzes the user's learning patterns and level of understanding and generates an optimal learning plan. This learning plan includes which learning materials to use, how much time to spend on each, and the learning order.

[0801] Step 5:

[0802] The server transmits the generated study plan to the terminal, which displays it to the user, who then begins studying according to the study plan.

[0803] Step 6:

[0804] Emotion data is generated using facial expressions and voice during training. For example, facial expression and voice analysis is performed using a camera and microphone.

[0805] Step 7:

[0806] The terminal collects the user's emotion data in real time and transmits it to the server.

[0807] Step 8:

[0808] The server uses an emotion engine to analyze the received emotion data and recognize the user's emotional state (e.g., confusion, satisfaction, fatigue, etc.).

[0809] Step 9:

[0810] The server determines if the lesson plan needs to be adjusted based on the perceived emotional state, for example, adjusting the lesson plan to slow down the pace or provide additional explanation if the user is confused.

[0811] Step 10:

[0812] The server sends the adjusted learning plan and additional explanations to the terminal, which displays them to the user.

[0813] Step 11:

[0814] If a user encounters a problem while studying, they can enter a question and submit it to the system.

[0815] Step 12:

[0816] The device sends the user's question to the server, which then passes the question to an artificial intelligence engine, requesting it to generate appropriate explanations and examples.

[0817] Step 13:

[0818] The AI ​​engine generates explanations and examples based on the user's question and sends them to the server, which then sends them to the device, which displays them to the user.

[0819] Step 14:

[0820] The device records the user's learning activities in real time and transmits the progress data to the server, which periodically evaluates the learning progress and has the AI ​​engine analyze the progress data.

[0821] Step 15:

[0822] Based on the analysis results, the server suggests areas for improvement to the user. It also sends messages to the device to maintain motivation, including encouraging messages, based on the evaluation results generated by the emotion engine.

[0823] Step 16:

[0824] The device displays encouraging messages and notifications of areas for improvement to the user, helping them to stay motivated to continue learning.

[0825] Example 2

[0826] 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."

[0827] Conventional learning support systems collect users' learning history and progress and provide learning plans based on that information. However, they are unable to provide support that takes into account the user's emotional state. Therefore, there is a need for a method to effectively support users in maintaining their motivation and understanding difficult content. Furthermore, there is a need for a method to generate personalized encouraging messages in real time according to the user's learning progress and deliver them at the appropriate time.

[0828] 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.

[0829] In this invention, the server includes a means for collecting the user's learning history and progress, a means including an artificial intelligence engine for analyzing the collected data to generate an optimal learning plan for the user, and a means including an emotion engine for collecting and analyzing the user's emotion data, thereby making it possible to effectively analyze the user's learning pattern and level of understanding and adjust the learning plan and encouraging messages.

[0830] "User's learning history" refers to a record of all learning activities that a user has performed in the past, including information such as learning content, study time, and test results.

[0831] "Progress" is data that indicates the user's learning progress, and includes information such as the current learning stage, level of achievement, and level of understanding.

[0832] An "artificial intelligence engine" refers to an algorithm or program that analyzes collected data and generates the optimal learning plan for the user.

[0833] An "emotion engine" refers to an algorithm or program that collects and analyzes emotional data such as a user's facial expressions and voice.

[0834] A "study plan" is a specific instruction plan for a user to effectively progress through their studies, and includes the learning materials to be used, study time, study order, etc.

[0835] "Encouragement messages" refer to encouraging text or audio messages generated to motivate users to learn.

[0836] "Difficult content" refers to specific issues or concepts that users find difficult to understand while learning.

[0837] A "generative model" refers to an algorithm or program that automatically generates specific explanations and examples based on a user's questions or requests.

[0838] "Areas for reinforcement or improvement" indicates areas that need further reinforcement or improvement as a result of evaluating the user's learning situation.

[0839] "Motivational messages" refer to personalized messages of encouragement designed to maintain or increase a user's motivation to learn.

[0840] The present invention relates to a personal learning assistant system that individually optimizes a user's learning and improves learning efficiency. The system collects the user's learning history and progress and provides an appropriate learning plan based on that. It also uses an emotion engine to recognize the user's emotional state and adjusts the learning plan and encouraging messages accordingly, thereby maintaining the user's motivation.

[0841] Explanation of program processing

[0842] This system is composed of a server, a user terminal, an AI engine, and an emotion engine. The specific operation of each component is as follows:

[0843] User data collection

[0844] When a user logs in to the system, the device sends the login information to the server. The server retrieves the user's past learning history and progress from the database based on the user ID and temporarily stores it. This allows the server to store the user's learning content, study time, and test results.

[0845] Analyzing data and creating a learning plan

[0846] The server sends the temporarily stored data to an AI engine. The AI ​​engine analyzes the user's learning data, analyzing their learning patterns and level of understanding. Based on the analysis results, it generates an optimal learning plan and returns it to the server. This learning plan includes the learning materials to be used, the study time, and the study order.

[0847] Emotion recognition by emotion engine

[0848] While studying, the device uses a camera and microphone to collect the user's facial expressions and voice. The collected emotional data is sent to a server, which then transmits it to an emotion engine. The emotion engine analyzes the emotional data and recognizes the user's emotional state. Based on the analysis results, the server adjusts the study plan and encouraging messages.

[0849] Learning progress assessment and suggestions

[0850] The device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to the AI ​​engine. Based on the feedback from the AI ​​engine, the server makes appropriate suggestions to the user.

[0851] Explaining difficult content and providing concrete examples

[0852] When a user enters a question, the device sends it to the server, which passes the question to an artificial intelligence engine and uses a generative AI model to generate appropriate explanations and examples. The generated explanations and examples are then returned from the server to the device and displayed to the user.

[0853] Support for maintaining motivation

[0854] The server generates encouraging messages and achievements based on the user's learning progress and emotional data, and the device notifies the user of the messages received from the server, thus maintaining the user's motivation to continue learning.

[0855] Specific examples

[0856] For example, let us consider a case where a user (user ID: 001) wishes to learn the basics of programming.

[0857] 1. The user terminal sends User 001's login information to the system, and the server collects User 001's learning history and progress from the database. The collected data is sent to an artificial intelligence engine, which generates an optimal learning plan.

[0858] 2. The user device collects the user's facial expressions and voice during learning and sends them to the emotion engine. If the user is confused, the learning pace will be adjusted and additional explanations will be provided.

[0859] 3. If the user encounters a problem while studying, the user device sends the question to the server, and the server generates an explanation and concrete examples and provides them to the user.

[0860] 4. The server generates encouraging messages based on the user's progress and emotions, and the user's device notifies the user of these messages to help them continue their studies.

[0861] Prompt Sentence Examples

[0862] Generate the following learning plan based on the user's learning progress and past history: The user wants to learn the basics of programming.

[0863] In this way, the learning personal assistant system of the present invention provides flexible support tailored to the individual needs of the user, and realizes effective learning and continuous learning that takes into account the user's emotional state.

[0864] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0865] Step 1:

[0866] User login and data collection

[0867] When a user logs in to the system, the terminal sends the user's login information to the server.

[0868] Input: User ID and password

[0869] Processing: The server uses the user ID to retrieve the past learning history and progress from the database.

[0870] Output: User learning history and progress data

[0871] Specific operation: The terminal displays a login form and sends the ID and password entered by the user to the server. The server receives this and executes a database query. The result is temporarily saved.

[0872] Step 2:

[0873] Analyzing data and creating a learning plan

[0874] The server sends the temporarily stored user learning data to the artificial intelligence engine.

[0875] Input: User learning history and progress data

[0876] Processing: The artificial intelligence engine analyzes the data and analyzes the user's learning patterns and comprehension.

[0877] Output: Optimal study plan

[0878] How it works: The server sends the data to the AI ​​engine, which uses an analytical algorithm to generate a learning plan, which is then returned to the server in JSON format.

[0879] Step 3:

[0880] Emotion Recognition and Regulation

[0881] During learning, the device collects the user's facial expressions and voice using a camera and microphone and sends them to the server.

[0882] Input: User's facial expression data and voice data

[0883] Processing: The emotion engine analyzes these data and recognizes the user's emotional state.

[0884] Output: Feedback based on emotional state

[0885] Specific operation: The device activates the camera and microphone to collect data in real time. The collected data is sent to the server, which then relays it to the emotion engine. The analysis results are reflected as feedback in the form of learning plans and encouraging messages.

[0886] Step 4:

[0887] Learning progress assessment and suggestions

[0888] The device records the user's learning progress in real time and transmits it to the server.

[0889] Input: User's learning progress data

[0890] Processing: The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine.

[0891] Output: Suggested improvements and enhancements

[0892] How it works: The device records which page or learning material the user is currently studying and sends this to the server. The server uses a "progress assessment algorithm" to evaluate the data and sends the results to the AI ​​engine, which then provides feedback.

[0893] Step 5:

[0894] Explaining difficult content and providing concrete examples

[0895] The user enters a question and the terminal sends the question to the server.

[0896] Input: User's question

[0897] Processing: The server sends the question to an artificial intelligence engine, which uses a generative AI model to generate explanations and examples.

[0898] Output: Explanation and Examples

[0899] Specific operation: During learning, the user types "I don't understand the loop syntax." The device sends this question to the server, which then sends a request to the generative AI model to "provide a specific explanation." The generative AI model generates an explanation and a specific example and returns it to the server. The server then displays this to the user.

[0900] Step 6:

[0901] Support for maintaining motivation

[0902] The server generates encouraging messages and achievements based on the user's learning progress and emotional data.

[0903] Input: Learning progress data and emotion data

[0904] Processing: The server generates an encouraging message based on the data and sends it to the device.

[0905] Output: An encouraging message

[0906] Specific operation: The server periodically evaluates the "learning progress" and "emotional data" and generates encouraging messages such as "Keep up the good work!" The device notifies the user of this and displays it via voice or a pop-up.

[0907] Through these steps, the system is able to personalize and effectively support users' learning.

[0908] (Application example 2)

[0909] 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."

[0910] Conventional learning support systems provide learning plans based on the user's learning progress and history, and while they are effective to a certain extent, they do not adequately take into account the user's emotional state. As a result, they are unable to effectively address frustration and loss of motivation that users experience while learning, leaving issues with learning continuity. Furthermore, in brick-and-mortar learning support services, it is often difficult for users to immediately obtain the information they need, resulting in a poor quality learning experience.

[0911] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting a user's learning history and progress, means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user, means for evaluating the user's learning progress and suggesting areas for strengthening or improvement, means including a generative model that generates specific explanations and examples for difficult content, means for generating and providing messages to maintain motivation according to the user's learning progress, means including an emotion engine that recognizes the user's emotional state and adjusts the learning plan, means for recording the user's learning progress in real time, and means for providing learning support for the user to study specific information in a store. This enables effective learning support that comprehensively takes into account the user's emotional state and learning progress, and the quality of the learning experience can be improved by providing immediate and appropriate information in a physical store.

[0912] "User" refers to an individual who uses the system to advance their learning.

[0913] "Learning history" refers to a record of a user's past learning activities.

[0914] "Progress" refers to data that shows how far a user has progressed in their learning.

[0915] An "artificial intelligence engine" refers to software or hardware that analyzes collected data and generates optimal learning plans for users.

[0916] "Points of improvement" refers to areas of user learning that require particular reinforcement.

[0917] "Areas for improvement" refers to areas that particularly need improvement in user learning.

[0918] A "generative model" refers to an algorithm or software that generates explanations or examples under certain conditions.

[0919] "Messages to maintain motivation" refers to messages that motivate users to continue learning.

[0920] An "emotion engine" refers to software or hardware that recognizes emotions from a user's facial expressions, voice, etc.

[0921] "Real-time" refers to a state in which processing and analysis are carried out immediately at the present time.

[0922] "Study Progress" refers to data that indicates how far a user has progressed in their current study plan.

[0923] "In-store learning support" refers to providing support to users in physical stores to learn about products and services.

[0924] This invention is a learning personal assistant system that utilizes AI to personalize and effectively support users' learning. It combines an emotion engine to recognize the user's emotions and, based on those emotions, more effectively creates learning plans and maintains motivation.

[0925] The system includes a server, a user terminal, an artificial intelligence engine, and an emotion engine. Each of these components is described in detail below.

[0926] How we collect your data

[0927] The server receives login information from the user's device and retrieves the user's learning history and progress data from the database, allowing information such as the user's past learning content, study time, and test results to be stored on the server.

[0928] How to generate a lesson plan

[0929] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[0930] emotion recognition means

[0931] While studying, the user's device collects emotional data from the user's facial expressions and voice and sends it to the server. The emotion engine recognizes the user's emotions based on the received emotional data and uses this information to adjust the study plan and encouraging messages.

[0932] Learning progress assessment and suggestion tools

[0933] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[0934] A means of generating explanations and examples of difficult content

[0935] If a user encounters difficulty understanding a particular problem or complex content during learning, they can send a question from their device to the server. The server then passes the user's question to the generative model, which generates appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0936] Motivational message generation method

[0937] The server generates encouraging messages and achievements based on the user's learning progress and emotional data. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[0938] In-store learning support methods

[0939] When users learn about products or services in a physical store, they can learn specific information using their own devices or tablets installed in the store. The system instantly provides details and instructions on specific products, allowing users to obtain the information they want in a timely manner. The system also improves the quality of the learning experience by providing appropriate support and encouraging messages based on the user's learning progress and emotional state.

[0940] Specific examples

[0941] As a concrete example, let's consider the case where a user wants to learn how to use a new rice cooker at an electronics store. The user's device sends login information to the server, which then collects the user's past usage history. The artificial intelligence engine analyzes this and generates an optimal learning plan for how to use the rice cooker. The user's device uses the store's camera to send the user's facial expressions to the emotion engine, which recognizes the user's emotional state. The server then generates appropriate explanations and examples to answer the question, resolving the user's doubts. By providing messages to maintain motivation, the user's learning experience is optimized.

[0942] Prompt Sentence Examples

[0943] "I want to learn how to use new appliances. Can you tell me the next step for the appliances I currently use?"

[0944] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

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

[0946] Step 1:

[0947] User data collection

[0948] When a user logs in from their device, the server receives the login information and retrieves the user's learning history and progress data from the database. This input data includes past learning content, study time, and test results, and uses this information to create an individual user profile. As output, the user's learning history and progress are temporarily stored on the server.

[0949] Step 2:

[0950] Generate a learning plan

[0951] The server sends the collected user data to an AI engine, which analyzes the user's learning data. Using learning history and progress as input data, the AI ​​engine analyzes the user's learning patterns and level of understanding. This generates an optimal learning plan. As an output, the optimal learning plan, which includes learning materials, study time, and study order, is stored on the server.

[0952] Step 3:

[0953] emotion recognition

[0954] During learning, the user device collects emotion data from the user's facial expressions and voice and sends it to the server. Images of the user's facial expressions and recorded voice data are used as input data. The emotion engine analyzes this data and recognizes the user's emotional state. As output, data on the user's emotions (e.g., satisfaction, confusion, impatience) is generated and stored on the server.

[0955] Step 4:

[0956] Assessment and recommendations for learning progress

[0957] The server receives learning progress data sent from the user's device in real time. The input data includes the current progress. The server periodically evaluates this data and sends it to an artificial intelligence engine to identify areas for improvement and strengthening. This generates appropriate feedback for the user. As an output, progress evaluation results and feedback are generated and stored on the server.

[0958] Step 5:

[0959] Explaining complex content and generating examples

[0960] When a user inputs a question during learning, the question is sent from the user's device to the server. The input data includes the user's question. The server passes this data to a generative model, which generates appropriate explanations and concrete examples. As output, explanations and concrete examples of difficult content are generated and provided to the user.

[0961] Step 6:

[0962] Generate motivational messages

[0963] The server generates encouraging messages and achievements based on learning progress and emotional data. Input data includes progress assessment results and emotional states. The generated messages are customized according to the progress and goal achievement status. As output, the customized encouraging messages are stored in the server and sent to the user's device.

[0964] Step 7:

[0965] In-store learning support

[0966] When a user learns about a product or service in a physical store, they learn specific information using their device or a tablet device in the store. The input data includes information about the product or service the user wants to learn about. The server immediately provides details about the specific product and how to use it, allowing the user to obtain the information they want to learn in a timely manner. The output provides detailed information about the product or service, as well as messages of support and encouragement.

[0967] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] [Third embodiment]

[0972] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0973] 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.

[0974] 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).

[0975] 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.

[0976] 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.

[0977] 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).

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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.

[0983] 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."

[0984] This invention describes an AI-based learning personal assistant system to personalize and effectively assist users in their learning.

[0985] This system includes a server, a user terminal, and an artificial intelligence engine. The system operates as follows.

[0986] User data collection

[0987] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[0988] Analyzing data and creating a learning plan

[0989] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[0990] Learning progress assessment and suggestions

[0991] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[0992] Explaining difficult topics and providing examples

[0993] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[0994] Support for maintaining motivation

[0995] The server generates encouraging messages and achievements based on the user's learning progress. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[0996] Specific examples

[0997] For example, let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user's device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to an artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. If the user encounters difficulties during learning, the user's device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. Additionally, depending on the user's progress, the server generates encouraging messages, which the user's device notifies, helping them continue their learning.

[0998] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[0999] The processing flow will be explained below.

[1000] Step 1:

[1001] The user logs in to the system, enters the authentication information to log in, and presses the submit button.

[1002] Step 2:

[1003] The terminal receives the user's login information and sends it to the server, which includes the user ID and password.

[1004] Step 3:

[1005] After verifying that the user has entered the correct authentication information, the server retrieves the user's learning history and progress data from the database, including past learning content, study time, test results, etc.

[1006] Step 4:

[1007] The server sends the acquired user data to an AI engine, which analyzes the user's learning history and progress and generates an optimal learning plan.

[1008] Step 5:

[1009] Based on the analysis results, the AI ​​engine generates an optimal study plan for the user, which includes recommended learning materials, study time allocation, and study order.

[1010] Step 6:

[1011] The server sends the generated learning plan to the terminal, which displays the learning plan to the user.

[1012] Step 7:

[1013] The user performs the learning activity. The user uses the learning material according to the learning content, and if the user has any questions or encounters difficult content, the user inputs the questions into the system.

[1014] Step 8:

[1015] The device sends the user's question to the server, which then passes the question to an artificial intelligence engine, requesting it to generate appropriate explanations and examples.

[1016] Step 9:

[1017] The AI ​​engine generates explanations and examples based on the user's question and sends them to the server, which then sends them to the device, which displays them to the user.

[1018] Step 10:

[1019] The device records the user's learning activities in real time and transmits the progress data to the server, which periodically evaluates the learning progress and has the AI ​​engine analyze the progress data.

[1020] Step 11:

[1021] Based on the analysis results, the server will suggest areas for improvement and strengthen the user, and will also send motivational messages, including encouraging messages generated by the AI ​​engine, to the device.

[1022] Step 12:

[1023] The device displays encouraging messages and notifications of areas for improvement to the user, helping them to stay motivated to continue learning.

[1024] Example 1

[1025] 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."

[1026] Conventional learning support systems have not provided sufficient personalized learning support that takes into account each user's progress and learning history. Furthermore, when users encounter difficult content during learning, it is difficult to provide specific explanations and examples at the appropriate time. As a result, users' learning efficiency and motivation can decline.

[1027] 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.

[1028] In this invention, the server includes: means for collecting a user's learning history and progress; means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user; means for evaluating the user's learning progress and suggesting areas for strengthening or improvement; means including a generative model that generates specific explanations and examples based on questions entered by the user for specific problems or difficult content; means for generating and providing messages to maintain motivation according to the user's learning progress; and means for generating encouraging messages according to the user's learning plan and progress and notifying the user terminal. This makes it possible to provide learning support and maintain motivation that is optimized for each individual user.

[1029] A "user" is an individual who uses the system to carry out learning activities.

[1030] "Learning history" is a record of the learning activities that a user has undertaken to date.

[1031] "Progress" refers to the user's current achievement or progress in learning.

[1032] "Means of collection" refers to the functions and mechanisms for inputting and storing a user's learning history and progress into the system.

[1033] "Analyzing data" means organizing information based on collected learning data and extracting useful insights.

[1034] An "artificial intelligence engine" refers to the entire algorithm or system that analyzes a user's learning data and generates the optimal learning plan.

[1035] A "study plan" is a plan that includes the study materials to be used, study time, study order, etc., to enable the user to study efficiently.

[1036] "Means of evaluation" are functions and mechanisms for regularly checking users' learning progress and measuring the results.

[1037] "Improvements" are areas where users should learn more.

[1038] "Areas for improvement" are areas that users don't understand or items that need to be corrected to improve efficiency.

[1039] A "generative model" is a computational model that can generate appropriate explanations and concrete examples in response to questions that users have.

[1040] Maintaining "motivation" involves activities that include actions and messages that motivate users to continue learning.

[1041] "Means for generating and providing messages" refers to a function or mechanism for creating messages according to the user's progress and informing the user of these messages.

[1042] "Encouraging messages" are positive words or notifications that motivate users to continue learning.

[1043] A "user terminal" is a device (smartphone, tablet, PC, etc.) that a user uses to access the system and carry out learning activities.

[1044] The present invention describes a learning personal assistant system that utilizes artificial intelligence to personalize and effectively assist users in their learning. The system includes a server, a user terminal, and an artificial intelligence engine.

[1045] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from a database (e.g., MySQL) and temporarily stores it. This allows the server to accumulate information such as the user's past learning content, study time, and test results.

[1046] The server sends the collected data to an artificial intelligence engine (for example, OpenAI's GPT-3), which analyzes the user's learning data. The artificial intelligence engine analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes which learning materials to use, how much time to spend on them, and the order in which they should be studied.

[1047] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine. The artificial intelligence engine analyzes the evaluation results and identifies areas for strengthening and improvement. The server receives feedback from the artificial intelligence engine and sends it to the user's device. The user can then receive feedback on which areas need strengthening or improvement based on their own progress.

[1048] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[1049] The server generates encouraging messages and achievements based on the user's learning progress. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, keeping the user motivated to continue learning.

[1050] Specific examples

[1051] Let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user's device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to an artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. If the user encounters difficulties during learning, the user's device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. Additionally, depending on the user's progress, the server generates encouraging messages, which the user's device notifies the user of, supporting them in continuing their learning.

[1052] Example prompts for generative AI models

[1053] "User ID: 001 is having trouble with the basics of programming. Please provide an explanation and concrete examples based on the user's learning history."

[1054] "Generate an encouraging message based on the progress of user ID: 001."

[1055] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[1056] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1057] Step 1:

[1058] A user logs in to the system.

[1059] Specific behavior:

[1060] The user launches the learning app, enters their user ID and password on the login screen, and presses the "Login" button. This causes the user device to send the entered login information to the server.

[1061] input:

[1062] User ID and password

[1063] output:

[1064] The login information is sent to the server.

[1065] Step 2:

[1066] The server retrieves the user's learning history and progress from the database.

[1067] Specific behavior:

[1068] The server receives the login information, searches for and retrieves the user's learning history and progress from a database (e.g., MySQL) based on the user ID, and stores the retrieved data in temporary memory (e.g., Redis).

[1069] input:

[1070] User ID

[1071] output:

[1072] Learning history and progress data is stored in temporary memory.

[1073] Step 3:

[1074] The server sends the collected data to an artificial intelligence engine.

[1075] Specific behavior:

[1076] The server sends the user's learning data stored in temporary memory to an artificial intelligence engine (e.g., GPT-3).

[1077] input:

[1078] User learning history and progress data

[1079] output:

[1080] The data is sent to an artificial intelligence engine.

[1081] Step 4:

[1082] The artificial intelligence engine analyzes the user's learning data and generates the optimal learning plan.

[1083] Specific behavior:

[1084] The AI ​​engine analyzes the received learning data, analysing the user's learning patterns and level of understanding. Based on the results, it generates an optimal learning plan, including the learning materials to be used, study time, and learning order, and returns it to the server.

[1085] input:

[1086] User learning data

[1087] output:

[1088] The best study plan

[1089] Step 5:

[1090] The server sends the learning plan to the user's device.

[1091] Specific behavior:

[1092] The server receives the optimal learning plan from the AI ​​engine and sends it to the user's device, which displays it to the user and tells them what to study next.

[1093] input:

[1094] The best study plan

[1095] output:

[1096] The learning plan will be displayed on the user's device.

[1097] Step 6:

[1098] The user's device records the user's learning progress in real time and transmits it to the server.

[1099] Specific behavior:

[1100] As the user progresses through their studies, the user's device records the progress of the study, including the start time, end time, and study items, in real time, and sends this information to the server at regular intervals (e.g., every 30 minutes).

[1101] input:

[1102] Learning progress data

[1103] output:

[1104] Progress data is sent to the server.

[1105] Step 7:

[1106] The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine.

[1107] Specific behavior:

[1108] The server evaluates the user's progress based on the received learning progress data and sends the results to the AI ​​engine, which analyzes the evaluation data and identifies areas for improvement.

[1109] input:

[1110] Learning progress data

[1111] output:

[1112] The evaluation results are sent to an artificial intelligence engine.

[1113] Step 8:

[1114] The artificial intelligence engine analyzes the evaluation results and identifies areas for strengthening and improvement.

[1115] Specific behavior:

[1116] The AI ​​engine analyzes the evaluation data, identifies areas where the user needs to improve and provides feedback to the server.

[1117] input:

[1118] Evaluation results

[1119] output:

[1120] Feedback on enhancements and improvements

[1121] Step 9:

[1122] The server sends feedback on enhancements and improvements to the user's device.

[1123] Specific behavior:

[1124] The server receives feedback from the AI ​​engine and sends it to the user's device, which displays the feedback to the user and provides advice based on their progress.

[1125] input:

[1126] feedback

[1127] output:

[1128] Feedback is displayed on the user's device.

[1129] Step 10:

[1130] The user types a question.

[1131] Specific behavior:

[1132] If a user encounters a problem while learning, they enter a question into the question input field within the learning app and press the "Submit" button.

[1133] input:

[1134] Question

[1135] output:

[1136] A question is sent from the user terminal to the server.

[1137] Step 11:

[1138] The server sends the question to the artificial intelligence engine.

[1139] Specific behavior:

[1140] The server passes the question sent from the user's device to the artificial intelligence engine, requesting it to generate an explanation and specific examples.

[1141] input:

[1142] Question

[1143] output:

[1144] The question is sent to an artificial intelligence engine.

[1145] Step 12:

[1146] The artificial intelligence engine generates explanations and examples based on the question.

[1147] Specific behavior:

[1148] The AI ​​engine analyzes the question and generates appropriate explanations and examples, which are then sent to the server.

[1149] input:

[1150] Question

[1151] output:

[1152] Explanation and examples

[1153] Step 13:

[1154] The server sends explanations and examples to the user's terminal.

[1155] Specific behavior:

[1156] The server sends the explanations and concrete examples received from the artificial intelligence engine to the user terminal, which then displays them to the user.

[1157] input:

[1158] Explanation and examples

[1159] output:

[1160] Explanations and examples are displayed on the user's device.

[1161] Step 14:

[1162] The server generates encouraging messages based on the user's progress.

[1163] Specific behavior:

[1164] The server analyzes the user's learning progress data and automatically generates encouraging messages and achievements, which are customized based on the user's progress and goal achievements.

[1165] input:

[1166] Learning progress data

[1167] output:

[1168] Encouraging messages and achievements

[1169] Step 15:

[1170] The server sends encouraging messages to the user terminal.

[1171] Specific behavior:

[1172] The server transmits the generated encouraging message to the user terminal, and the user terminal notifies the user of the message.

[1173] input:

[1174] Messages of encouragement

[1175] output:

[1176] The message is sent to the user terminal.

[1177] Through these steps, the system can personalize and effectively support users' learning activities.

[1178] (Application example 1)

[1179] 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."

[1180] The problem that this invention aims to solve is to individually optimize a user's learning, provide effective learning support, provide real-time explanations for stumbling blocks and questions during learning, and maintain the user's motivation. Furthermore, by realizing this across multiple devices, it aims to improve the user's learning experience.

[1181] 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.

[1182] In this invention, the server includes means for collecting a user's learning history and progress, means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user, means for evaluating the user's learning progress and suggesting areas for strengthening or improvement, means including a generative model that generates specific explanations and examples for difficult content, means for generating and providing messages to maintain motivation according to the user's learning progress, means for providing a personalized learning plan on multiple devices, and means for generating explanations in real time in response to the user's questions. This makes it possible to comprehensively support the user's learning experience and achieve individually optimized learning.

[1183] "Means for collecting a user's learning history and progress" refers to devices or software that record what a user has learned in the past and their progress at that time, and consolidate this information into a system.

[1184] "Means including an artificial intelligence engine that analyzes collected data and generates optimal learning plans for users" refers to devices or software that use AI to analyze collected user learning data and create optimal learning plans for each user based on that data.

[1185] "Means for assessing a user's learning progress and suggesting areas for reinforcement or improvement" refers to devices or software that periodically check a user's learning status and suggest areas that need reinforcement or improvement in order to support effective learning.

[1186] "Means including a generative model that generates specific explanations and examples for difficult content" refers to devices or software that use a generative model to automatically generate specific, easy-to-understand explanations and examples for content that users find difficult to understand while studying.

[1187] "Means for generating and providing messages to maintain motivation according to the user's learning progress" refers to devices or software that generate encouraging and supportive messages according to the user's learning progress, motivating the user to continue learning.

[1188] "Means for providing personalized learning plans on multiple devices" refers to devices or software that make learning plans customized for each user available on multiple devices, such as smartphones, tablets, and smart glasses.

[1189] "Means for generating explanations in real time in response to user questions" refers to devices or software that instantly generate and provide appropriate explanations in response to questions that users have while studying.

[1190] To realize the system of the present invention, a server, a user terminal, and an artificial intelligence engine (AI engine) are required. This system provides learning support to users through the following specific process.

[1191] Major hardware and software configurations

[1192] Hardware:

[1193] Server: AWS (Amazon Web Services) or Google Cloud

[1194] User devices: smartphones, tablets, smart glasses

[1195] software:

[1196] Database: MySQL

[1197] Artificial intelligence engine: Google Cloud AI, OpenAI GPT

[1198] System Operation Overview

[1199] 1. User data collection:

[1200] Users log in to the system from their devices. The login information is sent to the server, which retrieves past learning history and progress from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be aggregated on the server.

[1201] 2. Analyze the data and generate a learning plan:

[1202] The server sends the collected data to an AI engine, which analyzes the data, analyzes the user's learning patterns and level of understanding, and generates an optimal learning plan, including specific learning material recommendations and study time allocations.

[1203] 3. Learning progress assessment and suggestions:

[1204] The user's device records the learning progress in real time and sends it to the server, which periodically evaluates it and sends it to the AI ​​engine to identify areas that need strengthening or improvement, and the user can receive feedback based on this.

[1205] 4. Explanation of difficult content:

[1206] When a user inputs a question during learning, the question is sent to the server, which passes it to the AI ​​engine to generate an explanation and concrete examples. The generated content is then sent to the device and provided to the user.

[1207] 5. Motivation support:

[1208] The server generates encouraging messages and achievements based on learning progress, which the device notifies the user and motivates them to continue learning.

[1209] 6. Multi-device compatibility:

[1210] Learning plans, feedback and explanations are available across multiple devices including smartphones, tablets and smart glasses.

[1211] Specific examples

[1212] For example, let's say a user (user ID: 001) wants to learn the basics of programming. The user logs into the system using their smartphone. The server collects user 001's learning history and progress from the database and sends it to the AI ​​engine. The AI ​​engine analyzes the data and generates an optimal learning plan including the next learning step. If the user gets stuck while learning, they can input a question, and the server will generate explanations and concrete examples and provide them to the user. The server also generates encouraging messages according to the user's learning progress and notifies them to keep the user motivated.

[1213] Prompt Sentence Examples

[1214] Users find it difficult to understand the basic programming concept of "loop structure." Please provide a detailed explanation with concrete examples.

[1215] In this way, the system of the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[1216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1217] Step 1: Collect user data

[1218] A user logs into the system from their device. The login information is sent to the server. The server retrieves past learning history and progress from the database and temporarily stores it. The aggregated data includes the user's past learning content, study time, test results, etc.

[1219] Input: User login information

[1220] Data processing / calculation: Obtaining learning history and progress from the database

[1221] Output: Captured learning history and progress data

[1222] Step 2: Analyze the data and generate a learning plan

[1223] The server sends the collected data to an AI engine, which analyzes the data and analyzes the user's learning patterns and level of understanding. Based on the analysis results, an optimal learning plan is generated for the user. This plan includes which learning materials to use, how much time to spend on them, and the order in which they should be studied.

[1224] Input: Learning history and progress data

[1225] Data processing / calculation: Data analysis and plan generation using an AI engine

[1226] Output: Optimal study plan

[1227] Step 3: Assessment and recommendations for learning progress

[1228] The user's device records the learning progress in real time and sends it to the server, which then periodically sends it to the AI ​​engine to evaluate the user's progress. Based on the evaluation, suggestions for improvements and enhancements are made.

[1229] Input: Real-time learning progress data

[1230] Data processing / calculation: Progress evaluation and proposal generation using an AI engine

[1231] Output: Enhancements and Improvements

[1232] Step 4: Explaining the complexities

[1233] When a user inputs a question during learning, the question is sent to the server, which passes it to the AI ​​engine to generate an explanation and concrete examples. The generated content is then sent to the device and provided to the user.

[1234] Input: User's question

[1235] Data processing / calculation: Explanations and concrete examples generated by AI engine

[1236] Output: Generated explanations and examples

[1237] Step 5: Support to maintain motivation

[1238] The server generates encouraging messages and achievements based on the user's learning progress. Messages are customized according to the user's progress and sent to the user's device.

[1239] Input: User's learning progress data

[1240] Data processing / calculation: Server-generated encouragement messages and achievements

[1241] Output: Generated encouragement message and achievement

[1242] Step 6: Multi-device compatibility

[1243] The learning plans, feedback, and explanations are available on multiple devices, including smartphones, tablets, and smart glasses, with the data being sent from the server to each device in an appropriate format.

[1244] Input: Generated lesson plans, explanations, and feedback data

[1245] Data processing / calculation: Device-compatible format generation and data transmission

[1246] Output: Data converted into a format that can be used by each device

[1247] 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.

[1248] This invention is a learning personal assistant system that utilizes AI to personalize and effectively support users' learning. It combines an emotion engine to recognize the user's emotions and, based on those emotions, more effectively creates learning plans and maintains motivation.

[1249] This system includes a server, a user terminal, an artificial intelligence engine, and an emotion engine. The system operates as follows.

[1250] User data collection

[1251] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[1252] Analyzing data and creating a learning plan

[1253] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[1254] Emotion recognition by emotion engine

[1255] While studying, the user's device collects emotional data from the user's facial expressions and voice and sends it to the server. The emotion engine recognizes the user's emotions based on the received emotional data and uses this information to adjust the study plan and encouraging messages.

[1256] Learning progress assessment and suggestions

[1257] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[1258] Explaining difficult topics and providing examples

[1259] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[1260] Support for maintaining motivation

[1261] The server generates encouraging messages and achievements based on the user's learning progress and emotional data. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[1262] Specific examples

[1263] For example, let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to the artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. The user device sends the user's facial expressions and voice to the emotion engine while learning, and if the user is confused, it adjusts the learning pace and provides additional explanations. If the user stumbles while learning, the user device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. The server also generates encouraging messages based on the user's progress and emotions, and the user device notifies the user of this, helping them continue their learning.

[1264] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[1265] The processing flow will be explained below.

[1266] Step 1:

[1267] The user logs in to the system, enters the authentication information to log in, and presses the submit button.

[1268] Step 2:

[1269] The terminal receives the user's login information and sends it to the server. This login information includes the user ID and password.

[1270] Step 3:

[1271] The server verifies the user's authentication information and, if correct, retrieves the user's learning history and progress data from a database, including past learning content, study time, test results, etc.

[1272] Step 4:

[1273] The server sends the acquired user data to an AI engine, which analyzes the learning data. The AI ​​engine analyzes the user's learning patterns and level of understanding and generates an optimal learning plan. This learning plan includes which learning materials to use, how much time to spend on each, and the learning order.

[1274] Step 5:

[1275] The server transmits the generated study plan to the terminal, which displays it to the user, who then begins studying according to the study plan.

[1276] Step 6:

[1277] Emotion data is generated using facial expressions and voice during training. For example, facial expression and voice analysis is performed using a camera and microphone.

[1278] Step 7:

[1279] The terminal collects the user's emotion data in real time and transmits it to the server.

[1280] Step 8:

[1281] The server uses an emotion engine to analyze the received emotion data and recognize the user's emotional state (e.g., confusion, satisfaction, fatigue, etc.).

[1282] Step 9:

[1283] The server determines if the lesson plan needs to be adjusted based on the perceived emotional state, for example, adjusting the lesson plan to slow down the pace or provide additional explanation if the user is confused.

[1284] Step 10:

[1285] The server sends the adjusted learning plan and additional explanations to the terminal, which displays them to the user.

[1286] Step 11:

[1287] If a user encounters a problem while studying, they can enter a question and submit it to the system.

[1288] Step 12:

[1289] The device sends the user's question to the server, which then passes the question to an artificial intelligence engine, requesting it to generate appropriate explanations and examples.

[1290] Step 13:

[1291] The AI ​​engine generates explanations and examples based on the user's question and sends them to the server, which then sends them to the device, which displays them to the user.

[1292] Step 14:

[1293] The device records the user's learning activities in real time and transmits the progress data to the server, which periodically evaluates the learning progress and has the AI ​​engine analyze the progress data.

[1294] Step 15:

[1295] Based on the analysis results, the server suggests areas for improvement to the user. It also sends messages to the device to maintain motivation, including encouraging messages, based on the evaluation results generated by the emotion engine.

[1296] Step 16:

[1297] The device displays encouraging messages and notifications of areas for improvement to the user, helping them to stay motivated to continue learning.

[1298] Example 2

[1299] 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."

[1300] Conventional learning support systems collect users' learning history and progress and provide learning plans based on that information. However, they are unable to provide support that takes into account the user's emotional state. Therefore, there is a need for a method to effectively support users in maintaining their motivation and understanding difficult content. Furthermore, there is a need for a method to generate personalized encouraging messages in real time according to the user's learning progress and deliver them at the appropriate time.

[1301] 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.

[1302] In this invention, the server includes a means for collecting the user's learning history and progress, a means including an artificial intelligence engine for analyzing the collected data to generate an optimal learning plan for the user, and a means including an emotion engine for collecting and analyzing the user's emotion data, thereby making it possible to effectively analyze the user's learning pattern and level of understanding and adjust the learning plan and encouraging messages.

[1303] "User's learning history" refers to a record of all learning activities that a user has performed in the past, including information such as learning content, study time, and test results.

[1304] "Progress" is data that indicates the user's learning progress, and includes information such as the current learning stage, level of achievement, and level of understanding.

[1305] An "artificial intelligence engine" refers to an algorithm or program that analyzes collected data and generates the optimal learning plan for the user.

[1306] An "emotion engine" refers to an algorithm or program that collects and analyzes emotional data such as a user's facial expressions and voice.

[1307] A "study plan" is a specific instruction plan for a user to effectively progress through their studies, and includes the learning materials to be used, study time, study order, etc.

[1308] "Encouragement messages" refer to encouraging text or audio messages generated to motivate users to learn.

[1309] "Difficult content" refers to specific issues or concepts that users find difficult to understand while learning.

[1310] A "generative model" refers to an algorithm or program that automatically generates specific explanations and examples based on a user's questions or requests.

[1311] "Areas for reinforcement or improvement" indicates areas that need further reinforcement or improvement as a result of evaluating the user's learning situation.

[1312] "Motivational messages" refer to personalized messages of encouragement designed to maintain or increase a user's motivation to learn.

[1313] The present invention relates to a personal learning assistant system that individually optimizes a user's learning and improves learning efficiency. The system collects the user's learning history and progress and provides an appropriate learning plan based on that. It also uses an emotion engine to recognize the user's emotional state and adjusts the learning plan and encouraging messages accordingly, thereby maintaining the user's motivation.

[1314] Explanation of program processing

[1315] This system is composed of a server, a user terminal, an AI engine, and an emotion engine. The specific operation of each component is as follows:

[1316] User data collection

[1317] When a user logs in to the system, the device sends the login information to the server. The server retrieves the user's past learning history and progress from the database based on the user ID and temporarily stores it. This allows the server to store the user's learning content, study time, and test results.

[1318] Analyzing data and creating a learning plan

[1319] The server sends the temporarily stored data to an AI engine. The AI ​​engine analyzes the user's learning data, analyzing their learning patterns and level of understanding. Based on the analysis results, it generates an optimal learning plan and returns it to the server. This learning plan includes the learning materials to be used, the study time, and the study order.

[1320] Emotion recognition by emotion engine

[1321] While studying, the device uses a camera and microphone to collect the user's facial expressions and voice. The collected emotional data is sent to a server, which then transmits it to an emotion engine. The emotion engine analyzes the emotional data and recognizes the user's emotional state. Based on the analysis results, the server adjusts the study plan and encouraging messages.

[1322] Learning progress assessment and suggestions

[1323] The device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to the AI ​​engine. Based on the feedback from the AI ​​engine, the server makes appropriate suggestions to the user.

[1324] Explaining difficult content and providing concrete examples

[1325] When a user enters a question, the device sends it to the server, which passes the question to an artificial intelligence engine and uses a generative AI model to generate appropriate explanations and examples. The generated explanations and examples are then returned from the server to the device and displayed to the user.

[1326] Support for maintaining motivation

[1327] The server generates encouraging messages and achievements based on the user's learning progress and emotional data, and the device notifies the user of the messages received from the server, thus maintaining the user's motivation to continue learning.

[1328] Specific examples

[1329] For example, let us consider a case where a user (user ID: 001) wishes to learn the basics of programming.

[1330] 1. The user terminal sends User 001's login information to the system, and the server collects User 001's learning history and progress from the database. The collected data is sent to an artificial intelligence engine, which generates an optimal learning plan.

[1331] 2. The user device collects the user's facial expressions and voice during learning and sends them to the emotion engine. If the user is confused, the learning pace will be adjusted and additional explanations will be provided.

[1332] 3. If the user encounters a problem while studying, the user device sends the question to the server, and the server generates an explanation and concrete examples and provides them to the user.

[1333] 4. The server generates encouraging messages based on the user's progress and emotions, and the user's device notifies the user of these messages to help them continue their studies.

[1334] Prompt Sentence Examples

[1335] Generate the following learning plan based on the user's learning progress and past history: The user wants to learn the basics of programming.

[1336] In this way, the learning personal assistant system of the present invention provides flexible support tailored to the individual needs of the user, and realizes effective learning and continuous learning that takes into account the user's emotional state.

[1337] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1338] Step 1:

[1339] User login and data collection

[1340] When a user logs in to the system, the terminal sends the user's login information to the server.

[1341] Input: User ID and password

[1342] Processing: The server uses the user ID to retrieve the past learning history and progress from the database.

[1343] Output: User learning history and progress data

[1344] Specific operation: The terminal displays a login form and sends the ID and password entered by the user to the server. The server receives this and executes a database query. The result is temporarily saved.

[1345] Step 2:

[1346] Analyzing data and creating a learning plan

[1347] The server sends the temporarily stored user learning data to the artificial intelligence engine.

[1348] Input: User learning history and progress data

[1349] Processing: The artificial intelligence engine analyzes the data and analyzes the user's learning patterns and comprehension.

[1350] Output: Optimal study plan

[1351] How it works: The server sends the data to the AI ​​engine, which uses an analytical algorithm to generate a learning plan, which is then returned to the server in JSON format.

[1352] Step 3:

[1353] Emotion Recognition and Regulation

[1354] During learning, the device collects the user's facial expressions and voice using a camera and microphone and sends them to the server.

[1355] Input: User's facial expression data and voice data

[1356] Processing: The emotion engine analyzes these data and recognizes the user's emotional state.

[1357] Output: Feedback based on emotional state

[1358] Specific operation: The device activates the camera and microphone to collect data in real time. The collected data is sent to the server, which then relays it to the emotion engine. The analysis results are reflected as feedback in the form of learning plans and encouraging messages.

[1359] Step 4:

[1360] Learning progress assessment and suggestions

[1361] The device records the user's learning progress in real time and transmits it to the server.

[1362] Input: User's learning progress data

[1363] Processing: The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine.

[1364] Output: Suggested improvements and enhancements

[1365] How it works: The device records which page or learning material the user is currently studying and sends this to the server. The server uses a "progress assessment algorithm" to evaluate the data and sends the results to the AI ​​engine, which then provides feedback.

[1366] Step 5:

[1367] Explaining difficult content and providing concrete examples

[1368] The user enters a question and the terminal sends the question to the server.

[1369] Input: User's question

[1370] Processing: The server sends the question to an artificial intelligence engine, which uses a generative AI model to generate explanations and examples.

[1371] Output: Explanation and Examples

[1372] Specific operation: During learning, the user types "I don't understand the loop syntax." The device sends this question to the server, which then sends a request to the generative AI model to "provide a specific explanation." The generative AI model generates an explanation and a specific example and returns it to the server. The server then displays this to the user.

[1373] Step 6:

[1374] Support for maintaining motivation

[1375] The server generates encouraging messages and achievements based on the user's learning progress and emotional data.

[1376] Input: Learning progress data and emotion data

[1377] Processing: The server generates an encouraging message based on the data and sends it to the device.

[1378] Output: An encouraging message

[1379] Specific operation: The server periodically evaluates the "learning progress" and "emotional data" and generates encouraging messages such as "Keep up the good work!" The device notifies the user of this and displays it via voice or a pop-up.

[1380] Through these steps, the system is able to personalize and effectively support users' learning.

[1381] (Application example 2)

[1382] 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."

[1383] Conventional learning support systems provide learning plans based on the user's learning progress and history, and while they are effective to a certain extent, they do not adequately take into account the user's emotional state. As a result, they are unable to effectively address frustration and loss of motivation that users experience while learning, leaving issues with learning continuity. Furthermore, in brick-and-mortar learning support services, it is often difficult for users to immediately obtain the information they need, resulting in a poor quality learning experience.

[1384] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting a user's learning history and progress, means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user, means for evaluating the user's learning progress and suggesting areas for strengthening or improvement, means including a generative model that generates specific explanations and examples for difficult content, means for generating and providing messages to maintain motivation according to the user's learning progress, means including an emotion engine that recognizes the user's emotional state and adjusts the learning plan, means for recording the user's learning progress in real time, and means for providing learning support for the user to study specific information in a store. This enables effective learning support that comprehensively takes into account the user's emotional state and learning progress, and the quality of the learning experience can be improved by providing immediate and appropriate information in a physical store.

[1385] "User" refers to an individual who uses the system to advance their learning.

[1386] "Learning history" refers to a record of a user's past learning activities.

[1387] "Progress" refers to data that shows how far a user has progressed in their learning.

[1388] An "artificial intelligence engine" refers to software or hardware that analyzes collected data and generates optimal learning plans for users.

[1389] "Points of improvement" refers to areas of user learning that require particular reinforcement.

[1390] "Areas for improvement" refers to areas that particularly need improvement in user learning.

[1391] A "generative model" refers to an algorithm or software that generates explanations or examples under certain conditions.

[1392] "Messages to maintain motivation" refers to messages that motivate users to continue learning.

[1393] An "emotion engine" refers to software or hardware that recognizes emotions from a user's facial expressions, voice, etc.

[1394] "Real-time" refers to a state in which processing and analysis are carried out immediately at the present time.

[1395] "Study Progress" refers to data that indicates how far a user has progressed in their current study plan.

[1396] "In-store learning support" refers to providing support to users in physical stores to learn about products and services.

[1397] This invention is a learning personal assistant system that utilizes AI to personalize and effectively support users' learning. It combines an emotion engine to recognize the user's emotions and, based on those emotions, more effectively creates learning plans and maintains motivation.

[1398] The system includes a server, a user terminal, an artificial intelligence engine, and an emotion engine. Each of these components is described in detail below.

[1399] How we collect your data

[1400] The server receives login information from the user's device and retrieves the user's learning history and progress data from the database, allowing information such as the user's past learning content, study time, and test results to be stored on the server.

[1401] How to generate a lesson plan

[1402] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[1403] emotion recognition means

[1404] While studying, the user's device collects emotional data from the user's facial expressions and voice and sends it to the server. The emotion engine recognizes the user's emotions based on the received emotional data and uses this information to adjust the study plan and encouraging messages.

[1405] Learning progress assessment and suggestion tools

[1406] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[1407] A means of generating explanations and examples of difficult content

[1408] If a user encounters difficulty understanding a particular problem or complex content during learning, they can send a question from their device to the server. The server then passes the user's question to the generative model, which generates appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[1409] Motivational message generation method

[1410] The server generates encouraging messages and achievements based on the user's learning progress and emotional data. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[1411] In-store learning support methods

[1412] When users learn about products or services in a physical store, they can learn specific information using their own devices or tablets installed in the store. The system instantly provides details and instructions on specific products, allowing users to obtain the information they want in a timely manner. The system also improves the quality of the learning experience by providing appropriate support and encouraging messages based on the user's learning progress and emotional state.

[1413] Specific examples

[1414] As a concrete example, let's consider the case where a user wants to learn how to use a new rice cooker at an electronics store. The user's device sends login information to the server, which then collects the user's past usage history. The artificial intelligence engine analyzes this and generates an optimal learning plan for how to use the rice cooker. The user's device uses the store's camera to send the user's facial expressions to the emotion engine, which recognizes the user's emotional state. The server then generates appropriate explanations and examples to answer the question, resolving the user's doubts. By providing messages to maintain motivation, the user's learning experience is optimized.

[1415] Prompt Sentence Examples

[1416] "I want to learn how to use new appliances. Can you tell me the next step for the appliances I currently use?"

[1417] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[1418] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1419] Step 1:

[1420] User data collection

[1421] When a user logs in from their device, the server receives the login information and retrieves the user's learning history and progress data from the database. This input data includes past learning content, study time, and test results, and uses this information to create an individual user profile. As output, the user's learning history and progress are temporarily stored on the server.

[1422] Step 2:

[1423] Generate a learning plan

[1424] The server sends the collected user data to an AI engine, which analyzes the user's learning data. Using learning history and progress as input data, the AI ​​engine analyzes the user's learning patterns and level of understanding. This generates an optimal learning plan. As an output, the optimal learning plan, which includes learning materials, study time, and study order, is stored on the server.

[1425] Step 3:

[1426] emotion recognition

[1427] During learning, the user device collects emotion data from the user's facial expressions and voice and sends it to the server. Images of the user's facial expressions and recorded voice data are used as input data. The emotion engine analyzes this data and recognizes the user's emotional state. As output, data on the user's emotions (e.g., satisfaction, confusion, impatience) is generated and stored on the server.

[1428] Step 4:

[1429] Assessment and recommendations for learning progress

[1430] The server receives learning progress data sent from the user's device in real time. The input data includes the current progress. The server periodically evaluates this data and sends it to an artificial intelligence engine to identify areas for improvement and strengthening. This generates appropriate feedback for the user. As an output, progress evaluation results and feedback are generated and stored on the server.

[1431] Step 5:

[1432] Explaining complex content and generating examples

[1433] When a user inputs a question during learning, the question is sent from the user's device to the server. The input data includes the user's question. The server passes this data to a generative model, which generates appropriate explanations and concrete examples. As output, explanations and concrete examples of difficult content are generated and provided to the user.

[1434] Step 6:

[1435] Generate motivational messages

[1436] The server generates encouraging messages and achievements based on learning progress and emotional data. Input data includes progress assessment results and emotional states. The generated messages are customized according to the progress and goal achievement status. As output, the customized encouraging messages are stored in the server and sent to the user's device.

[1437] Step 7:

[1438] In-store learning support

[1439] When a user learns about a product or service in a physical store, they learn specific information using their device or a tablet device in the store. The input data includes information about the product or service the user wants to learn about. The server immediately provides details about the specific product and how to use it, allowing the user to obtain the information they want to learn in a timely manner. The output provides detailed information about the product or service, as well as messages of support and encouragement.

[1440] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] [Fourth embodiment]

[1445] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1446] 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.

[1447] 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).

[1448] 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.

[1449] 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.

[1450] 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).

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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.

[1457] 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."

[1458] This invention describes an AI-based learning personal assistant system to personalize and effectively assist users in their learning.

[1459] This system includes a server, a user terminal, and an artificial intelligence engine. The system operates as follows.

[1460] User data collection

[1461] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[1462] Analyzing data and creating a learning plan

[1463] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[1464] Learning progress assessment and suggestions

[1465] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[1466] Explaining difficult topics and providing examples

[1467] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[1468] Support for maintaining motivation

[1469] The server generates encouraging messages and achievements based on the user's learning progress. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[1470] Specific examples

[1471] For example, let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user's device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to an artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. If the user encounters difficulties during learning, the user's device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. Additionally, depending on the user's progress, the server generates encouraging messages, which the user's device notifies, helping them continue their learning.

[1472] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[1473] The processing flow will be explained below.

[1474] Step 1:

[1475] The user logs in to the system, enters the authentication information to log in, and presses the submit button.

[1476] Step 2:

[1477] The terminal receives the user's login information and sends it to the server, which includes the user ID and password.

[1478] Step 3:

[1479] After verifying that the user has entered the correct authentication information, the server retrieves the user's learning history and progress data from the database, including past learning content, study time, test results, etc.

[1480] Step 4:

[1481] The server sends the acquired user data to an AI engine, which analyzes the user's learning history and progress and generates an optimal learning plan.

[1482] Step 5:

[1483] Based on the analysis results, the AI ​​engine generates an optimal study plan for the user, which includes recommended learning materials, study time allocation, and study order.

[1484] Step 6:

[1485] The server sends the generated learning plan to the terminal, which displays the learning plan to the user.

[1486] Step 7:

[1487] The user performs the learning activity. The user uses the learning material according to the learning content, and if the user has any questions or encounters difficult content, the user inputs the questions into the system.

[1488] Step 8:

[1489] The device sends the user's question to the server, which then passes the question to an artificial intelligence engine, requesting it to generate appropriate explanations and examples.

[1490] Step 9:

[1491] The AI ​​engine generates explanations and examples based on the user's question and sends them to the server, which then sends them to the device, which displays them to the user.

[1492] Step 10:

[1493] The device records the user's learning activities in real time and transmits the progress data to the server, which periodically evaluates the learning progress and has the AI ​​engine analyze the progress data.

[1494] Step 11:

[1495] Based on the analysis results, the server will suggest areas for improvement and strengthen the user, and will also send motivational messages, including encouraging messages generated by the AI ​​engine, to the device.

[1496] Step 12:

[1497] The device displays encouraging messages and notifications of areas for improvement to the user, helping them to stay motivated to continue learning.

[1498] Example 1

[1499] 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."

[1500] Conventional learning support systems have not provided sufficient personalized learning support that takes into account each user's progress and learning history. Furthermore, when users encounter difficult content during learning, it is difficult to provide specific explanations and examples at the appropriate time. As a result, users' learning efficiency and motivation can decline.

[1501] 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.

[1502] In this invention, the server includes: means for collecting a user's learning history and progress; means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user; means for evaluating the user's learning progress and suggesting areas for strengthening or improvement; means including a generative model that generates specific explanations and examples based on questions entered by the user for specific problems or difficult content; means for generating and providing messages to maintain motivation according to the user's learning progress; and means for generating encouraging messages according to the user's learning plan and progress and notifying the user terminal. This makes it possible to provide learning support and maintain motivation that is optimized for each individual user.

[1503] A "user" is an individual who uses the system to carry out learning activities.

[1504] "Learning history" is a record of the learning activities that a user has undertaken to date.

[1505] "Progress" refers to the user's current achievement or progress in learning.

[1506] "Means of collection" refers to the functions and mechanisms for inputting and storing a user's learning history and progress into the system.

[1507] "Analyzing data" means organizing information based on collected learning data and extracting useful insights.

[1508] An "artificial intelligence engine" refers to the entire algorithm or system that analyzes a user's learning data and generates the optimal learning plan.

[1509] A "study plan" is a plan that includes the study materials to be used, study time, study order, etc., to enable the user to study efficiently.

[1510] "Means of evaluation" are functions and mechanisms for regularly checking users' learning progress and measuring the results.

[1511] "Improvements" are areas where users should learn more.

[1512] "Areas for improvement" are areas that users don't understand or items that need to be corrected to improve efficiency.

[1513] A "generative model" is a computational model that can generate appropriate explanations and concrete examples in response to questions that users have.

[1514] Maintaining "motivation" involves activities that include actions and messages that motivate users to continue learning.

[1515] "Means for generating and providing messages" refers to a function or mechanism for creating messages according to the user's progress and informing the user of these messages.

[1516] "Encouraging messages" are positive words or notifications that motivate users to continue learning.

[1517] A "user terminal" is a device (smartphone, tablet, PC, etc.) that a user uses to access the system and carry out learning activities.

[1518] The present invention describes a learning personal assistant system that utilizes artificial intelligence to personalize and effectively assist users in their learning. The system includes a server, a user terminal, and an artificial intelligence engine.

[1519] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from a database (e.g., MySQL) and temporarily stores it. This allows the server to accumulate information such as the user's past learning content, study time, and test results.

[1520] The server sends the collected data to an artificial intelligence engine (for example, OpenAI's GPT-3), which analyzes the user's learning data. The artificial intelligence engine analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes which learning materials to use, how much time to spend on them, and the order in which they should be studied.

[1521] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine. The artificial intelligence engine analyzes the evaluation results and identifies areas for strengthening and improvement. The server receives feedback from the artificial intelligence engine and sends it to the user's device. The user can then receive feedback on which areas need strengthening or improvement based on their own progress.

[1522] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[1523] The server generates encouraging messages and achievements based on the user's learning progress. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, keeping the user motivated to continue learning.

[1524] Specific examples

[1525] Let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user's device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to an artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. If the user encounters difficulties during learning, the user's device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. Additionally, depending on the user's progress, the server generates encouraging messages, which the user's device notifies the user of, supporting them in continuing their learning.

[1526] Example prompts for generative AI models

[1527] "User ID: 001 is having trouble with the basics of programming. Please provide an explanation and concrete examples based on the user's learning history."

[1528] "Generate an encouraging message based on the progress of user ID: 001."

[1529] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[1530] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1531] Step 1:

[1532] A user logs in to the system.

[1533] Specific behavior:

[1534] The user launches the learning app, enters their user ID and password on the login screen, and presses the "Login" button. This causes the user device to send the entered login information to the server.

[1535] input:

[1536] User ID and password

[1537] output:

[1538] The login information is sent to the server.

[1539] Step 2:

[1540] The server retrieves the user's learning history and progress from the database.

[1541] Specific behavior:

[1542] The server receives the login information, searches for and retrieves the user's learning history and progress from a database (e.g., MySQL) based on the user ID, and stores the retrieved data in temporary memory (e.g., Redis).

[1543] input:

[1544] User ID

[1545] output:

[1546] Learning history and progress data is stored in temporary memory.

[1547] Step 3:

[1548] The server sends the collected data to an artificial intelligence engine.

[1549] Specific behavior:

[1550] The server sends the user's learning data stored in temporary memory to an artificial intelligence engine (e.g., GPT-3).

[1551] input:

[1552] User learning history and progress data

[1553] output:

[1554] The data is sent to an artificial intelligence engine.

[1555] Step 4:

[1556] The artificial intelligence engine analyzes the user's learning data and generates the optimal learning plan.

[1557] Specific behavior:

[1558] The AI ​​engine analyzes the received learning data, analysing the user's learning patterns and level of understanding. Based on the results, it generates an optimal learning plan, including the learning materials to be used, study time, and learning order, and returns it to the server.

[1559] input:

[1560] User learning data

[1561] output:

[1562] The best study plan

[1563] Step 5:

[1564] The server sends the learning plan to the user's device.

[1565] Specific behavior:

[1566] The server receives the optimal learning plan from the AI ​​engine and sends it to the user's device, which displays it to the user and tells them what to study next.

[1567] input:

[1568] The best study plan

[1569] output:

[1570] The learning plan will be displayed on the user's device.

[1571] Step 6:

[1572] The user's device records the user's learning progress in real time and transmits it to the server.

[1573] Specific behavior:

[1574] As the user progresses through their studies, the user's device records the progress of the study, including the start time, end time, and study items, in real time, and sends this information to the server at regular intervals (e.g., every 30 minutes).

[1575] input:

[1576] Learning progress data

[1577] output:

[1578] Progress data is sent to the server.

[1579] Step 7:

[1580] The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine.

[1581] Specific behavior:

[1582] The server evaluates the user's progress based on the received learning progress data and sends the results to the AI ​​engine, which analyzes the evaluation data and identifies areas for improvement.

[1583] input:

[1584] Learning progress data

[1585] output:

[1586] The evaluation results are sent to an artificial intelligence engine.

[1587] Step 8:

[1588] The artificial intelligence engine analyzes the evaluation results and identifies areas for strengthening and improvement.

[1589] Specific behavior:

[1590] The AI ​​engine analyzes the evaluation data, identifies areas where the user needs to improve and provides feedback to the server.

[1591] input:

[1592] Evaluation results

[1593] output:

[1594] Feedback on enhancements and improvements

[1595] Step 9:

[1596] The server sends feedback on enhancements and improvements to the user's device.

[1597] Specific behavior:

[1598] The server receives feedback from the AI ​​engine and sends it to the user's device, which displays the feedback to the user and provides advice based on their progress.

[1599] input:

[1600] feedback

[1601] output:

[1602] Feedback is displayed on the user's device.

[1603] Step 10:

[1604] The user types a question.

[1605] Specific behavior:

[1606] If a user encounters a problem while learning, they enter a question into the question input field within the learning app and press the "Submit" button.

[1607] input:

[1608] Question

[1609] output:

[1610] A question is sent from the user terminal to the server.

[1611] Step 11:

[1612] The server sends the question to the artificial intelligence engine.

[1613] Specific behavior:

[1614] The server passes the question sent from the user's device to the artificial intelligence engine, requesting it to generate an explanation and specific examples.

[1615] input:

[1616] Question

[1617] output:

[1618] The question is sent to an artificial intelligence engine.

[1619] Step 12:

[1620] The artificial intelligence engine generates explanations and examples based on the question.

[1621] Specific behavior:

[1622] The AI ​​engine analyzes the question and generates appropriate explanations and examples, which are then sent to the server.

[1623] input:

[1624] Question

[1625] output:

[1626] Explanation and examples

[1627] Step 13:

[1628] The server sends explanations and examples to the user's terminal.

[1629] Specific behavior:

[1630] The server sends the explanations and concrete examples received from the artificial intelligence engine to the user terminal, which then displays them to the user.

[1631] input:

[1632] Explanation and examples

[1633] output:

[1634] Explanations and examples are displayed on the user's device.

[1635] Step 14:

[1636] The server generates encouraging messages based on the user's progress.

[1637] Specific behavior:

[1638] The server analyzes the user's learning progress data and automatically generates encouraging messages and achievements, which are customized based on the user's progress and goal achievements.

[1639] input:

[1640] Learning progress data

[1641] output:

[1642] Encouraging messages and achievements

[1643] Step 15:

[1644] The server sends encouraging messages to the user terminal.

[1645] Specific behavior:

[1646] The server transmits the generated encouraging message to the user terminal, and the user terminal notifies the user of the message.

[1647] input:

[1648] Messages of encouragement

[1649] output:

[1650] The message is sent to the user terminal.

[1651] Through these steps, the system can personalize and effectively support users' learning activities.

[1652] (Application example 1)

[1653] 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."

[1654] The problem that this invention aims to solve is to individually optimize a user's learning, provide effective learning support, provide real-time explanations for stumbling blocks and questions during learning, and maintain the user's motivation. Furthermore, by realizing this across multiple devices, it aims to improve the user's learning experience.

[1655] 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.

[1656] In this invention, the server includes means for collecting a user's learning history and progress, means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user, means for evaluating the user's learning progress and suggesting areas for strengthening or improvement, means including a generative model that generates specific explanations and examples for difficult content, means for generating and providing messages to maintain motivation according to the user's learning progress, means for providing a personalized learning plan on multiple devices, and means for generating explanations in real time in response to the user's questions. This makes it possible to comprehensively support the user's learning experience and achieve individually optimized learning.

[1657] "Means for collecting a user's learning history and progress" refers to devices or software that record what a user has learned in the past and their progress at that time, and consolidate this information into a system.

[1658] "Means including an artificial intelligence engine that analyzes collected data and generates optimal learning plans for users" refers to devices or software that use AI to analyze collected user learning data and create optimal learning plans for each user based on that data.

[1659] "Means for assessing a user's learning progress and suggesting areas for reinforcement or improvement" refers to devices or software that periodically check a user's learning status and suggest areas that need reinforcement or improvement in order to support effective learning.

[1660] "Means including a generative model that generates specific explanations and examples for difficult content" refers to devices or software that use a generative model to automatically generate specific, easy-to-understand explanations and examples for content that users find difficult to understand while studying.

[1661] "Means for generating and providing messages to maintain motivation according to the user's learning progress" refers to devices or software that generate encouraging and supportive messages according to the user's learning progress, motivating the user to continue learning.

[1662] "Means for providing personalized learning plans on multiple devices" refers to devices or software that make learning plans customized for each user available on multiple devices, such as smartphones, tablets, and smart glasses.

[1663] "Means for generating explanations in real time in response to user questions" refers to devices or software that instantly generate and provide appropriate explanations in response to questions that users have while studying.

[1664] To realize the system of the present invention, a server, a user terminal, and an artificial intelligence engine (AI engine) are required. This system provides learning support to users through the following specific process.

[1665] Major hardware and software configurations

[1666] Hardware:

[1667] Server: AWS (Amazon Web Services) or Google Cloud

[1668] User devices: smartphones, tablets, smart glasses

[1669] software:

[1670] Database: MySQL

[1671] Artificial intelligence engine: Google Cloud AI, OpenAI GPT

[1672] System Operation Overview

[1673] 1. User data collection:

[1674] Users log in to the system from their devices. The login information is sent to the server, which retrieves past learning history and progress from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be aggregated on the server.

[1675] 2. Analyze the data and generate a learning plan:

[1676] The server sends the collected data to an AI engine, which analyzes the data, analyzes the user's learning patterns and level of understanding, and generates an optimal learning plan, including specific learning material recommendations and study time allocations.

[1677] 3. Learning progress assessment and suggestions:

[1678] The user's device records the learning progress in real time and sends it to the server, which periodically evaluates it and sends it to the AI ​​engine to identify areas that need strengthening or improvement, and the user can receive feedback based on this.

[1679] 4. Explanation of difficult content:

[1680] When a user inputs a question during learning, the question is sent to the server, which passes it to the AI ​​engine to generate an explanation and concrete examples. The generated content is then sent to the device and provided to the user.

[1681] 5. Motivation support:

[1682] The server generates encouraging messages and achievements based on learning progress, which the device notifies the user and motivates them to continue learning.

[1683] 6. Multi-device compatibility:

[1684] Learning plans, feedback and explanations are available across multiple devices including smartphones, tablets and smart glasses.

[1685] Specific examples

[1686] For example, let's say a user (user ID: 001) wants to learn the basics of programming. The user logs into the system using their smartphone. The server collects user 001's learning history and progress from the database and sends it to the AI ​​engine. The AI ​​engine analyzes the data and generates an optimal learning plan including the next learning step. If the user gets stuck while learning, they can input a question, and the server will generate explanations and concrete examples and provide them to the user. The server also generates encouraging messages according to the user's learning progress and notifies them to keep the user motivated.

[1687] Prompt Sentence Examples

[1688] Users find it difficult to understand the basic programming concept of "loop structure." Please provide a detailed explanation with concrete examples.

[1689] In this way, the system of the present invention provides flexible support tailored to the learning needs of each user, enabling effective and continuous learning.

[1690] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1691] Step 1: Collect user data

[1692] A user logs into the system from their device. The login information is sent to the server. The server retrieves past learning history and progress from the database and temporarily stores it. The aggregated data includes the user's past learning content, study time, test results, etc.

[1693] Input: User login information

[1694] Data processing / calculation: Obtaining learning history and progress from the database

[1695] Output: Captured learning history and progress data

[1696] Step 2: Analyze the data and generate a learning plan

[1697] The server sends the collected data to an AI engine, which analyzes the data and analyzes the user's learning patterns and level of understanding. Based on the analysis results, an optimal learning plan is generated for the user. This plan includes which learning materials to use, how much time to spend on them, and the order in which they should be studied.

[1698] Input: Learning history and progress data

[1699] Data processing / calculation: Data analysis and plan generation using an AI engine

[1700] Output: Optimal study plan

[1701] Step 3: Assessment and recommendations for learning progress

[1702] The user's device records the learning progress in real time and sends it to the server, which then periodically sends it to the AI ​​engine to evaluate the user's progress. Based on the evaluation, suggestions for improvements and enhancements are made.

[1703] Input: Real-time learning progress data

[1704] Data processing / calculation: Progress evaluation and proposal generation using an AI engine

[1705] Output: Enhancements and Improvements

[1706] Step 4: Explaining the complexities

[1707] When a user inputs a question during learning, the question is sent to the server, which passes it to the AI ​​engine to generate an explanation and concrete examples. The generated content is then sent to the device and provided to the user.

[1708] Input: User's question

[1709] Data processing / calculation: Explanations and concrete examples generated by AI engine

[1710] Output: Generated explanations and examples

[1711] Step 5: Support to maintain motivation

[1712] The server generates encouraging messages and achievements based on the user's learning progress. Messages are customized according to the user's progress and sent to the user's device.

[1713] Input: User's learning progress data

[1714] Data processing / calculation: Server-generated encouragement messages and achievements

[1715] Output: Generated encouragement message and achievement

[1716] Step 6: Multi-device compatibility

[1717] The learning plans, feedback, and explanations are available on multiple devices, including smartphones, tablets, and smart glasses, with the data being sent from the server to each device in an appropriate format.

[1718] Input: Generated lesson plans, explanations, and feedback data

[1719] Data processing / calculation: Device-compatible format generation and data transmission

[1720] Output: Data converted into a format that can be used by each device

[1721] 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.

[1722] This invention is a learning personal assistant system that utilizes AI to personalize and effectively support users' learning. It combines an emotion engine to recognize the user's emotions and, based on those emotions, more effectively creates learning plans and maintains motivation.

[1723] This system includes a server, a user terminal, an artificial intelligence engine, and an emotion engine. The system operates as follows.

[1724] User data collection

[1725] When a user logs in to the system, the user's device sends the login information to the server. The server retrieves the user's learning history and progress data from the database and temporarily stores it. This allows information such as the user's past learning content, study time, and test results to be accumulated on the server.

[1726] Analyzing data and creating a learning plan

[1727] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[1728] Emotion recognition by emotion engine

[1729] While studying, the user's device collects emotional data from the user's facial expressions and voice and sends it to the server. The emotion engine recognizes the user's emotions based on the received emotional data and uses this information to adjust the study plan and encouraging messages.

[1730] Learning progress assessment and suggestions

[1731] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[1732] Explaining difficult topics and providing examples

[1733] If a user has difficulty understanding a particular problem or complex content during their study, they can input a question. The user's device then sends this question to the server. The server then passes the user's question to an artificial intelligence engine, which uses a generative model to generate appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[1734] Support for maintaining motivation

[1735] The server generates encouraging messages and achievements based on the user's learning progress and emotional data. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[1736] Specific examples

[1737] For example, let's consider the case where a user (user ID: 001) wants to learn the basics of programming. The user device sends user 001's login information to the system, and the server collects user 001's learning history and progress from the database. The server sends this to the artificial intelligence engine, which analyzes the data and generates an optimal learning plan including the next steps in programming learning. The user device sends the user's facial expressions and voice to the emotion engine while learning, and if the user is confused, it adjusts the learning pace and provides additional explanations. If the user stumbles while learning, the user device sends the question to the server, and the server generates explanations and concrete examples to provide to the user. The server also generates encouraging messages based on the user's progress and emotions, and the user device notifies the user of this, helping them continue their learning.

[1738] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[1739] The processing flow will be explained below.

[1740] Step 1:

[1741] The user logs in to the system, enters the authentication information to log in, and presses the submit button.

[1742] Step 2:

[1743] The terminal receives the user's login information and sends it to the server. This login information includes the user ID and password.

[1744] Step 3:

[1745] The server verifies the user's authentication information and, if correct, retrieves the user's learning history and progress data from a database, including past learning content, study time, test results, etc.

[1746] Step 4:

[1747] The server sends the acquired user data to an AI engine, which analyzes the learning data. The AI ​​engine analyzes the user's learning patterns and level of understanding and generates an optimal learning plan. This learning plan includes which learning materials to use, how much time to spend on each, and the learning order.

[1748] Step 5:

[1749] The server transmits the generated study plan to the terminal, which displays it to the user, who then begins studying according to the study plan.

[1750] Step 6:

[1751] Emotion data is generated using facial expressions and voice during training. For example, facial expression and voice analysis is performed using a camera and microphone.

[1752] Step 7:

[1753] The terminal collects the user's emotion data in real time and transmits it to the server.

[1754] Step 8:

[1755] The server uses an emotion engine to analyze the received emotion data and recognize the user's emotional state (e.g., confusion, satisfaction, fatigue, etc.).

[1756] Step 9:

[1757] The server determines if the lesson plan needs to be adjusted based on the perceived emotional state, for example, adjusting the lesson plan to slow down the pace or provide additional explanation if the user is confused.

[1758] Step 10:

[1759] The server sends the adjusted learning plan and additional explanations to the terminal, which displays them to the user.

[1760] Step 11:

[1761] If a user encounters a problem while studying, they can enter a question and submit it to the system.

[1762] Step 12:

[1763] The device sends the user's question to the server, which then passes the question to an artificial intelligence engine, requesting it to generate appropriate explanations and examples.

[1764] Step 13:

[1765] The AI ​​engine generates explanations and examples based on the user's question and sends them to the server, which then sends them to the device, which displays them to the user.

[1766] Step 14:

[1767] The device records the user's learning activities in real time and transmits the progress data to the server, which periodically evaluates the learning progress and has the AI ​​engine analyze the progress data.

[1768] Step 15:

[1769] Based on the analysis results, the server suggests areas for improvement to the user. It also sends messages to the device to maintain motivation, including encouraging messages, based on the evaluation results generated by the emotion engine.

[1770] Step 16:

[1771] The device displays encouraging messages and notifications of areas for improvement to the user, helping them to stay motivated to continue learning.

[1772] Example 2

[1773] 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."

[1774] Conventional learning support systems collect users' learning history and progress and provide learning plans based on that information. However, they are unable to provide support that takes into account the user's emotional state. Therefore, there is a need for a method to effectively support users in maintaining their motivation and understanding difficult content. Furthermore, there is a need for a method to generate personalized encouraging messages in real time according to the user's learning progress and deliver them at the appropriate time.

[1775] 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.

[1776] In this invention, the server includes a means for collecting the user's learning history and progress, a means including an artificial intelligence engine for analyzing the collected data to generate an optimal learning plan for the user, and a means including an emotion engine for collecting and analyzing the user's emotion data, thereby making it possible to effectively analyze the user's learning pattern and level of understanding and adjust the learning plan and encouraging messages.

[1777] "User's learning history" refers to a record of all learning activities that a user has performed in the past, including information such as learning content, study time, and test results.

[1778] "Progress" is data that indicates the user's learning progress, and includes information such as the current learning stage, level of achievement, and level of understanding.

[1779] An "artificial intelligence engine" refers to an algorithm or program that analyzes collected data and generates the optimal learning plan for the user.

[1780] An "emotion engine" refers to an algorithm or program that collects and analyzes emotional data such as a user's facial expressions and voice.

[1781] A "study plan" is a specific instruction plan for a user to effectively progress through their studies, and includes the learning materials to be used, study time, study order, etc.

[1782] "Encouragement messages" refer to encouraging text or audio messages generated to motivate users to learn.

[1783] "Difficult content" refers to specific issues or concepts that users find difficult to understand while learning.

[1784] A "generative model" refers to an algorithm or program that automatically generates specific explanations and examples based on a user's questions or requests.

[1785] "Areas for reinforcement or improvement" indicates areas that need further reinforcement or improvement as a result of evaluating the user's learning situation.

[1786] "Motivational messages" refer to personalized messages of encouragement designed to maintain or increase a user's motivation to learn.

[1787] The present invention relates to a personal learning assistant system that individually optimizes a user's learning and improves learning efficiency. The system collects the user's learning history and progress and provides an appropriate learning plan based on that. It also uses an emotion engine to recognize the user's emotional state and adjusts the learning plan and encouraging messages accordingly, thereby maintaining the user's motivation.

[1788] Explanation of program processing

[1789] This system is composed of a server, a user terminal, an AI engine, and an emotion engine. The specific operation of each component is as follows:

[1790] User data collection

[1791] When a user logs in to the system, the device sends the login information to the server. The server retrieves the user's past learning history and progress from the database based on the user ID and temporarily stores it. This allows the server to store the user's learning content, study time, and test results.

[1792] Analyzing data and creating a learning plan

[1793] The server sends the temporarily stored data to an AI engine. The AI ​​engine analyzes the user's learning data, analyzing their learning patterns and level of understanding. Based on the analysis results, it generates an optimal learning plan and returns it to the server. This learning plan includes the learning materials to be used, the study time, and the study order.

[1794] Emotion recognition by emotion engine

[1795] While studying, the device uses a camera and microphone to collect the user's facial expressions and voice. The collected emotional data is sent to a server, which then transmits it to an emotion engine. The emotion engine analyzes the emotional data and recognizes the user's emotional state. Based on the analysis results, the server adjusts the study plan and encouraging messages.

[1796] Learning progress assessment and suggestions

[1797] The device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to the AI ​​engine. Based on the feedback from the AI ​​engine, the server makes appropriate suggestions to the user.

[1798] Explaining difficult content and providing concrete examples

[1799] When a user enters a question, the device sends it to the server, which passes the question to an artificial intelligence engine and uses a generative AI model to generate appropriate explanations and examples. The generated explanations and examples are then returned from the server to the device and displayed to the user.

[1800] Support for maintaining motivation

[1801] The server generates encouraging messages and achievements based on the user's learning progress and emotional data, and the device notifies the user of the messages received from the server, thus maintaining the user's motivation to continue learning.

[1802] Specific examples

[1803] For example, let us consider a case where a user (user ID: 001) wishes to learn the basics of programming.

[1804] 1. The user terminal sends User 001's login information to the system, and the server collects User 001's learning history and progress from the database. The collected data is sent to an artificial intelligence engine, which generates an optimal learning plan.

[1805] 2. The user device collects the user's facial expressions and voice during learning and sends them to the emotion engine. If the user is confused, the learning pace will be adjusted and additional explanations will be provided.

[1806] 3. If the user encounters a problem while studying, the user device sends the question to the server, and the server generates an explanation and concrete examples and provides them to the user.

[1807] 4. The server generates encouraging messages based on the user's progress and emotions, and the user's device notifies the user of these messages to help them continue their studies.

[1808] Prompt Sentence Examples

[1809] Generate the following learning plan based on the user's learning progress and past history: The user wants to learn the basics of programming.

[1810] In this way, the learning personal assistant system of the present invention provides flexible support tailored to the individual needs of the user, and realizes effective learning and continuous learning that takes into account the user's emotional state.

[1811] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1812] Step 1:

[1813] User login and data collection

[1814] When a user logs in to the system, the terminal sends the user's login information to the server.

[1815] Input: User ID and password

[1816] Processing: The server uses the user ID to retrieve the past learning history and progress from the database.

[1817] Output: User learning history and progress data

[1818] Specific operation: The terminal displays a login form and sends the ID and password entered by the user to the server. The server receives this and executes a database query. The result is temporarily saved.

[1819] Step 2:

[1820] Analyzing data and creating a learning plan

[1821] The server sends the temporarily stored user learning data to the artificial intelligence engine.

[1822] Input: User learning history and progress data

[1823] Processing: The artificial intelligence engine analyzes the data and analyzes the user's learning patterns and comprehension.

[1824] Output: Optimal study plan

[1825] How it works: The server sends the data to the AI ​​engine, which uses an analytical algorithm to generate a learning plan, which is then returned to the server in JSON format.

[1826] Step 3:

[1827] Emotion Recognition and Regulation

[1828] During learning, the device collects the user's facial expressions and voice using a camera and microphone and sends them to the server.

[1829] Input: User's facial expression data and voice data

[1830] Processing: The emotion engine analyzes these data and recognizes the user's emotional state.

[1831] Output: Feedback based on emotional state

[1832] Specific operation: The device activates the camera and microphone to collect data in real time. The collected data is sent to the server, which then relays it to the emotion engine. The analysis results are reflected as feedback in the form of learning plans and encouraging messages.

[1833] Step 4:

[1834] Learning progress assessment and suggestions

[1835] The device records the user's learning progress in real time and transmits it to the server.

[1836] Input: User's learning progress data

[1837] Processing: The server periodically evaluates the learning progress and sends the results to the artificial intelligence engine.

[1838] Output: Suggested improvements and enhancements

[1839] How it works: The device records which page or learning material the user is currently studying and sends this to the server. The server uses a "progress assessment algorithm" to evaluate the data and sends the results to the AI ​​engine, which then provides feedback.

[1840] Step 5:

[1841] Explaining difficult content and providing concrete examples

[1842] The user enters a question and the terminal sends the question to the server.

[1843] Input: User's question

[1844] Processing: The server sends the question to an artificial intelligence engine, which uses a generative AI model to generate explanations and examples.

[1845] Output: Explanation and Examples

[1846] Specific operation: During learning, the user types "I don't understand the loop syntax." The device sends this question to the server, which then sends a request to the generative AI model to "provide a specific explanation." The generative AI model generates an explanation and a specific example and returns it to the server. The server then displays this to the user.

[1847] Step 6:

[1848] Support for maintaining motivation

[1849] The server generates encouraging messages and achievements based on the user's learning progress and emotional data.

[1850] Input: Learning progress data and emotion data

[1851] Processing: The server generates an encouraging message based on the data and sends it to the device.

[1852] Output: An encouraging message

[1853] Specific operation: The server periodically evaluates the "learning progress" and "emotional data" and generates encouraging messages such as "Keep up the good work!" The device notifies the user of this and displays it via voice or a pop-up.

[1854] Through these steps, the system is able to personalize and effectively support users' learning.

[1855] (Application example 2)

[1856] 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."

[1857] Conventional learning support systems provide learning plans based on the user's learning progress and history, and while they are effective to a certain extent, they do not adequately take into account the user's emotional state. As a result, they are unable to effectively address frustration and loss of motivation that users experience while learning, leaving issues with learning continuity. Furthermore, in brick-and-mortar learning support services, it is often difficult for users to immediately obtain the information they need, resulting in a poor quality learning experience.

[1858] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting a user's learning history and progress, means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user, means for evaluating the user's learning progress and suggesting areas for strengthening or improvement, means including a generative model that generates specific explanations and examples for difficult content, means for generating and providing messages to maintain motivation according to the user's learning progress, means including an emotion engine that recognizes the user's emotional state and adjusts the learning plan, means for recording the user's learning progress in real time, and means for providing learning support for the user to study specific information in a store. This enables effective learning support that comprehensively takes into account the user's emotional state and learning progress, and the quality of the learning experience can be improved by providing immediate and appropriate information in a physical store.

[1859] "User" refers to an individual who uses the system to advance their learning.

[1860] "Learning history" refers to a record of a user's past learning activities.

[1861] "Progress" refers to data that shows how far a user has progressed in their learning.

[1862] An "artificial intelligence engine" refers to software or hardware that analyzes collected data and generates optimal learning plans for users.

[1863] "Points of improvement" refers to areas of user learning that require particular reinforcement.

[1864] "Areas for improvement" refers to areas that particularly need improvement in user learning.

[1865] A "generative model" refers to an algorithm or software that generates explanations or examples under certain conditions.

[1866] "Messages to maintain motivation" refers to messages that motivate users to continue learning.

[1867] An "emotion engine" refers to software or hardware that recognizes emotions from a user's facial expressions, voice, etc.

[1868] "Real-time" refers to a state in which processing and analysis are carried out immediately at the present time.

[1869] "Study Progress" refers to data that indicates how far a user has progressed in their current study plan.

[1870] "In-store learning support" refers to providing support to users in physical stores to learn about products and services.

[1871] This invention is a learning personal assistant system that utilizes AI to personalize and effectively support users' learning. It combines an emotion engine to recognize the user's emotions and, based on those emotions, more effectively creates learning plans and maintains motivation.

[1872] The system includes a server, a user terminal, an artificial intelligence engine, and an emotion engine. Each of these components is described in detail below.

[1873] How we collect your data

[1874] The server receives login information from the user's device and retrieves the user's learning history and progress data from the database, allowing information such as the user's past learning content, study time, and test results to be stored on the server.

[1875] How to generate a lesson plan

[1876] The server sends the collected data to an AI engine, which analyzes the user's learning data. The AI ​​engine then analyzes the user's learning patterns and level of understanding based on the collected data and generates an optimal learning plan. This learning plan includes information such as which learning materials to use, how much time to spend on each material, and the order in which they should be studied.

[1877] emotion recognition means

[1878] While studying, the user's device collects emotional data from the user's facial expressions and voice and sends it to the server. The emotion engine recognizes the user's emotions based on the received emotional data and uses this information to adjust the study plan and encouraging messages.

[1879] Learning progress assessment and suggestion tools

[1880] The user's device records the user's learning progress in real time and sends it to the server. The server periodically evaluates the learning progress and sends the evaluation results to an AI engine to identify areas for strengthening or improvement. This allows the user to receive feedback on which areas need strengthening or improvement based on their own progress.

[1881] A means of generating explanations and examples of difficult content

[1882] If a user encounters difficulty understanding a particular problem or complex content during learning, they can send a question from their device to the server. The server then passes the user's question to the generative model, which generates appropriate explanations and concrete examples. This allows the user to receive specific explanations about the complex content and deepen their understanding.

[1883] Motivational message generation method

[1884] The server generates encouraging messages and achievements based on the user's learning progress and emotional data. These messages are customized based on the progress and goal achievement. The user's device notifies the user of the messages received from the server, maintaining the user's motivation to continue learning.

[1885] In-store learning support methods

[1886] When users learn about products or services in a physical store, they can learn specific information using their own devices or tablets installed in the store. The system instantly provides details and instructions on specific products, allowing users to obtain the information they want in a timely manner. The system also improves the quality of the learning experience by providing appropriate support and encouraging messages based on the user's learning progress and emotional state.

[1887] Specific examples

[1888] As a concrete example, let's consider the case where a user wants to learn how to use a new rice cooker at an electronics store. The user's device sends login information to the server, which then collects the user's past usage history. The artificial intelligence engine analyzes this and generates an optimal learning plan for how to use the rice cooker. The user's device uses the store's camera to send the user's facial expressions to the emotion engine, which recognizes the user's emotional state. The server then generates appropriate explanations and examples to answer the question, resolving the user's doubts. By providing messages to maintain motivation, the user's learning experience is optimized.

[1889] Prompt Sentence Examples

[1890] "I want to learn how to use new appliances. Can you tell me the next step for the appliances I currently use?"

[1891] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[1892] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1893] Step 1:

[1894] User data collection

[1895] When a user logs in from their device, the server receives the login information and retrieves the user's learning history and progress data from the database. This input data includes past learning content, study time, and test results, and uses this information to create an individual user profile. As output, the user's learning history and progress are temporarily stored on the server.

[1896] Step 2:

[1897] Generate a learning plan

[1898] The server sends the collected user data to an AI engine, which analyzes the user's learning data. Using learning history and progress as input data, the AI ​​engine analyzes the user's learning patterns and level of understanding. This generates an optimal learning plan. As an output, the optimal learning plan, which includes learning materials, study time, and study order, is stored on the server.

[1899] Step 3:

[1900] emotion recognition

[1901] During learning, the user device collects emotion data from the user's facial expressions and voice and sends it to the server. Images of the user's facial expressions and recorded voice data are used as input data. The emotion engine analyzes this data and recognizes the user's emotional state. As output, data on the user's emotions (e.g., satisfaction, confusion, impatience) is generated and stored on the server.

[1902] Step 4:

[1903] Assessment and recommendations for learning progress

[1904] The server receives learning progress data sent from the user's device in real time. The input data includes the current progress. The server periodically evaluates this data and sends it to an artificial intelligence engine to identify areas for improvement and strengthening. This generates appropriate feedback for the user. As an output, progress evaluation results and feedback are generated and stored on the server.

[1905] Step 5:

[1906] Explaining complex content and generating examples

[1907] When a user inputs a question during learning, the question is sent from the user's device to the server. The input data includes the user's question. The server passes this data to a generative model, which generates appropriate explanations and concrete examples. As output, explanations and concrete examples of difficult content are generated and provided to the user.

[1908] Step 6:

[1909] Generate motivational messages

[1910] The server generates encouraging messages and achievements based on learning progress and emotional data. Input data includes progress assessment results and emotional states. The generated messages are customized according to the progress and goal achievement status. As output, the customized encouraging messages are stored in the server and sent to the user's device.

[1911] Step 7:

[1912] In-store learning support

[1913] When a user learns about a product or service in a physical store, they learn specific information using their device or a tablet device in the store. The input data includes information about the product or service the user wants to learn about. The server immediately provides details about the specific product and how to use it, allowing the user to obtain the information they want to learn in a timely manner. The output provides detailed information about the product or service, as well as messages of support and encouragement.

[1914] In this way, the present invention provides flexible support tailored to the learning needs of each user, enabling effective learning and continuous learning that takes into account emotional states.

[1915] 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.

[1916] 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.

[1917] 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.

[1918] 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.

[1919] 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.

[1920] 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.

[1921] 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).

[1922] 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.

[1923] 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."

[1924] 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.

[1925] 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).

[1926] 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.

[1927] 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.

[1928] 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.

[1929] 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.

[1930] 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.

[1931] 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.

[1932] 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.

[1933] 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.

[1934] 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.

[1935] 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.

[1936] The following is further disclosed regarding the above embodiment.

[1937] (Claim 1)

[1938] A means of collecting user learning history and progress;

[1939] means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user;

[1940] A means of assessing the user's learning progress and suggesting areas for enhancement or improvement;

[1941] A means including a generative model that generates specific explanations and examples for difficult content;

[1942] A means for generating and providing messages to maintain motivation according to the user's learning progress;

[1943] A system including:

[1944] (Claim 2)

[1945] The system of claim 1, wherein the generative model generates specific explanations and examples based on the content of the user's question.

[1946] (Claim 3)

[1947] 2. The system according to claim 1, further comprising a means for customizing messages for maintaining motivation according to the user's learning progress.

[1948] "Example 1"

[1949] (Claim 1)

[1950] A means of collecting user learning history and progress;

[1951] means including an artificial intelligence engine that analyzes the ...

Claims

1. A means of collecting user learning history and progress; means including an artificial intelligence engine that analyzes the collected data and generates an optimal learning plan for the user; A means of assessing the user's learning progress and suggesting areas for enhancement or improvement; A means including a generative model that generates specific explanations and examples for difficult content; A means for generating and providing messages to maintain motivation according to the user's learning progress; A system including:

2. The system of claim 1 , wherein the generative model generates specific explanations and examples based on the content of a user's question.

3. 2. The system according to claim 1, further comprising a means for customizing messages for maintaining motivation according to the user's learning progress.

Images