System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining information about a user's learning style and interests; means for transmitting the information to a server; means for receiving the information and analyzing the user's learning style and interests; means for generating a educational video game based on the analyzing result; means for transmitting the educational video game to a device; means for displaying the educational video game for the user to play; and means for optimizing a next educational video game based on the playing information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional educational platforms often provide uniform learning materials and methods without fully considering users' learning styles and interests. This makes it difficult to maintain users' motivation to learn and to achieve effective learning outcomes. There was also a need to reduce the stress of tackling subjects or fields that users find difficult and provide an enjoyable learning environment. [Means for solving the problem]

[0005] The present invention provides a system that automatically generates educational games based on a user's learning style and interests. Specifically, the system acquires user information, sends it to a server for analysis, and uses a generative AI model to generate educational games optimized for the user's learning style and interests. These educational games cover multiple subjects, including mathematics and English, and are designed to allow users to learn in a fun and effective way. Furthermore, the system collects user play data and reflects it in the generation of the next educational game, providing an even more optimized learning experience.

[0006] "User" refers to a learner or educator who uses the system.

[0007] "Learning style" refers to the way or means by which a user tends to understand and remember information, including visual, auditory, and experiential learning.

[0008] "Interests" refer to areas or topics that a user is particularly interested in and that motivate them to learn.

[0009] "Information acquisition methods" refers to the interfaces and processes that input and collect information from users about their learning styles and interests.

[0010] "Server" refers to a computer system that receives, analyzes, and processes information sent by users.

[0011] "Analysis tools" refers to algorithms and models that evaluate and analyze learning styles and interests based on received user information.

[0012] "Generative AI model" refers to an artificial intelligence model that analyzes user information and generates educational games based on the results.

[0013] "Educational games" refers to interactive, game-style educational materials designed for learning.

[0014] "Play data" refers to data such as behavior logs and answer results generated when a user plays an educational game.

[0015] "Optimization measures" refer to the process of adjusting the content and difficulty of the next educational game to suit the user based on the collected play data. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

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

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention relates to a system that utilizes generative AI to automatically generate educational games based on a user's learning style and interests. This system provides a way for users to continue learning effectively while having fun. An embodiment of this system is described below.

[0038] System Overview

[0039] This system collects user information, analyzes it on the server, generates optimal educational games, and provides them to users. It can also collect user gameplay data and use it to optimize the next educational game.

[0040] Collecting user information

[0041] User: Users enter information about their learning style and interests, including their favorite subjects, areas of expertise, hobbies, etc.

[0042] Terminal: The terminal records the information entered by the user and transmits the data to the server. This process includes collecting information through the interface and transmitting it to the server.

[0043] Analysis of user information and generation of educational games

[0044] Server: The server receives user information sent from the device and uses a generative AI model to analyze the user's learning style and interests. Based on the analysis results, it automatically generates the most suitable educational game for the user.

[0045] For example, if a user likes mathematics, inputs calculation as their area of ​​expertise and reading as their hobby, the server will generate an educational game centered on calculation problems based on this information.The game is also designed to attract the user's interest by incorporating story elements related to reading.

[0046] Providing educational games

[0047] Server: The generated educational game is sent from the server to the device, allowing users to play the game on their own device.

[0048] Device: The device displays educational games received from the server to the user. The displayed games include interactive questions and stories, allowing users to learn while having fun.

[0049] Collecting user gameplay data and optimizing the next educational game

[0050] User: The user plays the provided educational game and solves the problems. During this process, play data such as the user's behavior log and answer results are generated.

[0051] Device: The device collects the user's play data and sends it to the server. This play data includes how the user solved the problem, the correct answer rate, answer choices, etc.

[0052] Server: The server analyzes the collected play data and optimizes the next educational game based on it, for example, by designing the game to focus on the problem types or areas in which the user struggled in the previous game.

[0053] In this way, the system of the present invention can enhance learning effectiveness by providing educational games customized to the user's learning needs. Users can learn while having fun, which makes it easier to maintain motivation, and this can lead to continued learning.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] Users input information about their learning style and interests through the device interface, such as their favorite subjects, areas of expertise, and hobbies, which then defines the user's learning needs.

[0057] Step 2:

[0058] The device collects the information entered by the user and sends it to the server. Specifically, it organizes the user-entered data and sends it as a POST request to the server's API endpoint.

[0059] Step 3:

[0060] The server inputs the user information received from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.).

[0061] Step 4:

[0062] Based on the analysis results, the server generates educational games optimized for the user's interests and learning style, with the generative AI model automatically combining math and English questions with related story elements.

[0063] Step 5:

[0064] The server sends the generated educational game to the device, including the game title, question list, choices and answers, and story.

[0065] Step 6:

[0066] The device receives the educational game from the server and displays it to the user, who can then solve problems and enjoy the story through the game screen.

[0067] Step 7:

[0068] The user plays the educational game provided through the device, specifically by answering questions, choosing answers from options, progressing through the story, and so on.

[0069] Step 8:

[0070] The device collects the user's gameplay data, including which options the user chose, whether they answered correctly or incorrectly, and the time it took.

[0071] Step 9:

[0072] The device sends the collected user play data to a server, which records the user's learning progress and trends.

[0073] Step 10:

[0074] The server analyzes the received user play data and, based on the analysis results, provides feedback to the AI ​​model to optimize the content and difficulty of the next educational game.

[0075] Step 11:

[0076] The server then generates a new, optimized educational game for the next time to continue meeting the user's learning needs, and this process repeats, ensuring the user continues to have an engaging and effective learning experience.

[0077] This is the specific processing flow of this system. Through this process, the user's learning effect can be improved and motivation can be maintained.

[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 educational systems often fail to achieve sufficient learning effectiveness due to the difficulty of customizing content to suit individual users' learning styles and interests. Furthermore, formulaic learning content fails to capture users' interest, resulting in reduced learning continuity. The present invention aims to solve these problems by providing educational content customized based on a user's learning style and interests, thereby improving learning effectiveness and increasing learning continuity.

[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 analyzing information about a user's learning style and interests using a generation AI model, means for generating educational content based on the analysis results, and means for optimizing the next educational content based on the user's play data, thereby making it possible to provide educational content customized to each user's individual learning style and interests.

[0083] "User learning style" refers to the individual way in which a learner most effectively comprehends, retains, and applies information.

[0084] "Interest Information" refers to data about particular subjects or activities that interest a user.

[0085] A "generative AI model" refers to an algorithm or system that creates new content based on data.

[0086] "Analyzing" refers to reviewing the collected information to identify characteristics of a user's learning style and interests.

[0087] "Educational Content" refers to the materials and activities used to help learners acquire specific knowledge or skills.

[0088] "Play Data" refers to data regarding the actions and results that occur when a user uses educational content.

[0089] "Optimize" refers to improving a system or process to maximize its efficiency and effectiveness in order to achieve a specific purpose.

[0090] "Customized Story Elements" means story elements that are individually created based on a user's interests and preferences.

[0091] "Server" means a computer system for storing, processing, and distributing data.

[0092] "Terminal" refers to a computer or mobile device that is directly operated by a user.

[0093] The present invention relates to a system that automatically generates educational content based on a user's learning style and interests using a generative AI model. This system enhances learning effectiveness by providing an educational experience that meets the individual needs of the user. Specific embodiments for implementing the present invention are described below.

[0094] overview

[0095] This system collects user information, analyzes it on the server, and generates optimal educational content to provide to users. It can also collect user content usage data and optimize the next educational content based on that data.

[0096] Collecting user information

[0097] User: The user inputs information about their learning style and interests via a terminal. For example, they provide information such as "I like math," "I'm good at calculations," and "My hobby is reading."

[0098] Terminal: The terminal records the information entered by the user and sends the data to the server via the HTTPS protocol, SSL encrypted.

[0099] Analyzing user information and generating educational content

[0100] Server: The server uses a generative AI model (such as one using TensorFlow or PyTorch) to analyze the user's learning style and interests based on the received user information. Based on the analysis results, it generates educational content that is optimal for the user.

[0101] Providing educational content

[0102] Server: The generated educational content is sent as data packets from the server to the device. Protocols used include HTTP and WebSocket.

[0103] Terminal: The terminal displays the educational content received from the server to the user. The displayed content is designed to be interactive so that the user can manipulate it. For example, the content is created and displayed using game engines such as Unity or Unreal Engine.

[0104] Collecting user content usage data and optimizing the next educational content

[0105] User: The user uses the provided educational content to progress with their studies. The behavioral logs and answers generated during use are recorded as usage data.

[0106] Device: The device collects and temporarily stores user usage data in real time, then periodically transmits the data to the server.

[0107] Server: The server analyzes the received usage data and re-uses the generative AI model to optimize the next educational content, for example, by taking into account the user's previous difficulties and new areas of interest.

[0108] Specific examples

[0109] As a concrete example, the following prompt sentence is input into the generative AI model:

[0110] Example prompt sentence:

[0111] "This user likes eighth-grade math, and is particularly interested in equations. He also enjoys reading historical novels. Use this information to generate educational content that is ideal for this user."

[0112] This allows the generative AI model to automatically generate educational content that focuses on mathematical equations and includes historical story elements, and delivers it to devices via a server. For example, users can enjoy educational content in the form of a game where they progress by solving equations against the backdrop of historical events.

[0113] In this way, the system of the present invention provides customized educational content to enhance the user's learning effect, and realizes a method for continuing learning while having fun.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] User: The user enters information about their learning style and interests through the application interface, for example, "I like math," "I'm good at math," or "I enjoy reading."

[0117] Input: User-entered information about their learning style and interests.

[0118] Output: Input information recorded on the terminal.

[0119] Step 2:

[0120] Terminal: The terminal sends the information entered by the user to the server as SSL-encrypted data via the HTTPS protocol.

[0121] Input: User information recorded on the device.

[0122] Output: Encrypted user information sent to the server.

[0123] Step 3:

[0124] Server: The server uses a generative AI model based on the received user information to analyze the user's learning style and interests. Deep learning frameworks such as TensorFlow and PyTorch can be used for the analysis.

[0125] Input: Encrypted user information.

[0126] Output: Analyzed learning style and interest data.

[0127] Step 4:

[0128] Server: The server generates educational content based on the analysis results. During this process, specific game content is designed using game engines such as Unity or Unreal Engine. For example, educational games containing calculation problems and story elements are generated.

[0129] Input: Analyzed learning style and interest data.

[0130] Output: Generated educational content (game data).

[0131] Step 5:

[0132] Server: The generated educational game is sent as a data packet from the server to the device. HTTP or WebSocket is used as the communication protocol.

[0133] Input: Generated educational content (game data).

[0134] Output: Educational content (game data) sent to the device.

[0135] Step 6:

[0136] Terminal: The terminal displays the educational game received from the server to the user. It uses Unity or Unreal Engine to provide an interactive user interface.

[0137] Input: Educational content (game data) sent to the device.

[0138] Output: Interactive educational content displayed to the user.

[0139] Step 7:

[0140] User: The user plays the provided educational game and progresses through their learning. The action logs and answers generated during play are recorded as play data.

[0141] Input: User learning behavior and its results.

[0142] Output: Play data recorded on the device.

[0143] Step 8:

[0144] Device: The device collects and temporarily stores the user's gameplay data in real time, and periodically transmits the data to the server.

[0145] Input: Play data recorded on the device.

[0146] Output: Play data sent to the server.

[0147] Step 9:

[0148] Server: The server analyzes the received play data and uses the generative AI model again to optimize the next educational content, for example, designing a new game taking into account the user's previous difficulties and new areas of interest.

[0149] Input: Play data sent to the server.

[0150] Output: Analysis results to optimize the next educational content.

[0151] (Application example 1)

[0152] 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."

[0153] Traditional educational systems have difficulty providing educational methods based on individual users' learning styles and interests. To improve the customer experience in physical stores, new methods are needed to attract customers' interest while providing educational benefits. Furthermore, there is room for improvement in the methods of providing rewards that motivate customers to visit stores.

[0154] 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.

[0155] In this invention, the server includes a means for collecting and analyzing user information, a means for generating individually customized educational games, and a means for providing the generated games to terminals and collecting play data. This makes it possible to improve the customer experience at physical stores and provide educational games based on customers' learning styles and interests. Furthermore, by allowing customers to earn rewards by playing games, it is possible to encourage repeat visits to stores and promote use.

[0156] "User" refers to each individual who uses the System, i.e., who provides information for the purpose of playing and learning educational games.

[0157] "Learning style" refers to a user's unique method or pattern of learning that is most effective for them, including the learning environment, way of understanding, and way of receiving information.

[0158] "Interests" refer to areas or topics that users have particular interests or concerns about, which are reflected in the content of educational games.

[0159] "Means of information acquisition" refers to methods or devices that collect information based on the user's input learning style and interests.

[0160] "Server" refers to a central processing unit that receives information over a network, processes and analyzes it, and returns the results.

[0161] "Educational games" refer to digital games created to facilitate learning and engage users. Learning content is presented in a game format.

[0162] "Terminal" refers to a device that is directly operated and used by a user, including smartphones, tablets, and PCs.

[0163] "Play Data" refers to data generated by a user while playing an educational game, including a user's behavior log and answers.

[0164] "Rewards" refers to rewards or benefits provided to users through playing educational games, including discount coupons and points.

[0165] A "physical store" refers to a store that exists in a physical location and where customers can visit in person to purchase products or services. This includes bookstores, electronics retailers, stationery stores, etc.

[0166] The present invention relates to a system that allows users to learn while having fun through educational games at a physical store and to earn rewards in the process. Specific embodiments will be described below.

[0167] System Overview

[0168] This system collects user information, analyzes it on the server, generates optimal educational games, and provides them to users. It also includes a mechanism for collecting user gameplay data and optimizing the next educational game based on that data.

[0169] Collection of User Information

[0170] Device: When users visit a physical store, they enter information about their learning style and interests, such as their favorite subjects, areas of expertise, and hobbies, via their device (smartphone, tablet, etc.).

[0171] Server: Receives user information sent from the device and stores it for analysis.

[0172] Analysis of user information and generation of educational games

[0173] Server: Uses a generative AI model (e.g., GPT-3) to analyze the user's learning style and interests, and automatically generates the most suitable educational game.

[0174] For example, if a user likes mathematics, inputs calculation as their specialty and reading as their hobby, the server will generate an educational game centered on calculation problems based on this information.The game will also incorporate story elements related to reading to attract the user's interest.

[0175] Providing educational games

[0176] Server: The generated educational game is sent from the server to the device.

[0177] Terminal: The terminal displays the educational games received from the server to the user, allowing the user to play them.

[0178] Collecting user gameplay data and optimizing the next educational game

[0179] User: Play the educational games provided and solve the problems.

[0180] Device: Collects user play data (e.g., answer results and behavior logs) and sends it to the server.

[0181] Server: Analyzes the collected play data and optimizes the next educational game based on it, for example, by designing the game to focus on the problem types or areas that the user struggled with in the previous game.

[0182] Offering benefits

[0183] Server: Provide rewards (discount coupons, points, etc.) to users who play educational games, which increases users' motivation to play the games.

[0184] Specific examples

[0185] Suppose a user visits a bookstore and enters into the application that they like "math" and that their hobby is "reading." In response, the generative AI model generates an "educational game with a storyline centered around math calculation problems" and sends it to the device. As the user plays this game, their play data is collected and reflected in the generation of the next game. In addition, completing the game will provide rewards such as discount coupons and points.

[0186] Example prompt for a generative AI model:

[0187] User Information:

[0188] Favorite subject: Mathematics

[0189] Specialty: Calculation

[0190] Hobbies: Reading

[0191] Use this to generate an educational game centered around math problems, and incorporate story elements related to reading to keep users engaged.

[0192] This invention improves the customer experience in physical stores while providing education tailored to users' learning styles and interests. Customers can learn while having fun and earn rewards, which is expected to encourage them to return to the store.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1:

[0195] Device:Collecting user information

[0196] Users use a device (smartphone, tablet, etc.) to enter information about their learning style and interests (favorite subjects, areas of expertise, hobbies, etc.).

[0197] Input: Information about the user's department, field, and hobbies

[0198] Output: Collected user information (e.g., in JSON format)

[0199] Step 2:

[0200] Terminal: Sending information to the server

[0201] The device sends the collected user information to the server, which may be encrypted to ensure information security.

[0202] Input: Collected user information

[0203] Output: User information sent to the server

[0204] Step 3:

[0205] Server: Receiving and analyzing user information

[0206] The server receives user information sent from the device and stores it in a database for analysis, using a generative AI model.

[0207] Input: User information sent from the device

[0208] Output: Analysis results (characteristics based on user's learning style and interests)

[0209] Step 4:

[0210] Server: Educational Game Generation

[0211] The server uses a generative AI model (such as GPT-3) based on the analysis results to automatically generate an optimal educational game. At this time, the prompt sentence is input into the generative model.

[0212] Input: Analysis results based on the user's learning style and interests, prompts such as "Generate an educational game based on user information"

[0213] Output: Generated educational game data

[0214] Step 5:

[0215] Server: Educational game distribution

[0216] The server transmits the generated educational game data to the terminal.

[0217] Input: Generated educational game data

[0218] Output: Educational game data sent to the device

[0219] Step 6:

[0220] Device: View and play games

[0221] The terminal displays the educational game received from the server to the user, allowing the user to play it.

[0222] Input: Educational game data sent from the server

[0223] Output: The display screen for the user to play

[0224] Step 7:

[0225] User: Playing the game

[0226] Users progress by playing the educational games provided and solving problems.

[0227] Input: Displayed educational game

[0228] Output: User play data (answer results, action logs, etc.)

[0229] Step 8:

[0230] Device: Collection and transmission of play data

[0231] The terminal collects play data generated by the user and transmits it to the server.

[0232] Input: User's play data

[0233] Output: Play data sent to the server

[0234] Step 9:

[0235] Server: Analysis of play data and optimization for the next game

[0236] The server analyzes the collected play data and uses it as feedback to optimize the next educational game, for example, by focusing on the problem types that the player struggled with in the previous game.

[0237] Input: User's play data

[0238] Output: Optimized next educational game

[0239] Step 10:

[0240] Server: Offering special benefits

[0241] After the user finishes playing the educational game, the server generates a reward (for example, a discount coupon or points) and sends it to the terminal.

[0242] Input: Educational game completion data

[0243] Output: Benefit data (discount coupons and points)

[0244] In this way, by following a series of steps from 1 to 10, users can learn and earn rewards by entering their information at a physical store and playing the most suitable educational game.

[0245] 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.

[0246] This invention relates to a system that uses generative AI to automatically generate educational games based on a user's learning style, interests, and emotions, allowing users to continue learning effectively while having fun.

[0247] System Overview

[0248] This system collects user information, analyzes it on the server, and generates optimal educational games to provide to users. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize the learning experience based on emotional data.

[0249] Collecting user information

[0250] User: The user inputs information about their learning style and interests through the device interface, such as their favorite subject, field of expertise, and hobbies. Furthermore, an emotion engine recognizes emotions in real time from the user's facial expressions and voice.

[0251] Terminal: The terminal records the information entered by the user and the emotion data from the emotion engine, and transmits the data to the server.

[0252] Analysis of user information and generation of educational games

[0253] Server: The server inputs user information and emotional data sent from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.). The server also evaluates the user's stress level and concentration level from the emotional data.

[0254] Educational Game Generation: Based on the analysis results and emotional data, the server generates educational games optimized for the user's interests and learning style. The generative AI model automatically combines math and English questions with related story elements, and also adjusts the difficulty level and incorporates encouraging messages based on the user's emotions.

[0255] For example, if a user indicates that they like math, that they are good at calculations, and that their hobby is reading, the server will use this information to generate an educational game centered around calculation problems. The game is also designed to attract users' interest by incorporating story elements related to reading. Furthermore, if the emotion engine detects that the user's stress level is high, it will slightly lower the difficulty of the game or display encouraging messages.

[0256] Providing educational games

[0257] Server: The generated educational game is sent from the server to the device. The sent content includes the game title, question list, choices and answers, story, etc.

[0258] Device: The device displays the educational game received from the server to the user. The user can solve problems and enjoy the story through the game screen.

[0259] Collecting user gameplay data and optimizing the next educational game

[0260] User: The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. The emotion engine also records the user's emotional data in real time while playing.

[0261] Device: The device collects the user's gameplay data and emotional data and sends it to the server. This play data includes the options the user chose, whether they answered correctly or incorrectly, and the time it took.

[0262] Server: The server analyzes the received user play data and emotional data. Based on the analysis results, it provides feedback to the generative AI model to optimize the content and difficulty of the next educational game.

[0263] In this way, the system of the present invention can enhance learning effectiveness by providing educational games that are customized to the user's learning needs and emotions. Users can learn while having fun, which helps them maintain their motivation and encourages continuous learning.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] Users input information about their learning style and interests through the device's interface, and the device also captures emotional data by recognizing the user's facial expressions and voice in real time.

[0267] Step 2:

[0268] The device collects information entered by the user and emotion data from the emotion engine, organizes this data, and sends it to the server via a POST request to an API endpoint.

[0269] Step 3:

[0270] The server receives user information sent from the device and inputs it into a generative AI model. The model analyzes the user's learning style and interests. It also includes emotional data to evaluate the user's emotional state.

[0271] Step 4:

[0272] Based on the analysis results, the server generates an educational game optimized for the user's interests and learning style. The generative AI model incorporates math and English questions, as well as difficulty adjustments and story elements based on the user's emotions. For example, if a user enjoys reading, the game story will include reading-related content.

[0273] Step 5:

[0274] The server then sends the generated educational game to the device, including the game title, a list of questions, choices and answers, a story, and feedback based on emotion data.

[0275] Step 6:

[0276] The device receives educational games from the server and displays them to users, allowing them to solve problems and enjoy stories through the game screen. It also provides real-time feedback based on emotional data.

[0277] Step 7:

[0278] The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. During this process, the emotion engine records the user's emotional data in real time.

[0279] Step 8:

[0280] The device collects the user's gameplay data and emotional data, including the user's choices, correct and incorrect answers, time taken, and emotional changes.

[0281] Step 9:

[0282] The terminal transmits the collected user play data and emotion data to the server, which is used as feedback data for the next game generation.

[0283] Step 10:

[0284] The server then analyzes the received user play data and emotional data, providing input to the generative AI model to optimize the content and difficulty of the next educational game.

[0285] Step 11:

[0286] The server regenerates the next optimized educational game to keep responding to the user's learning needs and emotional state, thereby providing the user with a continuously engaging and effective learning experience.

[0287] In this way, the system of the present invention, which combines an emotion engine, can enhance learning effectiveness by providing educational games customized to the user's learning needs and emotions. Users can learn while having fun, which makes it easier to maintain motivation, and this can be expected to encourage continuous learning.

[0288] Example 2

[0289] 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."

[0290] Conventional educational systems have difficulty customizing learning experiences based on users' learning styles and interests, making it difficult to provide optimal learning experiences for individual users. Furthermore, the learning experience has not been optimized with users' emotions in mind, which can lead to stress and a decline in motivation, which can have a negative impact on learning efficiency.

[0291] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring information on the user's learning style and interests, means for collecting user emotion data in real time, and means for generating an educational game based on the analysis results and the emotion data. This makes it possible to provide a customized learning experience based on the user's learning style and interests, and to timely adjust the learning content and difficulty level according to the user's emotions, thereby reducing stress and increasing motivation.

[0292] "Learning style" refers to the most effective way a user comprehends and learns information, and is often divided into categories such as visual, auditory, and experiential.

[0293] "Interests" refers to the subjects or areas in which you have a particular interest, including, for example, an interest in a particular subject or theme, such as math, languages, or science.

[0294] "Emotional data" refers to data that indicates the user's emotional state obtained in real time from facial expressions, voice, etc. This includes the user's stress level and concentration level.

[0295] A "generative AI model" refers to an algorithm or software that uses artificial intelligence technology to analyze user information and emotional data and automatically generate optimal educational games.

[0296] "Educational games" are programs that help users learn and provide educational content in the form of games, customized to the user's learning style, interests, and emotions.

[0297] "Play Data" refers to data recorded when a User plays an educational game, including choices, correct and incorrect answers, and play time.

[0298] "Optimization" refers to the process of adjusting the content and difficulty of future educational games based on collected data to provide the optimal learning experience for users.

[0299] This invention relates to a system that uses a generative AI model to automatically generate educational games based on a user's learning style, interests, and emotions, allowing users to continue learning effectively while having fun.

[0300] System Overview

[0301] This system collects user information, analyzes it on the server, and generates optimal educational games to provide to users. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize the learning experience based on emotional data.

[0302] Collection of User Information

[0303] User: The user inputs information about their learning style and interests through the device interface. This information includes, for example, their favorite subject, areas of expertise, and hobbies. In addition, an emotion engine is activated that recognizes emotions in real time from the user's facial expressions and voice.

[0304] Terminal: The terminal records the information entered by the user and the emotion data from the emotion engine, and transmits the data to the server.

[0305] Analysis of user information and generation of educational games

[0306] Server: The server inputs user information and emotional data sent from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.). The server also evaluates the user's stress level and concentration level from the emotional data.

[0307] Educational Game Generation: Based on the analysis results and emotional data, the server generates educational games optimized for the user's interests and learning style. The generative AI model automatically combines math and language problems with related story elements, and also adjusts the difficulty level and incorporates encouraging messages according to the user's emotions.

[0308] Providing educational games

[0309] Server: The generated educational game is sent from the server to the device. The sent content includes the game title, question list, choices and answers, story, etc.

[0310] Terminal: The terminal displays the educational game received from the server to the user. The user can solve problems and enjoy the story through the game screen.

[0311] Collecting user gameplay data and optimizing the next educational game

[0312] User: The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. The emotion engine also records the user's emotional data in real time while playing.

[0313] Device: The device collects the user's gameplay data and emotional data and sends it to the server. This play data includes the options the user chose, whether the questions were correct or incorrect, and the time it took.

[0314] Server: The server analyzes the received user play data and emotional data. Based on the analysis results, it provides feedback to the AI ​​model to optimize the content and difficulty of the next educational game.

[0315] Specific examples

[0316] For example, if a user likes math, enters calculation as their specialty and reading as their hobby, the server will generate an educational game centered around calculation problems based on this information. The game is also designed to attract users' interest by incorporating story elements related to reading. Furthermore, if the emotion engine recognizes that the user's stress level is high, it will slightly lower the difficulty of the game or display encouraging messages.

[0317] Prompt Sentence Examples

[0318] Below are some example prompts for interacting with generative AI models:

[0319] "The user's learning style is visual, their area of ​​interest is mathematics, their specialty is calculations, and their hobby is reading. Based on their emotional data, we recognize that their stress level is high. Generate an educational game that is appropriate for the user."

[0320] In this way, the system of the present invention provides users with educational games that are customized to their learning needs and emotions, enhancing learning effectiveness. Users can learn while having fun, which helps them stay motivated and encourages continuous learning.

[0321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0322] Step 1:

[0323] Entering user information

[0324] User: The user uses the device interface to input information about their learning style and interests (e.g., favorite subject, field of expertise, hobbies, etc.). The input information is recorded in a database. In addition, the user's facial expressions and voice are captured in real time using a camera and microphone, generating emotional data.

[0325] Input: Information about the user's learning style and interests, facial expressions, and voice data

[0326] Output: Collecting user information and emotion data

[0327] Step 2:

[0328] Sending data

[0329] Terminal: The terminal transmits the collected user information and emotion data to the server. At this time, the data is encrypted to ensure security.

[0330] Input: Collected user information and emotion data

[0331] Output: Encrypted data sent to the server

[0332] Step 3:

[0333] Analysis of user information

[0334] Server: The server inputs the received user information and emotional data into the generative AI model. The generative AI model analyzes the user's learning style and interests, and evaluates stress levels and concentration levels from the emotional data. The analysis results are stored in a database.

[0335] Input: User information and emotion data

[0336] Output: Analysis results (learning style, interest, stress level, concentration)

[0337] Step 4:

[0338] Educational Game Generation

[0339] Server: The server uses the generative AI model to generate educational games based on the analysis results, combining math and language problems, relevant story elements, and emotionally-driven difficulty adjustments and encouraging messages. The generated games are stored in a database.

[0340] Input: Analysis results (learning style, interest, stress level, concentration)

[0341] Output: Generated educational game

[0342] Step 5:

[0343] Providing educational games

[0344] Server: The server sends the generated educational game to the device. The data is encrypted during transmission.

[0345] Input: Generated educational game

[0346] Output: Encrypted data sent to the device

[0347] Step 6:

[0348] Game Display

[0349] Terminal: The terminal displays the received educational game to the user, who can solve problems and enjoy the story through the game screen.

[0350] Input: Educational game received from the server

[0351] Output: The educational game displayed to the user

[0352] Step 7:

[0353] Gameplay data collection

[0354] User: The user plays the educational game, answering questions, choosing options, and progressing through the story. The emotion engine records the user's emotional data in real time while playing.

[0355] Input: educational game play behavior and changes in facial expressions and voice

[0356] Output: Play data and emotion data

[0357] Step 8:

[0358] Sending data

[0359] Terminal: The terminal transmits the user's play data and emotion data to the server.

[0360] Input: Play data and emotion data

[0361] Output: Encrypted data sent to the server

[0362] Step 9:

[0363] Subsequent optimizations

[0364] Server: The server analyzes the received play data and emotional data and reflects the results in the generative AI model, which generates feedback to optimize the content and difficulty of future educational games.

[0365] Input: Play data and emotion data

[0366] Output: Generative AI model reflected in subsequent optimizations

[0367] (Application example 2)

[0368] 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."

[0369] While traditional educational game systems are specialized for users' learning styles and interests, they do not consider real-time optimization based on individual emotional states, limiting the quality of the learning experience. Furthermore, online shopping sites are required to combine learning and entertainment to help users effectively understand product information while having fun, but such systems have not been adequately provided. Furthermore, there is a lack of an efficient method for providing appropriate incentives to support users' learning outcomes and increase their purchasing motivation.

[0370] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0371] In this invention, the server includes means for acquiring information about a user's learning style and interests, means for transmitting the information to the server, means for receiving the information and analyzing the user's learning style and interests, means for generating an educational game based on the analysis results, means for collecting the emotional data in real time and transmitting it to the server, means for optimizing the next educational game based on the play data and emotional data, and means for providing incentives based on the results of the educational game. This makes it possible to provide educational games optimized for individual users in real time and link their learning results to purchasing motivation.

[0372] A "user" is an individual who uses the system to learn or make purchases.

[0373] "Learning style" refers to the method or means (visual, auditory, experiential, etc.) in which a user learns most effectively.

[0374] "Interests" refers to the subjects, fields, hobbies, and activities that a user is particularly interested in.

[0375] "Means of information acquisition" refers to the mechanism by which users use devices to input data about their learning style and interests.

[0376] "Server" refers to the central processing unit that receives information sent by users, analyzes it, and generates educational games.

[0377] "Educational games" refers to educational content in the form of games that are generated based on the user's learning style and interests to promote learning.

[0378] "Emotional Data" refers to data indicative of a user's real-time emotional state collected while playing an educational game.

[0379] "Play Data" refers to data such as choices, response times, correct and incorrect answers, etc. that are recorded when a user plays an educational game.

[0380] "Incentives" refers to rewards or benefits offered to encourage users to learn or purchase.

[0381] "Device" refers to an electronic device (smartphone, tablet, PC, etc.) that a user uses to conduct learning or purchasing activities.

[0382] "Real-time" refers to near-simultaneous collection and processing of data.

[0383] The present invention relates to a system that uses a generative AI model to provide individually optimized educational games based on a user's learning style, interests, and emotions on an online shopping site. The purpose of this system is to allow users to learn while having fun and actively engage in purchasing activities. Specific embodiments are described below.

[0384] Overall system configuration

[0385] 1. Obtaining user information

[0386] Users use their devices to input information about their learning style and interests, such as their purchasing history, academic interests, and hobbies. Furthermore, an emotion recognition engine (Emotion Engine) is activated to collect real-time emotional data from users.

[0387] 2. Transmission and Analysis of Information

[0388] The device sends the collected user information and emotional data to a server. The server receives this information and analyzes the user's learning style and interests. The user's emotional data is analyzed in real time to evaluate stress levels and concentration levels.

[0389] 3. Educational Game Generation

[0390] The server generates an optimal educational game based on the analysis results. It uses a generative AI model (such as GPT-3) to combine math and English questions with related story elements. It also adjusts the game's difficulty and incorporates supportive messages based on the emotional data.

[0391] Hardware and software used

[0392] Devices (smartphones, tablets, PCs, etc.): Act as the user interface and collect and transmit user information and emotional data.

[0393] Emotion Recognition Engine (EmotionEngine): Acquires emotional data in real time from the user's facial expressions and voice.

[0394] Generative AI models (such as GPT-3): AI models that generate educational games based on analysis results.

[0395] Server (backend system using web frameworks such as Django): Analyzes user information and emotional data, and generates and transmits educational games.

[0396] Examples of concrete examples and prompts

[0397] For example, if a user is interested in fashion and has recently purchased a T-shirt, jeans, and sneakers, the server will generate a fashion quiz game based on this information. If the emotional data shows a high level of concentration and is positive, the server will present slightly more difficult questions. Each time the user answers correctly, the server will provide incentives such as discount coupons.

[0398] Example prompt sentence:

[0399] "The user is interested in fashion and recently purchased a t-shirt, jeans, and sneakers. Their sentiment data is positive and shows high concentration. Use this information to generate a fashion-related quiz."

[0400] In this way, the system of the present invention generates educational games based on the user's learning style, interests, and emotions, allowing the user to enjoy learning while engaging in purchasing activities, which is expected to improve the user's purchasing experience and increase learning effectiveness.

[0401] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0402] Step 1:

[0403] Entering and retrieving user information

[0404] The device provides an interface for users to input information about their learning style and interests. Users input their purchasing history, favorite subjects, hobbies, etc. The device also uses the Emotion Engine to collect real-time emotional data from the user's facial expressions and voice. The input data consists of user information (learning style, interests, purchasing history) and emotional data (facial expression recognition, voice analysis). This data is temporarily stored inside the device.

[0405] Step 2:

[0406] Sending information

[0407] The device sends the temporarily saved user information and emotion data to the server. Specifically, the user information and emotion data are packaged in JSON format and sent to the server via an HTTPS request. The input is user information and emotion data, and the output is data sent to the server.

[0408] Step 3:

[0409] Analysis of information

[0410] The server analyzes the received user information and emotional data. This analysis uses a generative AI model (e.g., GPT-3). As a result of the analysis, the server extracts the user's learning style, interests, stress level, and concentration level. The input is user information and emotional data, and the output is the analysis results (learning style, interests, and emotional state).

[0411] Step 4:

[0412] Educational Game Generation

[0413] The server generates an educational game based on the analysis results. A generative AI model is used for this. For example, if the user is interested in fashion, a fashion quiz is generated. The game difficulty and support messages are also adjusted based on the emotional data. The input is the analysis results, and the output is the generated educational game data.

[0414] Step 5:

[0415] Educational Game Submission

[0416] The server sends the generated educational game data to the device using the HTTPS protocol. The input is educational game data, and the output is game data sent to the device.

[0417] Step 6:

[0418] View and play games

[0419] The device displays the educational game to the user. The user plays the game and answers questions. Specifically, the device records the user's choices and answer times. The input is educational game data, and the output is user play data.

[0420] Step 7:

[0421] Collection and transmission of play data

[0422] The device collects the user's play data in real time and sends it to the server. The play data includes the user's choices, response time, correct and incorrect answers, etc. The input is the user's play data, and the output is the play data sent to the server.

[0423] Step 8:

[0424] Data reanalysis and game optimization

[0425] The server reanalyzes the received play data and emotional data and uses it to optimize the next educational game. It uses a generative AI model to provide feedback to adjust the game's content and difficulty. The input is play data and emotional data, and the output is an optimized educational game.

[0426] Step 9:

[0427] Offering incentives

[0428] The server provides incentives to users based on the results of the educational game. Specifically, it generates discount coupons according to the number of questions answered correctly and sends them to the terminal. The input is the results of the educational game, and the output is the incentive (discount coupon).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] [Second embodiment]

[0433] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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."

[0445] The present invention relates to a system that utilizes generative AI to automatically generate educational games based on a user's learning style and interests. This system provides a way for users to continue learning effectively while having fun. An embodiment of this system is described below.

[0446] System Overview

[0447] This system collects user information, analyzes it on the server, generates optimal educational games, and provides them to users. It can also collect user gameplay data and use it to optimize the next educational game.

[0448] Collecting user information

[0449] User: Users enter information about their learning style and interests, including their favorite subjects, areas of expertise, hobbies, etc.

[0450] Terminal: The terminal records the information entered by the user and transmits the data to the server. This process includes collecting information through the interface and transmitting it to the server.

[0451] Analysis of user information and generation of educational games

[0452] Server: The server receives user information sent from the device and uses a generative AI model to analyze the user's learning style and interests. Based on the analysis results, it automatically generates the most suitable educational game for the user.

[0453] For example, if a user likes mathematics, inputs calculation as their area of ​​expertise and reading as their hobby, the server will generate an educational game centered on calculation problems based on this information.The game is also designed to attract the user's interest by incorporating story elements related to reading.

[0454] Providing educational games

[0455] Server: The generated educational game is sent from the server to the device, allowing users to play the game on their own device.

[0456] Device: The device displays educational games received from the server to the user. The displayed games include interactive questions and stories, allowing users to learn while having fun.

[0457] Collecting user gameplay data and optimizing the next educational game

[0458] User: The user plays the provided educational game and solves the problems. During this process, play data such as the user's behavior log and answer results are generated.

[0459] Device: The device collects the user's play data and sends it to the server. This play data includes how the user solved the problem, the correct answer rate, answer choices, etc.

[0460] Server: The server analyzes the collected play data and optimizes the next educational game based on it, for example, by designing the game to focus on the problem types or areas in which the user struggled in the previous game.

[0461] In this way, the system of the present invention can enhance learning effectiveness by providing educational games customized to the user's learning needs. Users can learn while having fun, which makes it easier to maintain motivation, and this can lead to continued learning.

[0462] The processing flow will be explained below.

[0463] Step 1:

[0464] Users input information about their learning style and interests through the device interface, such as their favorite subjects, areas of expertise, and hobbies, which then defines the user's learning needs.

[0465] Step 2:

[0466] The device collects the information entered by the user and sends it to the server. Specifically, it organizes the user-entered data and sends it as a POST request to the server's API endpoint.

[0467] Step 3:

[0468] The server inputs the user information received from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.).

[0469] Step 4:

[0470] Based on the analysis results, the server generates educational games optimized for the user's interests and learning style, with the generative AI model automatically combining math and English questions with related story elements.

[0471] Step 5:

[0472] The server sends the generated educational game to the device, including the game title, question list, choices and answers, and story.

[0473] Step 6:

[0474] The device receives the educational game from the server and displays it to the user, who can then solve problems and enjoy the story through the game screen.

[0475] Step 7:

[0476] The user plays the educational game provided through the device, specifically by answering questions, choosing answers from options, progressing through the story, and so on.

[0477] Step 8:

[0478] The device collects the user's gameplay data, including which options the user chose, whether they answered correctly or incorrectly, and the time it took.

[0479] Step 9:

[0480] The device sends the collected user play data to a server, which records the user's learning progress and trends.

[0481] Step 10:

[0482] The server analyzes the received user play data and, based on the analysis results, provides feedback to the AI ​​model to optimize the content and difficulty of the next educational game.

[0483] Step 11:

[0484] The server then generates a new, optimized educational game for the next time to continue meeting the user's learning needs, and this process repeats, ensuring the user continues to have an engaging and effective learning experience.

[0485] This is the specific processing flow of this system. Through this process, the user's learning effect can be improved and motivation can be maintained.

[0486] Example 1

[0487] 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."

[0488] Conventional educational systems often fail to achieve sufficient learning effectiveness due to the difficulty of customizing content to suit individual users' learning styles and interests. Furthermore, formulaic learning content fails to capture users' interest, resulting in reduced learning continuity. The present invention aims to solve these problems by providing educational content customized based on a user's learning style and interests, thereby improving learning effectiveness and increasing learning continuity.

[0489] 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.

[0490] In this invention, the server includes means for analyzing information about a user's learning style and interests using a generation AI model, means for generating educational content based on the analysis results, and means for optimizing the next educational content based on the user's play data, thereby making it possible to provide educational content customized to each user's individual learning style and interests.

[0491] "User learning style" refers to the individual way in which a learner most effectively comprehends, retains, and applies information.

[0492] "Interest Information" refers to data about particular subjects or activities that interest a user.

[0493] A "generative AI model" refers to an algorithm or system that creates new content based on data.

[0494] "Analyzing" refers to reviewing the collected information to identify characteristics of a user's learning style and interests.

[0495] "Educational Content" refers to the materials and activities used to help learners acquire specific knowledge or skills.

[0496] "Play Data" refers to data regarding the actions and results that occur when a user uses educational content.

[0497] "Optimize" refers to improving a system or process to maximize its efficiency and effectiveness in order to achieve a specific purpose.

[0498] "Customized Story Elements" means story elements that are individually created based on a user's interests and preferences.

[0499] "Server" means a computer system for storing, processing, and distributing data.

[0500] "Terminal" refers to a computer or mobile device that is directly operated by a user.

[0501] The present invention relates to a system that automatically generates educational content based on a user's learning style and interests using a generative AI model. This system enhances learning effectiveness by providing an educational experience that meets the individual needs of the user. Specific embodiments for implementing the present invention are described below.

[0502] overview

[0503] This system collects user information, analyzes it on the server, and generates optimal educational content to provide to users. It can also collect user content usage data and optimize the next educational content based on that data.

[0504] Collecting user information

[0505] User: The user inputs information about their learning style and interests via a terminal. For example, they provide information such as "I like math," "I'm good at calculations," and "My hobby is reading."

[0506] Terminal: The terminal records the information entered by the user and sends the data to the server via the HTTPS protocol, SSL encrypted.

[0507] Analyzing user information and generating educational content

[0508] Server: The server uses a generative AI model (such as one using TensorFlow or PyTorch) to analyze the user's learning style and interests based on the received user information. Based on the analysis results, it generates educational content that is optimal for the user.

[0509] Providing educational content

[0510] Server: The generated educational content is sent as data packets from the server to the device. Protocols used include HTTP and WebSocket.

[0511] Terminal: The terminal displays the educational content received from the server to the user. The displayed content is designed to be interactive so that the user can manipulate it. For example, the content is created and displayed using game engines such as Unity or Unreal Engine.

[0512] Collecting user content usage data and optimizing the next educational content

[0513] User: The user uses the provided educational content to progress with their studies. The behavioral logs and answers generated during use are recorded as usage data.

[0514] Device: The device collects and temporarily stores user usage data in real time, then periodically transmits the data to the server.

[0515] Server: The server analyzes the received usage data and re-uses the generative AI model to optimize the next educational content, for example, by taking into account the user's previous difficulties and new areas of interest.

[0516] Specific examples

[0517] As a concrete example, the following prompt sentence is input into the generative AI model:

[0518] Example prompt sentence:

[0519] "This user likes eighth-grade math, and is particularly interested in equations. He also enjoys reading historical novels. Use this information to generate educational content that is ideal for this user."

[0520] This allows the generative AI model to automatically generate educational content that focuses on mathematical equations and includes historical story elements, and delivers it to devices via a server. For example, users can enjoy educational content in the form of a game where they progress by solving equations against the backdrop of historical events.

[0521] In this way, the system of the present invention provides customized educational content to enhance the user's learning effect, and realizes a method for continuing learning while having fun.

[0522] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0523] Step 1:

[0524] User: The user enters information about their learning style and interests through the application interface, for example, "I like math," "I'm good at math," or "I enjoy reading."

[0525] Input: User-entered information about their learning style and interests.

[0526] Output: Input information recorded on the terminal.

[0527] Step 2:

[0528] Terminal: The terminal sends the information entered by the user to the server as SSL-encrypted data via the HTTPS protocol.

[0529] Input: User information recorded on the device.

[0530] Output: Encrypted user information sent to the server.

[0531] Step 3:

[0532] Server: The server uses a generative AI model based on the received user information to analyze the user's learning style and interests. Deep learning frameworks such as TensorFlow and PyTorch can be used for the analysis.

[0533] Input: Encrypted user information.

[0534] Output: Analyzed learning style and interest data.

[0535] Step 4:

[0536] Server: The server generates educational content based on the analysis results. During this process, specific game content is designed using game engines such as Unity or Unreal Engine. For example, educational games containing calculation problems and story elements are generated.

[0537] Input: Analyzed learning style and interest data.

[0538] Output: Generated educational content (game data).

[0539] Step 5:

[0540] Server: The generated educational game is sent as a data packet from the server to the device. HTTP or WebSocket is used as the communication protocol.

[0541] Input: Generated educational content (game data).

[0542] Output: Educational content (game data) sent to the device.

[0543] Step 6:

[0544] Terminal: The terminal displays the educational game received from the server to the user. It uses Unity or Unreal Engine to provide an interactive user interface.

[0545] Input: Educational content (game data) sent to the device.

[0546] Output: Interactive educational content displayed to the user.

[0547] Step 7:

[0548] User: The user plays the provided educational game and progresses through their learning. The action logs and answers generated during play are recorded as play data.

[0549] Input: User learning behavior and its results.

[0550] Output: Play data recorded on the device.

[0551] Step 8:

[0552] Device: The device collects and temporarily stores the user's gameplay data in real time, and periodically transmits the data to the server.

[0553] Input: Play data recorded on the device.

[0554] Output: Play data sent to the server.

[0555] Step 9:

[0556] Server: The server analyzes the received play data and uses the generative AI model again to optimize the next educational content, for example, designing a new game taking into account the user's previous difficulties and new areas of interest.

[0557] Input: Play data sent to the server.

[0558] Output: Analysis results to optimize the next educational content.

[0559] (Application example 1)

[0560] 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."

[0561] Traditional educational systems have difficulty providing educational methods based on individual users' learning styles and interests. To improve the customer experience in physical stores, new methods are needed to attract customers' interest while providing educational benefits. Furthermore, there is room for improvement in the methods of providing rewards that motivate customers to visit stores.

[0562] 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.

[0563] In this invention, the server includes a means for collecting and analyzing user information, a means for generating individually customized educational games, and a means for providing the generated games to terminals and collecting play data. This makes it possible to improve the customer experience at physical stores and provide educational games based on customers' learning styles and interests. Furthermore, by allowing customers to earn rewards by playing games, it is possible to encourage repeat visits to stores and promote use.

[0564] "User" refers to each individual who uses the System, i.e., who provides information for the purpose of playing and learning educational games.

[0565] "Learning style" refers to a user's unique method or pattern of learning that is most effective for them, including the learning environment, way of understanding, and way of receiving information.

[0566] "Interests" refer to areas or topics that users have particular interests or concerns about, which are reflected in the content of educational games.

[0567] "Means of information acquisition" refers to methods or devices that collect information based on the user's input learning style and interests.

[0568] "Server" refers to a central processing unit that receives information over a network, processes and analyzes it, and returns the results.

[0569] "Educational games" refer to digital games created to facilitate learning and engage users. Learning content is presented in a game format.

[0570] "Terminal" refers to a device that is directly operated and used by a user, including smartphones, tablets, and PCs.

[0571] "Play Data" refers to data generated by a user while playing an educational game, including a user's behavior log and answers.

[0572] "Rewards" refers to rewards or benefits provided to users through playing educational games, including discount coupons and points.

[0573] A "physical store" refers to a store that exists in a physical location and where customers can visit in person to purchase products or services. This includes bookstores, electronics retailers, stationery stores, etc.

[0574] The present invention relates to a system that allows users to learn while having fun through educational games at a physical store and to earn rewards in the process. Specific embodiments will be described below.

[0575] System Overview

[0576] This system collects user information, analyzes it on the server, generates optimal educational games, and provides them to users. It also includes a mechanism for collecting user gameplay data and optimizing the next educational game based on that data.

[0577] Collection of User Information

[0578] Device: When users visit a physical store, they enter information about their learning style and interests, such as their favorite subjects, areas of expertise, and hobbies, via their device (smartphone, tablet, etc.).

[0579] Server: Receives user information sent from the device and stores it for analysis.

[0580] Analysis of user information and generation of educational games

[0581] Server: Uses a generative AI model (e.g., GPT-3) to analyze the user's learning style and interests, and automatically generates the most suitable educational game.

[0582] For example, if a user likes mathematics, inputs calculation as their specialty and reading as their hobby, the server will generate an educational game centered on calculation problems based on this information.The game will also incorporate story elements related to reading to attract the user's interest.

[0583] Providing educational games

[0584] Server: The generated educational game is sent from the server to the device.

[0585] Terminal: The terminal displays the educational games received from the server to the user, allowing the user to play them.

[0586] Collecting user gameplay data and optimizing the next educational game

[0587] User: Play the educational games provided and solve the problems.

[0588] Device: Collects user play data (e.g., answer results and behavior logs) and sends it to the server.

[0589] Server: Analyzes the collected play data and optimizes the next educational game based on it, for example, by designing the game to focus on the problem types or areas that the user struggled with in the previous game.

[0590] Offering benefits

[0591] Server: Provide rewards (discount coupons, points, etc.) to users who play educational games, which increases users' motivation to play the games.

[0592] Specific examples

[0593] Suppose a user visits a bookstore and enters into the application that they like "math" and that their hobby is "reading." In response, the generative AI model generates an "educational game with a storyline centered around math calculation problems" and sends it to the device. As the user plays this game, their play data is collected and reflected in the generation of the next game. In addition, completing the game will provide rewards such as discount coupons and points.

[0594] Example prompt for a generative AI model:

[0595] User Information:

[0596] Favorite subject: Mathematics

[0597] Specialty: Calculation

[0598] Hobbies: Reading

[0599] Use this to generate an educational game centered around math problems, and incorporate story elements related to reading to keep users engaged.

[0600] This invention improves the customer experience in physical stores while providing education tailored to users' learning styles and interests. Customers can learn while having fun and earn rewards, which is expected to encourage them to return to the store.

[0601] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0602] Step 1:

[0603] Device:Collecting user information

[0604] Users use a device (smartphone, tablet, etc.) to enter information about their learning style and interests (favorite subjects, areas of expertise, hobbies, etc.).

[0605] Input: Information about the user's department, field, and hobbies

[0606] Output: Collected user information (e.g., in JSON format)

[0607] Step 2:

[0608] Terminal: Sending information to the server

[0609] The device sends the collected user information to the server, which may be encrypted to ensure information security.

[0610] Input: Collected user information

[0611] Output: User information sent to the server

[0612] Step 3:

[0613] Server: Receiving and analyzing user information

[0614] The server receives user information sent from the device and stores it in a database for analysis, using a generative AI model.

[0615] Input: User information sent from the device

[0616] Output: Analysis results (characteristics based on user's learning style and interests)

[0617] Step 4:

[0618] Server: Educational Game Generation

[0619] The server uses a generative AI model (such as GPT-3) based on the analysis results to automatically generate an optimal educational game. At this time, the prompt sentence is input into the generative model.

[0620] Input: Analysis results based on the user's learning style and interests, prompts such as "Generate an educational game based on user information"

[0621] Output: Generated educational game data

[0622] Step 5:

[0623] Server: Educational game distribution

[0624] The server transmits the generated educational game data to the terminal.

[0625] Input: Generated educational game data

[0626] Output: Educational game data sent to the device

[0627] Step 6:

[0628] Device: View and play games

[0629] The terminal displays the educational game received from the server to the user, allowing the user to play it.

[0630] Input: Educational game data sent from the server

[0631] Output: The display screen for the user to play

[0632] Step 7:

[0633] User: Playing the game

[0634] Users progress by playing the educational games provided and solving problems.

[0635] Input: Displayed educational game

[0636] Output: User play data (answer results, action logs, etc.)

[0637] Step 8:

[0638] Device: Collection and transmission of play data

[0639] The terminal collects play data generated by the user and transmits it to the server.

[0640] Input: User's play data

[0641] Output: Play data sent to the server

[0642] Step 9:

[0643] Server: Analysis of play data and optimization for the next game

[0644] The server analyzes the collected play data and uses it as feedback to optimize the next educational game, for example, by focusing on the problem types that the player struggled with in the previous game.

[0645] Input: User's play data

[0646] Output: Optimized next educational game

[0647] Step 10:

[0648] Server: Offering special benefits

[0649] After the user finishes playing the educational game, the server generates a reward (for example, a discount coupon or points) and sends it to the terminal.

[0650] Input: Educational game completion data

[0651] Output: Benefit data (discount coupons and points)

[0652] In this way, by following a series of steps from 1 to 10, users can learn and earn rewards by entering their information at a physical store and playing the most suitable educational game.

[0653] 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.

[0654] This invention relates to a system that uses generative AI to automatically generate educational games based on a user's learning style, interests, and emotions, allowing users to continue learning effectively while having fun.

[0655] System Overview

[0656] This system collects user information, analyzes it on the server, and generates optimal educational games to provide to users. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize the learning experience based on emotional data.

[0657] Collecting user information

[0658] User: The user inputs information about their learning style and interests through the device interface, such as their favorite subject, field of expertise, and hobbies. Furthermore, an emotion engine recognizes emotions in real time from the user's facial expressions and voice.

[0659] Terminal: The terminal records the information entered by the user and the emotion data from the emotion engine, and transmits the data to the server.

[0660] Analysis of user information and generation of educational games

[0661] Server: The server inputs user information and emotional data sent from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.). The server also evaluates the user's stress level and concentration level from the emotional data.

[0662] Educational Game Generation: Based on the analysis results and emotional data, the server generates educational games optimized for the user's interests and learning style. The generative AI model automatically combines math and English questions with related story elements, and also adjusts the difficulty level and incorporates encouraging messages based on the user's emotions.

[0663] For example, if a user indicates that they like math, that they are good at calculations, and that their hobby is reading, the server will use this information to generate an educational game centered around calculation problems. The game is also designed to attract users' interest by incorporating story elements related to reading. Furthermore, if the emotion engine detects that the user's stress level is high, it will slightly lower the difficulty of the game or display encouraging messages.

[0664] Providing educational games

[0665] Server: The generated educational game is sent from the server to the device. The sent content includes the game title, question list, choices and answers, story, etc.

[0666] Device: The device displays the educational game received from the server to the user. The user can solve problems and enjoy the story through the game screen.

[0667] Collecting user gameplay data and optimizing the next educational game

[0668] User: The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. The emotion engine also records the user's emotional data in real time while playing.

[0669] Device: The device collects the user's gameplay data and emotional data and sends it to the server. This play data includes the options the user chose, whether they answered correctly or incorrectly, and the time it took.

[0670] Server: The server analyzes the received user play data and emotional data. Based on the analysis results, it provides feedback to the generative AI model to optimize the content and difficulty of the next educational game.

[0671] In this way, the system of the present invention can enhance learning effectiveness by providing educational games that are customized to the user's learning needs and emotions. Users can learn while having fun, which helps them maintain their motivation and encourages continuous learning.

[0672] The processing flow will be explained below.

[0673] Step 1:

[0674] Users input information about their learning style and interests through the device's interface, and the device also captures emotional data by recognizing the user's facial expressions and voice in real time.

[0675] Step 2:

[0676] The device collects information entered by the user and emotion data from the emotion engine, organizes this data, and sends it to the server via a POST request to an API endpoint.

[0677] Step 3:

[0678] The server receives user information sent from the device and inputs it into a generative AI model. The model analyzes the user's learning style and interests. It also includes emotional data to evaluate the user's emotional state.

[0679] Step 4:

[0680] Based on the analysis results, the server generates an educational game optimized for the user's interests and learning style. The generative AI model incorporates math and English questions, as well as difficulty adjustments and story elements based on the user's emotions. For example, if a user enjoys reading, the game story will include reading-related content.

[0681] Step 5:

[0682] The server then sends the generated educational game to the device, including the game title, a list of questions, choices and answers, a story, and feedback based on emotion data.

[0683] Step 6:

[0684] The device receives educational games from the server and displays them to users, allowing them to solve problems and enjoy stories through the game screen. It also provides real-time feedback based on emotional data.

[0685] Step 7:

[0686] The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. During this process, the emotion engine records the user's emotional data in real time.

[0687] Step 8:

[0688] The device collects the user's gameplay data and emotional data, including the user's choices, correct and incorrect answers, time taken, and emotional changes.

[0689] Step 9:

[0690] The terminal transmits the collected user play data and emotion data to the server, which is used as feedback data for the next game generation.

[0691] Step 10:

[0692] The server then analyzes the received user play data and emotional data, providing input to the generative AI model to optimize the content and difficulty of the next educational game.

[0693] Step 11:

[0694] The server regenerates the next optimized educational game to keep responding to the user's learning needs and emotional state, thereby providing the user with a continuously engaging and effective learning experience.

[0695] In this way, the system of the present invention, which combines an emotion engine, can enhance learning effectiveness by providing educational games customized to the user's learning needs and emotions. Users can learn while having fun, which makes it easier to maintain motivation, and this can be expected to encourage continuous learning.

[0696] Example 2

[0697] 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."

[0698] Conventional educational systems have difficulty customizing learning experiences based on users' learning styles and interests, making it difficult to provide optimal learning experiences for individual users. Furthermore, the learning experience has not been optimized with users' emotions in mind, which can lead to stress and a decline in motivation, which can have a negative impact on learning efficiency.

[0699] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring information on the user's learning style and interests, means for collecting user emotion data in real time, and means for generating an educational game based on the analysis results and the emotion data. This makes it possible to provide a customized learning experience based on the user's learning style and interests, and to timely adjust the learning content and difficulty level according to the user's emotions, thereby reducing stress and increasing motivation.

[0700] "Learning style" refers to the most effective way a user comprehends and learns information, and is often divided into categories such as visual, auditory, and experiential.

[0701] "Interests" refers to the subjects or areas in which you have a particular interest, including, for example, an interest in a particular subject or theme, such as math, languages, or science.

[0702] "Emotional data" refers to data that indicates the user's emotional state obtained in real time from facial expressions, voice, etc. This includes the user's stress level and concentration level.

[0703] A "generative AI model" refers to an algorithm or software that uses artificial intelligence technology to analyze user information and emotional data and automatically generate optimal educational games.

[0704] "Educational games" are programs that help users learn and provide educational content in the form of games, customized to the user's learning style, interests, and emotions.

[0705] "Play Data" refers to data recorded when a User plays an educational game, including choices, correct and incorrect answers, and play time.

[0706] "Optimization" refers to the process of adjusting the content and difficulty of future educational games based on collected data to provide the optimal learning experience for users.

[0707] This invention relates to a system that uses a generative AI model to automatically generate educational games based on a user's learning style, interests, and emotions, allowing users to continue learning effectively while having fun.

[0708] System Overview

[0709] This system collects user information, analyzes it on the server, and generates optimal educational games to provide to users. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize the learning experience based on emotional data.

[0710] Collection of User Information

[0711] User: The user inputs information about their learning style and interests through the device interface. This information includes, for example, their favorite subject, areas of expertise, and hobbies. In addition, an emotion engine is activated that recognizes emotions in real time from the user's facial expressions and voice.

[0712] Terminal: The terminal records the information entered by the user and the emotion data from the emotion engine, and transmits the data to the server.

[0713] Analysis of user information and generation of educational games

[0714] Server: The server inputs user information and emotional data sent from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.). The server also evaluates the user's stress level and concentration level from the emotional data.

[0715] Educational Game Generation: Based on the analysis results and emotional data, the server generates educational games optimized for the user's interests and learning style. The generative AI model automatically combines math and language problems with related story elements, and also adjusts the difficulty level and incorporates encouraging messages according to the user's emotions.

[0716] Providing educational games

[0717] Server: The generated educational game is sent from the server to the device. The sent content includes the game title, question list, choices and answers, story, etc.

[0718] Terminal: The terminal displays the educational game received from the server to the user. The user can solve problems and enjoy the story through the game screen.

[0719] Collecting user gameplay data and optimizing the next educational game

[0720] User: The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. The emotion engine also records the user's emotional data in real time while playing.

[0721] Device: The device collects the user's gameplay data and emotional data and sends it to the server. This play data includes the options the user chose, whether the questions were correct or incorrect, and the time it took.

[0722] Server: The server analyzes the received user play data and emotional data. Based on the analysis results, it provides feedback to the AI ​​model to optimize the content and difficulty of the next educational game.

[0723] Specific examples

[0724] For example, if a user likes math, enters calculation as their specialty and reading as their hobby, the server will generate an educational game centered around calculation problems based on this information. The game is also designed to attract users' interest by incorporating story elements related to reading. Furthermore, if the emotion engine recognizes that the user's stress level is high, it will slightly lower the difficulty of the game or display encouraging messages.

[0725] Prompt Sentence Examples

[0726] Below are some example prompts for interacting with generative AI models:

[0727] "The user's learning style is visual, their area of ​​interest is mathematics, their specialty is calculations, and their hobby is reading. Based on their emotional data, we recognize that their stress level is high. Generate an educational game that is appropriate for the user."

[0728] In this way, the system of the present invention provides users with educational games that are customized to their learning needs and emotions, enhancing learning effectiveness. Users can learn while having fun, which helps them stay motivated and encourages continuous learning.

[0729] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0730] Step 1:

[0731] Entering user information

[0732] User: The user uses the device interface to input information about their learning style and interests (e.g., favorite subject, field of expertise, hobbies, etc.). The input information is recorded in a database. In addition, the user's facial expressions and voice are captured in real time using a camera and microphone, generating emotional data.

[0733] Input: Information about the user's learning style and interests, facial expressions, and voice data

[0734] Output: Collecting user information and emotion data

[0735] Step 2:

[0736] Sending data

[0737] Terminal: The terminal transmits the collected user information and emotion data to the server. At this time, the data is encrypted to ensure security.

[0738] Input: Collected user information and emotion data

[0739] Output: Encrypted data sent to the server

[0740] Step 3:

[0741] Analysis of user information

[0742] Server: The server inputs the received user information and emotional data into the generative AI model. The generative AI model analyzes the user's learning style and interests, and evaluates stress levels and concentration levels from the emotional data. The analysis results are stored in a database.

[0743] Input: User information and emotion data

[0744] Output: Analysis results (learning style, interest, stress level, concentration)

[0745] Step 4:

[0746] Educational Game Generation

[0747] Server: The server uses the generative AI model to generate educational games based on the analysis results, combining math and language problems, relevant story elements, and emotionally-driven difficulty adjustments and encouraging messages. The generated games are stored in a database.

[0748] Input: Analysis results (learning style, interest, stress level, concentration)

[0749] Output: Generated educational game

[0750] Step 5:

[0751] Providing educational games

[0752] Server: The server sends the generated educational game to the device. The data is encrypted during transmission.

[0753] Input: Generated educational game

[0754] Output: Encrypted data sent to the device

[0755] Step 6:

[0756] Game Display

[0757] Terminal: The terminal displays the received educational game to the user, who can solve problems and enjoy the story through the game screen.

[0758] Input: Educational game received from the server

[0759] Output: The educational game displayed to the user

[0760] Step 7:

[0761] Gameplay data collection

[0762] User: The user plays the educational game, answering questions, choosing options, and progressing through the story. The emotion engine records the user's emotional data in real time while playing.

[0763] Input: educational game play behavior and changes in facial expressions and voice

[0764] Output: Play data and emotion data

[0765] Step 8:

[0766] Sending data

[0767] Terminal: The terminal transmits the user's play data and emotion data to the server.

[0768] Input: Play data and emotion data

[0769] Output: Encrypted data sent to the server

[0770] Step 9:

[0771] Subsequent optimizations

[0772] Server: The server analyzes the received play data and emotional data and reflects the results in the generative AI model, which generates feedback to optimize the content and difficulty of future educational games.

[0773] Input: Play data and emotion data

[0774] Output: Generative AI model reflected in subsequent optimizations

[0775] (Application example 2)

[0776] 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."

[0777] While traditional educational game systems are specialized for users' learning styles and interests, they do not consider real-time optimization based on individual emotional states, limiting the quality of the learning experience. Furthermore, online shopping sites are required to combine learning and entertainment to help users effectively understand product information while having fun, but such systems have not been adequately provided. Furthermore, there is a lack of an efficient method for providing appropriate incentives to support users' learning outcomes and increase their purchasing motivation.

[0778] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0779] In this invention, the server includes means for acquiring information about a user's learning style and interests, means for transmitting the information to the server, means for receiving the information and analyzing the user's learning style and interests, means for generating an educational game based on the analysis results, means for collecting the emotional data in real time and transmitting it to the server, means for optimizing the next educational game based on the play data and emotional data, and means for providing incentives based on the results of the educational game. This makes it possible to provide educational games optimized for individual users in real time and link their learning results to purchasing motivation.

[0780] A "user" is an individual who uses the system to learn or make purchases.

[0781] "Learning style" refers to the method or means (visual, auditory, experiential, etc.) in which a user learns most effectively.

[0782] "Interests" refers to the subjects, fields, hobbies, and activities that a user is particularly interested in.

[0783] "Means of information acquisition" refers to the mechanism by which users use devices to input data about their learning style and interests.

[0784] "Server" refers to the central processing unit that receives information sent by users, analyzes it, and generates educational games.

[0785] "Educational games" refers to educational content in the form of games that are generated based on the user's learning style and interests to promote learning.

[0786] "Emotional Data" refers to data indicative of a user's real-time emotional state collected while playing an educational game.

[0787] "Play Data" refers to data such as choices, response times, correct and incorrect answers, etc. that are recorded when a user plays an educational game.

[0788] "Incentives" refers to rewards or benefits offered to encourage users to learn or purchase.

[0789] "Device" refers to an electronic device (smartphone, tablet, PC, etc.) that a user uses to conduct learning or purchasing activities.

[0790] "Real-time" refers to near-simultaneous collection and processing of data.

[0791] The present invention relates to a system that uses a generative AI model to provide individually optimized educational games based on a user's learning style, interests, and emotions on an online shopping site. The purpose of this system is to allow users to learn while having fun and actively engage in purchasing activities. Specific embodiments are described below.

[0792] Overall system configuration

[0793] 1. Obtaining user information

[0794] Users use their devices to input information about their learning style and interests, such as their purchasing history, academic interests, and hobbies. Furthermore, an emotion recognition engine (Emotion Engine) is activated to collect real-time emotional data from users.

[0795] 2. Transmission and Analysis of Information

[0796] The device sends the collected user information and emotional data to a server. The server receives this information and analyzes the user's learning style and interests. The user's emotional data is analyzed in real time to evaluate stress levels and concentration levels.

[0797] 3. Educational Game Generation

[0798] The server generates an optimal educational game based on the analysis results. It uses a generative AI model (such as GPT-3) to combine math and English questions with related story elements. It also adjusts the game's difficulty and incorporates supportive messages based on the emotional data.

[0799] Hardware and software used

[0800] Devices (smartphones, tablets, PCs, etc.): Act as the user interface and collect and transmit user information and emotional data.

[0801] Emotion Recognition Engine (EmotionEngine): Acquires emotional data in real time from the user's facial expressions and voice.

[0802] Generative AI models (such as GPT-3): AI models that generate educational games based on analysis results.

[0803] Server (backend system using web frameworks such as Django): Analyzes user information and emotional data, and generates and transmits educational games.

[0804] Examples of concrete examples and prompts

[0805] For example, if a user is interested in fashion and has recently purchased a T-shirt, jeans, and sneakers, the server will generate a fashion quiz game based on this information. If the emotional data shows a high level of concentration and is positive, the server will present slightly more difficult questions. Each time the user answers correctly, the server will provide incentives such as discount coupons.

[0806] Example prompt sentence:

[0807] "The user is interested in fashion and recently purchased a t-shirt, jeans, and sneakers. Their sentiment data is positive and shows high concentration. Use this information to generate a fashion-related quiz."

[0808] In this way, the system of the present invention generates educational games based on the user's learning style, interests, and emotions, allowing the user to enjoy learning while engaging in purchasing activities, which is expected to improve the user's purchasing experience and increase learning effectiveness.

[0809] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0810] Step 1:

[0811] Entering and retrieving user information

[0812] The device provides an interface for users to input information about their learning style and interests. Users input their purchasing history, favorite subjects, hobbies, etc. The device also uses the Emotion Engine to collect real-time emotional data from the user's facial expressions and voice. The input data consists of user information (learning style, interests, purchasing history) and emotional data (facial expression recognition, voice analysis). This data is temporarily stored inside the device.

[0813] Step 2:

[0814] Sending information

[0815] The device sends the temporarily saved user information and emotion data to the server. Specifically, the user information and emotion data are packaged in JSON format and sent to the server via an HTTPS request. The input is user information and emotion data, and the output is data sent to the server.

[0816] Step 3:

[0817] Analysis of information

[0818] The server analyzes the received user information and emotional data. This analysis uses a generative AI model (e.g., GPT-3). As a result of the analysis, the server extracts the user's learning style, interests, stress level, and concentration level. The input is user information and emotional data, and the output is the analysis results (learning style, interests, and emotional state).

[0819] Step 4:

[0820] Educational Game Generation

[0821] The server generates an educational game based on the analysis results. A generative AI model is used for this. For example, if the user is interested in fashion, a fashion quiz is generated. The game difficulty and support messages are also adjusted based on the emotional data. The input is the analysis results, and the output is the generated educational game data.

[0822] Step 5:

[0823] Educational Game Submission

[0824] The server sends the generated educational game data to the device using the HTTPS protocol. The input is educational game data, and the output is game data sent to the device.

[0825] Step 6:

[0826] View and play games

[0827] The device displays the educational game to the user. The user plays the game and answers questions. Specifically, the device records the user's choices and answer times. The input is educational game data, and the output is user play data.

[0828] Step 7:

[0829] Collection and transmission of play data

[0830] The device collects the user's play data in real time and sends it to the server. The play data includes the user's choices, response time, correct and incorrect answers, etc. The input is the user's play data, and the output is the play data sent to the server.

[0831] Step 8:

[0832] Data reanalysis and game optimization

[0833] The server reanalyzes the received play data and emotional data and uses it to optimize the next educational game. It uses a generative AI model to provide feedback to adjust the game's content and difficulty. The input is play data and emotional data, and the output is an optimized educational game.

[0834] Step 9:

[0835] Offering incentives

[0836] The server provides incentives to users based on the results of the educational game. Specifically, it generates discount coupons according to the number of questions answered correctly and sends them to the terminal. The input is the results of the educational game, and the output is the incentive (discount coupon).

[0837] 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.

[0838] 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.

[0839] 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.

[0840] [Third embodiment]

[0841] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0842] 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.

[0843] 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).

[0844] 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.

[0845] 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.

[0846] 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).

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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."

[0853] The present invention relates to a system that utilizes generative AI to automatically generate educational games based on a user's learning style and interests. This system provides a way for users to continue learning effectively while having fun. An embodiment of this system is described below.

[0854] System Overview

[0855] This system collects user information, analyzes it on the server, generates optimal educational games, and provides them to users. It can also collect user gameplay data and use it to optimize the next educational game.

[0856] Collecting user information

[0857] User: Users enter information about their learning style and interests, including their favorite subjects, areas of expertise, hobbies, etc.

[0858] Terminal: The terminal records the information entered by the user and transmits the data to the server. This process includes collecting information through the interface and transmitting it to the server.

[0859] Analysis of user information and generation of educational games

[0860] Server: The server receives user information sent from the device and uses a generative AI model to analyze the user's learning style and interests. Based on the analysis results, it automatically generates the most suitable educational game for the user.

[0861] For example, if a user likes mathematics, inputs calculation as their area of ​​expertise and reading as their hobby, the server will generate an educational game centered on calculation problems based on this information.The game is also designed to attract the user's interest by incorporating story elements related to reading.

[0862] Providing educational games

[0863] Server: The generated educational game is sent from the server to the device, allowing users to play the game on their own device.

[0864] Device: The device displays educational games received from the server to the user. The displayed games include interactive questions and stories, allowing users to learn while having fun.

[0865] Collecting user gameplay data and optimizing the next educational game

[0866] User: The user plays the provided educational game and solves the problems. During this process, play data such as the user's behavior log and answer results are generated.

[0867] Device: The device collects the user's play data and sends it to the server. This play data includes how the user solved the problem, the correct answer rate, answer choices, etc.

[0868] Server: The server analyzes the collected play data and optimizes the next educational game based on it, for example, by designing the game to focus on the problem types or areas in which the user struggled in the previous game.

[0869] In this way, the system of the present invention can enhance learning effectiveness by providing educational games customized to the user's learning needs. Users can learn while having fun, which makes it easier to maintain motivation, and this can lead to continued learning.

[0870] The processing flow will be explained below.

[0871] Step 1:

[0872] Users input information about their learning style and interests through the device interface, such as their favorite subjects, areas of expertise, and hobbies, which then defines the user's learning needs.

[0873] Step 2:

[0874] The device collects the information entered by the user and sends it to the server. Specifically, it organizes the user-entered data and sends it as a POST request to the server's API endpoint.

[0875] Step 3:

[0876] The server inputs the user information received from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.).

[0877] Step 4:

[0878] Based on the analysis results, the server generates educational games optimized for the user's interests and learning style, with the generative AI model automatically combining math and English questions with related story elements.

[0879] Step 5:

[0880] The server sends the generated educational game to the device, including the game title, question list, choices and answers, and story.

[0881] Step 6:

[0882] The device receives the educational game from the server and displays it to the user, who can then solve problems and enjoy the story through the game screen.

[0883] Step 7:

[0884] The user plays the educational game provided through the device, specifically by answering questions, choosing answers from options, progressing through the story, and so on.

[0885] Step 8:

[0886] The device collects the user's gameplay data, including which options the user chose, whether they answered correctly or incorrectly, and the time it took.

[0887] Step 9:

[0888] The device sends the collected user play data to a server, which records the user's learning progress and trends.

[0889] Step 10:

[0890] The server analyzes the received user play data and, based on the analysis results, provides feedback to the AI ​​model to optimize the content and difficulty of the next educational game.

[0891] Step 11:

[0892] The server then generates a new, optimized educational game for the next time to continue meeting the user's learning needs, and this process repeats, ensuring the user continues to have an engaging and effective learning experience.

[0893] This is the specific processing flow of this system. Through this process, the user's learning effect can be improved and motivation can be maintained.

[0894] Example 1

[0895] 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."

[0896] Conventional educational systems often fail to achieve sufficient learning effectiveness due to the difficulty of customizing content to suit individual users' learning styles and interests. Furthermore, formulaic learning content fails to capture users' interest, resulting in reduced learning continuity. The present invention aims to solve these problems by providing educational content customized based on a user's learning style and interests, thereby improving learning effectiveness and increasing learning continuity.

[0897] 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.

[0898] In this invention, the server includes means for analyzing information about a user's learning style and interests using a generation AI model, means for generating educational content based on the analysis results, and means for optimizing the next educational content based on the user's play data, thereby making it possible to provide educational content customized to each user's individual learning style and interests.

[0899] "User learning style" refers to the individual way in which a learner most effectively comprehends, retains, and applies information.

[0900] "Interest Information" refers to data about particular subjects or activities that interest a user.

[0901] A "generative AI model" refers to an algorithm or system that creates new content based on data.

[0902] "Analyzing" refers to reviewing the collected information to identify characteristics of a user's learning style and interests.

[0903] "Educational Content" refers to the materials and activities used to help learners acquire specific knowledge or skills.

[0904] "Play Data" refers to data regarding the actions and results that occur when a user uses educational content.

[0905] "Optimize" refers to improving a system or process to maximize its efficiency and effectiveness in order to achieve a specific purpose.

[0906] "Customized Story Elements" means story elements that are individually created based on a user's interests and preferences.

[0907] "Server" means a computer system for storing, processing, and distributing data.

[0908] "Terminal" refers to a computer or mobile device that is directly operated by a user.

[0909] The present invention relates to a system that automatically generates educational content based on a user's learning style and interests using a generative AI model. This system enhances learning effectiveness by providing an educational experience that meets the individual needs of the user. Specific embodiments for implementing the present invention are described below.

[0910] overview

[0911] This system collects user information, analyzes it on the server, and generates optimal educational content to provide to users. It can also collect user content usage data and optimize the next educational content based on that data.

[0912] Collecting user information

[0913] User: The user inputs information about their learning style and interests via a terminal. For example, they provide information such as "I like math," "I'm good at calculations," and "My hobby is reading."

[0914] Terminal: The terminal records the information entered by the user and sends the data to the server via the HTTPS protocol, SSL encrypted.

[0915] Analyzing user information and generating educational content

[0916] Server: The server uses a generative AI model (such as one using TensorFlow or PyTorch) to analyze the user's learning style and interests based on the received user information. Based on the analysis results, it generates educational content that is optimal for the user.

[0917] Providing educational content

[0918] Server: The generated educational content is sent as data packets from the server to the device. Protocols used include HTTP and WebSocket.

[0919] Terminal: The terminal displays the educational content received from the server to the user. The displayed content is designed to be interactive so that the user can manipulate it. For example, the content is created and displayed using game engines such as Unity or Unreal Engine.

[0920] Collecting user content usage data and optimizing the next educational content

[0921] User: The user uses the provided educational content to progress with their studies. The behavioral logs and answers generated during use are recorded as usage data.

[0922] Device: The device collects and temporarily stores user usage data in real time, then periodically transmits the data to the server.

[0923] Server: The server analyzes the received usage data and re-uses the generative AI model to optimize the next educational content, for example, by taking into account the user's previous difficulties and new areas of interest.

[0924] Specific examples

[0925] As a concrete example, the following prompt sentence is input into the generative AI model:

[0926] Example prompt sentence:

[0927] "This user likes eighth-grade math, and is particularly interested in equations. He also enjoys reading historical novels. Use this information to generate educational content that is ideal for this user."

[0928] This allows the generative AI model to automatically generate educational content that focuses on mathematical equations and includes historical story elements, and delivers it to devices via a server. For example, users can enjoy educational content in the form of a game where they progress by solving equations against the backdrop of historical events.

[0929] In this way, the system of the present invention provides customized educational content to enhance the user's learning effect, and realizes a method for continuing learning while having fun.

[0930] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0931] Step 1:

[0932] User: The user enters information about their learning style and interests through the application interface, for example, "I like math," "I'm good at math," or "I enjoy reading."

[0933] Input: User-entered information about their learning style and interests.

[0934] Output: Input information recorded on the terminal.

[0935] Step 2:

[0936] Terminal: The terminal sends the information entered by the user to the server as SSL-encrypted data via the HTTPS protocol.

[0937] Input: User information recorded on the device.

[0938] Output: Encrypted user information sent to the server.

[0939] Step 3:

[0940] Server: The server uses a generative AI model based on the received user information to analyze the user's learning style and interests. Deep learning frameworks such as TensorFlow and PyTorch can be used for the analysis.

[0941] Input: Encrypted user information.

[0942] Output: Analyzed learning style and interest data.

[0943] Step 4:

[0944] Server: The server generates educational content based on the analysis results. During this process, specific game content is designed using game engines such as Unity or Unreal Engine. For example, educational games containing calculation problems and story elements are generated.

[0945] Input: Analyzed learning style and interest data.

[0946] Output: Generated educational content (game data).

[0947] Step 5:

[0948] Server: The generated educational game is sent as a data packet from the server to the device. HTTP or WebSocket is used as the communication protocol.

[0949] Input: Generated educational content (game data).

[0950] Output: Educational content (game data) sent to the device.

[0951] Step 6:

[0952] Terminal: The terminal displays the educational game received from the server to the user. It uses Unity or Unreal Engine to provide an interactive user interface.

[0953] Input: Educational content (game data) sent to the device.

[0954] Output: Interactive educational content displayed to the user.

[0955] Step 7:

[0956] User: The user plays the provided educational game and progresses through their learning. The action logs and answers generated during play are recorded as play data.

[0957] Input: User learning behavior and its results.

[0958] Output: Play data recorded on the device.

[0959] Step 8:

[0960] Device: The device collects and temporarily stores the user's gameplay data in real time, and periodically transmits the data to the server.

[0961] Input: Play data recorded on the device.

[0962] Output: Play data sent to the server.

[0963] Step 9:

[0964] Server: The server analyzes the received play data and uses the generative AI model again to optimize the next educational content, for example, designing a new game taking into account the user's previous difficulties and new areas of interest.

[0965] Input: Play data sent to the server.

[0966] Output: Analysis results to optimize the next educational content.

[0967] (Application example 1)

[0968] 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."

[0969] Traditional educational systems have difficulty providing educational methods based on individual users' learning styles and interests. To improve the customer experience in physical stores, new methods are needed to attract customers' interest while providing educational benefits. Furthermore, there is room for improvement in the methods of providing rewards that motivate customers to visit stores.

[0970] 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.

[0971] In this invention, the server includes a means for collecting and analyzing user information, a means for generating individually customized educational games, and a means for providing the generated games to terminals and collecting play data. This makes it possible to improve the customer experience at physical stores and provide educational games based on customers' learning styles and interests. Furthermore, by allowing customers to earn rewards by playing games, it is possible to encourage repeat visits to stores and promote use.

[0972] "User" refers to each individual who uses the System, i.e., who provides information for the purpose of playing and learning educational games.

[0973] "Learning style" refers to a user's unique method or pattern of learning that is most effective for them, including the learning environment, way of understanding, and way of receiving information.

[0974] "Interests" refer to areas or topics that users have particular interests or concerns about, which are reflected in the content of educational games.

[0975] "Means of information acquisition" refers to methods or devices that collect information based on the user's input learning style and interests.

[0976] "Server" refers to a central processing unit that receives information over a network, processes and analyzes it, and returns the results.

[0977] "Educational games" refer to digital games created to facilitate learning and engage users. Learning content is presented in a game format.

[0978] "Terminal" refers to a device that is directly operated and used by a user, including smartphones, tablets, and PCs.

[0979] "Play Data" refers to data generated by a user while playing an educational game, including a user's behavior log and answers.

[0980] "Rewards" refers to rewards or benefits provided to users through playing educational games, including discount coupons and points.

[0981] A "physical store" refers to a store that exists in a physical location and where customers can visit in person to purchase products or services. This includes bookstores, electronics retailers, stationery stores, etc.

[0982] The present invention relates to a system that allows users to learn while having fun through educational games at a physical store and to earn rewards in the process. Specific embodiments will be described below.

[0983] System Overview

[0984] This system collects user information, analyzes it on the server, generates optimal educational games, and provides them to users. It also includes a mechanism for collecting user gameplay data and optimizing the next educational game based on that data.

[0985] Collection of User Information

[0986] Device: When users visit a physical store, they enter information about their learning style and interests, such as their favorite subjects, areas of expertise, and hobbies, via their device (smartphone, tablet, etc.).

[0987] Server: Receives user information sent from the device and stores it for analysis.

[0988] Analysis of user information and generation of educational games

[0989] Server: Uses a generative AI model (e.g., GPT-3) to analyze the user's learning style and interests, and automatically generates the most suitable educational game.

[0990] For example, if a user likes mathematics, inputs calculation as their specialty and reading as their hobby, the server will generate an educational game centered on calculation problems based on this information.The game will also incorporate story elements related to reading to attract the user's interest.

[0991] Providing educational games

[0992] Server: The generated educational game is sent from the server to the device.

[0993] Terminal: The terminal displays the educational games received from the server to the user, allowing the user to play them.

[0994] Collecting user gameplay data and optimizing the next educational game

[0995] User: Play the educational games provided and solve the problems.

[0996] Device: Collects user play data (e.g., answer results and behavior logs) and sends it to the server.

[0997] Server: Analyzes the collected play data and optimizes the next educational game based on it, for example, by designing the game to focus on the problem types or areas that the user struggled with in the previous game.

[0998] Offering benefits

[0999] Server: Provide rewards (discount coupons, points, etc.) to users who play educational games, which increases users' motivation to play the games.

[1000] Specific examples

[1001] Suppose a user visits a bookstore and enters into the application that they like "math" and that their hobby is "reading." In response, the generative AI model generates an "educational game with a storyline centered around math calculation problems" and sends it to the device. As the user plays this game, their play data is collected and reflected in the generation of the next game. In addition, completing the game will provide rewards such as discount coupons and points.

[1002] Example prompt for a generative AI model:

[1003] User Information:

[1004] Favorite subject: Mathematics

[1005] Specialty: Calculation

[1006] Hobbies: Reading

[1007] Use this to generate an educational game centered around math problems, and incorporate story elements related to reading to keep users engaged.

[1008] This invention improves the customer experience in physical stores while providing education tailored to users' learning styles and interests. Customers can learn while having fun and earn rewards, which is expected to encourage them to return to the store.

[1009] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1010] Step 1:

[1011] Device:Collecting user information

[1012] Users use a device (smartphone, tablet, etc.) to enter information about their learning style and interests (favorite subjects, areas of expertise, hobbies, etc.).

[1013] Input: Information about the user's department, field, and hobbies

[1014] Output: Collected user information (e.g., in JSON format)

[1015] Step 2:

[1016] Terminal: Sending information to the server

[1017] The device sends the collected user information to the server, which may be encrypted to ensure information security.

[1018] Input: Collected user information

[1019] Output: User information sent to the server

[1020] Step 3:

[1021] Server: Receiving and analyzing user information

[1022] The server receives user information sent from the device and stores it in a database for analysis, using a generative AI model.

[1023] Input: User information sent from the device

[1024] Output: Analysis results (characteristics based on user's learning style and interests)

[1025] Step 4:

[1026] Server: Educational Game Generation

[1027] The server uses a generative AI model (such as GPT-3) based on the analysis results to automatically generate an optimal educational game. At this time, the prompt sentence is input into the generative model.

[1028] Input: Analysis results based on the user's learning style and interests, prompts such as "Generate an educational game based on user information"

[1029] Output: Generated educational game data

[1030] Step 5:

[1031] Server: Educational game distribution

[1032] The server transmits the generated educational game data to the terminal.

[1033] Input: Generated educational game data

[1034] Output: Educational game data sent to the device

[1035] Step 6:

[1036] Device: View and play games

[1037] The terminal displays the educational game received from the server to the user, allowing the user to play it.

[1038] Input: Educational game data sent from the server

[1039] Output: The display screen for the user to play

[1040] Step 7:

[1041] User: Playing the game

[1042] Users progress by playing the educational games provided and solving problems.

[1043] Input: Displayed educational game

[1044] Output: User play data (answer results, action logs, etc.)

[1045] Step 8:

[1046] Device: Collection and transmission of play data

[1047] The terminal collects play data generated by the user and transmits it to the server.

[1048] Input: User's play data

[1049] Output: Play data sent to the server

[1050] Step 9:

[1051] Server: Analysis of play data and optimization for the next game

[1052] The server analyzes the collected play data and uses it as feedback to optimize the next educational game, for example, by focusing on the problem types that the player struggled with in the previous game.

[1053] Input: User's play data

[1054] Output: Optimized next educational game

[1055] Step 10:

[1056] Server: Offering special benefits

[1057] After the user finishes playing the educational game, the server generates a reward (for example, a discount coupon or points) and sends it to the terminal.

[1058] Input: Educational game completion data

[1059] Output: Benefit data (discount coupons and points)

[1060] In this way, by following a series of steps from 1 to 10, users can learn and earn rewards by entering their information at a physical store and playing the most suitable educational game.

[1061] 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.

[1062] This invention relates to a system that uses generative AI to automatically generate educational games based on a user's learning style, interests, and emotions, allowing users to continue learning effectively while having fun.

[1063] System Overview

[1064] This system collects user information, analyzes it on the server, and generates optimal educational games to provide to users. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize the learning experience based on emotional data.

[1065] Collecting user information

[1066] User: The user inputs information about their learning style and interests through the device interface, such as their favorite subject, field of expertise, and hobbies. Furthermore, an emotion engine recognizes emotions in real time from the user's facial expressions and voice.

[1067] Terminal: The terminal records the information entered by the user and the emotion data from the emotion engine, and transmits the data to the server.

[1068] Analysis of user information and generation of educational games

[1069] Server: The server inputs user information and emotional data sent from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.). The server also evaluates the user's stress level and concentration level from the emotional data.

[1070] Educational Game Generation: Based on the analysis results and emotional data, the server generates educational games optimized for the user's interests and learning style. The generative AI model automatically combines math and English questions with related story elements, and also adjusts the difficulty level and incorporates encouraging messages based on the user's emotions.

[1071] For example, if a user indicates that they like math, that they are good at calculations, and that their hobby is reading, the server will use this information to generate an educational game centered around calculation problems. The game is also designed to attract users' interest by incorporating story elements related to reading. Furthermore, if the emotion engine detects that the user's stress level is high, it will slightly lower the difficulty of the game or display encouraging messages.

[1072] Providing educational games

[1073] Server: The generated educational game is sent from the server to the device. The sent content includes the game title, question list, choices and answers, story, etc.

[1074] Device: The device displays the educational game received from the server to the user. The user can solve problems and enjoy the story through the game screen.

[1075] Collecting user gameplay data and optimizing the next educational game

[1076] User: The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. The emotion engine also records the user's emotional data in real time while playing.

[1077] Device: The device collects the user's gameplay data and emotional data and sends it to the server. This play data includes the options the user chose, whether they answered correctly or incorrectly, and the time it took.

[1078] Server: The server analyzes the received user play data and emotional data. Based on the analysis results, it provides feedback to the generative AI model to optimize the content and difficulty of the next educational game.

[1079] In this way, the system of the present invention can enhance learning effectiveness by providing educational games that are customized to the user's learning needs and emotions. Users can learn while having fun, which helps them maintain their motivation and encourages continuous learning.

[1080] The processing flow will be explained below.

[1081] Step 1:

[1082] Users input information about their learning style and interests through the device's interface, and the device also captures emotional data by recognizing the user's facial expressions and voice in real time.

[1083] Step 2:

[1084] The device collects information entered by the user and emotion data from the emotion engine, organizes this data, and sends it to the server via a POST request to an API endpoint.

[1085] Step 3:

[1086] The server receives user information sent from the device and inputs it into a generative AI model. The model analyzes the user's learning style and interests. It also includes emotional data to evaluate the user's emotional state.

[1087] Step 4:

[1088] Based on the analysis results, the server generates an educational game optimized for the user's interests and learning style. The generative AI model incorporates math and English questions, as well as difficulty adjustments and story elements based on the user's emotions. For example, if a user enjoys reading, the game story will include reading-related content.

[1089] Step 5:

[1090] The server then sends the generated educational game to the device, including the game title, a list of questions, choices and answers, a story, and feedback based on emotion data.

[1091] Step 6:

[1092] The device receives educational games from the server and displays them to users, allowing them to solve problems and enjoy stories through the game screen. It also provides real-time feedback based on emotional data.

[1093] Step 7:

[1094] The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. During this process, the emotion engine records the user's emotional data in real time.

[1095] Step 8:

[1096] The device collects the user's gameplay data and emotional data, including the user's choices, correct and incorrect answers, time taken, and emotional changes.

[1097] Step 9:

[1098] The terminal transmits the collected user play data and emotion data to the server, which is used as feedback data for the next game generation.

[1099] Step 10:

[1100] The server then analyzes the received user play data and emotional data, providing input to the generative AI model to optimize the content and difficulty of the next educational game.

[1101] Step 11:

[1102] The server regenerates the next optimized educational game to keep responding to the user's learning needs and emotional state, thereby providing the user with a continuously engaging and effective learning experience.

[1103] In this way, the system of the present invention, which combines an emotion engine, can enhance learning effectiveness by providing educational games customized to the user's learning needs and emotions. Users can learn while having fun, which makes it easier to maintain motivation, and this can be expected to encourage continuous learning.

[1104] Example 2

[1105] 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."

[1106] Conventional educational systems have difficulty customizing learning experiences based on users' learning styles and interests, making it difficult to provide optimal learning experiences for individual users. Furthermore, the learning experience has not been optimized with users' emotions in mind, which can lead to stress and a decline in motivation, which can have a negative impact on learning efficiency.

[1107] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring information on the user's learning style and interests, means for collecting user emotion data in real time, and means for generating an educational game based on the analysis results and the emotion data. This makes it possible to provide a customized learning experience based on the user's learning style and interests, and to timely adjust the learning content and difficulty level according to the user's emotions, thereby reducing stress and increasing motivation.

[1108] "Learning style" refers to the most effective way a user comprehends and learns information, and is often divided into categories such as visual, auditory, and experiential.

[1109] "Interests" refers to the subjects or areas in which you have a particular interest, including, for example, an interest in a particular subject or theme, such as math, languages, or science.

[1110] "Emotional data" refers to data that indicates the user's emotional state obtained in real time from facial expressions, voice, etc. This includes the user's stress level and concentration level.

[1111] A "generative AI model" refers to an algorithm or software that uses artificial intelligence technology to analyze user information and emotional data and automatically generate optimal educational games.

[1112] "Educational games" are programs that help users learn and provide educational content in the form of games, customized to the user's learning style, interests, and emotions.

[1113] "Play Data" refers to data recorded when a User plays an educational game, including choices, correct and incorrect answers, and play time.

[1114] "Optimization" refers to the process of adjusting the content and difficulty of future educational games based on collected data to provide the optimal learning experience for users.

[1115] This invention relates to a system that uses a generative AI model to automatically generate educational games based on a user's learning style, interests, and emotions, allowing users to continue learning effectively while having fun.

[1116] System Overview

[1117] This system collects user information, analyzes it on the server, and generates optimal educational games to provide to users. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize the learning experience based on emotional data.

[1118] Collection of User Information

[1119] User: The user inputs information about their learning style and interests through the device interface. This information includes, for example, their favorite subject, areas of expertise, and hobbies. In addition, an emotion engine is activated that recognizes emotions in real time from the user's facial expressions and voice.

[1120] Terminal: The terminal records the information entered by the user and the emotion data from the emotion engine, and transmits the data to the server.

[1121] Analysis of user information and generation of educational games

[1122] Server: The server inputs user information and emotional data sent from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.). The server also evaluates the user's stress level and concentration level from the emotional data.

[1123] Educational Game Generation: Based on the analysis results and emotional data, the server generates educational games optimized for the user's interests and learning style. The generative AI model automatically combines math and language problems with related story elements, and also adjusts the difficulty level and incorporates encouraging messages according to the user's emotions.

[1124] Providing educational games

[1125] Server: The generated educational game is sent from the server to the device. The sent content includes the game title, question list, choices and answers, story, etc.

[1126] Terminal: The terminal displays the educational game received from the server to the user. The user can solve problems and enjoy the story through the game screen.

[1127] Collecting user gameplay data and optimizing the next educational game

[1128] User: The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. The emotion engine also records the user's emotional data in real time while playing.

[1129] Device: The device collects the user's gameplay data and emotional data and sends it to the server. This play data includes the options the user chose, whether the questions were correct or incorrect, and the time it took.

[1130] Server: The server analyzes the received user play data and emotional data. Based on the analysis results, it provides feedback to the AI ​​model to optimize the content and difficulty of the next educational game.

[1131] Specific examples

[1132] For example, if a user likes math, enters calculation as their specialty and reading as their hobby, the server will generate an educational game centered around calculation problems based on this information. The game is also designed to attract users' interest by incorporating story elements related to reading. Furthermore, if the emotion engine recognizes that the user's stress level is high, it will slightly lower the difficulty of the game or display encouraging messages.

[1133] Prompt Sentence Examples

[1134] Below are some example prompts for interacting with generative AI models:

[1135] "The user's learning style is visual, their area of ​​interest is mathematics, their specialty is calculations, and their hobby is reading. Based on their emotional data, we recognize that their stress level is high. Generate an educational game that is appropriate for the user."

[1136] In this way, the system of the present invention provides users with educational games that are customized to their learning needs and emotions, enhancing learning effectiveness. Users can learn while having fun, which helps them stay motivated and encourages continuous learning.

[1137] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1138] Step 1:

[1139] Entering user information

[1140] User: The user uses the device interface to input information about their learning style and interests (e.g., favorite subject, field of expertise, hobbies, etc.). The input information is recorded in a database. In addition, the user's facial expressions and voice are captured in real time using a camera and microphone, generating emotional data.

[1141] Input: Information about the user's learning style and interests, facial expressions, and voice data

[1142] Output: Collecting user information and emotion data

[1143] Step 2:

[1144] Sending data

[1145] Terminal: The terminal transmits the collected user information and emotion data to the server. At this time, the data is encrypted to ensure security.

[1146] Input: Collected user information and emotion data

[1147] Output: Encrypted data sent to the server

[1148] Step 3:

[1149] Analysis of user information

[1150] Server: The server inputs the received user information and emotional data into the generative AI model. The generative AI model analyzes the user's learning style and interests, and evaluates stress levels and concentration levels from the emotional data. The analysis results are stored in a database.

[1151] Input: User information and emotion data

[1152] Output: Analysis results (learning style, interest, stress level, concentration)

[1153] Step 4:

[1154] Educational Game Generation

[1155] Server: The server uses the generative AI model to generate educational games based on the analysis results, combining math and language problems, relevant story elements, and emotionally-driven difficulty adjustments and encouraging messages. The generated games are stored in a database.

[1156] Input: Analysis results (learning style, interest, stress level, concentration)

[1157] Output: Generated educational game

[1158] Step 5:

[1159] Providing educational games

[1160] Server: The server sends the generated educational game to the device. The data is encrypted during transmission.

[1161] Input: Generated educational game

[1162] Output: Encrypted data sent to the device

[1163] Step 6:

[1164] Game Display

[1165] Terminal: The terminal displays the received educational game to the user, who can solve problems and enjoy the story through the game screen.

[1166] Input: Educational game received from the server

[1167] Output: The educational game displayed to the user

[1168] Step 7:

[1169] Gameplay data collection

[1170] User: The user plays the educational game, answering questions, choosing options, and progressing through the story. The emotion engine records the user's emotional data in real time while playing.

[1171] Input: educational game play behavior and changes in facial expressions and voice

[1172] Output: Play data and emotion data

[1173] Step 8:

[1174] Sending data

[1175] Terminal: The terminal transmits the user's play data and emotion data to the server.

[1176] Input: Play data and emotion data

[1177] Output: Encrypted data sent to the server

[1178] Step 9:

[1179] Subsequent optimizations

[1180] Server: The server analyzes the received play data and emotional data and reflects the results in the generative AI model, which generates feedback to optimize the content and difficulty of future educational games.

[1181] Input: Play data and emotion data

[1182] Output: Generative AI model reflected in subsequent optimizations

[1183] (Application example 2)

[1184] 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."

[1185] While traditional educational game systems are specialized for users' learning styles and interests, they do not consider real-time optimization based on individual emotional states, limiting the quality of the learning experience. Furthermore, online shopping sites are required to combine learning and entertainment to help users effectively understand product information while having fun, but such systems have not been adequately provided. Furthermore, there is a lack of an efficient method for providing appropriate incentives to support users' learning outcomes and increase their purchasing motivation.

[1186] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1187] In this invention, the server includes means for acquiring information about a user's learning style and interests, means for transmitting the information to the server, means for receiving the information and analyzing the user's learning style and interests, means for generating an educational game based on the analysis results, means for collecting the emotional data in real time and transmitting it to the server, means for optimizing the next educational game based on the play data and emotional data, and means for providing incentives based on the results of the educational game. This makes it possible to provide educational games optimized for individual users in real time and link their learning results to purchasing motivation.

[1188] A "user" is an individual who uses the system to learn or make purchases.

[1189] "Learning style" refers to the method or means (visual, auditory, experiential, etc.) in which a user learns most effectively.

[1190] "Interests" refers to the subjects, fields, hobbies, and activities that a user is particularly interested in.

[1191] "Means of information acquisition" refers to the mechanism by which users use devices to input data about their learning style and interests.

[1192] "Server" refers to the central processing unit that receives information sent by users, analyzes it, and generates educational games.

[1193] "Educational games" refers to educational content in the form of games that are generated based on the user's learning style and interests to promote learning.

[1194] "Emotional Data" refers to data indicative of a user's real-time emotional state collected while playing an educational game.

[1195] "Play Data" refers to data such as choices, response times, correct and incorrect answers, etc. that are recorded when a user plays an educational game.

[1196] "Incentives" refers to rewards or benefits offered to encourage users to learn or purchase.

[1197] "Device" refers to an electronic device (smartphone, tablet, PC, etc.) that a user uses to conduct learning or purchasing activities.

[1198] "Real-time" refers to near-simultaneous collection and processing of data.

[1199] The present invention relates to a system that uses a generative AI model to provide individually optimized educational games based on a user's learning style, interests, and emotions on an online shopping site. The purpose of this system is to allow users to learn while having fun and actively engage in purchasing activities. Specific embodiments are described below.

[1200] Overall system configuration

[1201] 1. Obtaining user information

[1202] Users use their devices to input information about their learning style and interests, such as their purchasing history, academic interests, and hobbies. Furthermore, an emotion recognition engine (Emotion Engine) is activated to collect real-time emotional data from users.

[1203] 2. Transmission and Analysis of Information

[1204] The device sends the collected user information and emotional data to a server. The server receives this information and analyzes the user's learning style and interests. The user's emotional data is analyzed in real time to evaluate stress levels and concentration levels.

[1205] 3. Educational Game Generation

[1206] The server generates an optimal educational game based on the analysis results. It uses a generative AI model (such as GPT-3) to combine math and English questions with related story elements. It also adjusts the game's difficulty and incorporates supportive messages based on the emotional data.

[1207] Hardware and software used

[1208] Devices (smartphones, tablets, PCs, etc.): Act as the user interface and collect and transmit user information and emotional data.

[1209] Emotion Recognition Engine (EmotionEngine): Acquires emotional data in real time from the user's facial expressions and voice.

[1210] Generative AI models (such as GPT-3): AI models that generate educational games based on analysis results.

[1211] Server (backend system using web frameworks such as Django): Analyzes user information and emotional data, and generates and transmits educational games.

[1212] Examples of concrete examples and prompts

[1213] For example, if a user is interested in fashion and has recently purchased a T-shirt, jeans, and sneakers, the server will generate a fashion quiz game based on this information. If the emotional data shows a high level of concentration and is positive, the server will present slightly more difficult questions. Each time the user answers correctly, the server will provide incentives such as discount coupons.

[1214] Example prompt sentence:

[1215] "The user is interested in fashion and recently purchased a t-shirt, jeans, and sneakers. Their sentiment data is positive and shows high concentration. Use this information to generate a fashion-related quiz."

[1216] In this way, the system of the present invention generates educational games based on the user's learning style, interests, and emotions, allowing the user to enjoy learning while engaging in purchasing activities, which is expected to improve the user's purchasing experience and increase learning effectiveness.

[1217] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1218] Step 1:

[1219] Entering and retrieving user information

[1220] The device provides an interface for users to input information about their learning style and interests. Users input their purchasing history, favorite subjects, hobbies, etc. The device also uses the Emotion Engine to collect real-time emotional data from the user's facial expressions and voice. The input data consists of user information (learning style, interests, purchasing history) and emotional data (facial expression recognition, voice analysis). This data is temporarily stored inside the device.

[1221] Step 2:

[1222] Sending information

[1223] The device sends the temporarily saved user information and emotion data to the server. Specifically, the user information and emotion data are packaged in JSON format and sent to the server via an HTTPS request. The input is user information and emotion data, and the output is data sent to the server.

[1224] Step 3:

[1225] Analysis of information

[1226] The server analyzes the received user information and emotional data. This analysis uses a generative AI model (e.g., GPT-3). As a result of the analysis, the server extracts the user's learning style, interests, stress level, and concentration level. The input is user information and emotional data, and the output is the analysis results (learning style, interests, and emotional state).

[1227] Step 4:

[1228] Educational Game Generation

[1229] The server generates an educational game based on the analysis results. A generative AI model is used for this. For example, if the user is interested in fashion, a fashion quiz is generated. The game difficulty and support messages are also adjusted based on the emotional data. The input is the analysis results, and the output is the generated educational game data.

[1230] Step 5:

[1231] Educational Game Submission

[1232] The server sends the generated educational game data to the device using the HTTPS protocol. The input is educational game data, and the output is game data sent to the device.

[1233] Step 6:

[1234] View and play games

[1235] The device displays the educational game to the user. The user plays the game and answers questions. Specifically, the device records the user's choices and answer times. The input is educational game data, and the output is user play data.

[1236] Step 7:

[1237] Collection and transmission of play data

[1238] The device collects the user's play data in real time and sends it to the server. The play data includes the user's choices, response time, correct and incorrect answers, etc. The input is the user's play data, and the output is the play data sent to the server.

[1239] Step 8:

[1240] Data reanalysis and game optimization

[1241] The server reanalyzes the received play data and emotional data and uses it to optimize the next educational game. It uses a generative AI model to provide feedback to adjust the game's content and difficulty. The input is play data and emotional data, and the output is an optimized educational game.

[1242] Step 9:

[1243] Offering incentives

[1244] The server provides incentives to users based on the results of the educational game. Specifically, it generates discount coupons according to the number of questions answered correctly and sends them to the terminal. The input is the results of the educational game, and the output is the incentive (discount coupon).

[1245] 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.

[1246] 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.

[1247] 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.

[1248] [Fourth embodiment]

[1249] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1250] 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.

[1251] 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).

[1252] 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.

[1253] 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.

[1254] 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).

[1255] 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.

[1256] 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.

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] 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."

[1262] The present invention relates to a system that utilizes generative AI to automatically generate educational games based on a user's learning style and interests. This system provides a way for users to continue learning effectively while having fun. An embodiment of this system is described below.

[1263] System Overview

[1264] This system collects user information, analyzes it on the server, generates optimal educational games, and provides them to users. It can also collect user gameplay data and use it to optimize the next educational game.

[1265] Collecting user information

[1266] User: Users enter information about their learning style and interests, including their favorite subjects, areas of expertise, hobbies, etc.

[1267] Terminal: The terminal records the information entered by the user and transmits the data to the server. This process includes collecting information through the interface and transmitting it to the server.

[1268] Analysis of user information and generation of educational games

[1269] Server: The server receives user information sent from the device and uses a generative AI model to analyze the user's learning style and interests. Based on the analysis results, it automatically generates the most suitable educational game for the user.

[1270] For example, if a user likes mathematics, inputs calculation as their area of ​​expertise and reading as their hobby, the server will generate an educational game centered on calculation problems based on this information.The game is also designed to attract the user's interest by incorporating story elements related to reading.

[1271] Providing educational games

[1272] Server: The generated educational game is sent from the server to the device, allowing users to play the game on their own device.

[1273] Device: The device displays educational games received from the server to the user. The displayed games include interactive questions and stories, allowing users to learn while having fun.

[1274] Collecting user gameplay data and optimizing the next educational game

[1275] User: The user plays the provided educational game and solves the problems. During this process, play data such as the user's behavior log and answer results are generated.

[1276] Device: The device collects the user's play data and sends it to the server. This play data includes how the user solved the problem, the correct answer rate, answer choices, etc.

[1277] Server: The server analyzes the collected play data and optimizes the next educational game based on it, for example, by designing the game to focus on the problem types or areas in which the user struggled in the previous game.

[1278] In this way, the system of the present invention can enhance learning effectiveness by providing educational games customized to the user's learning needs. Users can learn while having fun, which makes it easier to maintain motivation, and this can lead to continued learning.

[1279] The processing flow will be explained below.

[1280] Step 1:

[1281] Users input information about their learning style and interests through the device interface, such as their favorite subjects, areas of expertise, and hobbies, which then defines the user's learning needs.

[1282] Step 2:

[1283] The device collects the information entered by the user and sends it to the server. Specifically, it organizes the user-entered data and sends it as a POST request to the server's API endpoint.

[1284] Step 3:

[1285] The server inputs the user information received from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.).

[1286] Step 4:

[1287] Based on the analysis results, the server generates educational games optimized for the user's interests and learning style, with the generative AI model automatically combining math and English questions with related story elements.

[1288] Step 5:

[1289] The server sends the generated educational game to the device, including the game title, question list, choices and answers, and story.

[1290] Step 6:

[1291] The device receives the educational game from the server and displays it to the user, who can then solve problems and enjoy the story through the game screen.

[1292] Step 7:

[1293] The user plays the educational game provided through the device, specifically by answering questions, choosing answers from options, progressing through the story, and so on.

[1294] Step 8:

[1295] The device collects the user's gameplay data, including which options the user chose, whether they answered correctly or incorrectly, and the time it took.

[1296] Step 9:

[1297] The device sends the collected user play data to a server, which records the user's learning progress and trends.

[1298] Step 10:

[1299] The server analyzes the received user play data and, based on the analysis results, provides feedback to the AI ​​model to optimize the content and difficulty of the next educational game.

[1300] Step 11:

[1301] The server then generates a new, optimized educational game for the next time to continue meeting the user's learning needs, and this process repeats, ensuring the user continues to have an engaging and effective learning experience.

[1302] This is the specific processing flow of this system. Through this process, the user's learning effect can be improved and motivation can be maintained.

[1303] Example 1

[1304] 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."

[1305] Conventional educational systems often fail to achieve sufficient learning effectiveness due to the difficulty of customizing content to suit individual users' learning styles and interests. Furthermore, formulaic learning content fails to capture users' interest, resulting in reduced learning continuity. The present invention aims to solve these problems by providing educational content customized based on a user's learning style and interests, thereby improving learning effectiveness and increasing learning continuity.

[1306] 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.

[1307] In this invention, the server includes means for analyzing information about a user's learning style and interests using a generation AI model, means for generating educational content based on the analysis results, and means for optimizing the next educational content based on the user's play data, thereby making it possible to provide educational content customized to each user's individual learning style and interests.

[1308] "User learning style" refers to the individual way in which a learner most effectively comprehends, retains, and applies information.

[1309] "Interest Information" refers to data about particular subjects or activities that interest a user.

[1310] A "generative AI model" refers to an algorithm or system that creates new content based on data.

[1311] "Analyzing" refers to reviewing the collected information to identify characteristics of a user's learning style and interests.

[1312] "Educational Content" refers to the materials and activities used to help learners acquire specific knowledge or skills.

[1313] "Play Data" refers to data regarding the actions and results that occur when a user uses educational content.

[1314] "Optimize" refers to improving a system or process to maximize its efficiency and effectiveness in order to achieve a specific purpose.

[1315] "Customized Story Elements" means story elements that are individually created based on a user's interests and preferences.

[1316] "Server" means a computer system for storing, processing, and distributing data.

[1317] "Terminal" refers to a computer or mobile device that is directly operated by a user.

[1318] The present invention relates to a system that automatically generates educational content based on a user's learning style and interests using a generative AI model. This system enhances learning effectiveness by providing an educational experience that meets the individual needs of the user. Specific embodiments for implementing the present invention are described below.

[1319] overview

[1320] This system collects user information, analyzes it on the server, and generates optimal educational content to provide to users. It can also collect user content usage data and optimize the next educational content based on that data.

[1321] Collecting user information

[1322] User: The user inputs information about their learning style and interests via a terminal. For example, they provide information such as "I like math," "I'm good at calculations," and "My hobby is reading."

[1323] Terminal: The terminal records the information entered by the user and sends the data to the server via the HTTPS protocol, SSL encrypted.

[1324] Analyzing user information and generating educational content

[1325] Server: The server uses a generative AI model (such as one using TensorFlow or PyTorch) to analyze the user's learning style and interests based on the received user information. Based on the analysis results, it generates educational content that is optimal for the user.

[1326] Providing educational content

[1327] Server: The generated educational content is sent as data packets from the server to the device. Protocols used include HTTP and WebSocket.

[1328] Terminal: The terminal displays the educational content received from the server to the user. The displayed content is designed to be interactive so that the user can manipulate it. For example, the content is created and displayed using game engines such as Unity or Unreal Engine.

[1329] Collecting user content usage data and optimizing the next educational content

[1330] User: The user uses the provided educational content to progress with their studies. The behavioral logs and answers generated during use are recorded as usage data.

[1331] Device: The device collects and temporarily stores user usage data in real time, then periodically transmits the data to the server.

[1332] Server: The server analyzes the received usage data and re-uses the generative AI model to optimize the next educational content, for example, by taking into account the user's previous difficulties and new areas of interest.

[1333] Specific examples

[1334] As a concrete example, the following prompt sentence is input into the generative AI model:

[1335] Example prompt sentence:

[1336] "This user likes eighth-grade math, and is particularly interested in equations. He also enjoys reading historical novels. Use this information to generate educational content that is ideal for this user."

[1337] This allows the generative AI model to automatically generate educational content that focuses on mathematical equations and includes historical story elements, and delivers it to devices via a server. For example, users can enjoy educational content in the form of a game where they progress by solving equations against the backdrop of historical events.

[1338] In this way, the system of the present invention provides customized educational content to enhance the user's learning effect, and realizes a method for continuing learning while having fun.

[1339] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1340] Step 1:

[1341] User: The user enters information about their learning style and interests through the application interface, for example, "I like math," "I'm good at math," or "I enjoy reading."

[1342] Input: User-entered information about their learning style and interests.

[1343] Output: Input information recorded on the terminal.

[1344] Step 2:

[1345] Terminal: The terminal sends the information entered by the user to the server as SSL-encrypted data via the HTTPS protocol.

[1346] Input: User information recorded on the device.

[1347] Output: Encrypted user information sent to the server.

[1348] Step 3:

[1349] Server: The server uses a generative AI model based on the received user information to analyze the user's learning style and interests. Deep learning frameworks such as TensorFlow and PyTorch can be used for the analysis.

[1350] Input: Encrypted user information.

[1351] Output: Analyzed learning style and interest data.

[1352] Step 4:

[1353] Server: The server generates educational content based on the analysis results. During this process, specific game content is designed using game engines such as Unity or Unreal Engine. For example, educational games containing calculation problems and story elements are generated.

[1354] Input: Analyzed learning style and interest data.

[1355] Output: Generated educational content (game data).

[1356] Step 5:

[1357] Server: The generated educational game is sent as a data packet from the server to the device. HTTP or WebSocket is used as the communication protocol.

[1358] Input: Generated educational content (game data).

[1359] Output: Educational content (game data) sent to the device.

[1360] Step 6:

[1361] Terminal: The terminal displays the educational game received from the server to the user. It uses Unity or Unreal Engine to provide an interactive user interface.

[1362] Input: Educational content (game data) sent to the device.

[1363] Output: Interactive educational content displayed to the user.

[1364] Step 7:

[1365] User: The user plays the provided educational game and progresses through their learning. The action logs and answers generated during play are recorded as play data.

[1366] Input: User learning behavior and its results.

[1367] Output: Play data recorded on the device.

[1368] Step 8:

[1369] Device: The device collects and temporarily stores the user's gameplay data in real time, and periodically transmits the data to the server.

[1370] Input: Play data recorded on the device.

[1371] Output: Play data sent to the server.

[1372] Step 9:

[1373] Server: The server analyzes the received play data and uses the generative AI model again to optimize the next educational content, for example, designing a new game taking into account the user's previous difficulties and new areas of interest.

[1374] Input: Play data sent to the server.

[1375] Output: Analysis results to optimize the next educational content.

[1376] (Application example 1)

[1377] 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."

[1378] Traditional educational systems have difficulty providing educational methods based on individual users' learning styles and interests. To improve the customer experience in physical stores, new methods are needed to attract customers' interest while providing educational benefits. Furthermore, there is room for improvement in the methods of providing rewards that motivate customers to visit stores.

[1379] 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.

[1380] In this invention, the server includes a means for collecting and analyzing user information, a means for generating individually customized educational games, and a means for providing the generated games to terminals and collecting play data. This makes it possible to improve the customer experience at physical stores and provide educational games based on customers' learning styles and interests. Furthermore, by allowing customers to earn rewards by playing games, it is possible to encourage repeat visits to stores and promote use.

[1381] "User" refers to each individual who uses the System, i.e., who provides information for the purpose of playing and learning educational games.

[1382] "Learning style" refers to a user's unique method or pattern of learning that is most effective for them, including the learning environment, way of understanding, and way of receiving information.

[1383] "Interests" refer to areas or topics that users have particular interests or concerns about, which are reflected in the content of educational games.

[1384] "Means of information acquisition" refers to methods or devices that collect information based on the user's input learning style and interests.

[1385] "Server" refers to a central processing unit that receives information over a network, processes and analyzes it, and returns the results.

[1386] "Educational games" refer to digital games created to facilitate learning and engage users. Learning content is presented in a game format.

[1387] "Terminal" refers to a device that is directly operated and used by a user, including smartphones, tablets, and PCs.

[1388] "Play Data" refers to data generated by a user while playing an educational game, including a user's behavior log and answers.

[1389] "Rewards" refers to rewards or benefits provided to users through playing educational games, including discount coupons and points.

[1390] A "physical store" refers to a store that exists in a physical location and where customers can visit in person to purchase products or services. This includes bookstores, electronics retailers, stationery stores, etc.

[1391] The present invention relates to a system that allows users to learn while having fun through educational games at a physical store and to earn rewards in the process. Specific embodiments will be described below.

[1392] System Overview

[1393] This system collects user information, analyzes it on the server, generates optimal educational games, and provides them to users. It also includes a mechanism for collecting user gameplay data and optimizing the next educational game based on that data.

[1394] Collection of User Information

[1395] Device: When users visit a physical store, they enter information about their learning style and interests, such as their favorite subjects, areas of expertise, and hobbies, via their device (smartphone, tablet, etc.).

[1396] Server: Receives user information sent from the device and stores it for analysis.

[1397] Analysis of user information and generation of educational games

[1398] Server: Uses a generative AI model (e.g., GPT-3) to analyze the user's learning style and interests, and automatically generates the most suitable educational game.

[1399] For example, if a user likes mathematics, inputs calculation as their specialty and reading as their hobby, the server will generate an educational game centered on calculation problems based on this information.The game will also incorporate story elements related to reading to attract the user's interest.

[1400] Providing educational games

[1401] Server: The generated educational game is sent from the server to the device.

[1402] Terminal: The terminal displays the educational games received from the server to the user, allowing the user to play them.

[1403] Collecting user gameplay data and optimizing the next educational game

[1404] User: Play the educational games provided and solve the problems.

[1405] Device: Collects user play data (e.g., answer results and behavior logs) and sends it to the server.

[1406] Server: Analyzes the collected play data and optimizes the next educational game based on it, for example, by designing the game to focus on the problem types or areas that the user struggled with in the previous game.

[1407] Offering benefits

[1408] Server: Provide rewards (discount coupons, points, etc.) to users who play educational games, which increases users' motivation to play the games.

[1409] Specific examples

[1410] Suppose a user visits a bookstore and enters into the application that they like "math" and that their hobby is "reading." In response, the generative AI model generates an "educational game with a storyline centered around math calculation problems" and sends it to the device. As the user plays this game, their play data is collected and reflected in the generation of the next game. In addition, completing the game will provide rewards such as discount coupons and points.

[1411] Example prompt for a generative AI model:

[1412] User Information:

[1413] Favorite subject: Mathematics

[1414] Specialty: Calculation

[1415] Hobbies: Reading

[1416] Use this to generate an educational game centered around math problems, and incorporate story elements related to reading to keep users engaged.

[1417] This invention improves the customer experience in physical stores while providing education tailored to users' learning styles and interests. Customers can learn while having fun and earn rewards, which is expected to encourage them to return to the store.

[1418] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1419] Step 1:

[1420] Device:Collecting user information

[1421] Users use a device (smartphone, tablet, etc.) to enter information about their learning style and interests (favorite subjects, areas of expertise, hobbies, etc.).

[1422] Input: Information about the user's department, field, and hobbies

[1423] Output: Collected user information (e.g., in JSON format)

[1424] Step 2:

[1425] Terminal: Sending information to the server

[1426] The device sends the collected user information to the server, which may be encrypted to ensure information security.

[1427] Input: Collected user information

[1428] Output: User information sent to the server

[1429] Step 3:

[1430] Server: Receiving and analyzing user information

[1431] The server receives user information sent from the device and stores it in a database for analysis, using a generative AI model.

[1432] Input: User information sent from the device

[1433] Output: Analysis results (characteristics based on user's learning style and interests)

[1434] Step 4:

[1435] Server: Educational Game Generation

[1436] The server uses a generative AI model (such as GPT-3) based on the analysis results to automatically generate an optimal educational game. At this time, the prompt sentence is input into the generative model.

[1437] Input: Analysis results based on the user's learning style and interests, prompts such as "Generate an educational game based on user information"

[1438] Output: Generated educational game data

[1439] Step 5:

[1440] Server: Educational game distribution

[1441] The server transmits the generated educational game data to the terminal.

[1442] Input: Generated educational game data

[1443] Output: Educational game data sent to the device

[1444] Step 6:

[1445] Device: View and play games

[1446] The terminal displays the educational game received from the server to the user, allowing the user to play it.

[1447] Input: Educational game data sent from the server

[1448] Output: The display screen for the user to play

[1449] Step 7:

[1450] User: Playing the game

[1451] Users progress by playing the educational games provided and solving problems.

[1452] Input: Displayed educational game

[1453] Output: User play data (answer results, action logs, etc.)

[1454] Step 8:

[1455] Device: Collection and transmission of play data

[1456] The terminal collects play data generated by the user and transmits it to the server.

[1457] Input: User's play data

[1458] Output: Play data sent to the server

[1459] Step 9:

[1460] Server: Analysis of play data and optimization for the next game

[1461] The server analyzes the collected play data and uses it as feedback to optimize the next educational game, for example, by focusing on the problem types that the player struggled with in the previous game.

[1462] Input: User's play data

[1463] Output: Optimized next educational game

[1464] Step 10:

[1465] Server: Offering special benefits

[1466] After the user finishes playing the educational game, the server generates a reward (for example, a discount coupon or points) and sends it to the terminal.

[1467] Input: Educational game completion data

[1468] Output: Benefit data (discount coupons and points)

[1469] In this way, by following a series of steps from 1 to 10, users can learn and earn rewards by entering their information at a physical store and playing the most suitable educational game.

[1470] 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.

[1471] This invention relates to a system that uses generative AI to automatically generate educational games based on a user's learning style, interests, and emotions, allowing users to continue learning effectively while having fun.

[1472] System Overview

[1473] This system collects user information, analyzes it on the server, and generates optimal educational games to provide to users. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize the learning experience based on emotional data.

[1474] Collecting user information

[1475] User: The user inputs information about their learning style and interests through the device interface, such as their favorite subject, field of expertise, and hobbies. Furthermore, an emotion engine recognizes emotions in real time from the user's facial expressions and voice.

[1476] Terminal: The terminal records the information entered by the user and the emotion data from the emotion engine, and transmits the data to the server.

[1477] Analysis of user information and generation of educational games

[1478] Server: The server inputs user information and emotional data sent from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.). The server also evaluates the user's stress level and concentration level from the emotional data.

[1479] Educational Game Generation: Based on the analysis results and emotional data, the server generates educational games optimized for the user's interests and learning style. The generative AI model automatically combines math and English questions with related story elements, and also adjusts the difficulty level and incorporates encouraging messages based on the user's emotions.

[1480] For example, if a user indicates that they like math, that they are good at calculations, and that their hobby is reading, the server will use this information to generate an educational game centered around calculation problems. The game is also designed to attract users' interest by incorporating story elements related to reading. Furthermore, if the emotion engine detects that the user's stress level is high, it will slightly lower the difficulty of the game or display encouraging messages.

[1481] Providing educational games

[1482] Server: The generated educational game is sent from the server to the device. The sent content includes the game title, question list, choices and answers, story, etc.

[1483] Device: The device displays the educational game received from the server to the user. The user can solve problems and enjoy the story through the game screen.

[1484] Collecting user gameplay data and optimizing the next educational game

[1485] User: The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. The emotion engine also records the user's emotional data in real time while playing.

[1486] Device: The device collects the user's gameplay data and emotional data and sends it to the server. This play data includes the options the user chose, whether they answered correctly or incorrectly, and the time it took.

[1487] Server: The server analyzes the received user play data and emotional data. Based on the analysis results, it provides feedback to the generative AI model to optimize the content and difficulty of the next educational game.

[1488] In this way, the system of the present invention can enhance learning effectiveness by providing educational games that are customized to the user's learning needs and emotions. Users can learn while having fun, which helps them maintain their motivation and encourages continuous learning.

[1489] The processing flow will be explained below.

[1490] Step 1:

[1491] Users input information about their learning style and interests through the device's interface, and the device also captures emotional data by recognizing the user's facial expressions and voice in real time.

[1492] Step 2:

[1493] The device collects information entered by the user and emotion data from the emotion engine, organizes this data, and sends it to the server via a POST request to an API endpoint.

[1494] Step 3:

[1495] The server receives user information sent from the device and inputs it into a generative AI model. The model analyzes the user's learning style and interests. It also includes emotional data to evaluate the user's emotional state.

[1496] Step 4:

[1497] Based on the analysis results, the server generates an educational game optimized for the user's interests and learning style. The generative AI model incorporates math and English questions, as well as difficulty adjustments and story elements based on the user's emotions. For example, if a user enjoys reading, the game story will include reading-related content.

[1498] Step 5:

[1499] The server then sends the generated educational game to the device, including the game title, a list of questions, choices and answers, a story, and feedback based on emotion data.

[1500] Step 6:

[1501] The device receives educational games from the server and displays them to users, allowing them to solve problems and enjoy stories through the game screen. It also provides real-time feedback based on emotional data.

[1502] Step 7:

[1503] The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. During this process, the emotion engine records the user's emotional data in real time.

[1504] Step 8:

[1505] The device collects the user's gameplay data and emotional data, including the user's choices, correct and incorrect answers, time taken, and emotional changes.

[1506] Step 9:

[1507] The terminal transmits the collected user play data and emotion data to the server, which is used as feedback data for the next game generation.

[1508] Step 10:

[1509] The server then analyzes the received user play data and emotional data, providing input to the generative AI model to optimize the content and difficulty of the next educational game.

[1510] Step 11:

[1511] The server regenerates the next optimized educational game to keep responding to the user's learning needs and emotional state, thereby providing the user with a continuously engaging and effective learning experience.

[1512] In this way, the system of the present invention, which combines an emotion engine, can enhance learning effectiveness by providing educational games customized to the user's learning needs and emotions. Users can learn while having fun, which makes it easier to maintain motivation, and this can be expected to encourage continuous learning.

[1513] Example 2

[1514] 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."

[1515] Conventional educational systems have difficulty customizing learning experiences based on users' learning styles and interests, making it difficult to provide optimal learning experiences for individual users. Furthermore, the learning experience has not been optimized with users' emotions in mind, which can lead to stress and a decline in motivation, which can have a negative impact on learning efficiency.

[1516] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring information on the user's learning style and interests, means for collecting user emotion data in real time, and means for generating an educational game based on the analysis results and the emotion data. This makes it possible to provide a customized learning experience based on the user's learning style and interests, and to timely adjust the learning content and difficulty level according to the user's emotions, thereby reducing stress and increasing motivation.

[1517] "Learning style" refers to the most effective way a user comprehends and learns information, and is often divided into categories such as visual, auditory, and experiential.

[1518] "Interests" refers to the subjects or areas in which you have a particular interest, including, for example, an interest in a particular subject or theme, such as math, languages, or science.

[1519] "Emotional data" refers to data that indicates the user's emotional state obtained in real time from facial expressions, voice, etc. This includes the user's stress level and concentration level.

[1520] A "generative AI model" refers to an algorithm or software that uses artificial intelligence technology to analyze user information and emotional data and automatically generate optimal educational games.

[1521] "Educational games" are programs that help users learn and provide educational content in the form of games, customized to the user's learning style, interests, and emotions.

[1522] "Play Data" refers to data recorded when a User plays an educational game, including choices, correct and incorrect answers, and play time.

[1523] "Optimization" refers to the process of adjusting the content and difficulty of future educational games based on collected data to provide the optimal learning experience for users.

[1524] This invention relates to a system that uses a generative AI model to automatically generate educational games based on a user's learning style, interests, and emotions, allowing users to continue learning effectively while having fun.

[1525] System Overview

[1526] This system collects user information, analyzes it on the server, and generates optimal educational games to provide to users. In addition, by combining it with an emotion engine that recognizes user emotions, it is possible to optimize the learning experience based on emotional data.

[1527] Collection of User Information

[1528] User: The user inputs information about their learning style and interests through the device interface. This information includes, for example, their favorite subject, areas of expertise, and hobbies. In addition, an emotion engine is activated that recognizes emotions in real time from the user's facial expressions and voice.

[1529] Terminal: The terminal records the information entered by the user and the emotion data from the emotion engine, and transmits the data to the server.

[1530] Analysis of user information and generation of educational games

[1531] Server: The server inputs user information and emotional data sent from the device into a generative AI model for analysis. The initial analysis evaluates the user's learning style (e.g., visual, auditory, etc.) and interests (hobbies, favorite subjects, etc.). The server also evaluates the user's stress level and concentration level from the emotional data.

[1532] Educational Game Generation: Based on the analysis results and emotional data, the server generates educational games optimized for the user's interests and learning style. The generative AI model automatically combines math and language problems with related story elements, and also adjusts the difficulty level and incorporates encouraging messages according to the user's emotions.

[1533] Providing educational games

[1534] Server: The generated educational game is sent from the server to the device. The sent content includes the game title, question list, choices and answers, story, etc.

[1535] Terminal: The terminal displays the educational game received from the server to the user. The user can solve problems and enjoy the story through the game screen.

[1536] Collecting user gameplay data and optimizing the next educational game

[1537] User: The user plays the provided educational game by answering questions, choosing answers from options, progressing through the story, etc. The emotion engine also records the user's emotional data in real time while playing.

[1538] Device: The device collects the user's gameplay data and emotional data and sends it to the server. This play data includes the options the user chose, whether the questions were correct or incorrect, and the time it took.

[1539] Server: The server analyzes the received user play data and emotional data. Based on the analysis results, it provides feedback to the AI ​​model to optimize the content and difficulty of the next educational game.

[1540] Specific examples

[1541] For example, if a user likes math, enters calculation as their specialty and reading as their hobby, the server will generate an educational game centered around calculation problems based on this information. The game is also designed to attract users' interest by incorporating story elements related to reading. Furthermore, if the emotion engine recognizes that the user's stress level is high, it will slightly lower the difficulty of the game or display encouraging messages.

[1542] Prompt Sentence Examples

[1543] Below are some example prompts for interacting with generative AI models:

[1544] "The user's learning style is visual, their area of ​​interest is mathematics, their specialty is calculations, and their hobby is reading. Based on their emotional data, we recognize that their stress level is high. Generate an educational game that is appropriate for the user."

[1545] In this way, the system of the present invention provides users with educational games that are customized to their learning needs and emotions, enhancing learning effectiveness. Users can learn while having fun, which helps them stay motivated and encourages continuous learning.

[1546] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1547] Step 1:

[1548] Entering user information

[1549] User: The user uses the device interface to input information about their learning style and interests (e.g., favorite subject, field of expertise, hobbies, etc.). The input information is recorded in a database. In addition, the user's facial expressions and voice are captured in real time using a camera and microphone, generating emotional data.

[1550] Input: Information about the user's learning style and interests, facial expressions, and voice data

[1551] Output: Collecting user information and emotion data

[1552] Step 2:

[1553] Sending data

[1554] Terminal: The terminal transmits the collected user information and emotion data to the server. At this time, the data is encrypted to ensure security.

[1555] Input: Collected user information and emotion data

[1556] Output: Encrypted data sent to the server

[1557] Step 3:

[1558] Analysis of user information

[1559] Server: The server inputs the received user information and emotional data into the generative AI model. The generative AI model analyzes the user's learning style and interests, and evaluates stress levels and concentration levels from the emotional data. The analysis results are stored in a database.

[1560] Input: User information and emotion data

[1561] Output: Analysis results (learning style, interest, stress level, concentration)

[1562] Step 4:

[1563] Educational Game Generation

[1564] Server: The server uses the generative AI model to generate educational games based on the analysis results, combining math and language problems, relevant story elements, and emotionally-driven difficulty adjustments and encouraging messages. The generated games are stored in a database.

[1565] Input: Analysis results (learning style, interest, stress level, concentration)

[1566] Output: Generated educational game

[1567] Step 5:

[1568] Providing educational games

[1569] Server: The server sends the generated educational game to the device. The data is encrypted during transmission.

[1570] Input: Generated educational game

[1571] Output: Encrypted data sent to the device

[1572] Step 6:

[1573] Game Display

[1574] Terminal: The terminal displays the received educational game to the user, who can solve problems and enjoy the story through the game screen.

[1575] Input: Educational game received from the server

[1576] Output: The educational game displayed to the user

[1577] Step 7:

[1578] Gameplay data collection

[1579] User: The user plays the educational game, answering questions, choosing options, and progressing through the story. The emotion engine records the user's emotional data in real time while playing.

[1580] Input: educational game play behavior and changes in facial expressions and voice

[1581] Output: Play data and emotion data

[1582] Step 8:

[1583] Sending data

[1584] Terminal: The terminal transmits the user's play data and emotion data to the server.

[1585] Input: Play data and emotion data

[1586] Output: Encrypted data sent to the server

[1587] Step 9:

[1588] Subsequent optimizations

[1589] Server: The server analyzes the received play data and emotional data and reflects the results in the generative AI model, which generates feedback to optimize the content and difficulty of future educational games.

[1590] Input: Play data and emotion data

[1591] Output: Generative AI model reflected in subsequent optimizations

[1592] (Application example 2)

[1593] 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."

[1594] While traditional educational game systems are specialized for users' learning styles and interests, they do not consider real-time optimization based on individual emotional states, limiting the quality of the learning experience. Furthermore, online shopping sites are required to combine learning and entertainment to help users effectively understand product information while having fun, but such systems have not been adequately provided. Furthermore, there is a lack of an efficient method for providing appropriate incentives to support users' learning outcomes and increase their purchasing motivation.

[1595] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1596] In this invention, the server includes means for acquiring information about a user's learning style and interests, means for transmitting the information to the server, means for receiving the information and analyzing the user's learning style and interests, means for generating an educational game based on the analysis results, means for collecting the emotional data in real time and transmitting it to the server, means for optimizing the next educational game based on the play data and emotional data, and means for providing incentives based on the results of the educational game. This makes it possible to provide educational games optimized for individual users in real time and link their learning results to purchasing motivation.

[1597] A "user" is an individual who uses the system to learn or make purchases.

[1598] "Learning style" refers to the method or means (visual, auditory, experiential, etc.) in which a user learns most effectively.

[1599] "Interests" refers to the subjects, fields, hobbies, and activities that a user is particularly interested in.

[1600] "Means of information acquisition" refers to the mechanism by which users use devices to input data about their learning style and interests.

[1601] "Server" refers to the central processing unit that receives information sent by users, analyzes it, and generates educational games.

[1602] "Educational games" refers to educational content in the form of games that are generated based on the user's learning style and interests to promote learning.

[1603] "Emotional Data" refers to data indicative of a user's real-time emotional state collected while playing an educational game.

[1604] "Play Data" refers to data such as choices, response times, correct and incorrect answers, etc. that are recorded when a user plays an educational game.

[1605] "Incentives" refers to rewards or benefits offered to encourage users to learn or purchase.

[1606] "Device" refers to an electronic device (smartphone, tablet, PC, etc.) that a user uses to conduct learning or purchasing activities.

[1607] "Real-time" refers to near-simultaneous collection and processing of data.

[1608] The present invention relates to a system that uses a generative AI model to provide individually optimized educational games based on a user's learning style, interests, and emotions on an online shopping site. The purpose of this system is to allow users to learn while having fun and actively engage in purchasing activities. Specific embodiments are described below.

[1609] Overall system configuration

[1610] 1. Obtaining user information

[1611] Users use their devices to input information about their learning style and interests, such as their purchasing history, academic interests, and hobbies. Furthermore, an emotion recognition engine (Emotion Engine) is activated to collect real-time emotional data from users.

[1612] 2. Transmission and Analysis of Information

[1613] The device sends the collected user information and emotional data to a server. The server receives this information and analyzes the user's learning style and interests. The user's emotional data is analyzed in real time to evaluate stress levels and concentration levels.

[1614] 3. Educational Game Generation

[1615] The server generates an optimal educational game based on the analysis results. It uses a generative AI model (such as GPT-3) to combine math and English questions with related story elements. It also adjusts the game's difficulty and incorporates supportive messages based on the emotional data.

[1616] Hardware and software used

[1617] Devices (smartphones, tablets, PCs, etc.): Act as the user interface and collect and transmit user information and emotional data.

[1618] Emotion Recognition Engine (EmotionEngine): Acquires emotional data in real time from the user's facial expressions and voice.

[1619] Generative AI models (such as GPT-3): AI models that generate educational games based on analysis results.

[1620] Server (backend system using web frameworks such as Django): Analyzes user information and emotional data, and generates and transmits educational games.

[1621] Examples of concrete examples and prompts

[1622] For example, if a user is interested in fashion and has recently purchased a T-shirt, jeans, and sneakers, the server will generate a fashion quiz game based on this information. If the emotional data shows a high level of concentration and is positive, the server will present slightly more difficult questions. Each time the user answers correctly, the server will provide incentives such as discount coupons.

[1623] Example prompt sentence:

[1624] "The user is interested in fashion and recently purchased a t-shirt, jeans, and sneakers. Their sentiment data is positive and shows high concentration. Use this information to generate a fashion-related quiz."

[1625] In this way, the system of the present invention generates educational games based on the user's learning style, interests, and emotions, allowing the user to enjoy learning while engaging in purchasing activities, which is expected to improve the user's purchasing experience and increase learning effectiveness.

[1626] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1627] Step 1:

[1628] Entering and retrieving user information

[1629] The device provides an interface for users to input information about their learning style and interests. Users input their purchasing history, favorite subjects, hobbies, etc. The device also uses the Emotion Engine to collect real-time emotional data from the user's facial expressions and voice. The input data consists of user information (learning style, interests, purchasing history) and emotional data (facial expression recognition, voice analysis). This data is temporarily stored inside the device.

[1630] Step 2:

[1631] Sending information

[1632] The device sends the temporarily saved user information and emotion data to the server. Specifically, the user information and emotion data are packaged in JSON format and sent to the server via an HTTPS request. The input is user information and emotion data, and the output is data sent to the server.

[1633] Step 3:

[1634] Analysis of information

[1635] The server analyzes the received user information and emotional data. This analysis uses a generative AI model (e.g., GPT-3). As a result of the analysis, the server extracts the user's learning style, interests, stress level, and concentration level. The input is user information and emotional data, and the output is the analysis results (learning style, interests, and emotional state).

[1636] Step 4:

[1637] Educational Game Generation

[1638] The server generates an educational game based on the analysis results. A generative AI model is used for this. For example, if the user is interested in fashion, a fashion quiz is generated. The game difficulty and support messages are also adjusted based on the emotional data. The input is the analysis results, and the output is the generated educational game data.

[1639] Step 5:

[1640] Educational Game Submission

[1641] The server sends the generated educational game data to the device using the HTTPS protocol. The input is educational game data, and the output is game data sent to the device.

[1642] Step 6:

[1643] View and play games

[1644] The device displays the educational game to the user. The user plays the game and answers questions. Specifically, the device records the user's choices and answer times. The input is educational game data, and the output is user play data.

[1645] Step 7:

[1646] Collection and transmission of play data

[1647] The device collects the user's play data in real time and sends it to the server. The play data includes the user's choices, response time, correct and incorrect answers, etc. The input is the user's play data, and the output is the play data sent to the server.

[1648] Step 8:

[1649] Data reanalysis and game optimization

[1650] The server reanalyzes the received play data and emotional data and uses it to optimize the next educational game. It uses a generative AI model to provide feedback to adjust the game's content and difficulty. The input is play data and emotional data, and the output is an optimized educational game.

[1651] Step 9:

[1652] Offering incentives

[1653] The server provides incentives to users based on the results of the educational game. Specifically, it generates discount coupons according to the number of questions answered correctly and sends them to the terminal. The input is the results of the educational game, and the output is the incentive (discount coupon).

[1654] 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.

[1655] 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.

[1656] 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 robot 414.

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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).

[1661] 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.

[1662] 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."

[1663] 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.

[1664] 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).

[1665] 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.

[1666] 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.

[1667] 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.

[1668] 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.

[1669] 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.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] 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.

[1675] The following is further disclosed regarding the above embodiment.

[1676] (Claim 1)

[1677] a means of obtaining information about the user's learning style and interests;

[1678] means for transmitting the information to a server;

[1679] means for receiving said information and analyzing the user's learning style and interests;

[1680] means for generating an educational game based on the analysis results;

[1681] means for transmitting the educational game to a terminal;

[1682] means for displaying said educational game for a user to play;

[1683] means for collecting play data of the user and transmitting it to a server;

[1684] and optimizing the next educational game based on the play data.

[1685] (Claim 2)

[1686] 10. The system of claim 1, wherein the generated educational games correspond to multiple subjects, such as mathematics and English.

[1687] (Claim 3)

[1688] 10. The system of claim 1, wherein the system generates an educational game that includes story elements that are customized based on a user's interests.

[1689] "Example 1"

[1690] (Claim 1)

[1691] a means of obtaining information about the user's learning style and interests;

[1692] means for transmitting the information to a server;

[1693] means for receiving said information and analyzing the user's learning style and interests using a generative AI model;

[1694] means for generating educational content based on the analysis results;

[1695] means for transmitting the educational content to a terminal;

[1696] means for displaying said educational content so that it can be played by a user;

[1697] means for collecting play data of the user and transmitting it to a server;

[1698] A system including a means for optimizing the next educational content based on the play data.

[1699] (Claim 2)

[1700] 10. The system of claim 1, wherein the generated educational content corresponds to a plurality of subject areas.

[1701] (Claim 3)

[1702] 10. The system of claim 1, wherein the system generates educational content that includes story elements that are customized based on a user's interests.

[1703] "Application Example 1"

[1704] (Claim 1)

[1705] a means of obtaining information about the user's learning style and interests;

[1706] means for transmitting the information to a server;

[1707] means for receiving said information and analyzing the user's learning style and interests;

[1708] means for generating an educational game based on the analysis results;

[1709] means for transmitting the educational game to a terminal;

[1710] means for displaying said educational game for a user to play;

[1711] means for collecting play data of the user and transmitting it to a server;

[1712] A means for optimizing a next educational game based on the play data;

[1713] A way to offer educational games based on learning styles and interests to customers visiting brick-and-mortar stores.

[1714] and means for providing rewards that can be obtained by playing the educational game.

[1715] (Claim 2)

[1716] 10. The system of claim 1, wherein the generated educational games correspond to multiple subject areas, such as mathematics and language.

[1717] (Claim 3)

[1718] 10. The system of claim 1, wherein the system generates an educational game that includes story elements that are customized based on a user's interests.

[1719] (Claim 4)

[1720] 2. The system according to claim 1, wherein the reward is a discount coupon or points.

[1721] "Example 2: Combining Emotion Engines"

[1722] (Claim 1)

[1723] a means of obtaining information about the user's learning style and interests;

[1724] means for transmitting the information to a server;

[1725] means for receiving said information and analyzing the user's learning style and interests;

[1726] A means of collecting user sentiment data in real time;

[1727] means for generating an educational game based on the analysis results and emotion data;

[1728] means for transmitting the educational game to a terminal;

[1729] means for displaying said educational game for a user to play;

[1730] means for collecting play data and emotion data of the user and transmitting the data to a server;

[1731] a means for optimizing a next educational game based on the play data and emotion data;

[1732] A means to reflect the optimization of educational games in the generative AI model for future games,

[1733] A system including:

[1734] (Claim 2)

[1735] 10. The system of claim 1, wherein the generated educational games correspond to multiple subject areas, such as mathematics and language.

[1736] (Claim 3)

[1737] 10. The system of claim 1, which generates educational games that include story elements customized based on a user's interests and difficulty adjustments and messages depending on the user's emotions.

[1738] "Application example 2 when combining emotion engines"

[1739] (Claim 1)

[1740] a means of obtaining information about the user's learning style and interests;

[1741] means for transmitting the information to a server;

[1742] means for receiving said information and analyzing the user's learning style and interests;

[1743] means for generating an educational game based on the analysis results;

[1744] means for transmitting the educational game to a terminal;

[1745] means for displaying said educational game for a user to play;

[1746] means for collecting the user's emotion data in real time and transmitting it to a server;

[1747] means for collecting play data of the user and transmitting it to a server;

[1748] a means for optimizing a next educational game based on the play data and emotion data;

[1749] and means for providing an incentive based on the outcome of said educational game.

[1750] (Claim 2)

[1751] 10. The system of claim 1, wherein the generated educational games correspond to multiple subjects, such as mathematics and English.

[1752] (Claim 3)

[1753] 10. The system of claim 1, wherein the system generates an educational game that includes story elements that are customized based on a user's interests. [Explanation of symbols]

[1754] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of obtaining information about the user's learning style and interests; means for transmitting the information to a server; means for receiving said information and analyzing the user's learning style and interests; means for generating an educational game based on the analysis results; means for transmitting the educational game to a terminal; means for displaying said educational game for a user to play; means for collecting play data of the user and transmitting it to a server; and optimizing the next educational game based on the play data.

2. The system of claim 1 , wherein the generated educational games correspond to multiple subjects, such as mathematics and English.

3. The system of claim 1 , which generates educational games that include story elements that are customized based on a user's interests.

Images