System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting user preferences and learning styles; means for storing the collected user data; means for generating personalized learning materials based on the stored data; and means for transmitting the generated learning materials to the user's terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional learning materials are unable to accommodate the individual needs and preferences of various learners, such as children, working adults, and the elderly, making it difficult for each learner to study effectively. Furthermore, they cannot be flexibly adjusted according to the learner's level of understanding and learning progress, which can reduce learning effectiveness. The purpose of this invention is to solve these problems and support effective learning by providing optimal learning materials according to the learner's individual needs and preferences. [Means for solving the problem]

[0005] The present invention is a system that includes a means for collecting user preferences and learning styles, a means for saving the collected user data, a means for generating individually customized learning materials based on the saved data, and a means for transmitting the generated learning materials to the user's device. Furthermore, in generating the learning materials, the level of difficulty of the text, the frequency of use of images, the style of the images, the characteristics of the voices, and the characteristics of the explanatory characters can be customized. This system can provide learning materials that meet the individual needs and preferences of each user, thereby improving learning effectiveness. Furthermore, by further including a means for collecting feedback from users and adjusting the learning materials based on the collected feedback, flexible adjustments can be made according to the learner's progress and level of understanding.

[0006] "User" refers to an individual or organization that uses this system to study.

[0007] "Preferences" refer to the tastes and preferences that a user has for particular learning materials.

[0008] "Learning style" refers to the method, format, or technique in which a user learns most effectively.

[0009] "Means of collection" refers to mechanisms such as questionnaires and sensors for obtaining information about users' preferences and learning styles.

[0010] "Storage means" refers to a database or storage device for storing collected data on user preferences and learning styles.

[0011] "Generative means" refers to generative AI models and algorithms that create individually customized learning materials based on collected and stored data.

[0012] "Transmission means" refers to the communication network and protocols used to transmit the generated learning materials to the user's terminal.

[0013] "Learning materials" refers to educational content such as texts, images, audio, and characters that users use for learning.

[0014] "Difficulty of the text" refers to the degree of difficulty in understanding the text provided as learning material.

[0015] "Image frequency" refers to an indicator of how frequently an image is used within the learning material.

[0016] "Image style" refers to the visual design or theme (e.g., anime-style, film-style) of the images used in the learning materials.

[0017] "Audio features" refer to the attributes of the audio used in the learning material (e.g., the voice quality and speaking style of the voice actor).

[0018] An "explanatory character" refers to a character who appears in the learning material and provides explanations and narration.

[0019] "Feedback" refers to opinions, impressions, and reports of improvements provided by users after learning.

[0020] "Adjustment" refers to the methods and processes used to improve or change learning materials or system behavior in the future based on the collected feedback. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] An embodiment of the present invention is a system for generating and providing individually customized learning materials that enable users to study effectively. The system includes multiple means for collecting user preferences and learning styles and generating materials that meet individual learning needs.

[0043] System Overview

[0044] Collecting user preferences and learning styles

[0045] 1. When a user accesses the system for the first time, a questionnaire is displayed on the screen, including questions about the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and preferences for the character who will be narrating.

[0046] 2. The terminal collects data from the user's responses to the questionnaire and sends it to the server.

[0047] Store and manage user data

[0048] 3. The server stores the received survey data in a database, along with the user's profile information.

[0049] Generate customized learning materials

[0050] 4. The server uses a generative AI model (e.g., GPT-4 (registered trademark) or an image generation model) to generate learning materials based on the collected user data. Specifically, it customizes the following elements:

[0051] Text content according to the level of difficulty

[0052] Image styles to suit user preferences (anime, movie, etc.)

[0053] Generate voices with your chosen voice actor

[0054] Explanation animation by user-defined characters

[0055] Delivery of learning materials

[0056] 5. The server consolidates the generated learning materials and sends them to the terminal as a package.

[0057] 6. The device displays the received learning material on the screen and plays the audio.

[0058] Specific examples

[0059] Example 1: History lessons for junior high school students

[0060] 1. A user (Mr. Tanaka, a junior high school student) accesses the system for the first time. A questionnaire appears on the screen, and Mr. Tanaka answers as follows:

[0061] Level of difficulty: Junior high school level

[0062] Image usage frequency: High

[0063] Image Style: Cinematic

[0064] Voice characteristics: Male voice actor B

[0065] Description Character: Ancient Roman soldier style

[0066] 2. The device sends the collected data to the server, which stores it in a database.

[0067] 3. The server uses the generative AI model to generate a history textbook for junior high school students that makes extensive use of cinematic-style imagery, then audio-records it in the voice of voice actor B and creates an animation featuring characters resembling ancient Roman soldiers.

[0068] 4. The server consolidates the generated learning materials and sends them to the terminal.

[0069] 5. The device displays the learning material on Tanaka's screen and plays the audio. Tanaka learns the history content while watching movie-style images and listening to the audio and character explanations as he progresses through his studies.

[0070] Example 2: Health education for the elderly

[0071] 1. The user (an elderly person named Suzuki) accesses the system and answers the displayed questionnaire as follows:

[0072] Difficulty of the text: Easy

[0073] Image Frequency: Medium

[0074] Picture Style:Realistic

[0075] Voice characteristics: Female voice actor A

[0076] Description Character: Modern doctor style

[0077] 2. The device sends the data to the server, which stores it.

[0078] 3. The server uses the generative AI model to generate gently worded text using realistic images, creates audio in the voice of female voice actor A, and generates explanations by a character that looks like a modern doctor.

[0079] 4. The server consolidates these learning materials and sends them to the terminal.

[0080] 5. The device displays the learning materials on Suzuki's screen and plays the audio. Suzuki learns health knowledge while looking at realistic images and listens to the audio explanations.

[0081] As described above, this system can provide learning materials that are individually tailored to each user's preferences and learning style, enabling effective learning. This allows for high learning efficiency and satisfaction that could not be achieved with conventional, uniform learning materials.

[0082] The processing flow will be explained below.

[0083] Step 1:

[0084] A user accesses the learning system for the first time. Upon access, a questionnaire about preferences and learning styles is displayed as an initial setting.

[0085] Step 2:

[0086] The device displays a survey form to the user, which the user answers, including the following items:

[0087] Difficulty of the text

[0088] Image frequency

[0089] Image Style

[0090] Audio Features

[0091] Description Character Preferences

[0092] Step 3:

[0093] The user answers the questionnaire form and presses the send button. The response data is collected and sent to the system by the terminal.

[0094] Step 4:

[0095] The device sends the collected survey data to the server, encoded in an appropriate format such as JSON.

[0096] Step 5:

[0097] The server stores the received survey data in a database, along with the user's profile information (ID, name, etc.).

[0098] Step 6:

[0099] The server invokes a generative AI model (e.g., GPT-4) to generate customized training text based on the stored user data.

[0100] Step 7:

[0101] The server invokes an image generation process to generate an image in the style selected by the user (e.g., film style, anime style), using an image generation model such as DALL-E.

[0102] Step 8:

[0103] The server invokes a speech generation process to convert the training text into a voice of the voice actor selected by the user, specifically, a Text-to-Speech (TTS) engine.

[0104] Step 9:

[0105] The server invokes the character generation process, which generates a character based on the character style selected by the user (e.g., ancient Roman soldier, modern doctor).

[0106] Step 10:

[0107] The server integrates the generated text, images, audio, and character animations and packages them as learning materials.

[0108] Step 11:

[0109] The server sends the integrated learning material package to the terminal, using a communication protocol such as the Internet.

[0110] Step 12:

[0111] The device displays the received learning material on the user's screen and plays the audio. Images, text, audio, and characters are arranged and played appropriately, and the user can begin learning.

[0112] Step 13:

[0113] After studying, users provide feedback, including the quality of the learning material, their level of understanding, and changes in their preferences.

[0114] Step 14:

[0115] The device collects feedback data and sends it to a server, which stores it in a database and uses it to generate future learning materials.

[0116] The above are the specific processing steps of the system based on the claims. Through these steps, learning materials tailored to individual user needs and preferences can be efficiently generated and provided.

[0117] Example 1

[0118] 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."

[0119] Conventional learning systems often provide uniform learning materials and are unable to accommodate individual users' preferences and learning styles, resulting in reduced learning efficiency and difficulty in improving user satisfaction. Furthermore, there is a lack of means to generate and appropriately distribute learning materials optimized for each user, making it difficult to provide an effective learning experience.

[0120] 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.

[0121] In this invention, the server includes means for collecting user preferences and learning styles, means for storing the collected user data, means for generating customized learning materials based on the user data using a generative AI model, means for transmitting the generated learning materials to the user's terminal, and means for displaying and playing the integrated learning materials on the user's terminal, thereby providing learning materials optimized according to each user's preferences and learning style, enabling effective learning.

[0122] "User preferences and learning styles" refer to the user's personal learning preferences and the methods and formats that maximize learning efficiency.

[0123] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to automatically generate learning materials such as text, images, audio, and animations based on user data.

[0124] A "prompt sentence" refers to an input sentence given to a generative AI model to generate the desired output.

[0125] "Learning materials" refers to information content such as text, images, audio, and animations that users use to study.

[0126] "Terminal" refers to the device (computer, smartphone, tablet, etc.) that a user uses to access the system and view and use learning materials.

[0127] "Server" refers to a computer system that processes and stores data sent by users, distributes generated learning materials, etc.

[0128] "Database" refers to a system or structure for storing and managing collected data such as user preferences, learning styles, and survey results.

[0129] "Feedback" refers to the evaluations and opinions provided by users after using learning materials, and is used to adjust the quality and content of the learning materials based on this.

[0130] A "survey" refers to a collection of questions presented to a user to gather information about their preferences and learning style.

[0131] An embodiment of the present invention is a system for generating and providing individually customized learning materials that enable users to study effectively. The system includes multiple means for collecting user preferences and learning styles and generating materials that meet individual learning needs.

[0132] The main components of this system are the user device, the server, and the generative AI model. Specific examples of devices include smartphones, tablets, and PCs, while the server is a cloud server or dedicated server. GPT-4 and an image generation model are used as generative AI models.

[0133] Collecting user preferences and learning styles

[0134] When users first access the system, they are presented with a survey screen, which includes the following items:

[0135] Difficulty level of the text (e.g. elementary school, junior high school, high school)

[0136] Frequency of image use (e.g. low, medium, high)

[0137] Image style (e.g., anime, film, realistic)

[0138] Voice characteristics (e.g. male voice actor A, female voice actor B)

[0139] Describe the character's preference (e.g., Roman soldier, modern doctor)

[0140] The user answers these questions and sends the survey data from the terminal to the server using a communication method such as an HTTP request.

[0141] Store and manage user data

[0142] The server stores the received survey data in a database, which contains the user's profile information and survey responses.

[0143] Generate customized learning materials

[0144] The server generates customized learning materials using a generative AI model based on the received data. This generation process includes inputting prompt sentences into the generative AI model.

[0145] An example of a specific prompt is as follows:

[0146] "Please explain a history lesson for junior high school students using movie-style images in the voice of male voice actor B. I also need an animation featuring a character that looks like an ancient Roman soldier."

[0147] The generative AI model generates text, images, audio, and animations based on the prompts, and the generated content is collected on a server and integrated into a learning package.

[0148] Delivery and display of learning materials

[0149] The server then sends the generated learning package to the terminal, which then displays the received learning material to the user and plays audio as needed.

[0150] Specific examples

[0151] A specific example of this system is shown below.

[0152] Example 1: History lessons for junior high school students

[0153] A user (a junior high school student) accesses the system for the first time and answers a questionnaire as follows:

[0154] Level of difficulty: Junior high school level

[0155] Image usage frequency: High

[0156] Image Style: Cinematic

[0157] Voice characteristics: Male voice actor B

[0158] Description Character: Ancient Roman soldier style

[0159] The device sends the collected data to a server, which stores it in a database. The server uses a generative AI model to generate learning materials based on the above settings and creates a learning package. This package is sent to the device. The device displays the received learning materials on the screen and plays audio. The user learns the historical content while watching movie-style images and listening to audio and character explanations as they progress through their studies.

[0160] Example 2: Health education for the elderly

[0161] A user (senior citizen) accesses the system and answers the questionnaire as follows:

[0162] Difficulty of the text: Easy

[0163] Image Frequency: Medium

[0164] Picture Style:Realistic

[0165] Voice characteristics: Female voice actor A

[0166] Description Character: Modern doctor style

[0167] The device sends the data to the server, which stores it. The server uses a generative AI model to generate gently worded text using realistic images, creates audio in the voice of female voice actor A, and generates explanations by a character that looks like a modern doctor. These learning materials are then integrated and sent to the device. The device then displays the received learning materials on its screen and plays the audio. The user learns health knowledge while viewing realistic images and receives explanations while listening to the audio.

[0168] In this way, the system can individually accommodate each user's preferences and learning style, promoting effective learning.

[0169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0170] Step 1: The user accesses the system.

[0171] Input: User access (e.g., typing a URL in a web browser).

[0172] Output: Display of the survey screen.

[0173] Specific operation: The user accesses the system's URL using a browser on a smartphone or PC.

[0174] Step 2: The device will display the survey screen.

[0175] Input: The system's web page request.

[0176] Output: Display of the survey screen.

[0177] Specific operation: The device receives HTML data from the server and displays a questionnaire screen to the user. The questionnaire includes questions about the difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and preferences for explanatory characters.

[0178] Step 3: The user completes the survey.

[0179] Input: User's survey responses.

[0180] Output: User response data.

[0181] Specific operation: The user enters the answer to the questionnaire item and presses the submit button. At this point, the response data is collected on the device.

[0182] Step 4: The terminal transmits the user response data to the server.

[0183] Input: User response data.

[0184] Output: Sending data to the server.

[0185] Specific operation: The device sends the collected response data to the server using an HTTP request or WebSocket.

[0186] Step 5: The server receives the survey data and stores it in a database.

[0187] Input: User response data sent from the device.

[0188] Output: Confirmation of saving to database.

[0189] Specific operation: The server analyzes the received survey data and executes an INSERT statement to the corresponding user record in the database to save it.

[0190] Step 6: The server generates a prompt sentence based on the user data and inputs it into the generative AI model.

[0191] Input: User data.

[0192] Output: Prompt sentence and learning material.

[0193] Specific operation: The server generates prompts based on the user's preferences and learning style. For example, a sentence like "Please explain history for junior high school students using movie-style images in the voice of male voice actor B. An animation featuring characters resembling ancient Roman soldiers is also required." is input into the generative AI model.

[0194] Step 7: The generative AI model generates customized learning materials.

[0195] Input: The prompt text sent by the server.

[0196] Output: Customized text, images, audio, animation.

[0197] Specific operation: The generative AI model generates text, images, audio, and animation based on the prompt. For example, GPT-4 generates text, the image generation model generates images, and the speech synthesis model generates audio.

[0198] Step 8: The server integrates the generated learning materials and creates a learning package.

[0199] Input: Multiple learning materials (text, images, audio, animation) from a generative AI model.

[0200] Output: A learning package.

[0201] Specific operation: The server combines each generated material into a single learning package and creates a JSON file to manage metadata.

[0202] Step 9: The server sends the learning package to the terminal.

[0203] Input: Learning package.

[0204] Output: Sending data to the terminal.

[0205] Specific operation: The server sends the learning package to the device using HTTP responses or WebSockets.

[0206] Step 10: The terminal receives the learning package and displays and plays it for the user.

[0207] Input: The learning package sent from the server.

[0208] Output: Screen display and audio playback.

[0209] What it does: The device analyzes the received learning package, displays text and images on the screen, plays audio files, and displays animations on the screen.

[0210] (Application example 1)

[0211] 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."

[0212] Conventional online shopping systems lack the ability to customize services to suit individual user preferences and styles, making it difficult to enhance user satisfaction. In particular, the lack of personalized recommendations that reflect each user's unique shopping style and product preferences is an obstacle to improving the user experience.

[0213] 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.

[0214] In this invention, the server includes means for collecting user preferences and shopping styles, means for storing the collected user data, means for generating individually customized product recommendations based on the stored data, means for transmitting the generated product recommendations to the user's terminal, means for collecting feedback regarding the product recommendations, and means for adjusting the product recommendations based on the collected feedback, thereby enabling personalized product recommendations based on the user's individual preferences and styles.

[0215] "User preferences and shopping style" refers to the user's tastes and purchasing behavior, product categories of interest, purchasing budget, color and design preferences, and the like.

[0216] "Collection Methods" means systems and methods for obtaining user data through surveys or automated behavioral tracking.

[0217] "Storage means" refers to a system or method for storing and managing collected user data in a storage device such as a database.

[0218] "Means for generating customized product recommendations" means a system or method for creating individually optimized product listings and related information based on collected and stored user data.

[0219] "Transmission means" refers to a network communication means or method for delivering the generated product recommendation information to the user's terminal.

[0220] "Feedback collection means" means a system or method that provides a form or interface for collecting user-provided opinions or ratings.

[0221] "Adjustment" refers to systems and methods for optimizing product recommendation content and algorithms based on collected feedback.

[0222] A "generative AI model" is an artificial intelligence model used for natural language processing, image generation, etc., and includes advanced machine learning algorithms such as GPT-4 and DALL-E.

[0223] A "prompt" refers to a text instruction entered into a generative AI model to cause it to generate a particular output.

[0224] System Overview

[0225] This invention is a virtual shopping system that provides individually customized product recommendations based on a user's preferences and shopping style. The system includes the following major components: means for collecting user preferences and shopping style, means for storing the collected user data, means for generating individually customized product recommendations based on the stored data, means for transmitting the generated product recommendations to the user's terminal, means for collecting feedback regarding the product recommendations, and means for adjusting the product recommendations based on the collected feedback.

[0226] Collecting user preferences and shopping styles

[0227] 1. When a user accesses the system for the first time, a shopping survey is displayed on the screen.

[0228] Questionnaire questions include preferred colors, styles, budget ranges, and areas of interest.

[0229] The user responds to the survey.

[0230] 2. The terminal collects the questionnaire data answered by the user and sends it to the server.

[0231] Store and manage user data

[0232] 3. The server stores the received survey data in a database (e.g., MySQL (registered trademark)). User profile information is also recorded.

[0233] Generating customized product recommendations

[0234] 4. The server uses a generative AI model (e.g., GPT-4, image generation model DALL-E) to generate product recommendations based on the collected user data.

[0235] Specifically, customize the following elements:

[0236] A list of products that match the user's preferences

[0237] Recommended product images (anime style, realistic style, etc.)

[0238] Audio explanation of the product

[0239] Animated introduction using characters created by the user

[0240] Product recommendation delivery

[0241] 5. The server consolidates the generated product recommendations and sends them to the terminal as a package.

[0242] 6. The device displays the received product recommendation on the screen and plays it back as audio.

[0243] Collecting and adjusting feedback on product recommendations

[0244] 7. The device collects feedback from the user and sends it to the server.

[0245] 8. The server optimizes the content and algorithm of product recommendations based on the collected feedback.

[0246] Specific examples

[0247] Example 1: Fashion item recommendation

[0248] 1. A user (e.g., Mr. A) accesses the system for the first time and answers a questionnaire.

[0249] "Favorite color: Blue, Style: Casual, Budget: Under 10,000 yen, Interests: Sneakers"

[0250] 2. The device sends the collected data to the server, which stores it in a database.

[0251] 3. The server uses the generative AI model to generate product lists and images based on the following prompt:

[0252] "Generate a list of recommended fashion items based on user A's preferences. Style is casual, color is blue, and budget is under 10,000 yen."

[0253] "Create anime-style product images based on the generated product list."

[0254] 4. The server sends the generated product recommendation package to the terminal, which displays it to the user and explains it aloud.

[0255] 5. The user reviews the recommended products and provides feedback.

[0256] 6. The device sends feedback to the server, which then adjusts the algorithm based on that feedback.

[0257] The system can provide a personalized shopping experience that reflects a user's individual tastes and style.

[0258] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0259] Step 1:

[0260] When a user accesses the system for the first time, a shopping questionnaire is displayed on the terminal. The user answers questions about their preferred colors, styles, budget range, areas of interest, etc. The input information is basic data for making personalized recommendations for the user. The terminal collects the questionnaire data answered by the user. Input: User's questionnaire answers. Output: Collected questionnaire data.

[0261] Step 2:

[0262] The terminal sends the collected survey data to the server. The server verifies the received survey data and stores it in a database (e.g. MySQL). The stored data also includes user profile information. Input: Survey data. Output: User data stored in the database.

[0263] Step 3:

[0264] The server uses a generative AI model (e.g., GPT-4) to generate product recommendations based on the collected and stored user data. Specifically, it uses the stored data as input and issues prompts to the AI ​​model to generate a product list.

[0265] Example prompt sentence:

[0266] "Generate a list of recommended products based on user A's preferences. Style is casual, color is blue, and budget is under 10,000 yen."

[0267] Input: saved user data, prompt text. Output: generated product list.

[0268] Step 4:

[0269] The server generates customized product images based on the product list using an image generation model (e.g., DALL-E).

[0270] Example prompt sentence:

[0271] "Create anime-style product images based on the generated product list."

[0272] Input: Product list, prompt. Output: Generated product images.

[0273] Step 5:

[0274] The server combines the generated product list and product images and sends them as a package to the terminal. The terminal displays the received product recommendations on the screen and plays back audio descriptions using the speech generation model. Input: Product list and product images. Output: Product recommendations displayed on the terminal and audio descriptions.

[0275] Step 6:

[0276] The user reviews the displayed product recommendations and provides feedback based on their purchasing intentions and interests. The terminal collects the user's feedback. Input: User's feedback. Output: Collected feedback.

[0277] Step 7:

[0278] The device sends the collected feedback to the server, which makes adjustments to optimize the product recommendation algorithm and content based on the received feedback. Input: User feedback. Output: Adjusted product recommendation algorithm and data.

[0279] Through the above processing steps, personalized product recommendations based on the user's preferences are provided.

[0280] 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.

[0281] An embodiment of the present invention is a system that provides individually customized learning materials to enable users to study effectively, recognizes users' emotions in real time, and adjusts the learning materials appropriately based on that information. The system collects users' preferences, learning styles, and emotions, and generates and provides optimal educational content based on this information.

[0282] System Overview

[0283] Collecting user preferences and learning styles

[0284] 1. When a user first accesses the system, they are presented with a questionnaire about their preferences and learning style, including the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and the preference for narrators.

[0285] 2. The terminal collects data from the user's responses to the questionnaire and sends it to the server.

[0286] Store and manage user data

[0287] 3. The server stores the received survey data in a database, along with the user's profile information.

[0288] Emotion Recognition and Data Collection

[0289] 4. The device uses devices such as a camera and microphone to collect emotional data in real time from the user's facial expressions and voice.

[0290] 5. The device analyzes the collected emotion data and uses an emotion engine to identify the user's current emotional state.

[0291] 6. The device sends the identified emotion data to the server.

[0292] 7. The server stores the received emotion data in a database.

[0293] Generate customized learning materials

[0294] 8. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate training materials based on the stored user data and emotion data. The generated training materials include the following elements:

[0295] Text content according to the level of difficulty

[0296] Image styles to suit user preferences (anime, movie, etc.)

[0297] Voice generated by selected voice actors

[0298] Explanation animation by user-defined characters

[0299] Delivery of learning materials

[0300] 9. The server consolidates the generated learning materials and sends them to the terminal as a package.

[0301] 10. The device displays the received learning material on the screen and plays the audio.

[0302] Dynamic Adjustment

[0303] 11. The device continues to collect emotional data in real time while learning, and if adjustments are needed to suit different conditions, it sends that information to the server.

[0304] 12. The server dynamically adjusts the content of the learning material based on the latest emotional data received and sends it back to the device.

[0305] Specific examples

[0306] Example 1: English language learning for primary school students

[0307] 1. A user (Mr. Sato, an elementary school student) accesses the system for the first time. He answers the questionnaire displayed on the screen with the following options: "Text difficulty: Elementary school-aged," "Image usage frequency: High," "Image style: Anime-style," "Audio characteristics: Child's voice," and "Explanatory character: Animal character."

[0308] 2. The terminal sends the survey data to the server, which stores the data in a database.

[0309] 3. The device uses a camera and microphone to collect emotional data from Sato's facial expressions and voice, and then uses an emotion engine to identify his emotional state.

[0310] 4. The device sends the emotion data to the server, which stores it in a database.

[0311] 5. Based on the saved data, the server generates English textbooks for elementary school students, featuring a wide range of cartoon-style images. The audio is recorded using a child's voice, and animated animal characters are created.

[0312] 6. The server consolidates the generated learning materials and sends them to the terminal.

[0313] 7. The device displays the learning material on Sato's screen and plays the audio.

[0314] 8. The device will collect emotional data while learning, and if Sato's emotions change, it will send that information to the server.

[0315] 9. The server dynamically adjusts the learning material as needed and sends it back to the device.

[0316] Example 2: History study for high school graduation exams

[0317] 1. A user (high school student named Tanaka) accesses the system and answers the questionnaire with the following options: "Text difficulty: for high school students," "Image use frequency: medium," "Image style: realistic," "Audio characteristics: male voice actor A," and "Explanatory character: historical figure-like."

[0318] 2. The terminal sends the survey data to the server, which stores the data in a database.

[0319] 3. The device uses a camera and microphone to collect emotion data from Tanaka's facial expressions and voice, and then uses an emotion engine to identify her emotional state.

[0320] 4. The device sends the emotion data to the server, which stores it in a database.

[0321] 5. Based on the saved data, the server generates a history textbook for high school students using realistic images. Voices are recorded by male voice actor A, and animations of characters resembling historical figures are created.

[0322] 6. The server consolidates the generated learning materials and sends them to the terminal.

[0323] 7. The device displays the learning material on Tanaka's screen and plays the audio.

[0324] 8. The device will collect emotional data while learning, and if Tanaka's emotions change, it will send that information to the server.

[0325] 9. The server dynamically adjusts the learning material as needed and sends it back to the device.

[0326] In this way, the present invention is a system that provides learning materials that are individually customized based on the user's preferences, learning style, and emotions, helping the user achieve high learning effectiveness. This provides a highly accurate learning experience that could not be achieved with conventional, uniform learning materials.

[0327] The processing flow will be explained below.

[0328] Step 1:

[0329] When a user first accesses the system, they are presented with a questionnaire about their preferences and learning style, including the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the audio, and their preference for explanatory characters.

[0330] Step 2:

[0331] The device collects the data of the user's responses to the survey and sends it to the server, encoded in an appropriate format such as JSON.

[0332] Step 3:

[0333] The server stores the received survey data in a database, including user profile information (ID, name, etc.).

[0334] Step 4:

[0335] The device uses devices such as a camera and microphone to collect emotional data in real time from the user's facial expressions and voice.

[0336] Step 5:

[0337] The device analyzes the collected emotion data and identifies the user's current emotional state using an emotion engine, which includes algorithms for facial and voice analysis.

[0338] Step 6:

[0339] The device sends the identified emotion data to the server, which is also encoded in an appropriate format such as JSON.

[0340] Step 7:

[0341] The server stores the received emotion data in a database, where it is linked to the user's profile.

[0342] Step 8:

[0343] The server invokes a generative AI model (e.g., GPT-4) to generate individually customized training text based on the stored user data and sentiment data.

[0344] Step 9:

[0345] The server invokes an image generation process to generate an image in the style selected by the user (e.g., film style, anime style), using an image generation model such as DALL-E.

[0346] Step 10:

[0347] The server invokes a speech generation process to translate the training text into a voice of the selected voice actor, specifically, using a Text-to-Speech (TTS) engine.

[0348] Step 11:

[0349] The server invokes a character generation process to generate a character based on the character style selected by the user (e.g., an ancient Roman soldier or a modern doctor).

[0350] Step 12:

[0351] The server integrates the generated text, images, audio, and character animations and packages them as learning materials.

[0352] Step 13:

[0353] The server sends the integrated learning material package to the terminal, using a communication protocol such as the Internet.

[0354] Step 14:

[0355] The device displays the received learning material on the user's screen and plays the audio. Images, text, audio, and characters are arranged and played appropriately, and the user can begin learning.

[0356] Step 15:

[0357] The device continues to collect emotional data in real time while learning, and if the user's emotional state changes, the data is also sent to the server.

[0358] Step 16:

[0359] The server dynamically adjusts the learning material based on the latest emotional data it receives, for example, by adding more engaging content or images if the user is losing interest.

[0360] Step 17:

[0361] The server then sends the modified or adjusted learning material back to the device, which then displays the new material and plays the audio.

[0362] In this way, the system supports effective learning by providing and dynamically adjusting learning materials that are individually customized based on the user's preferences, learning style, and even emotional state.

[0363] Example 2

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

[0365] Conventional learning systems have difficulty customizing learning materials to suit individual users' preferences and learning styles, and have been unable to provide appropriate learning materials according to the user's emotional state. This has resulted in problems with users not being able to fully achieve their learning goals.

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

[0367] In this invention, the server includes means for collecting user preferences and learning styles, means for saving the collected user data, means for collecting emotional data from the user's facial expressions and voice using devices such as a camera and microphone and analyzing the emotional data, means for saving the collected emotional data, means for using a generative AI model to generate individually customized learning materials based on the saved user data and emotional data, means for transmitting the generated learning materials to the user's device, and means for collecting emotional data in real time even during learning and dynamically adjusting the learning materials, thereby making it possible to provide optimal learning materials according to the user's preferences and emotional state.

[0368] "User preferences and learning style" refers to the user's preferred content format, difficulty level, frequency of use, visual and auditory elements, and preferred learning methods.

[0369] "Customized learning materials" refers to educational content generated based on a user's preferences, learning style, and real-time emotional data.

[0370] "Emotional Data" refers to data about a user's current emotional state collected from the user's facial expressions and voice using devices such as a camera or microphone.

[0371] "Generative AI models" refer to artificial intelligence algorithms that generate learning materials based on collected user and emotional data. Specifically, they include AI models that perform natural language processing and image generation.

[0372] "Means for dynamic adjustment" refers to the function of analyzing the user's emotional data in real time and updating or changing the content of the learning material as needed.

[0373] "Terminal" refers to any device that a user accesses, including, for example, a PC, smartphone, or tablet.

[0374] "Server" refers to a remote computer system that stores and processes user data and sentiment data, including databases and infrastructure for running AI models.

[0375] "Survey data" refers to the response data to questions about preferences and learning styles that users answer when they first access the system.

[0376] An "emotion engine" refers to software or algorithms that analyze user data acquired through a camera or microphone and identify their emotional state.

[0377] The embodiment of the present invention is a system that provides individually customized learning materials to enable users to study effectively, recognizes the user's emotions in real time, and adjusts the learning materials appropriately based on that information. This system is described in detail below.

[0378] Collecting user preferences and learning styles

[0379] When a user first accesses the system, the device displays a questionnaire about preferences and learning style through a user interface. This questionnaire includes the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and the preference of explanatory characters. When the user answers the questionnaire, the device collects the data and sends it to a server. The device uses a user interface that runs on a web browser or a mobile app.

[0380] Store and manage user data

[0381] The server stores the received survey data in a relational database (e.g., MySQL, PostgreSQL), and also records user profile information.

[0382] Emotion Recognition and Data Collection

[0383] The device uses a camera and microphone to collect emotion data from the user's facial expressions and voice in real time. The devices used here include a PC's built-in camera, an external webcam, and a microphone. The collected emotion data is analyzed by the device, and the user's emotional state is identified using an emotion engine (e.g., Microsoft® Azure® Face API, Google® Cloud Speech-to-Text API). The identified emotion data is sent from the device to a server, which stores it in a database.

[0384] Generate customized learning materials

[0385] The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate training materials based on the stored user data and emotion data. The generated training materials include the following elements:

[0386] Text content according to the level of difficulty

[0387] Image styles to suit user preferences (anime, movie, etc.)

[0388] Voice generated by selected voice actors

[0389] Explanation animation by user-defined characters

[0390] Delivery of learning materials

[0391] The server integrates the generated learning materials and sends them as a package to the device, which then displays the received learning materials on the screen and plays the audio.

[0392] Dynamic Adjustment

[0393] The device continues to collect emotional data in real time while learning and sends it to the server. The server dynamically adjusts the content of the learning materials based on the latest emotional data and sends them back to the device. This allows the device to provide optimal learning materials according to the user's emotional state.

[0394] Specific examples

[0395] Example 1: English language learning for primary school students

[0396] 1. A user (elementary school student) accesses the system for the first time and answers the questionnaire with the following options: "Text difficulty: for elementary school students," "Frequency of image use: high," "Image style: anime-style," "Audio characteristics: child's voice," and "Explanatory character: animal character."

[0397] 2. The terminal sends the survey data to the server, which stores the data in a database.

[0398] 3. The device uses a camera and microphone to collect emotional data from facial expressions and voice, and then uses an emotion engine to identify the emotional state.

[0399] 4. The device sends the emotion data to the server, which stores it in a database.

[0400] 5. Based on the saved data, the server generates English textbooks for elementary school students, featuring a wide range of cartoon-style images. Audio is recorded using children's voices, and animations featuring animal characters are created.

[0401] 6. The server consolidates the generated learning materials and sends them to the terminal.

[0402] 7. The device displays the learning material on the screen and plays the audio.

[0403] 8. The device collects emotional data during learning and sends the information to the server as needed.

[0404] 9. The server dynamically adjusts the learning material and sends it back to the device.

[0405] Prompt Sentence Examples

[0406] "Generate an anime-style English learning textbook for elementary school students. Images should be used frequently, with children's voices and animal characters as explanatory characters."

[0407] Example 2: History study for high school graduation exams

[0408] 1. The user (high school student) accesses the system and answers the questionnaire with the following options: "Text difficulty: for high school students," "Image use frequency: medium," "Image style: realistic," "Audio characteristics: male voice actor," and "Explanatory character: historical figure style."

[0409] 2. The terminal sends the survey data to the server, which stores the data in a database.

[0410] 3. The device uses a camera and microphone to collect emotional data from facial expressions and voice, and then uses an emotion engine to identify the emotional state.

[0411] 4. The device sends the emotion data to the server, which stores it in a database.

[0412] 5. Based on the saved data, the server generates historical textbooks for high school students using realistic images. Audio is recorded by male voice actors, and animated characters that resemble historical figures are created.

[0413] 6. The server consolidates the generated learning materials and sends them to the terminal.

[0414] 7. The device displays the learning material on the screen and plays the audio.

[0415] 8. The device collects emotional data during learning and sends the information to the server as needed.

[0416] 9. The server dynamically adjusts the learning material and sends it back to the device.

[0417] Prompt Sentence Examples

[0418] "Generate a realistic history textbook for high school students. Images should be used moderately, audio should be provided by a male voice actor, and explanatory characters should look like historical figures."

[0419] In this way, the present invention is a system that provides learning materials that are individually customized based on the user's preferences, learning style, and emotions, helping the user achieve high learning effectiveness. This provides a highly accurate learning experience that could not be achieved with conventional, uniform learning materials.

[0420] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0421] Step 1: Collect user surveys

[0422] 1-1. The user accesses the system for the first time. The questionnaire includes questions about the difficulty of the text, the frequency of image use, the style of the image, the characteristics of the voice, and the preference for the explanatory character.

[0423] Input: The user answers the survey items.

[0424] Operation: A questionnaire screen is displayed and the user answers each item.

[0425] Output: User response data.

[0426] 1-2. The device collects the user's response data and sends it to the server.

[0427] Input: User response data.

[0428] Operation: The device sends the response data to the server.

[0429] Output: Survey data sent to the server.

[0430] Step 2: Save user data

[0431] 2-1. The server stores the received survey data in a relational database, such as MySQL or PostgreSQL.

[0432] Input: Survey data.

[0433] How it works: The server saves the survey data in a database.

[0434] Output: Survey data stored in a database.

[0435] 2-2. The server also records the user's profile information.

[0436] Input: User's personal information.

[0437] How it works: The server stores user profile information in a database.

[0438] Output: User profile information stored in a database.

[0439] Step 3: Collecting emotion data

[0440] 3-1. The device uses a camera and microphone to collect emotional data from the user's facial expressions and voice in real time. The devices used include the PC's built-in camera, an external webcam, and a microphone.

[0441] Input: User facial expressions and voice collected by camera and microphone.

[0442] What it does: Your device collects data through its camera and microphone.

[0443] Output: Collected emotion data.

[0444] 3-2. The device analyzes the collected emotion data and identifies the user's current emotional state using an emotion engine, such as the Microsoft Azure Face API or the Google Cloud Speech-to-Text API.

[0445] Input: Collected emotion data.

[0446] How it works: The emotion engine analyzes the emotion data and identifies the user's emotional state.

[0447] Output: Identified emotion data.

[0448] 3-3. The device sends the identified emotion data to the server.

[0449] Input: Identified emotion data.

[0450] Operation: The device sends emotion data to the server.

[0451] Output: Emotion data sent to the server.

[0452] 3-4. The server stores the received emotion data in a database.

[0453] Input: Emotion data.

[0454] How it works: The server stores emotion data in a database.

[0455] Output: Emotion data stored in a database.

[0456] Step 4: Generate customized learning materials

[0457] 4-1. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate learning materials based on the stored user data and emotion data.

[0458] Input: User data and emotion data.

[0459] How it works: The AI ​​model analyzes the data and generates optimal learning materials for the user.

[0460] Output: The generated learning material.

[0461] 4-2. The generated learning materials include the following elements:

[0462] Text content according to the level of difficulty

[0463] Image styles to suit user preferences (anime, movie, etc.)

[0464] Voice generated by selected voice actors

[0465] Explanation animation by user-defined characters

[0466] Input: Individual elements of user data (e.g. difficulty of text, frequency of image use, etc.).

[0467] How it works: The AI ​​model generates materials based on each element.

[0468] Output: Each element of the customized learning material.

[0469] Step 5: Deliver learning materials

[0470] 5-1. The server integrates the generated learning materials and sends them to the terminal as a package.

[0471] Input: Generated learning material.

[0472] How it works: The server collects the material into a single package and sends it to the device.

[0473] Output: The learning material package sent to the device.

[0474] 5-2. The device displays the received learning material on the screen and plays the audio.

[0475] Input: Received learning material package.

[0476] What it does: The device displays the material on the screen and plays the audio.

[0477] Output: Learning material that is visible and audible to the user.

[0478] Step 6: Dynamic adjustment

[0479] 6-1. The device continues to collect emotional data in real time even during learning, and if adjustments are needed to suit different conditions, it sends that information to the server.

[0480] Input: Emotion data collected in real time.

[0481] Operation: The device continues to collect emotion data and transmits it to the server.

[0482] Output: The latest emotion data sent to the server.

[0483] 6-2. The server dynamically adjusts the content of the learning material based on the latest emotional data received and sends it back to the device.

[0484] Input: Latest emotion data.

[0485] How it works: The server analyzes the emotion data and adjusts the learning material as needed.

[0486] Output: Dynamically adjusted learning material.

[0487] (Application example 2)

[0488] 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."

[0489] With current learning systems, it is difficult to customize learning materials to suit each user's preferences and learning style. It is also extremely difficult to grasp the user's emotional state in real time while learning and instantly adjust the learning materials. This results in problems such as users being unable to study effectively and reduced learning efficiency.

[0490] 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.

[0491] In this invention, the server includes means for collecting user preferences and learning styles, means for storing the collected user data, means for generating individually customized learning materials based on the stored data and the user's emotional data, means for transmitting the generated learning materials to the user's terminal, and means for collecting emotional data in real time during learning and dynamically adjusting the materials. This allows the server to provide individually customized learning materials, enabling users to achieve high learning effectiveness.

[0492] "Preferences" refer to the types and formats of learning content that a user particularly prefers.

[0493] "Learning style" refers to a particular learning method or approach that a user takes to effectively learn.

[0494] "Emotion data" is data that indicates the user's current emotional state, extracted from the user's facial expressions and voice.

[0495] "Customized learning materials" refers to learning content that is individually tailored to a user based on their preferences, learning style, and emotional data.

[0496] "Collecting in real time" means that data is collected continuously while the user is studying.

[0497] "Dynamic adjustment" refers to changing the content of learning materials on the fly based on collected data.

[0498] "Terminal" refers to a device used by a user, such as a smartphone or smart glasses.

[0499] "Server" refers to the central computing system that stores user data and generates and delivers learning materials.

[0500] System configuration explanation

[0501] The system of the present invention mainly includes means for collecting user preferences and learning styles, means for collecting emotional data in real time, means for generating individually customized learning materials based on the stored data and the user's emotional data, and means for transmitting the generated learning materials to a terminal.

[0502] Hardware and software used

[0503] The system uses the following hardware and software:

[0504] Device: The smartphone or smart glasses used by the user, including the camera, microphone, and other input devices.

[0505] Server: A high-performance computing system, either on cloud or on-premise, that stores user data and generates and delivers learning materials.

[0506] Emotion recognition software: Facial expression recognition libraries and voice analysis tools (e.g., EmotionRecognizer).

[0507] Generative AI models: High-performance text and image generation models such as GPT-4.

[0508] Program processing overview

[0509] 1. The device initially collects data by conducting a survey about the user's preferences and learning style.

[0510] 2. The device sends the collected data to the server, which stores it in a database.

[0511] 3. The device uses a camera and microphone to collect and analyze emotional data from the user's facial expressions and voice in real time.

[0512] 4. The device sends the analyzed emotion data to the server, which stores it in a database.

[0513] 5. The server generates customized learning materials using a generative AI model based on the stored user data and emotion data.

[0514] 6. The server sends the generated learning material to the terminal, which displays or plays it to the user.

[0515] 7. The device continues to collect emotional data in real time during training and transmits the information to the server as needed.

[0516] 8. The server dynamically adjusts the learning material based on the latest emotional data and sends it back to the device.

[0517] Specific examples

[0518] For example, when a user visits a store, they put on the smart glasses and the learning process proceeds as follows:

[0519] 1. Survey collection: The user answers the survey and enters information such as "Image usage frequency: high frequency," "Image style: realistic," and "Audio characteristics: male voice."

[0520] 2. Data storage: The survey results are sent to the server and stored in the database.

[0521] 3. Emotion data collection: The camera in the smart glasses captures facial expressions and analyzes them in real time.

[0522] 4. Learning material generation: The server uses the generative AI model to create customized learning content.

[0523] 5. Content delivery: The learning content is sent to the device and the user begins learning.

[0524] 6. Real-time adjustment: Materials are dynamically adjusted according to the user's emotional state.

[0525] Prompt Sentence Examples

[0526] "User profile: They frequently use realistic images and prefer characters with male voices."

[0527] "Sentiment data: Interest is currently waning. Use this information to provide more engaging content."

[0528] This system allows users to receive individually customized learning materials on the spot, resulting in higher learning effectiveness.

[0529] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0530] Step 1:

[0531] A user accesses the system using a terminal (smartphone or smart glasses). The terminal displays a questionnaire to the user about their preferences and learning style. The user answers the questionnaire and enters the data. The user's questionnaire data is entered into the terminal. The terminal collects this data and sends it to the server.

[0532] Step 2:

[0533] The server receives the survey data sent from the device. The received data is stored in a database. The server stores the user's profile information, as well as their preferences and learning style data, for a long period of time. The input is the survey data, and the output is the stored data.

[0534] Step 3:

[0535] The device collects the user's facial expressions and voice in real time using a camera and microphone. The collected data is analyzed using a facial expression recognition library and a voice analysis tool (e.g., EmotionRecognizer). The device then sends the analyzed emotion data to a server. The input is facial expression and voice data, and the output is the analyzed emotion data.

[0536] Step 4:

[0537] The server receives the emotion data sent from the device. The received data is stored in a database. The server identifies and records the user's current emotional state. The input is the emotion data, and the output is the stored emotion data.

[0538] Step 5:

[0539] The server generates customized learning materials using a generative AI model (e.g., GPT-4) based on the stored user data and emotional data. Learning content, such as text, images, and audio, is created based on prompts input to the generative AI model. The input is user data and emotional data, and the output is customized learning materials.

[0540] Step 6:

[0541] The server integrates the generated learning materials and sends them to the terminal. The learning materials are optimized for easy understanding by the user. The input is the generated learning materials, and the output is the learning materials delivered to the terminal.

[0542] Step 7:

[0543] The terminal receives learning materials sent from the server. The terminal displays and plays these materials to the user. The user then uses the customized learning materials to progress through their learning. The input is the delivered learning materials, and the output is the user's execution of the learning.

[0544] Step 8:

[0545] During training, the device continues to collect the user's facial expressions and voice in real time using a camera and microphone. If the emotional data changes, it sends that data to the server. The input is the continuously collected emotional data, and the output is the updated emotional data.

[0546] Step 9:

[0547] The server dynamically adjusts the learning materials accordingly based on the latest emotional data. The generative AI model is again used to update the content based on the new prompt. The input is the latest emotional data, and the output is the dynamically adjusted learning materials.

[0548] Step 10:

[0549] The server sends the adjusted learning materials back to the terminal. The terminal displays and plays these materials again to the user. The user continues learning adapted to the new conditions. The input is the adjusted learning materials, and the output is the user's continued learning.

[0550] This allows users to use individually customized learning materials and enjoy a learning environment that adapts in real time as they learn.

[0551] 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.

[0552] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0553] 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.

[0554] [Second embodiment]

[0555] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0556] 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.

[0557] 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).

[0558] 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.

[0559] 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.

[0560] 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).

[0561] 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. 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.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] In the smart glasses 214, 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.

[0566] 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."

[0567] An embodiment of the present invention is a system for generating and providing individually customized learning materials that enable users to study effectively. The system includes multiple means for collecting user preferences and learning styles and generating materials that meet individual learning needs.

[0568] System Overview

[0569] Collecting user preferences and learning styles

[0570] 1. When a user accesses the system for the first time, a questionnaire is displayed on the screen, including questions about the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and preferences for the character who will be narrating.

[0571] 2. The terminal collects data from the user's responses to the questionnaire and sends it to the server.

[0572] Store and manage user data

[0573] 3. The server stores the received survey data in a database, along with the user's profile information.

[0574] Generate customized learning materials

[0575] 4. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate learning materials based on the collected user data. Specifically, it customizes the following elements:

[0576] Text content according to the level of difficulty

[0577] Image styles to suit user preferences (anime, movie, etc.)

[0578] Generate voices with your chosen voice actor

[0579] Explanation animation by user-defined characters

[0580] Delivery of learning materials

[0581] 5. The server consolidates the generated learning materials and sends them to the terminal as a package.

[0582] 6. The device displays the received learning material on the screen and plays the audio.

[0583] Specific examples

[0584] Example 1: History lessons for junior high school students

[0585] 1. A user (Mr. Tanaka, a junior high school student) accesses the system for the first time. A questionnaire appears on the screen, and Mr. Tanaka answers as follows:

[0586] Level of difficulty: Junior high school level

[0587] Image usage frequency: High

[0588] Image Style: Cinematic

[0589] Voice characteristics: Male voice actor B

[0590] Description Character: Ancient Roman soldier style

[0591] 2. The device sends the collected data to the server, which stores it in a database.

[0592] 3. The server uses the generative AI model to generate a history textbook for junior high school students that makes extensive use of cinematic-style imagery, then audio-records it in the voice of voice actor B and creates an animation featuring characters resembling ancient Roman soldiers.

[0593] 4. The server consolidates the generated learning materials and sends them to the terminal.

[0594] 5. The device displays the learning material on Tanaka's screen and plays the audio. Tanaka learns the history content while watching movie-style images and listening to the audio and character explanations as he progresses through his studies.

[0595] Example 2: Health education for the elderly

[0596] 1. The user (an elderly person named Suzuki) accesses the system and answers the displayed questionnaire as follows:

[0597] Difficulty of the text: Easy

[0598] Image Frequency: Medium

[0599] Picture Style:Realistic

[0600] Voice characteristics: Female voice actor A

[0601] Description Character: Modern doctor style

[0602] 2. The device sends the data to the server, which stores it.

[0603] 3. The server uses the generative AI model to generate gently worded text using realistic images, creates audio in the voice of female voice actor A, and generates explanations by a character that looks like a modern doctor.

[0604] 4. The server consolidates these learning materials and sends them to the terminal.

[0605] 5. The device displays the learning materials on Suzuki's screen and plays the audio. Suzuki learns health knowledge while looking at realistic images and listens to the audio explanations.

[0606] As described above, this system can provide learning materials that are individually tailored to each user's preferences and learning style, enabling effective learning. This allows for high learning efficiency and satisfaction that could not be achieved with conventional, uniform learning materials.

[0607] The processing flow will be explained below.

[0608] Step 1:

[0609] A user accesses the learning system for the first time. Upon access, a questionnaire about preferences and learning styles is displayed as an initial setting.

[0610] Step 2:

[0611] The device displays a survey form to the user, which the user answers, including the following items:

[0612] Difficulty of the text

[0613] Image frequency

[0614] Image Style

[0615] Audio Features

[0616] Description Character Preferences

[0617] Step 3:

[0618] The user answers the questionnaire form and presses the send button. The response data is collected and sent to the system by the terminal.

[0619] Step 4:

[0620] The device sends the collected survey data to the server, encoded in an appropriate format such as JSON.

[0621] Step 5:

[0622] The server stores the received survey data in a database, along with the user's profile information (ID, name, etc.).

[0623] Step 6:

[0624] The server invokes a generative AI model (e.g., GPT-4) to generate customized training text based on the stored user data.

[0625] Step 7:

[0626] The server invokes an image generation process to generate an image in the style selected by the user (e.g., film style, anime style), using an image generation model such as DALL-E.

[0627] Step 8:

[0628] The server invokes a speech generation process to convert the training text into a voice of the voice actor selected by the user, specifically, a Text-to-Speech (TTS) engine.

[0629] Step 9:

[0630] The server invokes the character generation process, which generates a character based on the character style selected by the user (e.g., ancient Roman soldier, modern doctor).

[0631] Step 10:

[0632] The server integrates the generated text, images, audio, and character animations and packages them as learning materials.

[0633] Step 11:

[0634] The server sends the integrated learning material package to the terminal, using a communication protocol such as the Internet.

[0635] Step 12:

[0636] The device displays the received learning material on the user's screen and plays the audio. Images, text, audio, and characters are arranged and played appropriately, and the user can begin learning.

[0637] Step 13:

[0638] After studying, users provide feedback, including the quality of the learning material, their level of understanding, and changes in their preferences.

[0639] Step 14:

[0640] The device collects feedback data and sends it to a server, which stores it in a database and uses it to generate future learning materials.

[0641] The above are the specific processing steps of the system based on the claims. Through these steps, learning materials tailored to individual user needs and preferences can be efficiently generated and provided.

[0642] Example 1

[0643] 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."

[0644] Conventional learning systems often provide uniform learning materials and are unable to accommodate individual users' preferences and learning styles, resulting in reduced learning efficiency and difficulty in improving user satisfaction. Furthermore, there is a lack of means to generate and appropriately distribute learning materials optimized for each user, making it difficult to provide an effective learning experience.

[0645] 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.

[0646] In this invention, the server includes means for collecting user preferences and learning styles, means for storing the collected user data, means for generating customized learning materials based on the user data using a generative AI model, means for transmitting the generated learning materials to the user's terminal, and means for displaying and playing the integrated learning materials on the user's terminal, thereby providing learning materials optimized according to each user's preferences and learning style, enabling effective learning.

[0647] "User preferences and learning styles" refer to the user's personal learning preferences and the methods and formats that maximize learning efficiency.

[0648] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to automatically generate learning materials such as text, images, audio, and animations based on user data.

[0649] A "prompt sentence" refers to an input sentence given to a generative AI model to generate the desired output.

[0650] "Learning materials" refers to information content such as text, images, audio, and animations that users use to study.

[0651] "Terminal" refers to the device (computer, smartphone, tablet, etc.) that a user uses to access the system and view and use learning materials.

[0652] "Server" refers to a computer system that processes and stores data sent by users, distributes generated learning materials, etc.

[0653] "Database" refers to a system or structure for storing and managing collected data such as user preferences, learning styles, and survey results.

[0654] "Feedback" refers to the evaluations and opinions provided by users after using learning materials, and is used to adjust the quality and content of the learning materials based on this.

[0655] A "survey" refers to a collection of questions presented to a user to gather information about their preferences and learning style.

[0656] An embodiment of the present invention is a system for generating and providing individually customized learning materials that enable users to study effectively. The system includes multiple means for collecting user preferences and learning styles and generating materials that meet individual learning needs.

[0657] The main components of this system are the user device, the server, and the generative AI model. Specific examples of devices include smartphones, tablets, and PCs, while the server is a cloud server or dedicated server. GPT-4 and an image generation model are used as generative AI models.

[0658] Collecting user preferences and learning styles

[0659] When users first access the system, they are presented with a survey screen, which includes the following items:

[0660] Difficulty level of the text (e.g. elementary school, junior high school, high school)

[0661] Frequency of image use (e.g. low, medium, high)

[0662] Image style (e.g., anime, film, realistic)

[0663] Voice characteristics (e.g. male voice actor A, female voice actor B)

[0664] Describe the character's preference (e.g., Roman soldier, modern doctor)

[0665] The user answers these questions and sends the survey data from the terminal to the server using a communication method such as an HTTP request.

[0666] Store and manage user data

[0667] The server stores the received survey data in a database, which contains the user's profile information and survey responses.

[0668] Generate customized learning materials

[0669] The server generates customized learning materials using a generative AI model based on the received data. This generation process includes inputting prompt sentences into the generative AI model.

[0670] An example of a specific prompt is as follows:

[0671] "Please explain a history lesson for junior high school students using movie-style images in the voice of male voice actor B. I also need an animation featuring a character that looks like an ancient Roman soldier."

[0672] The generative AI model generates text, images, audio, and animations based on the prompts, and the generated content is collected on a server and integrated into a learning package.

[0673] Delivery and display of learning materials

[0674] The server then sends the generated learning package to the terminal, which then displays the received learning material to the user and plays audio as needed.

[0675] Specific examples

[0676] A specific example of this system is shown below.

[0677] Example 1: History lessons for junior high school students

[0678] A user (a junior high school student) accesses the system for the first time and answers a questionnaire as follows:

[0679] Level of difficulty: Junior high school level

[0680] Image usage frequency: High

[0681] Image Style: Cinematic

[0682] Voice characteristics: Male voice actor B

[0683] Description Character: Ancient Roman soldier style

[0684] The device sends the collected data to a server, which stores it in a database. The server uses a generative AI model to generate learning materials based on the above settings and creates a learning package. This package is sent to the device. The device displays the received learning materials on the screen and plays audio. The user learns the historical content while watching movie-style images and listening to audio and character explanations as they progress through their studies.

[0685] Example 2: Health education for the elderly

[0686] A user (senior citizen) accesses the system and answers the questionnaire as follows:

[0687] Difficulty of the text: Easy

[0688] Image Frequency: Medium

[0689] Picture Style:Realistic

[0690] Voice characteristics: Female voice actor A

[0691] Description Character: Modern doctor style

[0692] The device sends the data to the server, which stores it. The server uses a generative AI model to generate gently worded text using realistic images, creates audio in the voice of female voice actor A, and generates explanations by a character that looks like a modern doctor. These learning materials are then integrated and sent to the device. The device then displays the received learning materials on its screen and plays the audio. The user learns health knowledge while viewing realistic images and receives explanations while listening to the audio.

[0693] In this way, the system can individually accommodate each user's preferences and learning style, promoting effective learning.

[0694] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0695] Step 1: The user accesses the system.

[0696] Input: User access (e.g., typing a URL in a web browser).

[0697] Output: Display of the survey screen.

[0698] Specific operation: The user accesses the system's URL using a browser on a smartphone or PC.

[0699] Step 2: The device will display the survey screen.

[0700] Input: The system's web page request.

[0701] Output: Display of the survey screen.

[0702] Specific operation: The device receives HTML data from the server and displays a questionnaire screen to the user. The questionnaire includes questions about the difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and preferences for explanatory characters.

[0703] Step 3: The user completes the survey.

[0704] Input: User's survey responses.

[0705] Output: User response data.

[0706] Specific operation: The user enters the answer to the questionnaire item and presses the submit button. At this point, the response data is collected on the device.

[0707] Step 4: The terminal transmits the user response data to the server.

[0708] Input: User response data.

[0709] Output: Sending data to the server.

[0710] Specific operation: The device sends the collected response data to the server using an HTTP request or WebSocket.

[0711] Step 5: The server receives the survey data and stores it in a database.

[0712] Input: User response data sent from the device.

[0713] Output: Confirmation of saving to database.

[0714] Specific operation: The server analyzes the received survey data and executes an INSERT statement to the corresponding user record in the database to save it.

[0715] Step 6: The server generates a prompt sentence based on the user data and inputs it into the generative AI model.

[0716] Input: User data.

[0717] Output: Prompt sentence and learning material.

[0718] Specific operation: The server generates prompts based on the user's preferences and learning style. For example, a sentence like "Please explain history for junior high school students using movie-style images in the voice of male voice actor B. An animation featuring characters resembling ancient Roman soldiers is also required." is input into the generative AI model.

[0719] Step 7: The generative AI model generates customized learning materials.

[0720] Input: The prompt text sent by the server.

[0721] Output: Customized text, images, audio, animation.

[0722] Specific operation: The generative AI model generates text, images, audio, and animation based on the prompt. For example, GPT-4 generates text, the image generation model generates images, and the speech synthesis model generates audio.

[0723] Step 8: The server integrates the generated learning materials and creates a learning package.

[0724] Input: Multiple learning materials (text, images, audio, animation) from a generative AI model.

[0725] Output: A learning package.

[0726] Specific operation: The server combines each generated material into a single learning package and creates a JSON file to manage metadata.

[0727] Step 9: The server sends the learning package to the terminal.

[0728] Input: Learning package.

[0729] Output: Sending data to the terminal.

[0730] Specific operation: The server sends the learning package to the device using HTTP responses or WebSockets.

[0731] Step 10: The terminal receives the learning package and displays and plays it for the user.

[0732] Input: The learning package sent from the server.

[0733] Output: Screen display and audio playback.

[0734] What it does: The device analyzes the received learning package, displays text and images on the screen, plays audio files, and displays animations on the screen.

[0735] (Application example 1)

[0736] 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."

[0737] Conventional online shopping systems lack the ability to customize services to suit individual user preferences and styles, making it difficult to enhance user satisfaction. In particular, the lack of personalized recommendations that reflect each user's unique shopping style and product preferences is an obstacle to improving the user experience.

[0738] 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.

[0739] In this invention, the server includes means for collecting user preferences and shopping styles, means for storing the collected user data, means for generating individually customized product recommendations based on the stored data, means for transmitting the generated product recommendations to the user's terminal, means for collecting feedback regarding the product recommendations, and means for adjusting the product recommendations based on the collected feedback, thereby enabling personalized product recommendations based on the user's individual preferences and styles.

[0740] "User preferences and shopping style" refers to the user's tastes and purchasing behavior, product categories of interest, purchasing budget, color and design preferences, and the like.

[0741] "Collection Methods" means systems and methods for obtaining user data through surveys or automated behavioral tracking.

[0742] "Storage means" refers to a system or method for storing and managing collected user data in a storage device such as a database.

[0743] "Means for generating customized product recommendations" means a system or method for creating individually optimized product listings and related information based on collected and stored user data.

[0744] "Transmission means" refers to a network communication means or method for delivering the generated product recommendation information to the user's terminal.

[0745] "Feedback collection means" means a system or method that provides a form or interface for collecting user-provided opinions or ratings.

[0746] "Adjustment" refers to systems and methods for optimizing product recommendation content and algorithms based on collected feedback.

[0747] A "generative AI model" is an artificial intelligence model used for natural language processing, image generation, etc., and includes advanced machine learning algorithms such as GPT-4 and DALL-E.

[0748] A "prompt" refers to a text instruction entered into a generative AI model to cause it to generate a particular output.

[0749] System Overview

[0750] This invention is a virtual shopping system that provides individually customized product recommendations based on a user's preferences and shopping style. The system includes the following major components: means for collecting user preferences and shopping style, means for storing the collected user data, means for generating individually customized product recommendations based on the stored data, means for transmitting the generated product recommendations to the user's terminal, means for collecting feedback regarding the product recommendations, and means for adjusting the product recommendations based on the collected feedback.

[0751] Collecting user preferences and shopping styles

[0752] 1. When a user accesses the system for the first time, a shopping survey is displayed on the screen.

[0753] Questionnaire questions include preferred colors, styles, budget ranges, and areas of interest.

[0754] The user responds to the survey.

[0755] 2. The terminal collects the questionnaire data answered by the user and sends it to the server.

[0756] Store and manage user data

[0757] 3. The server stores the received survey data in a database (e.g., MySQL), along with the user's profile information.

[0758] Generating customized product recommendations

[0759] 4. The server uses a generative AI model (e.g., GPT-4, image generation model DALL-E) to generate product recommendations based on the collected user data.

[0760] Specifically, customize the following elements:

[0761] A list of products that match the user's preferences

[0762] Recommended product images (anime style, realistic style, etc.)

[0763] Audio explanation of the product

[0764] Animated introduction using characters created by the user

[0765] Product recommendation delivery

[0766] 5. The server consolidates the generated product recommendations and sends them to the terminal as a package.

[0767] 6. The device displays the received product recommendation on the screen and plays it back as audio.

[0768] Collecting and adjusting feedback on product recommendations

[0769] 7. The device collects feedback from the user and sends it to the server.

[0770] 8. The server optimizes the content and algorithm of product recommendations based on the collected feedback.

[0771] Specific examples

[0772] Example 1: Fashion item recommendation

[0773] 1. A user (e.g., Mr. A) accesses the system for the first time and answers a questionnaire.

[0774] "Favorite color: Blue, Style: Casual, Budget: Under 10,000 yen, Interests: Sneakers"

[0775] 2. The device sends the collected data to the server, which stores it in a database.

[0776] 3. The server uses the generative AI model to generate product lists and images based on the following prompt:

[0777] "Generate a list of recommended fashion items based on user A's preferences. Style is casual, color is blue, and budget is under 10,000 yen."

[0778] "Create anime-style product images based on the generated product list."

[0779] 4. The server sends the generated product recommendation package to the terminal, which displays it to the user and explains it aloud.

[0780] 5. The user reviews the recommended products and provides feedback.

[0781] 6. The device sends feedback to the server, which then adjusts the algorithm based on that feedback.

[0782] The system can provide a personalized shopping experience that reflects a user's individual tastes and style.

[0783] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0784] Step 1:

[0785] When a user accesses the system for the first time, a shopping questionnaire is displayed on the terminal. The user answers questions about their preferred colors, styles, budget range, areas of interest, etc. The input information is basic data for making personalized recommendations for the user. The terminal collects the questionnaire data answered by the user. Input: User's questionnaire answers. Output: Collected questionnaire data.

[0786] Step 2:

[0787] The terminal sends the collected survey data to the server. The server verifies the received survey data and stores it in a database (e.g. MySQL). The stored data also includes user profile information. Input: Survey data. Output: User data stored in the database.

[0788] Step 3:

[0789] The server uses a generative AI model (e.g., GPT-4) to generate product recommendations based on the collected and stored user data. Specifically, it uses the stored data as input and issues prompts to the AI ​​model to generate a product list.

[0790] Example prompt sentence:

[0791] "Generate a list of recommended products based on user A's preferences. Style is casual, color is blue, and budget is under 10,000 yen."

[0792] Input: saved user data, prompt text. Output: generated product list.

[0793] Step 4:

[0794] The server generates customized product images based on the product list using an image generation model (e.g., DALL-E).

[0795] Example prompt sentence:

[0796] "Create anime-style product images based on the generated product list."

[0797] Input: Product list, prompt. Output: Generated product images.

[0798] Step 5:

[0799] The server combines the generated product list and product images and sends them as a package to the terminal. The terminal displays the received product recommendations on the screen and plays back audio descriptions using the speech generation model. Input: Product list and product images. Output: Product recommendations displayed on the terminal and audio descriptions.

[0800] Step 6:

[0801] The user reviews the displayed product recommendations and provides feedback based on their purchasing intentions and interests. The terminal collects the user's feedback. Input: User's feedback. Output: Collected feedback.

[0802] Step 7:

[0803] The device sends the collected feedback to the server, which makes adjustments to optimize the product recommendation algorithm and content based on the received feedback. Input: User feedback. Output: Adjusted product recommendation algorithm and data.

[0804] Through the above processing steps, personalized product recommendations based on the user's preferences are provided.

[0805] 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.

[0806] An embodiment of the present invention is a system that provides individually customized learning materials to enable users to study effectively, recognizes users' emotions in real time, and adjusts the learning materials appropriately based on that information. The system collects users' preferences, learning styles, and emotions, and generates and provides optimal educational content based on this information.

[0807] System Overview

[0808] Collecting user preferences and learning styles

[0809] 1. When a user first accesses the system, they are presented with a questionnaire about their preferences and learning style, including the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and the preference for narrators.

[0810] 2. The terminal collects data from the user's responses to the questionnaire and sends it to the server.

[0811] Store and manage user data

[0812] 3. The server stores the received survey data in a database, along with the user's profile information.

[0813] Emotion Recognition and Data Collection

[0814] 4. The device uses devices such as a camera and microphone to collect emotional data in real time from the user's facial expressions and voice.

[0815] 5. The device analyzes the collected emotion data and uses an emotion engine to identify the user's current emotional state.

[0816] 6. The device sends the identified emotion data to the server.

[0817] 7. The server stores the received emotion data in a database.

[0818] Generate customized learning materials

[0819] 8. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate training materials based on the stored user data and emotion data. The generated training materials include the following elements:

[0820] Text content according to the level of difficulty

[0821] Image styles to suit user preferences (anime, movie, etc.)

[0822] Voice generated by selected voice actors

[0823] Explanation animation by user-defined characters

[0824] Delivery of learning materials

[0825] 9. The server consolidates the generated learning materials and sends them to the terminal as a package.

[0826] 10. The device displays the received learning material on the screen and plays the audio.

[0827] Dynamic Adjustment

[0828] 11. The device continues to collect emotional data in real time while learning, and if adjustments are needed to suit different conditions, it sends that information to the server.

[0829] 12. The server dynamically adjusts the content of the learning material based on the latest emotional data received and sends it back to the device.

[0830] Specific examples

[0831] Example 1: English language learning for primary school students

[0832] 1. A user (Mr. Sato, an elementary school student) accesses the system for the first time. He answers the questionnaire displayed on the screen with the following options: "Text difficulty: Elementary school-aged," "Image usage frequency: High," "Image style: Anime-style," "Audio characteristics: Child's voice," and "Explanatory character: Animal character."

[0833] 2. The terminal sends the survey data to the server, which stores the data in a database.

[0834] 3. The device uses a camera and microphone to collect emotional data from Sato's facial expressions and voice, and then uses an emotion engine to identify his emotional state.

[0835] 4. The device sends the emotion data to the server, which stores it in a database.

[0836] 5. Based on the saved data, the server generates English textbooks for elementary school students, featuring a wide range of cartoon-style images. The audio is recorded using a child's voice, and animated animal characters are created.

[0837] 6. The server consolidates the generated learning materials and sends them to the terminal.

[0838] 7. The device displays the learning material on Sato's screen and plays the audio.

[0839] 8. The device will collect emotional data while learning, and if Sato's emotions change, it will send that information to the server.

[0840] 9. The server dynamically adjusts the learning material as needed and sends it back to the device.

[0841] Example 2: History study for high school graduation exams

[0842] 1. A user (high school student named Tanaka) accesses the system and answers the questionnaire with the following options: "Text difficulty: for high school students," "Image use frequency: medium," "Image style: realistic," "Audio characteristics: male voice actor A," and "Explanatory character: historical figure-like."

[0843] 2. The terminal sends the survey data to the server, which stores the data in a database.

[0844] 3. The device uses a camera and microphone to collect emotion data from Tanaka's facial expressions and voice, and then uses an emotion engine to identify her emotional state.

[0845] 4. The device sends the emotion data to the server, which stores it in a database.

[0846] 5. Based on the saved data, the server generates a history textbook for high school students using realistic images. Voices are recorded by male voice actor A, and animations of characters resembling historical figures are created.

[0847] 6. The server consolidates the generated learning materials and sends them to the terminal.

[0848] 7. The device displays the learning material on Tanaka's screen and plays the audio.

[0849] 8. The device will collect emotional data while learning, and if Tanaka's emotions change, it will send that information to the server.

[0850] 9. The server dynamically adjusts the learning material as needed and sends it back to the device.

[0851] In this way, the present invention is a system that provides learning materials that are individually customized based on the user's preferences, learning style, and emotions, helping the user achieve high learning effectiveness. This provides a highly accurate learning experience that could not be achieved with conventional, uniform learning materials.

[0852] The processing flow will be explained below.

[0853] Step 1:

[0854] When a user first accesses the system, they are presented with a questionnaire about their preferences and learning style, including the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the audio, and their preference for explanatory characters.

[0855] Step 2:

[0856] The device collects the data of the user's responses to the survey and sends it to the server, encoded in an appropriate format such as JSON.

[0857] Step 3:

[0858] The server stores the received survey data in a database, including user profile information (ID, name, etc.).

[0859] Step 4:

[0860] The device uses devices such as a camera and microphone to collect emotional data in real time from the user's facial expressions and voice.

[0861] Step 5:

[0862] The device analyzes the collected emotion data and identifies the user's current emotional state using an emotion engine, which includes algorithms for facial and voice analysis.

[0863] Step 6:

[0864] The device sends the identified emotion data to the server, which is also encoded in an appropriate format such as JSON.

[0865] Step 7:

[0866] The server stores the received emotion data in a database, where it is linked to the user's profile.

[0867] Step 8:

[0868] The server invokes a generative AI model (e.g., GPT-4) to generate individually customized training text based on the stored user data and sentiment data.

[0869] Step 9:

[0870] The server invokes an image generation process to generate an image in the style selected by the user (e.g., film style, anime style), using an image generation model such as DALL-E.

[0871] Step 10:

[0872] The server invokes a speech generation process to translate the training text into a voice of the selected voice actor, specifically, using a Text-to-Speech (TTS) engine.

[0873] Step 11:

[0874] The server invokes a character generation process to generate a character based on the character style selected by the user (e.g., an ancient Roman soldier or a modern doctor).

[0875] Step 12:

[0876] The server integrates the generated text, images, audio, and character animations and packages them as learning materials.

[0877] Step 13:

[0878] The server sends the integrated learning material package to the terminal, using a communication protocol such as the Internet.

[0879] Step 14:

[0880] The device displays the received learning material on the user's screen and plays the audio. Images, text, audio, and characters are arranged and played appropriately, and the user can begin learning.

[0881] Step 15:

[0882] The device continues to collect emotional data in real time while learning, and if the user's emotional state changes, the data is also sent to the server.

[0883] Step 16:

[0884] The server dynamically adjusts the learning material based on the latest emotional data it receives, for example, by adding more engaging content or images if the user is losing interest.

[0885] Step 17:

[0886] The server then sends the modified or adjusted learning material back to the device, which then displays the new material and plays the audio.

[0887] In this way, the system supports effective learning by providing and dynamically adjusting learning materials that are individually customized based on the user's preferences, learning style, and even emotional state.

[0888] Example 2

[0889] 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."

[0890] Conventional learning systems have difficulty customizing learning materials to suit individual users' preferences and learning styles, and have been unable to provide appropriate learning materials according to the user's emotional state. This has resulted in problems with users not being able to fully achieve their learning goals.

[0891] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0892] In this invention, the server includes means for collecting user preferences and learning styles, means for saving the collected user data, means for collecting emotional data from the user's facial expressions and voice using devices such as a camera and microphone and analyzing the emotional data, means for saving the collected emotional data, means for using a generative AI model to generate individually customized learning materials based on the saved user data and emotional data, means for transmitting the generated learning materials to the user's device, and means for collecting emotional data in real time even during learning and dynamically adjusting the learning materials, thereby making it possible to provide optimal learning materials according to the user's preferences and emotional state.

[0893] "User preferences and learning style" refers to the user's preferred content format, difficulty level, frequency of use, visual and auditory elements, and preferred learning methods.

[0894] "Customized learning materials" refers to educational content generated based on a user's preferences, learning style, and real-time emotional data.

[0895] "Emotional Data" refers to data about a user's current emotional state collected from the user's facial expressions and voice using devices such as a camera or microphone.

[0896] "Generative AI models" refer to artificial intelligence algorithms that generate learning materials based on collected user and emotional data. Specifically, they include AI models that perform natural language processing and image generation.

[0897] "Means for dynamic adjustment" refers to the function of analyzing the user's emotional data in real time and updating or changing the content of the learning material as needed.

[0898] "Terminal" refers to any device that a user accesses, including, for example, a PC, smartphone, or tablet.

[0899] "Server" refers to a remote computer system that stores and processes user data and sentiment data, including databases and infrastructure for running AI models.

[0900] "Survey data" refers to the response data to questions about preferences and learning styles that users answer when they first access the system.

[0901] An "emotion engine" refers to software or algorithms that analyze user data acquired through a camera or microphone and identify their emotional state.

[0902] The embodiment of the present invention is a system that provides individually customized learning materials to enable users to study effectively, recognizes the user's emotions in real time, and adjusts the learning materials appropriately based on that information. This system is described in detail below.

[0903] Collecting user preferences and learning styles

[0904] When a user first accesses the system, the device displays a questionnaire about preferences and learning style through a user interface. This questionnaire includes the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and the preference of explanatory characters. When the user answers the questionnaire, the device collects the data and sends it to a server. The device uses a user interface that runs on a web browser or a mobile app.

[0905] Store and manage user data

[0906] The server stores the received survey data in a relational database (e.g., MySQL, PostgreSQL), and also records user profile information.

[0907] Emotion Recognition and Data Collection

[0908] The device uses a camera and microphone to collect emotion data from the user's facial expressions and voice in real time. The devices used here include a PC's built-in camera, an external webcam, and a microphone. The collected emotion data is analyzed by the device, and the user's emotional state is identified using an emotion engine (e.g., Microsoft Azure Face API, Google Cloud Speech-to-Text API). The identified emotion data is sent from the device to a server, which stores it in a database.

[0909] Generate customized learning materials

[0910] The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate training materials based on the stored user data and emotion data. The generated training materials include the following elements:

[0911] Text content according to the level of difficulty

[0912] Image styles to suit user preferences (anime, movie, etc.)

[0913] Voice generated by selected voice actors

[0914] Explanation animation by user-defined characters

[0915] Delivery of learning materials

[0916] The server integrates the generated learning materials and sends them as a package to the device, which then displays the received learning materials on the screen and plays the audio.

[0917] Dynamic Adjustment

[0918] The device continues to collect emotional data in real time while learning and sends it to the server. The server dynamically adjusts the content of the learning materials based on the latest emotional data and sends them back to the device. This allows the device to provide optimal learning materials according to the user's emotional state.

[0919] Specific examples

[0920] Example 1: English language learning for primary school students

[0921] 1. A user (elementary school student) accesses the system for the first time and answers the questionnaire with the following options: "Text difficulty: for elementary school students," "Frequency of image use: high," "Image style: anime-style," "Audio characteristics: child's voice," and "Explanatory character: animal character."

[0922] 2. The terminal sends the survey data to the server, which stores the data in a database.

[0923] 3. The device uses a camera and microphone to collect emotional data from facial expressions and voice, and then uses an emotion engine to identify the emotional state.

[0924] 4. The device sends the emotion data to the server, which stores it in a database.

[0925] 5. Based on the saved data, the server generates English textbooks for elementary school students, featuring a wide range of cartoon-style images. Audio is recorded using children's voices, and animations featuring animal characters are created.

[0926] 6. The server consolidates the generated learning materials and sends them to the terminal.

[0927] 7. The device displays the learning material on the screen and plays the audio.

[0928] 8. The device collects emotional data during learning and sends the information to the server as needed.

[0929] 9. The server dynamically adjusts the learning material and sends it back to the device.

[0930] Prompt Sentence Examples

[0931] "Generate an anime-style English learning textbook for elementary school students. Images should be used frequently, with children's voices and animal characters as explanatory characters."

[0932] Example 2: History study for high school graduation exams

[0933] 1. The user (high school student) accesses the system and answers the questionnaire with the following options: "Text difficulty: for high school students," "Image use frequency: medium," "Image style: realistic," "Audio characteristics: male voice actor," and "Explanatory character: historical figure style."

[0934] 2. The terminal sends the survey data to the server, which stores the data in a database.

[0935] 3. The device uses a camera and microphone to collect emotional data from facial expressions and voice, and then uses an emotion engine to identify the emotional state.

[0936] 4. The device sends the emotion data to the server, which stores it in a database.

[0937] 5. Based on the saved data, the server generates historical textbooks for high school students using realistic images. Audio is recorded by male voice actors, and animated characters that resemble historical figures are created.

[0938] 6. The server consolidates the generated learning materials and sends them to the terminal.

[0939] 7. The device displays the learning material on the screen and plays the audio.

[0940] 8. The device collects emotional data during learning and sends the information to the server as needed.

[0941] 9. The server dynamically adjusts the learning material and sends it back to the device.

[0942] Prompt Sentence Examples

[0943] "Generate a realistic history textbook for high school students. Images should be used moderately, audio should be provided by a male voice actor, and explanatory characters should look like historical figures."

[0944] In this way, the present invention is a system that provides learning materials that are individually customized based on the user's preferences, learning style, and emotions, helping the user achieve high learning effectiveness. This provides a highly accurate learning experience that could not be achieved with conventional, uniform learning materials.

[0945] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0946] Step 1: Collect user surveys

[0947] 1-1. The user accesses the system for the first time. The questionnaire includes questions about the difficulty of the text, the frequency of image use, the style of the image, the characteristics of the voice, and the preference for the explanatory character.

[0948] Input: The user answers the survey items.

[0949] Operation: A questionnaire screen is displayed and the user answers each item.

[0950] Output: User response data.

[0951] 1-2. The device collects the user's response data and sends it to the server.

[0952] Input: User response data.

[0953] Operation: The device sends the response data to the server.

[0954] Output: Survey data sent to the server.

[0955] Step 2: Save user data

[0956] 2-1. The server stores the received survey data in a relational database, such as MySQL or PostgreSQL.

[0957] Input: Survey data.

[0958] How it works: The server saves the survey data in a database.

[0959] Output: Survey data stored in a database.

[0960] 2-2. The server also records the user's profile information.

[0961] Input: User's personal information.

[0962] How it works: The server stores user profile information in a database.

[0963] Output: User profile information stored in a database.

[0964] Step 3: Collecting emotion data

[0965] 3-1. The device uses a camera and microphone to collect emotional data from the user's facial expressions and voice in real time. The devices used include the PC's built-in camera, an external webcam, and a microphone.

[0966] Input: User facial expressions and voice collected by camera and microphone.

[0967] What it does: Your device collects data through its camera and microphone.

[0968] Output: Collected emotion data.

[0969] 3-2. The device analyzes the collected emotion data and identifies the user's current emotional state using an emotion engine, such as the Microsoft Azure Face API or the Google Cloud Speech-to-Text API.

[0970] Input: Collected emotion data.

[0971] How it works: The emotion engine analyzes the emotion data and identifies the user's emotional state.

[0972] Output: Identified emotion data.

[0973] 3-3. The device sends the identified emotion data to the server.

[0974] Input: Identified emotion data.

[0975] Operation: The device sends emotion data to the server.

[0976] Output: Emotion data sent to the server.

[0977] 3-4. The server stores the received emotion data in a database.

[0978] Input: Emotion data.

[0979] How it works: The server stores emotion data in a database.

[0980] Output: Emotion data stored in a database.

[0981] Step 4: Generate customized learning materials

[0982] 4-1. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate learning materials based on the stored user data and emotion data.

[0983] Input: User data and emotion data.

[0984] How it works: The AI ​​model analyzes the data and generates optimal learning materials for the user.

[0985] Output: The generated learning material.

[0986] 4-2. The generated learning materials include the following elements:

[0987] Text content according to the level of difficulty

[0988] Image styles to suit user preferences (anime, movie, etc.)

[0989] Voice generated by selected voice actors

[0990] Explanation animation by user-defined characters

[0991] Input: Individual elements of user data (e.g. difficulty of text, frequency of image use, etc.).

[0992] How it works: The AI ​​model generates materials based on each element.

[0993] Output: Each element of the customized learning material.

[0994] Step 5: Deliver learning materials

[0995] 5-1. The server integrates the generated learning materials and sends them to the terminal as a package.

[0996] Input: Generated learning material.

[0997] How it works: The server collects the material into a single package and sends it to the device.

[0998] Output: The learning material package sent to the device.

[0999] 5-2. The device displays the received learning material on the screen and plays the audio.

[1000] Input: Received learning material package.

[1001] What it does: The device displays the material on the screen and plays the audio.

[1002] Output: Learning material that is visible and audible to the user.

[1003] Step 6: Dynamic adjustment

[1004] 6-1. The device continues to collect emotional data in real time even during learning, and if adjustments are needed to suit different conditions, it sends that information to the server.

[1005] Input: Emotion data collected in real time.

[1006] Operation: The device continues to collect emotion data and transmits it to the server.

[1007] Output: The latest emotion data sent to the server.

[1008] 6-2. The server dynamically adjusts the content of the learning material based on the latest emotional data received and sends it back to the device.

[1009] Input: Latest emotion data.

[1010] How it works: The server analyzes the emotion data and adjusts the learning material as needed.

[1011] Output: Dynamically adjusted learning material.

[1012] (Application example 2)

[1013] 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."

[1014] With current learning systems, it is difficult to customize learning materials to suit each user's preferences and learning style. It is also extremely difficult to grasp the user's emotional state in real time while learning and instantly adjust the learning materials. This results in problems such as users being unable to study effectively and reduced learning efficiency.

[1015] 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.

[1016] In this invention, the server includes means for collecting user preferences and learning styles, means for storing the collected user data, means for generating individually customized learning materials based on the stored data and the user's emotional data, means for transmitting the generated learning materials to the user's terminal, and means for collecting emotional data in real time during learning and dynamically adjusting the materials. This allows the server to provide individually customized learning materials, enabling users to achieve high learning effectiveness.

[1017] "Preferences" refer to the types and formats of learning content that a user particularly prefers.

[1018] "Learning style" refers to a particular learning method or approach that a user takes to effectively learn.

[1019] "Emotion data" is data that indicates the user's current emotional state, extracted from the user's facial expressions and voice.

[1020] "Customized learning materials" refers to learning content that is individually tailored to a user based on their preferences, learning style, and emotional data.

[1021] "Collecting in real time" means that data is collected continuously while the user is studying.

[1022] "Dynamic adjustment" refers to changing the content of learning materials on the fly based on collected data.

[1023] "Terminal" refers to a device used by a user, such as a smartphone or smart glasses.

[1024] "Server" refers to the central computing system that stores user data and generates and delivers learning materials.

[1025] System configuration explanation

[1026] The system of the present invention mainly includes means for collecting user preferences and learning styles, means for collecting emotional data in real time, means for generating individually customized learning materials based on the stored data and the user's emotional data, and means for transmitting the generated learning materials to a terminal.

[1027] Hardware and software used

[1028] The system uses the following hardware and software:

[1029] Device: The smartphone or smart glasses used by the user, including the camera, microphone, and other input devices.

[1030] Server: A high-performance computing system, either on cloud or on-premise, that stores user data and generates and delivers learning materials.

[1031] Emotion recognition software: Facial expression recognition libraries and voice analysis tools (e.g., EmotionRecognizer).

[1032] Generative AI models: High-performance text and image generation models such as GPT-4.

[1033] Program processing overview

[1034] 1. The device initially collects data by conducting a survey about the user's preferences and learning style.

[1035] 2. The device sends the collected data to the server, which stores it in a database.

[1036] 3. The device uses a camera and microphone to collect and analyze emotional data from the user's facial expressions and voice in real time.

[1037] 4. The device sends the analyzed emotion data to the server, which stores it in a database.

[1038] 5. The server generates customized learning materials using a generative AI model based on the stored user data and emotion data.

[1039] 6. The server sends the generated learning material to the terminal, which displays or plays it to the user.

[1040] 7. The device continues to collect emotional data in real time during training and transmits the information to the server as needed.

[1041] 8. The server dynamically adjusts the learning material based on the latest emotional data and sends it back to the device.

[1042] Specific examples

[1043] For example, when a user visits a store, they put on the smart glasses and the learning process proceeds as follows:

[1044] 1. Survey collection: The user answers the survey and enters information such as "Image usage frequency: high frequency," "Image style: realistic," and "Audio characteristics: male voice."

[1045] 2. Data storage: The survey results are sent to the server and stored in the database.

[1046] 3. Emotion data collection: The camera in the smart glasses captures facial expressions and analyzes them in real time.

[1047] 4. Learning material generation: The server uses the generative AI model to create customized learning content.

[1048] 5. Content delivery: The learning content is sent to the device and the user begins learning.

[1049] 6. Real-time adjustment: Materials are dynamically adjusted according to the user's emotional state.

[1050] Prompt Sentence Examples

[1051] "User profile: They frequently use realistic images and prefer characters with male voices."

[1052] "Sentiment data: Interest is currently waning. Use this information to provide more engaging content."

[1053] This system allows users to receive individually customized learning materials on the spot, resulting in higher learning effectiveness.

[1054] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1055] Step 1:

[1056] A user accesses the system using a terminal (smartphone or smart glasses). The terminal displays a questionnaire to the user about their preferences and learning style. The user answers the questionnaire and enters the data. The user's questionnaire data is entered into the terminal. The terminal collects this data and sends it to the server.

[1057] Step 2:

[1058] The server receives the survey data sent from the device. The received data is stored in a database. The server stores the user's profile information, as well as their preferences and learning style data, for a long period of time. The input is the survey data, and the output is the stored data.

[1059] Step 3:

[1060] The device collects the user's facial expressions and voice in real time using a camera and microphone. The collected data is analyzed using a facial expression recognition library and a voice analysis tool (e.g., EmotionRecognizer). The device then sends the analyzed emotion data to a server. The input is facial expression and voice data, and the output is the analyzed emotion data.

[1061] Step 4:

[1062] The server receives the emotion data sent from the device. The received data is stored in a database. The server identifies and records the user's current emotional state. The input is the emotion data, and the output is the stored emotion data.

[1063] Step 5:

[1064] The server generates customized learning materials using a generative AI model (e.g., GPT-4) based on the stored user data and emotional data. Learning content, such as text, images, and audio, is created based on prompts input to the generative AI model. The input is user data and emotional data, and the output is customized learning materials.

[1065] Step 6:

[1066] The server integrates the generated learning materials and sends them to the terminal. The learning materials are optimized for easy understanding by the user. The input is the generated learning materials, and the output is the learning materials delivered to the terminal.

[1067] Step 7:

[1068] The terminal receives learning materials sent from the server. The terminal displays and plays these materials to the user. The user then uses the customized learning materials to progress through their learning. The input is the delivered learning materials, and the output is the user's execution of the learning.

[1069] Step 8:

[1070] During training, the device continues to collect the user's facial expressions and voice in real time using a camera and microphone. If the emotional data changes, it sends that data to the server. The input is the continuously collected emotional data, and the output is the updated emotional data.

[1071] Step 9:

[1072] The server dynamically adjusts the learning materials accordingly based on the latest emotional data. The generative AI model is again used to update the content based on the new prompt. The input is the latest emotional data, and the output is the dynamically adjusted learning materials.

[1073] Step 10:

[1074] The server sends the adjusted learning materials back to the terminal. The terminal displays and plays these materials again to the user. The user continues learning adapted to the new conditions. The input is the adjusted learning materials, and the output is the user's continued learning.

[1075] This allows users to use individually customized learning materials and enjoy a learning environment that adapts in real time as they learn.

[1076] 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.

[1077] 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.

[1078] 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.

[1079] [Third embodiment]

[1080] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1081] 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.

[1082] 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).

[1083] 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.

[1084] 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.

[1085] 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).

[1086] 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. 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.

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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.

[1091] 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."

[1092] An embodiment of the present invention is a system for generating and providing individually customized learning materials that enable users to study effectively. The system includes multiple means for collecting user preferences and learning styles and generating materials that meet individual learning needs.

[1093] System Overview

[1094] Collecting user preferences and learning styles

[1095] 1. When a user accesses the system for the first time, a questionnaire is displayed on the screen, including questions about the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and preferences for the character who will be narrating.

[1096] 2. The terminal collects data from the user's responses to the questionnaire and sends it to the server.

[1097] Store and manage user data

[1098] 3. The server stores the received survey data in a database, along with the user's profile information.

[1099] Generate customized learning materials

[1100] 4. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate learning materials based on the collected user data. Specifically, it customizes the following elements:

[1101] Text content according to the level of difficulty

[1102] Image styles to suit user preferences (anime, movie, etc.)

[1103] Generate voices with your chosen voice actor

[1104] Explanation animation by user-defined characters

[1105] Delivery of learning materials

[1106] 5. The server consolidates the generated learning materials and sends them to the terminal as a package.

[1107] 6. The device displays the received learning material on the screen and plays the audio.

[1108] Specific examples

[1109] Example 1: History lessons for junior high school students

[1110] 1. A user (Mr. Tanaka, a junior high school student) accesses the system for the first time. A questionnaire appears on the screen, and Mr. Tanaka answers as follows:

[1111] Level of difficulty: Junior high school level

[1112] Image usage frequency: High

[1113] Image Style: Cinematic

[1114] Voice characteristics: Male voice actor B

[1115] Description Character: Ancient Roman soldier style

[1116] 2. The device sends the collected data to the server, which stores it in a database.

[1117] 3. The server uses the generative AI model to generate a history textbook for junior high school students that makes extensive use of cinematic-style imagery, then audio-records it in the voice of voice actor B and creates an animation featuring characters resembling ancient Roman soldiers.

[1118] 4. The server consolidates the generated learning materials and sends them to the terminal.

[1119] 5. The device displays the learning material on Tanaka's screen and plays the audio. Tanaka learns the history content while watching movie-style images and listening to the audio and character explanations as he progresses through his studies.

[1120] Example 2: Health education for the elderly

[1121] 1. The user (an elderly person named Suzuki) accesses the system and answers the displayed questionnaire as follows:

[1122] Difficulty of the text: Easy

[1123] Image Frequency: Medium

[1124] Picture Style:Realistic

[1125] Voice characteristics: Female voice actor A

[1126] Description Character: Modern doctor style

[1127] 2. The device sends the data to the server, which stores it.

[1128] 3. The server uses the generative AI model to generate gently worded text using realistic images, creates audio in the voice of female voice actor A, and generates explanations by a character that looks like a modern doctor.

[1129] 4. The server consolidates these learning materials and sends them to the terminal.

[1130] 5. The device displays the learning materials on Suzuki's screen and plays the audio. Suzuki learns health knowledge while looking at realistic images and listens to the audio explanations.

[1131] As described above, this system can provide learning materials that are individually tailored to each user's preferences and learning style, enabling effective learning. This allows for high learning efficiency and satisfaction that could not be achieved with conventional, uniform learning materials.

[1132] The processing flow will be explained below.

[1133] Step 1:

[1134] A user accesses the learning system for the first time. Upon access, a questionnaire about preferences and learning styles is displayed as an initial setting.

[1135] Step 2:

[1136] The device displays a survey form to the user, which the user answers, including the following items:

[1137] Difficulty of the text

[1138] Image frequency

[1139] Image Style

[1140] Audio Features

[1141] Description Character Preferences

[1142] Step 3:

[1143] The user answers the questionnaire form and presses the send button. The response data is collected and sent to the system by the terminal.

[1144] Step 4:

[1145] The device sends the collected survey data to the server, encoded in an appropriate format such as JSON.

[1146] Step 5:

[1147] The server stores the received survey data in a database, along with the user's profile information (ID, name, etc.).

[1148] Step 6:

[1149] The server invokes a generative AI model (e.g., GPT-4) to generate customized training text based on the stored user data.

[1150] Step 7:

[1151] The server invokes an image generation process to generate an image in the style selected by the user (e.g., film style, anime style), using an image generation model such as DALL-E.

[1152] Step 8:

[1153] The server invokes a speech generation process to convert the training text into a voice of the voice actor selected by the user, specifically, a Text-to-Speech (TTS) engine.

[1154] Step 9:

[1155] The server invokes the character generation process, which generates a character based on the character style selected by the user (e.g., ancient Roman soldier, modern doctor).

[1156] Step 10:

[1157] The server integrates the generated text, images, audio, and character animations and packages them as learning materials.

[1158] Step 11:

[1159] The server sends the integrated learning material package to the terminal, using a communication protocol such as the Internet.

[1160] Step 12:

[1161] The device displays the received learning material on the user's screen and plays the audio. Images, text, audio, and characters are arranged and played appropriately, and the user can begin learning.

[1162] Step 13:

[1163] After studying, users provide feedback, including the quality of the learning material, their level of understanding, and changes in their preferences.

[1164] Step 14:

[1165] The device collects feedback data and sends it to a server, which stores it in a database and uses it to generate future learning materials.

[1166] The above are the specific processing steps of the system based on the claims. Through these steps, learning materials tailored to individual user needs and preferences can be efficiently generated and provided.

[1167] Example 1

[1168] 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."

[1169] Conventional learning systems often provide uniform learning materials and are unable to accommodate individual users' preferences and learning styles, resulting in reduced learning efficiency and difficulty in improving user satisfaction. Furthermore, there is a lack of means to generate and appropriately distribute learning materials optimized for each user, making it difficult to provide an effective learning experience.

[1170] 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.

[1171] In this invention, the server includes means for collecting user preferences and learning styles, means for storing the collected user data, means for generating customized learning materials based on the user data using a generative AI model, means for transmitting the generated learning materials to the user's terminal, and means for displaying and playing the integrated learning materials on the user's terminal, thereby providing learning materials optimized according to each user's preferences and learning style, enabling effective learning.

[1172] "User preferences and learning styles" refer to the user's personal learning preferences and the methods and formats that maximize learning efficiency.

[1173] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to automatically generate learning materials such as text, images, audio, and animations based on user data.

[1174] A "prompt sentence" refers to an input sentence given to a generative AI model to generate the desired output.

[1175] "Learning materials" refers to information content such as text, images, audio, and animations that users use to study.

[1176] "Terminal" refers to the device (computer, smartphone, tablet, etc.) that a user uses to access the system and view and use learning materials.

[1177] "Server" refers to a computer system that processes and stores data sent by users, distributes generated learning materials, etc.

[1178] "Database" refers to a system or structure for storing and managing collected data such as user preferences, learning styles, and survey results.

[1179] "Feedback" refers to the evaluations and opinions provided by users after using learning materials, and is used to adjust the quality and content of the learning materials based on this.

[1180] A "survey" refers to a collection of questions presented to a user to gather information about their preferences and learning style.

[1181] An embodiment of the present invention is a system for generating and providing individually customized learning materials that enable users to study effectively. The system includes multiple means for collecting user preferences and learning styles and generating materials that meet individual learning needs.

[1182] The main components of this system are the user device, the server, and the generative AI model. Specific examples of devices include smartphones, tablets, and PCs, while the server is a cloud server or dedicated server. GPT-4 and an image generation model are used as generative AI models.

[1183] Collecting user preferences and learning styles

[1184] When users first access the system, they are presented with a survey screen, which includes the following items:

[1185] Difficulty level of the text (e.g. elementary school, junior high school, high school)

[1186] Frequency of image use (e.g. low, medium, high)

[1187] Image style (e.g., anime, film, realistic)

[1188] Voice characteristics (e.g. male voice actor A, female voice actor B)

[1189] Describe the character's preference (e.g., Roman soldier, modern doctor)

[1190] The user answers these questions and sends the survey data from the terminal to the server using a communication method such as an HTTP request.

[1191] Store and manage user data

[1192] The server stores the received survey data in a database, which contains the user's profile information and survey responses.

[1193] Generate customized learning materials

[1194] The server generates customized learning materials using a generative AI model based on the received data. This generation process includes inputting prompt sentences into the generative AI model.

[1195] An example of a specific prompt is as follows:

[1196] "Please explain a history lesson for junior high school students using movie-style images in the voice of male voice actor B. I also need an animation featuring a character that looks like an ancient Roman soldier."

[1197] The generative AI model generates text, images, audio, and animations based on the prompts, and the generated content is collected on a server and integrated into a learning package.

[1198] Delivery and display of learning materials

[1199] The server then sends the generated learning package to the terminal, which then displays the received learning material to the user and plays audio as needed.

[1200] Specific examples

[1201] A specific example of this system is shown below.

[1202] Example 1: History lessons for junior high school students

[1203] A user (a junior high school student) accesses the system for the first time and answers a questionnaire as follows:

[1204] Level of difficulty: Junior high school level

[1205] Image usage frequency: High

[1206] Image Style: Cinematic

[1207] Voice characteristics: Male voice actor B

[1208] Description Character: Ancient Roman soldier style

[1209] The device sends the collected data to a server, which stores it in a database. The server uses a generative AI model to generate learning materials based on the above settings and creates a learning package. This package is sent to the device. The device displays the received learning materials on the screen and plays audio. The user learns the historical content while watching movie-style images and listening to audio and character explanations as they progress through their studies.

[1210] Example 2: Health education for the elderly

[1211] A user (senior citizen) accesses the system and answers the questionnaire as follows:

[1212] Difficulty of the text: Easy

[1213] Image Frequency: Medium

[1214] Picture Style:Realistic

[1215] Voice characteristics: Female voice actor A

[1216] Description Character: Modern doctor style

[1217] The device sends the data to the server, which stores it. The server uses a generative AI model to generate gently worded text using realistic images, creates audio in the voice of female voice actor A, and generates explanations by a character that looks like a modern doctor. These learning materials are then integrated and sent to the device. The device then displays the received learning materials on its screen and plays the audio. The user learns health knowledge while viewing realistic images and receives explanations while listening to the audio.

[1218] In this way, the system can individually accommodate each user's preferences and learning style, promoting effective learning.

[1219] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1220] Step 1: The user accesses the system.

[1221] Input: User access (e.g., typing a URL in a web browser).

[1222] Output: Display of the survey screen.

[1223] Specific operation: The user accesses the system's URL using a browser on a smartphone or PC.

[1224] Step 2: The device will display the survey screen.

[1225] Input: The system's web page request.

[1226] Output: Display of the survey screen.

[1227] Specific operation: The device receives HTML data from the server and displays a questionnaire screen to the user. The questionnaire includes questions about the difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and preferences for explanatory characters.

[1228] Step 3: The user completes the survey.

[1229] Input: User's survey responses.

[1230] Output: User response data.

[1231] Specific operation: The user enters the answer to the questionnaire item and presses the submit button. At this point, the response data is collected on the device.

[1232] Step 4: The terminal transmits the user response data to the server.

[1233] Input: User response data.

[1234] Output: Sending data to the server.

[1235] Specific operation: The device sends the collected response data to the server using an HTTP request or WebSocket.

[1236] Step 5: The server receives the survey data and stores it in a database.

[1237] Input: User response data sent from the device.

[1238] Output: Confirmation of saving to database.

[1239] Specific operation: The server analyzes the received survey data and executes an INSERT statement to the corresponding user record in the database to save it.

[1240] Step 6: The server generates a prompt sentence based on the user data and inputs it into the generative AI model.

[1241] Input: User data.

[1242] Output: Prompt sentence and learning material.

[1243] Specific operation: The server generates prompts based on the user's preferences and learning style. For example, a sentence like "Please explain history for junior high school students using movie-style images in the voice of male voice actor B. An animation featuring characters resembling ancient Roman soldiers is also required." is input into the generative AI model.

[1244] Step 7: The generative AI model generates customized learning materials.

[1245] Input: The prompt text sent by the server.

[1246] Output: Customized text, images, audio, animation.

[1247] Specific operation: The generative AI model generates text, images, audio, and animation based on the prompt. For example, GPT-4 generates text, the image generation model generates images, and the speech synthesis model generates audio.

[1248] Step 8: The server integrates the generated learning materials and creates a learning package.

[1249] Input: Multiple learning materials (text, images, audio, animation) from a generative AI model.

[1250] Output: A learning package.

[1251] Specific operation: The server combines each generated material into a single learning package and creates a JSON file to manage metadata.

[1252] Step 9: The server sends the learning package to the terminal.

[1253] Input: Learning package.

[1254] Output: Sending data to the terminal.

[1255] Specific operation: The server sends the learning package to the device using HTTP responses or WebSockets.

[1256] Step 10: The terminal receives the learning package and displays and plays it for the user.

[1257] Input: The learning package sent from the server.

[1258] Output: Screen display and audio playback.

[1259] What it does: The device analyzes the received learning package, displays text and images on the screen, plays audio files, and displays animations on the screen.

[1260] (Application example 1)

[1261] 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."

[1262] Conventional online shopping systems lack the ability to customize services to suit individual user preferences and styles, making it difficult to enhance user satisfaction. In particular, the lack of personalized recommendations that reflect each user's unique shopping style and product preferences is an obstacle to improving the user experience.

[1263] 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.

[1264] In this invention, the server includes means for collecting user preferences and shopping styles, means for storing the collected user data, means for generating individually customized product recommendations based on the stored data, means for transmitting the generated product recommendations to the user's terminal, means for collecting feedback regarding the product recommendations, and means for adjusting the product recommendations based on the collected feedback, thereby enabling personalized product recommendations based on the user's individual preferences and styles.

[1265] "User preferences and shopping style" refers to the user's tastes and purchasing behavior, product categories of interest, purchasing budget, color and design preferences, and the like.

[1266] "Collection Methods" means systems and methods for obtaining user data through surveys or automated behavioral tracking.

[1267] "Storage means" refers to a system or method for storing and managing collected user data in a storage device such as a database.

[1268] "Means for generating customized product recommendations" means a system or method for creating individually optimized product listings and related information based on collected and stored user data.

[1269] "Transmission means" refers to a network communication means or method for delivering the generated product recommendation information to the user's terminal.

[1270] "Feedback collection means" means a system or method that provides a form or interface for collecting user-provided opinions or ratings.

[1271] "Adjustment" refers to systems and methods for optimizing product recommendation content and algorithms based on collected feedback.

[1272] A "generative AI model" is an artificial intelligence model used for natural language processing, image generation, etc., and includes advanced machine learning algorithms such as GPT-4 and DALL-E.

[1273] A "prompt" refers to a text instruction entered into a generative AI model to cause it to generate a particular output.

[1274] System Overview

[1275] This invention is a virtual shopping system that provides individually customized product recommendations based on a user's preferences and shopping style. The system includes the following major components: means for collecting user preferences and shopping style, means for storing the collected user data, means for generating individually customized product recommendations based on the stored data, means for transmitting the generated product recommendations to the user's terminal, means for collecting feedback regarding the product recommendations, and means for adjusting the product recommendations based on the collected feedback.

[1276] Collecting user preferences and shopping styles

[1277] 1. When a user accesses the system for the first time, a shopping survey is displayed on the screen.

[1278] Questionnaire questions include preferred colors, styles, budget ranges, and areas of interest.

[1279] The user responds to the survey.

[1280] 2. The terminal collects the questionnaire data answered by the user and sends it to the server.

[1281] Store and manage user data

[1282] 3. The server stores the received survey data in a database (e.g., MySQL), along with the user's profile information.

[1283] Generating customized product recommendations

[1284] 4. The server uses a generative AI model (e.g., GPT-4, image generation model DALL-E) to generate product recommendations based on the collected user data.

[1285] Specifically, customize the following elements:

[1286] A list of products that match the user's preferences

[1287] Recommended product images (anime style, realistic style, etc.)

[1288] Audio explanation of the product

[1289] Animated introduction using characters created by the user

[1290] Product recommendation delivery

[1291] 5. The server consolidates the generated product recommendations and sends them to the terminal as a package.

[1292] 6. The device displays the received product recommendation on the screen and plays it back as audio.

[1293] Collecting and adjusting feedback on product recommendations

[1294] 7. The device collects feedback from the user and sends it to the server.

[1295] 8. The server optimizes the content and algorithm of product recommendations based on the collected feedback.

[1296] Specific examples

[1297] Example 1: Fashion item recommendation

[1298] 1. A user (e.g., Mr. A) accesses the system for the first time and answers a questionnaire.

[1299] "Favorite color: Blue, Style: Casual, Budget: Under 10,000 yen, Interests: Sneakers"

[1300] 2. The device sends the collected data to the server, which stores it in a database.

[1301] 3. The server uses the generative AI model to generate product lists and images based on the following prompt:

[1302] "Generate a list of recommended fashion items based on user A's preferences. Style is casual, color is blue, and budget is under 10,000 yen."

[1303] "Create anime-style product images based on the generated product list."

[1304] 4. The server sends the generated product recommendation package to the terminal, which displays it to the user and explains it aloud.

[1305] 5. The user reviews the recommended products and provides feedback.

[1306] 6. The device sends feedback to the server, which then adjusts the algorithm based on that feedback.

[1307] The system can provide a personalized shopping experience that reflects a user's individual tastes and style.

[1308] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1309] Step 1:

[1310] When a user accesses the system for the first time, a shopping questionnaire is displayed on the terminal. The user answers questions about their preferred colors, styles, budget range, areas of interest, etc. The input information is basic data for making personalized recommendations for the user. The terminal collects the questionnaire data answered by the user. Input: User's questionnaire answers. Output: Collected questionnaire data.

[1311] Step 2:

[1312] The terminal sends the collected survey data to the server. The server verifies the received survey data and stores it in a database (e.g. MySQL). The stored data also includes user profile information. Input: Survey data. Output: User data stored in the database.

[1313] Step 3:

[1314] The server uses a generative AI model (e.g., GPT-4) to generate product recommendations based on the collected and stored user data. Specifically, it uses the stored data as input and issues prompts to the AI ​​model to generate a product list.

[1315] Example prompt sentence:

[1316] "Generate a list of recommended products based on user A's preferences. Style is casual, color is blue, and budget is under 10,000 yen."

[1317] Input: saved user data, prompt text. Output: generated product list.

[1318] Step 4:

[1319] The server generates customized product images based on the product list using an image generation model (e.g., DALL-E).

[1320] Example prompt sentence:

[1321] "Create anime-style product images based on the generated product list."

[1322] Input: Product list, prompt. Output: Generated product images.

[1323] Step 5:

[1324] The server combines the generated product list and product images and sends them as a package to the terminal. The terminal displays the received product recommendations on the screen and plays back audio descriptions using the speech generation model. Input: Product list and product images. Output: Product recommendations displayed on the terminal and audio descriptions.

[1325] Step 6:

[1326] The user reviews the displayed product recommendations and provides feedback based on their purchasing intentions and interests. The terminal collects the user's feedback. Input: User's feedback. Output: Collected feedback.

[1327] Step 7:

[1328] The device sends the collected feedback to the server, which makes adjustments to optimize the product recommendation algorithm and content based on the received feedback. Input: User feedback. Output: Adjusted product recommendation algorithm and data.

[1329] Through the above processing steps, personalized product recommendations based on the user's preferences are provided.

[1330] 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.

[1331] An embodiment of the present invention is a system that provides individually customized learning materials to enable users to study effectively, recognizes users' emotions in real time, and adjusts the learning materials appropriately based on that information. The system collects users' preferences, learning styles, and emotions, and generates and provides optimal educational content based on this information.

[1332] System Overview

[1333] Collecting user preferences and learning styles

[1334] 1. When a user first accesses the system, they are presented with a questionnaire about their preferences and learning style, including the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and the preference for narrators.

[1335] 2. The terminal collects data from the user's responses to the questionnaire and sends it to the server.

[1336] Store and manage user data

[1337] 3. The server stores the received survey data in a database, along with the user's profile information.

[1338] Emotion Recognition and Data Collection

[1339] 4. The device uses devices such as a camera and microphone to collect emotional data in real time from the user's facial expressions and voice.

[1340] 5. The device analyzes the collected emotion data and uses an emotion engine to identify the user's current emotional state.

[1341] 6. The device sends the identified emotion data to the server.

[1342] 7. The server stores the received emotion data in a database.

[1343] Generate customized learning materials

[1344] 8. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate training materials based on the stored user data and emotion data. The generated training materials include the following elements:

[1345] Text content according to the level of difficulty

[1346] Image styles to suit user preferences (anime, movie, etc.)

[1347] Voice generated by selected voice actors

[1348] Explanation animation by user-defined characters

[1349] Delivery of learning materials

[1350] 9. The server consolidates the generated learning materials and sends them to the terminal as a package.

[1351] 10. The device displays the received learning material on the screen and plays the audio.

[1352] Dynamic Adjustment

[1353] 11. The device continues to collect emotional data in real time while learning, and if adjustments are needed to suit different conditions, it sends that information to the server.

[1354] 12. The server dynamically adjusts the content of the learning material based on the latest emotional data received and sends it back to the device.

[1355] Specific examples

[1356] Example 1: English language learning for primary school students

[1357] 1. A user (Mr. Sato, an elementary school student) accesses the system for the first time. He answers the questionnaire displayed on the screen with the following options: "Text difficulty: Elementary school-aged," "Image usage frequency: High," "Image style: Anime-style," "Audio characteristics: Child's voice," and "Explanatory character: Animal character."

[1358] 2. The terminal sends the survey data to the server, which stores the data in a database.

[1359] 3. The device uses a camera and microphone to collect emotional data from Sato's facial expressions and voice, and then uses an emotion engine to identify his emotional state.

[1360] 4. The device sends the emotion data to the server, which stores it in a database.

[1361] 5. Based on the saved data, the server generates English textbooks for elementary school students, featuring a wide range of cartoon-style images. The audio is recorded using a child's voice, and animated animal characters are created.

[1362] 6. The server consolidates the generated learning materials and sends them to the terminal.

[1363] 7. The device displays the learning material on Sato's screen and plays the audio.

[1364] 8. The device will collect emotional data while learning, and if Sato's emotions change, it will send that information to the server.

[1365] 9. The server dynamically adjusts the learning material as needed and sends it back to the device.

[1366] Example 2: History study for high school graduation exams

[1367] 1. A user (high school student named Tanaka) accesses the system and answers the questionnaire with the following options: "Text difficulty: for high school students," "Image use frequency: medium," "Image style: realistic," "Audio characteristics: male voice actor A," and "Explanatory character: historical figure-like."

[1368] 2. The terminal sends the survey data to the server, which stores the data in a database.

[1369] 3. The device uses a camera and microphone to collect emotion data from Tanaka's facial expressions and voice, and then uses an emotion engine to identify her emotional state.

[1370] 4. The device sends the emotion data to the server, which stores it in a database.

[1371] 5. Based on the saved data, the server generates a history textbook for high school students using realistic images. Voices are recorded by male voice actor A, and animations of characters resembling historical figures are created.

[1372] 6. The server consolidates the generated learning materials and sends them to the terminal.

[1373] 7. The device displays the learning material on Tanaka's screen and plays the audio.

[1374] 8. The device will collect emotional data while learning, and if Tanaka's emotions change, it will send that information to the server.

[1375] 9. The server dynamically adjusts the learning material as needed and sends it back to the device.

[1376] In this way, the present invention is a system that provides learning materials that are individually customized based on the user's preferences, learning style, and emotions, helping the user achieve high learning effectiveness. This provides a highly accurate learning experience that could not be achieved with conventional, uniform learning materials.

[1377] The processing flow will be explained below.

[1378] Step 1:

[1379] When a user first accesses the system, they are presented with a questionnaire about their preferences and learning style, including the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the audio, and their preference for explanatory characters.

[1380] Step 2:

[1381] The device collects the data of the user's responses to the survey and sends it to the server, encoded in an appropriate format such as JSON.

[1382] Step 3:

[1383] The server stores the received survey data in a database, including user profile information (ID, name, etc.).

[1384] Step 4:

[1385] The device uses devices such as a camera and microphone to collect emotional data in real time from the user's facial expressions and voice.

[1386] Step 5:

[1387] The device analyzes the collected emotion data and identifies the user's current emotional state using an emotion engine, which includes algorithms for facial and voice analysis.

[1388] Step 6:

[1389] The device sends the identified emotion data to the server, which is also encoded in an appropriate format such as JSON.

[1390] Step 7:

[1391] The server stores the received emotion data in a database, where it is linked to the user's profile.

[1392] Step 8:

[1393] The server invokes a generative AI model (e.g., GPT-4) to generate individually customized training text based on the stored user data and sentiment data.

[1394] Step 9:

[1395] The server invokes an image generation process to generate an image in the style selected by the user (e.g., film style, anime style), using an image generation model such as DALL-E.

[1396] Step 10:

[1397] The server invokes a speech generation process to translate the training text into a voice of the selected voice actor, specifically, using a Text-to-Speech (TTS) engine.

[1398] Step 11:

[1399] The server invokes a character generation process to generate a character based on the character style selected by the user (e.g., an ancient Roman soldier or a modern doctor).

[1400] Step 12:

[1401] The server integrates the generated text, images, audio, and character animations and packages them as learning materials.

[1402] Step 13:

[1403] The server sends the integrated learning material package to the terminal, using a communication protocol such as the Internet.

[1404] Step 14:

[1405] The device displays the received learning material on the user's screen and plays the audio. Images, text, audio, and characters are arranged and played appropriately, and the user can begin learning.

[1406] Step 15:

[1407] The device continues to collect emotional data in real time while learning, and if the user's emotional state changes, the data is also sent to the server.

[1408] Step 16:

[1409] The server dynamically adjusts the learning material based on the latest emotional data it receives, for example, by adding more engaging content or images if the user is losing interest.

[1410] Step 17:

[1411] The server then sends the modified or adjusted learning material back to the device, which then displays the new material and plays the audio.

[1412] In this way, the system supports effective learning by providing and dynamically adjusting learning materials that are individually customized based on the user's preferences, learning style, and even emotional state.

[1413] Example 2

[1414] 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."

[1415] Conventional learning systems have difficulty customizing learning materials to suit individual users' preferences and learning styles, and have been unable to provide appropriate learning materials according to the user's emotional state. This has resulted in problems with users not being able to fully achieve their learning goals.

[1416] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1417] In this invention, the server includes means for collecting user preferences and learning styles, means for saving the collected user data, means for collecting emotional data from the user's facial expressions and voice using devices such as a camera and microphone and analyzing the emotional data, means for saving the collected emotional data, means for using a generative AI model to generate individually customized learning materials based on the saved user data and emotional data, means for transmitting the generated learning materials to the user's device, and means for collecting emotional data in real time even during learning and dynamically adjusting the learning materials, thereby making it possible to provide optimal learning materials according to the user's preferences and emotional state.

[1418] "User preferences and learning style" refers to the user's preferred content format, difficulty level, frequency of use, visual and auditory elements, and preferred learning methods.

[1419] "Customized learning materials" refers to educational content generated based on a user's preferences, learning style, and real-time emotional data.

[1420] "Emotional Data" refers to data about a user's current emotional state collected from the user's facial expressions and voice using devices such as a camera or microphone.

[1421] "Generative AI models" refer to artificial intelligence algorithms that generate learning materials based on collected user and emotional data. Specifically, they include AI models that perform natural language processing and image generation.

[1422] "Means for dynamic adjustment" refers to the function of analyzing the user's emotional data in real time and updating or changing the content of the learning material as needed.

[1423] "Terminal" refers to any device that a user accesses, including, for example, a PC, smartphone, or tablet.

[1424] "Server" refers to a remote computer system that stores and processes user data and sentiment data, including databases and infrastructure for running AI models.

[1425] "Survey data" refers to the response data to questions about preferences and learning styles that users answer when they first access the system.

[1426] An "emotion engine" refers to software or algorithms that analyze user data acquired through a camera or microphone and identify their emotional state.

[1427] The embodiment of the present invention is a system that provides individually customized learning materials to enable users to study effectively, recognizes the user's emotions in real time, and adjusts the learning materials appropriately based on that information. This system is described in detail below.

[1428] Collecting user preferences and learning styles

[1429] When a user first accesses the system, the device displays a questionnaire about preferences and learning style through a user interface. This questionnaire includes the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and the preference of explanatory characters. When the user answers the questionnaire, the device collects the data and sends it to a server. The device uses a user interface that runs on a web browser or a mobile app.

[1430] Store and manage user data

[1431] The server stores the received survey data in a relational database (e.g., MySQL, PostgreSQL), and also records user profile information.

[1432] Emotion Recognition and Data Collection

[1433] The device uses a camera and microphone to collect emotion data from the user's facial expressions and voice in real time. The devices used here include a PC's built-in camera, an external webcam, and a microphone. The collected emotion data is analyzed by the device, and the user's emotional state is identified using an emotion engine (e.g., Microsoft Azure Face API, Google Cloud Speech-to-Text API). The identified emotion data is sent from the device to a server, which stores it in a database.

[1434] Generate customized learning materials

[1435] The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate training materials based on the stored user data and emotion data. The generated training materials include the following elements:

[1436] Text content according to the level of difficulty

[1437] Image styles to suit user preferences (anime, movie, etc.)

[1438] Voice generated by selected voice actors

[1439] Explanation animation by user-defined characters

[1440] Delivery of learning materials

[1441] The server integrates the generated learning materials and sends them as a package to the device, which then displays the received learning materials on the screen and plays the audio.

[1442] Dynamic Adjustment

[1443] The device continues to collect emotional data in real time while learning and sends it to the server. The server dynamically adjusts the content of the learning materials based on the latest emotional data and sends them back to the device. This allows the device to provide optimal learning materials according to the user's emotional state.

[1444] Specific examples

[1445] Example 1: English language learning for primary school students

[1446] 1. A user (elementary school student) accesses the system for the first time and answers the questionnaire with the following options: "Text difficulty: for elementary school students," "Frequency of image use: high," "Image style: anime-style," "Audio characteristics: child's voice," and "Explanatory character: animal character."

[1447] 2. The terminal sends the survey data to the server, which stores the data in a database.

[1448] 3. The device uses a camera and microphone to collect emotional data from facial expressions and voice, and then uses an emotion engine to identify the emotional state.

[1449] 4. The device sends the emotion data to the server, which stores it in a database.

[1450] 5. Based on the saved data, the server generates English textbooks for elementary school students, featuring a wide range of cartoon-style images. Audio is recorded using children's voices, and animations featuring animal characters are created.

[1451] 6. The server consolidates the generated learning materials and sends them to the terminal.

[1452] 7. The device displays the learning material on the screen and plays the audio.

[1453] 8. The device collects emotional data during learning and sends the information to the server as needed.

[1454] 9. The server dynamically adjusts the learning material and sends it back to the device.

[1455] Prompt Sentence Examples

[1456] "Generate an anime-style English learning textbook for elementary school students. Images should be used frequently, with children's voices and animal characters as explanatory characters."

[1457] Example 2: History study for high school graduation exams

[1458] 1. The user (high school student) accesses the system and answers the questionnaire with the following options: "Text difficulty: for high school students," "Image use frequency: medium," "Image style: realistic," "Audio characteristics: male voice actor," and "Explanatory character: historical figure style."

[1459] 2. The terminal sends the survey data to the server, which stores the data in a database.

[1460] 3. The device uses a camera and microphone to collect emotional data from facial expressions and voice, and then uses an emotion engine to identify the emotional state.

[1461] 4. The device sends the emotion data to the server, which stores it in a database.

[1462] 5. Based on the saved data, the server generates historical textbooks for high school students using realistic images. Audio is recorded by male voice actors, and animated characters that resemble historical figures are created.

[1463] 6. The server consolidates the generated learning materials and sends them to the terminal.

[1464] 7. The device displays the learning material on the screen and plays the audio.

[1465] 8. The device collects emotional data during learning and sends the information to the server as needed.

[1466] 9. The server dynamically adjusts the learning material and sends it back to the device.

[1467] Prompt Sentence Examples

[1468] "Generate a realistic history textbook for high school students. Images should be used moderately, audio should be provided by a male voice actor, and explanatory characters should look like historical figures."

[1469] In this way, the present invention is a system that provides learning materials that are individually customized based on the user's preferences, learning style, and emotions, helping the user achieve high learning effectiveness. This provides a highly accurate learning experience that could not be achieved with conventional, uniform learning materials.

[1470] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1471] Step 1: Collect user surveys

[1472] 1-1. The user accesses the system for the first time. The questionnaire includes questions about the difficulty of the text, the frequency of image use, the style of the image, the characteristics of the voice, and the preference for the explanatory character.

[1473] Input: The user answers the survey items.

[1474] Operation: A questionnaire screen is displayed and the user answers each item.

[1475] Output: User response data.

[1476] 1-2. The device collects the user's response data and sends it to the server.

[1477] Input: User response data.

[1478] Operation: The device sends the response data to the server.

[1479] Output: Survey data sent to the server.

[1480] Step 2: Save user data

[1481] 2-1. The server stores the received survey data in a relational database, such as MySQL or PostgreSQL.

[1482] Input: Survey data.

[1483] How it works: The server saves the survey data in a database.

[1484] Output: Survey data stored in a database.

[1485] 2-2. The server also records the user's profile information.

[1486] Input: User's personal information.

[1487] How it works: The server stores user profile information in a database.

[1488] Output: User profile information stored in a database.

[1489] Step 3: Collecting emotion data

[1490] 3-1. The device uses a camera and microphone to collect emotional data from the user's facial expressions and voice in real time. The devices used include the PC's built-in camera, an external webcam, and a microphone.

[1491] Input: User facial expressions and voice collected by camera and microphone.

[1492] What it does: Your device collects data through its camera and microphone.

[1493] Output: Collected emotion data.

[1494] 3-2. The device analyzes the collected emotion data and identifies the user's current emotional state using an emotion engine, such as the Microsoft Azure Face API or the Google Cloud Speech-to-Text API.

[1495] Input: Collected emotion data.

[1496] How it works: The emotion engine analyzes the emotion data and identifies the user's emotional state.

[1497] Output: Identified emotion data.

[1498] 3-3. The device sends the identified emotion data to the server.

[1499] Input: Identified emotion data.

[1500] Operation: The device sends emotion data to the server.

[1501] Output: Emotion data sent to the server.

[1502] 3-4. The server stores the received emotion data in a database.

[1503] Input: Emotion data.

[1504] How it works: The server stores emotion data in a database.

[1505] Output: Emotion data stored in a database.

[1506] Step 4: Generate customized learning materials

[1507] 4-1. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate learning materials based on the stored user data and emotion data.

[1508] Input: User data and emotion data.

[1509] How it works: The AI ​​model analyzes the data and generates optimal learning materials for the user.

[1510] Output: The generated learning material.

[1511] 4-2. The generated learning materials include the following elements:

[1512] Text content according to the level of difficulty

[1513] Image styles to suit user preferences (anime, movie, etc.)

[1514] Voice generated by selected voice actors

[1515] Explanation animation by user-defined characters

[1516] Input: Individual elements of user data (e.g. difficulty of text, frequency of image use, etc.).

[1517] How it works: The AI ​​model generates materials based on each element.

[1518] Output: Each element of the customized learning material.

[1519] Step 5: Deliver learning materials

[1520] 5-1. The server integrates the generated learning materials and sends them to the terminal as a package.

[1521] Input: Generated learning material.

[1522] How it works: The server collects the material into a single package and sends it to the device.

[1523] Output: The learning material package sent to the device.

[1524] 5-2. The device displays the received learning material on the screen and plays the audio.

[1525] Input: Received learning material package.

[1526] What it does: The device displays the material on the screen and plays the audio.

[1527] Output: Learning material that is visible and audible to the user.

[1528] Step 6: Dynamic adjustment

[1529] 6-1. The device continues to collect emotional data in real time even during learning, and if adjustments are needed to suit different conditions, it sends that information to the server.

[1530] Input: Emotion data collected in real time.

[1531] Operation: The device continues to collect emotion data and transmits it to the server.

[1532] Output: The latest emotion data sent to the server.

[1533] 6-2. The server dynamically adjusts the content of the learning material based on the latest emotional data received and sends it back to the device.

[1534] Input: Latest emotion data.

[1535] How it works: The server analyzes the emotion data and adjusts the learning material as needed.

[1536] Output: Dynamically adjusted learning material.

[1537] (Application example 2)

[1538] 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."

[1539] With current learning systems, it is difficult to customize learning materials to suit each user's preferences and learning style. It is also extremely difficult to grasp the user's emotional state in real time while learning and instantly adjust the learning materials. This results in problems such as users being unable to study effectively and reduced learning efficiency.

[1540] 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.

[1541] In this invention, the server includes means for collecting user preferences and learning styles, means for storing the collected user data, means for generating individually customized learning materials based on the stored data and the user's emotional data, means for transmitting the generated learning materials to the user's terminal, and means for collecting emotional data in real time during learning and dynamically adjusting the materials. This allows the server to provide individually customized learning materials, enabling users to achieve high learning effectiveness.

[1542] "Preferences" refer to the types and formats of learning content that a user particularly prefers.

[1543] "Learning style" refers to a particular learning method or approach that a user takes to effectively learn.

[1544] "Emotion data" is data that indicates the user's current emotional state, extracted from the user's facial expressions and voice.

[1545] "Customized learning materials" refers to learning content that is individually tailored to a user based on their preferences, learning style, and emotional data.

[1546] "Collecting in real time" means that data is collected continuously while the user is studying.

[1547] "Dynamic adjustment" refers to changing the content of learning materials on the fly based on collected data.

[1548] "Terminal" refers to a device used by a user, such as a smartphone or smart glasses.

[1549] "Server" refers to the central computing system that stores user data and generates and delivers learning materials.

[1550] System configuration explanation

[1551] The system of the present invention mainly includes means for collecting user preferences and learning styles, means for collecting emotional data in real time, means for generating individually customized learning materials based on the stored data and the user's emotional data, and means for transmitting the generated learning materials to a terminal.

[1552] Hardware and software used

[1553] The system uses the following hardware and software:

[1554] Device: The smartphone or smart glasses used by the user, including the camera, microphone, and other input devices.

[1555] Server: A high-performance computing system, either on cloud or on-premise, that stores user data and generates and delivers learning materials.

[1556] Emotion recognition software: Facial expression recognition libraries and voice analysis tools (e.g., EmotionRecognizer).

[1557] Generative AI models: High-performance text and image generation models such as GPT-4.

[1558] Program processing overview

[1559] 1. The device initially collects data by conducting a survey about the user's preferences and learning style.

[1560] 2. The device sends the collected data to the server, which stores it in a database.

[1561] 3. The device uses a camera and microphone to collect and analyze emotional data from the user's facial expressions and voice in real time.

[1562] 4. The device sends the analyzed emotion data to the server, which stores it in a database.

[1563] 5. The server generates customized learning materials using a generative AI model based on the stored user data and emotion data.

[1564] 6. The server sends the generated learning material to the terminal, which displays or plays it to the user.

[1565] 7. The device continues to collect emotional data in real time during training and transmits the information to the server as needed.

[1566] 8. The server dynamically adjusts the learning material based on the latest emotional data and sends it back to the device.

[1567] Specific examples

[1568] For example, when a user visits a store, they put on the smart glasses and the learning process proceeds as follows:

[1569] 1. Survey collection: The user answers the survey and enters information such as "Image usage frequency: high frequency," "Image style: realistic," and "Audio characteristics: male voice."

[1570] 2. Data storage: The survey results are sent to the server and stored in the database.

[1571] 3. Emotion data collection: The camera in the smart glasses captures facial expressions and analyzes them in real time.

[1572] 4. Learning material generation: The server uses the generative AI model to create customized learning content.

[1573] 5. Content delivery: The learning content is sent to the device and the user begins learning.

[1574] 6. Real-time adjustment: Materials are dynamically adjusted according to the user's emotional state.

[1575] Prompt Sentence Examples

[1576] "User profile: They frequently use realistic images and prefer characters with male voices."

[1577] "Sentiment data: Interest is currently waning. Use this information to provide more engaging content."

[1578] This system allows users to receive individually customized learning materials on the spot, resulting in higher learning effectiveness.

[1579] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1580] Step 1:

[1581] A user accesses the system using a terminal (smartphone or smart glasses). The terminal displays a questionnaire to the user about their preferences and learning style. The user answers the questionnaire and enters the data. The user's questionnaire data is entered into the terminal. The terminal collects this data and sends it to the server.

[1582] Step 2:

[1583] The server receives the survey data sent from the device. The received data is stored in a database. The server stores the user's profile information, as well as their preferences and learning style data, for a long period of time. The input is the survey data, and the output is the stored data.

[1584] Step 3:

[1585] The device collects the user's facial expressions and voice in real time using a camera and microphone. The collected data is analyzed using a facial expression recognition library and a voice analysis tool (e.g., EmotionRecognizer). The device then sends the analyzed emotion data to a server. The input is facial expression and voice data, and the output is the analyzed emotion data.

[1586] Step 4:

[1587] The server receives the emotion data sent from the device. The received data is stored in a database. The server identifies and records the user's current emotional state. The input is the emotion data, and the output is the stored emotion data.

[1588] Step 5:

[1589] The server generates customized learning materials using a generative AI model (e.g., GPT-4) based on the stored user data and emotional data. Learning content, such as text, images, and audio, is created based on prompts input to the generative AI model. The input is user data and emotional data, and the output is customized learning materials.

[1590] Step 6:

[1591] The server integrates the generated learning materials and sends them to the terminal. The learning materials are optimized for easy understanding by the user. The input is the generated learning materials, and the output is the learning materials delivered to the terminal.

[1592] Step 7:

[1593] The terminal receives learning materials sent from the server. The terminal displays and plays these materials to the user. The user then uses the customized learning materials to progress through their learning. The input is the delivered learning materials, and the output is the user's execution of the learning.

[1594] Step 8:

[1595] During training, the device continues to collect the user's facial expressions and voice in real time using a camera and microphone. If the emotional data changes, it sends that data to the server. The input is the continuously collected emotional data, and the output is the updated emotional data.

[1596] Step 9:

[1597] The server dynamically adjusts the learning materials accordingly based on the latest emotional data. The generative AI model is again used to update the content based on the new prompt. The input is the latest emotional data, and the output is the dynamically adjusted learning materials.

[1598] Step 10:

[1599] The server sends the adjusted learning materials back to the terminal. The terminal displays and plays these materials again to the user. The user continues learning adapted to the new conditions. The input is the adjusted learning materials, and the output is the user's continued learning.

[1600] This allows users to use individually customized learning materials and enjoy a learning environment that adapts in real time as they learn.

[1601] 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.

[1602] 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.

[1603] 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.

[1604] [Fourth embodiment]

[1605] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1606] 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.

[1607] 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).

[1608] 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.

[1609] 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.

[1610] 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).

[1611] 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. 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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."

[1618] An embodiment of the present invention is a system for generating and providing individually customized learning materials that enable users to study effectively. The system includes multiple means for collecting user preferences and learning styles and generating materials that meet individual learning needs.

[1619] System Overview

[1620] Collecting user preferences and learning styles

[1621] 1. When a user accesses the system for the first time, a questionnaire is displayed on the screen, including questions about the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and preferences for the character who will be narrating.

[1622] 2. The terminal collects data from the user's responses to the questionnaire and sends it to the server.

[1623] Store and manage user data

[1624] 3. The server stores the received survey data in a database, along with the user's profile information.

[1625] Generate customized learning materials

[1626] 4. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate learning materials based on the collected user data. Specifically, it customizes the following elements:

[1627] Text content according to the level of difficulty

[1628] Image styles to suit user preferences (anime, movie, etc.)

[1629] Generate voices with your chosen voice actor

[1630] Explanation animation by user-defined characters

[1631] Delivery of learning materials

[1632] 5. The server consolidates the generated learning materials and sends them to the terminal as a package.

[1633] 6. The device displays the received learning material on the screen and plays the audio.

[1634] Specific examples

[1635] Example 1: History lessons for junior high school students

[1636] 1. A user (Mr. Tanaka, a junior high school student) accesses the system for the first time. A questionnaire appears on the screen, and Mr. Tanaka answers as follows:

[1637] Level of difficulty: Junior high school level

[1638] Image usage frequency: High

[1639] Image Style: Cinematic

[1640] Voice characteristics: Male voice actor B

[1641] Description Character: Ancient Roman soldier style

[1642] 2. The device sends the collected data to the server, which stores it in a database.

[1643] 3. The server uses the generative AI model to generate a history textbook for junior high school students that makes extensive use of cinematic-style imagery, then audio-records it in the voice of voice actor B and creates an animation featuring characters resembling ancient Roman soldiers.

[1644] 4. The server consolidates the generated learning materials and sends them to the terminal.

[1645] 5. The device displays the learning material on Tanaka's screen and plays the audio. Tanaka learns the history content while watching movie-style images and listening to the audio and character explanations as he progresses through his studies.

[1646] Example 2: Health education for the elderly

[1647] 1. The user (an elderly person named Suzuki) accesses the system and answers the displayed questionnaire as follows:

[1648] Difficulty of the text: Easy

[1649] Image Frequency: Medium

[1650] Picture Style:Realistic

[1651] Voice characteristics: Female voice actor A

[1652] Description Character: Modern doctor style

[1653] 2. The device sends the data to the server, which stores it.

[1654] 3. The server uses the generative AI model to generate gently worded text using realistic images, creates audio in the voice of female voice actor A, and generates explanations by a character that looks like a modern doctor.

[1655] 4. The server consolidates these learning materials and sends them to the terminal.

[1656] 5. The device displays the learning materials on Suzuki's screen and plays the audio. Suzuki learns health knowledge while looking at realistic images and listens to the audio explanations.

[1657] As described above, this system can provide learning materials that are individually tailored to each user's preferences and learning style, enabling effective learning. This allows for high learning efficiency and satisfaction that could not be achieved with conventional, uniform learning materials.

[1658] The processing flow will be explained below.

[1659] Step 1:

[1660] A user accesses the learning system for the first time. Upon access, a questionnaire about preferences and learning styles is displayed as an initial setting.

[1661] Step 2:

[1662] The device displays a survey form to the user, which the user answers, including the following items:

[1663] Difficulty of the text

[1664] Image frequency

[1665] Image Style

[1666] Audio Features

[1667] Description Character Preferences

[1668] Step 3:

[1669] The user answers the questionnaire form and presses the send button. The response data is collected and sent to the system by the terminal.

[1670] Step 4:

[1671] The device sends the collected survey data to the server, encoded in an appropriate format such as JSON.

[1672] Step 5:

[1673] The server stores the received survey data in a database, along with the user's profile information (ID, name, etc.).

[1674] Step 6:

[1675] The server invokes a generative AI model (e.g., GPT-4) to generate customized training text based on the stored user data.

[1676] Step 7:

[1677] The server invokes an image generation process to generate an image in the style selected by the user (e.g., film style, anime style), using an image generation model such as DALL-E.

[1678] Step 8:

[1679] The server invokes a speech generation process to convert the training text into a voice of the voice actor selected by the user, specifically, a Text-to-Speech (TTS) engine.

[1680] Step 9:

[1681] The server invokes the character generation process, which generates a character based on the character style selected by the user (e.g., ancient Roman soldier, modern doctor).

[1682] Step 10:

[1683] The server integrates the generated text, images, audio, and character animations and packages them as learning materials.

[1684] Step 11:

[1685] The server sends the integrated learning material package to the terminal, using a communication protocol such as the Internet.

[1686] Step 12:

[1687] The device displays the received learning material on the user's screen and plays the audio. Images, text, audio, and characters are arranged and played appropriately, and the user can begin learning.

[1688] Step 13:

[1689] After studying, users provide feedback, including the quality of the learning material, their level of understanding, and changes in their preferences.

[1690] Step 14:

[1691] The device collects feedback data and sends it to a server, which stores it in a database and uses it to generate future learning materials.

[1692] The above are the specific processing steps of the system based on the claims. Through these steps, learning materials tailored to individual user needs and preferences can be efficiently generated and provided.

[1693] Example 1

[1694] 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."

[1695] Conventional learning systems often provide uniform learning materials and are unable to accommodate individual users' preferences and learning styles, resulting in reduced learning efficiency and difficulty in improving user satisfaction. Furthermore, there is a lack of means to generate and appropriately distribute learning materials optimized for each user, making it difficult to provide an effective learning experience.

[1696] 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.

[1697] In this invention, the server includes means for collecting user preferences and learning styles, means for storing the collected user data, means for generating customized learning materials based on the user data using a generative AI model, means for transmitting the generated learning materials to the user's terminal, and means for displaying and playing the integrated learning materials on the user's terminal, thereby providing learning materials optimized according to each user's preferences and learning style, enabling effective learning.

[1698] "User preferences and learning styles" refer to the user's personal learning preferences and the methods and formats that maximize learning efficiency.

[1699] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to automatically generate learning materials such as text, images, audio, and animations based on user data.

[1700] A "prompt sentence" refers to an input sentence given to a generative AI model to generate the desired output.

[1701] "Learning materials" refers to information content such as text, images, audio, and animations that users use to study.

[1702] "Terminal" refers to the device (computer, smartphone, tablet, etc.) that a user uses to access the system and view and use learning materials.

[1703] "Server" refers to a computer system that processes and stores data sent by users, distributes generated learning materials, etc.

[1704] "Database" refers to a system or structure for storing and managing collected data such as user preferences, learning styles, and survey results.

[1705] "Feedback" refers to the evaluations and opinions provided by users after using learning materials, and is used to adjust the quality and content of the learning materials based on this.

[1706] A "survey" refers to a collection of questions presented to a user to gather information about their preferences and learning style.

[1707] An embodiment of the present invention is a system for generating and providing individually customized learning materials that enable users to study effectively. The system includes multiple means for collecting user preferences and learning styles and generating materials that meet individual learning needs.

[1708] The main components of this system are the user device, the server, and the generative AI model. Specific examples of devices include smartphones, tablets, and PCs, while the server is a cloud server or dedicated server. GPT-4 and an image generation model are used as generative AI models.

[1709] Collecting user preferences and learning styles

[1710] When users first access the system, they are presented with a survey screen, which includes the following items:

[1711] Difficulty level of the text (e.g. elementary school, junior high school, high school)

[1712] Frequency of image use (e.g. low, medium, high)

[1713] Image style (e.g., anime, film, realistic)

[1714] Voice characteristics (e.g. male voice actor A, female voice actor B)

[1715] Describe the character's preference (e.g., Roman soldier, modern doctor)

[1716] The user answers these questions and sends the survey data from the terminal to the server using a communication method such as an HTTP request.

[1717] Store and manage user data

[1718] The server stores the received survey data in a database, which contains the user's profile information and survey responses.

[1719] Generate customized learning materials

[1720] The server generates customized learning materials using a generative AI model based on the received data. This generation process includes inputting prompt sentences into the generative AI model.

[1721] An example of a specific prompt is as follows:

[1722] "Please explain a history lesson for junior high school students using movie-style images in the voice of male voice actor B. I also need an animation featuring a character that looks like an ancient Roman soldier."

[1723] The generative AI model generates text, images, audio, and animations based on the prompts, and the generated content is collected on a server and integrated into a learning package.

[1724] Delivery and display of learning materials

[1725] The server then sends the generated learning package to the terminal, which then displays the received learning material to the user and plays audio as needed.

[1726] Specific examples

[1727] A specific example of this system is shown below.

[1728] Example 1: History lessons for junior high school students

[1729] A user (a junior high school student) accesses the system for the first time and answers a questionnaire as follows:

[1730] Level of difficulty: Junior high school level

[1731] Image usage frequency: High

[1732] Image Style: Cinematic

[1733] Voice characteristics: Male voice actor B

[1734] Description Character: Ancient Roman soldier style

[1735] The device sends the collected data to a server, which stores it in a database. The server uses a generative AI model to generate learning materials based on the above settings and creates a learning package. This package is sent to the device. The device displays the received learning materials on the screen and plays audio. The user learns the historical content while watching movie-style images and listening to audio and character explanations as they progress through their studies.

[1736] Example 2: Health education for the elderly

[1737] A user (senior citizen) accesses the system and answers the questionnaire as follows:

[1738] Difficulty of the text: Easy

[1739] Image Frequency: Medium

[1740] Picture Style:Realistic

[1741] Voice characteristics: Female voice actor A

[1742] Description Character: Modern doctor style

[1743] The device sends the data to the server, which stores it. The server uses a generative AI model to generate gently worded text using realistic images, creates audio in the voice of female voice actor A, and generates explanations by a character that looks like a modern doctor. These learning materials are then integrated and sent to the device. The device then displays the received learning materials on its screen and plays the audio. The user learns health knowledge while viewing realistic images and receives explanations while listening to the audio.

[1744] In this way, the system can individually accommodate each user's preferences and learning style, promoting effective learning.

[1745] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1746] Step 1: The user accesses the system.

[1747] Input: User access (e.g., typing a URL in a web browser).

[1748] Output: Display of the survey screen.

[1749] Specific operation: The user accesses the system's URL using a browser on a smartphone or PC.

[1750] Step 2: The device will display the survey screen.

[1751] Input: The system's web page request.

[1752] Output: Display of the survey screen.

[1753] Specific operation: The device receives HTML data from the server and displays a questionnaire screen to the user. The questionnaire includes questions about the difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and preferences for explanatory characters.

[1754] Step 3: The user completes the survey.

[1755] Input: User's survey responses.

[1756] Output: User response data.

[1757] Specific operation: The user enters the answer to the questionnaire item and presses the submit button. At this point, the response data is collected on the device.

[1758] Step 4: The terminal transmits the user response data to the server.

[1759] Input: User response data.

[1760] Output: Sending data to the server.

[1761] Specific operation: The device sends the collected response data to the server using an HTTP request or WebSocket.

[1762] Step 5: The server receives the survey data and stores it in a database.

[1763] Input: User response data sent from the device.

[1764] Output: Confirmation of saving to database.

[1765] Specific operation: The server analyzes the received survey data and executes an INSERT statement to the corresponding user record in the database to save it.

[1766] Step 6: The server generates a prompt sentence based on the user data and inputs it into the generative AI model.

[1767] Input: User data.

[1768] Output: Prompt sentence and learning material.

[1769] Specific operation: The server generates prompts based on the user's preferences and learning style. For example, a sentence like "Please explain history for junior high school students using movie-style images in the voice of male voice actor B. An animation featuring characters resembling ancient Roman soldiers is also required." is input into the generative AI model.

[1770] Step 7: The generative AI model generates customized learning materials.

[1771] Input: The prompt text sent by the server.

[1772] Output: Customized text, images, audio, animation.

[1773] Specific operation: The generative AI model generates text, images, audio, and animation based on the prompt. For example, GPT-4 generates text, the image generation model generates images, and the speech synthesis model generates audio.

[1774] Step 8: The server integrates the generated learning materials and creates a learning package.

[1775] Input: Multiple learning materials (text, images, audio, animation) from a generative AI model.

[1776] Output: A learning package.

[1777] Specific operation: The server combines each generated material into a single learning package and creates a JSON file to manage metadata.

[1778] Step 9: The server sends the learning package to the terminal.

[1779] Input: Learning package.

[1780] Output: Sending data to the terminal.

[1781] Specific operation: The server sends the learning package to the device using HTTP responses or WebSockets.

[1782] Step 10: The terminal receives the learning package and displays and plays it for the user.

[1783] Input: The learning package sent from the server.

[1784] Output: Screen display and audio playback.

[1785] What it does: The device analyzes the received learning package, displays text and images on the screen, plays audio files, and displays animations on the screen.

[1786] (Application example 1)

[1787] 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."

[1788] Conventional online shopping systems lack the ability to customize services to suit individual user preferences and styles, making it difficult to enhance user satisfaction. In particular, the lack of personalized recommendations that reflect each user's unique shopping style and product preferences is an obstacle to improving the user experience.

[1789] 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.

[1790] In this invention, the server includes means for collecting user preferences and shopping styles, means for storing the collected user data, means for generating individually customized product recommendations based on the stored data, means for transmitting the generated product recommendations to the user's terminal, means for collecting feedback regarding the product recommendations, and means for adjusting the product recommendations based on the collected feedback, thereby enabling personalized product recommendations based on the user's individual preferences and styles.

[1791] "User preferences and shopping style" refers to the user's tastes and purchasing behavior, product categories of interest, purchasing budget, color and design preferences, and the like.

[1792] "Collection Methods" means systems and methods for obtaining user data through surveys or automated behavioral tracking.

[1793] "Storage means" refers to a system or method for storing and managing collected user data in a storage device such as a database.

[1794] "Means for generating customized product recommendations" means a system or method for creating individually optimized product listings and related information based on collected and stored user data.

[1795] "Transmission means" refers to a network communication means or method for delivering the generated product recommendation information to the user's terminal.

[1796] "Feedback collection means" means a system or method that provides a form or interface for collecting user-provided opinions or ratings.

[1797] "Adjustment" refers to systems and methods for optimizing product recommendation content and algorithms based on collected feedback.

[1798] A "generative AI model" is an artificial intelligence model used for natural language processing, image generation, etc., and includes advanced machine learning algorithms such as GPT-4 and DALL-E.

[1799] A "prompt" refers to a text instruction entered into a generative AI model to cause it to generate a particular output.

[1800] System Overview

[1801] This invention is a virtual shopping system that provides individually customized product recommendations based on a user's preferences and shopping style. The system includes the following major components: means for collecting user preferences and shopping style, means for storing the collected user data, means for generating individually customized product recommendations based on the stored data, means for transmitting the generated product recommendations to the user's terminal, means for collecting feedback regarding the product recommendations, and means for adjusting the product recommendations based on the collected feedback.

[1802] Collecting user preferences and shopping styles

[1803] 1. When a user accesses the system for the first time, a shopping survey is displayed on the screen.

[1804] Questionnaire questions include preferred colors, styles, budget ranges, and areas of interest.

[1805] The user responds to the survey.

[1806] 2. The terminal collects the questionnaire data answered by the user and sends it to the server.

[1807] Store and manage user data

[1808] 3. The server stores the received survey data in a database (e.g., MySQL), along with the user's profile information.

[1809] Generating customized product recommendations

[1810] 4. The server uses a generative AI model (e.g., GPT-4, image generation model DALL-E) to generate product recommendations based on the collected user data.

[1811] Specifically, customize the following elements:

[1812] A list of products that match the user's preferences

[1813] Recommended product images (anime style, realistic style, etc.)

[1814] Audio explanation of the product

[1815] Animated introduction using characters created by the user

[1816] Product recommendation delivery

[1817] 5. The server consolidates the generated product recommendations and sends them to the terminal as a package.

[1818] 6. The device displays the received product recommendation on the screen and plays it back as audio.

[1819] Collecting and adjusting feedback on product recommendations

[1820] 7. The device collects feedback from the user and sends it to the server.

[1821] 8. The server optimizes the content and algorithm of product recommendations based on the collected feedback.

[1822] Specific examples

[1823] Example 1: Fashion item recommendation

[1824] 1. A user (e.g., Mr. A) accesses the system for the first time and answers a questionnaire.

[1825] "Favorite color: Blue, Style: Casual, Budget: Under 10,000 yen, Interests: Sneakers"

[1826] 2. The device sends the collected data to the server, which stores it in a database.

[1827] 3. The server uses the generative AI model to generate product lists and images based on the following prompt:

[1828] "Generate a list of recommended fashion items based on user A's preferences. Style is casual, color is blue, and budget is under 10,000 yen."

[1829] "Create anime-style product images based on the generated product list."

[1830] 4. The server sends the generated product recommendation package to the terminal, which displays it to the user and explains it aloud.

[1831] 5. The user reviews the recommended products and provides feedback.

[1832] 6. The device sends feedback to the server, which then adjusts the algorithm based on that feedback.

[1833] The system can provide a personalized shopping experience that reflects a user's individual tastes and style.

[1834] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1835] Step 1:

[1836] When a user accesses the system for the first time, a shopping questionnaire is displayed on the terminal. The user answers questions about their preferred colors, styles, budget range, areas of interest, etc. The input information is basic data for making personalized recommendations for the user. The terminal collects the questionnaire data answered by the user. Input: User's questionnaire answers. Output: Collected questionnaire data.

[1837] Step 2:

[1838] The terminal sends the collected survey data to the server. The server verifies the received survey data and stores it in a database (e.g. MySQL). The stored data also includes user profile information. Input: Survey data. Output: User data stored in the database.

[1839] Step 3:

[1840] The server uses a generative AI model (e.g., GPT-4) to generate product recommendations based on the collected and stored user data. Specifically, it uses the stored data as input and issues prompts to the AI ​​model to generate a product list.

[1841] Example prompt sentence:

[1842] "Generate a list of recommended products based on user A's preferences. Style is casual, color is blue, and budget is under 10,000 yen."

[1843] Input: saved user data, prompt text. Output: generated product list.

[1844] Step 4:

[1845] The server generates customized product images based on the product list using an image generation model (e.g., DALL-E).

[1846] Example prompt sentence:

[1847] "Create anime-style product images based on the generated product list."

[1848] Input: Product list, prompt. Output: Generated product images.

[1849] Step 5:

[1850] The server combines the generated product list and product images and sends them as a package to the terminal. The terminal displays the received product recommendations on the screen and plays back audio descriptions using the speech generation model. Input: Product list and product images. Output: Product recommendations displayed on the terminal and audio descriptions.

[1851] Step 6:

[1852] The user reviews the displayed product recommendations and provides feedback based on their purchasing intentions and interests. The terminal collects the user's feedback. Input: User's feedback. Output: Collected feedback.

[1853] Step 7:

[1854] The device sends the collected feedback to the server, which makes adjustments to optimize the product recommendation algorithm and content based on the received feedback. Input: User feedback. Output: Adjusted product recommendation algorithm and data.

[1855] Through the above processing steps, personalized product recommendations based on the user's preferences are provided.

[1856] 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.

[1857] An embodiment of the present invention is a system that provides individually customized learning materials to enable users to study effectively, recognizes users' emotions in real time, and adjusts the learning materials appropriately based on that information. The system collects users' preferences, learning styles, and emotions, and generates and provides optimal educational content based on this information.

[1858] System Overview

[1859] Collecting user preferences and learning styles

[1860] 1. When a user first accesses the system, they are presented with a questionnaire about their preferences and learning style, including the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and the preference for narrators.

[1861] 2. The terminal collects data from the user's responses to the questionnaire and sends it to the server.

[1862] Store and manage user data

[1863] 3. The server stores the received survey data in a database, along with the user's profile information.

[1864] Emotion Recognition and Data Collection

[1865] 4. The device uses devices such as a camera and microphone to collect emotional data in real time from the user's facial expressions and voice.

[1866] 5. The device analyzes the collected emotion data and uses an emotion engine to identify the user's current emotional state.

[1867] 6. The device sends the identified emotion data to the server.

[1868] 7. The server stores the received emotion data in a database.

[1869] Generate customized learning materials

[1870] 8. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate training materials based on the stored user data and emotion data. The generated training materials include the following elements:

[1871] Text content according to the level of difficulty

[1872] Image styles to suit user preferences (anime, movie, etc.)

[1873] Voice generated by selected voice actors

[1874] Explanation animation by user-defined characters

[1875] Delivery of learning materials

[1876] 9. The server consolidates the generated learning materials and sends them to the terminal as a package.

[1877] 10. The device displays the received learning material on the screen and plays the audio.

[1878] Dynamic Adjustment

[1879] 11. The device continues to collect emotional data in real time while learning, and if adjustments are needed to suit different conditions, it sends that information to the server.

[1880] 12. The server dynamically adjusts the content of the learning material based on the latest emotional data received and sends it back to the device.

[1881] Specific examples

[1882] Example 1: English language learning for primary school students

[1883] 1. A user (Mr. Sato, an elementary school student) accesses the system for the first time. He answers the questionnaire displayed on the screen with the following options: "Text difficulty: Elementary school-aged," "Image usage frequency: High," "Image style: Anime-style," "Audio characteristics: Child's voice," and "Explanatory character: Animal character."

[1884] 2. The terminal sends the survey data to the server, which stores the data in a database.

[1885] 3. The device uses a camera and microphone to collect emotional data from Sato's facial expressions and voice, and then uses an emotion engine to identify his emotional state.

[1886] 4. The device sends the emotion data to the server, which stores it in a database.

[1887] 5. Based on the saved data, the server generates English textbooks for elementary school students, featuring a wide range of cartoon-style images. The audio is recorded using a child's voice, and animated animal characters are created.

[1888] 6. The server consolidates the generated learning materials and sends them to the terminal.

[1889] 7. The device displays the learning material on Sato's screen and plays the audio.

[1890] 8. The device will collect emotional data while learning, and if Sato's emotions change, it will send that information to the server.

[1891] 9. The server dynamically adjusts the learning material as needed and sends it back to the device.

[1892] Example 2: History study for high school graduation exams

[1893] 1. A user (high school student named Tanaka) accesses the system and answers the questionnaire with the following options: "Text difficulty: for high school students," "Image use frequency: medium," "Image style: realistic," "Audio characteristics: male voice actor A," and "Explanatory character: historical figure-like."

[1894] 2. The terminal sends the survey data to the server, which stores the data in a database.

[1895] 3. The device uses a camera and microphone to collect emotion data from Tanaka's facial expressions and voice, and then uses an emotion engine to identify her emotional state.

[1896] 4. The device sends the emotion data to the server, which stores it in a database.

[1897] 5. Based on the saved data, the server generates a history textbook for high school students using realistic images. Voices are recorded by male voice actor A, and animations of characters resembling historical figures are created.

[1898] 6. The server consolidates the generated learning materials and sends them to the terminal.

[1899] 7. The device displays the learning material on Tanaka's screen and plays the audio.

[1900] 8. The device will collect emotional data while learning, and if Tanaka's emotions change, it will send that information to the server.

[1901] 9. The server dynamically adjusts the learning material as needed and sends it back to the device.

[1902] In this way, the present invention is a system that provides learning materials that are individually customized based on the user's preferences, learning style, and emotions, helping the user achieve high learning effectiveness. This provides a highly accurate learning experience that could not be achieved with conventional, uniform learning materials.

[1903] The processing flow will be explained below.

[1904] Step 1:

[1905] When a user first accesses the system, they are presented with a questionnaire about their preferences and learning style, including the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the audio, and their preference for explanatory characters.

[1906] Step 2:

[1907] The device collects the data of the user's responses to the survey and sends it to the server, encoded in an appropriate format such as JSON.

[1908] Step 3:

[1909] The server stores the received survey data in a database, including user profile information (ID, name, etc.).

[1910] Step 4:

[1911] The device uses devices such as a camera and microphone to collect emotional data in real time from the user's facial expressions and voice.

[1912] Step 5:

[1913] The device analyzes the collected emotion data and identifies the user's current emotional state using an emotion engine, which includes algorithms for facial and voice analysis.

[1914] Step 6:

[1915] The device sends the identified emotion data to the server, which is also encoded in an appropriate format such as JSON.

[1916] Step 7:

[1917] The server stores the received emotion data in a database, where it is linked to the user's profile.

[1918] Step 8:

[1919] The server invokes a generative AI model (e.g., GPT-4) to generate individually customized training text based on the stored user data and sentiment data.

[1920] Step 9:

[1921] The server invokes an image generation process to generate an image in the style selected by the user (e.g., film style, anime style), using an image generation model such as DALL-E.

[1922] Step 10:

[1923] The server invokes a speech generation process to translate the training text into a voice of the selected voice actor, specifically, using a Text-to-Speech (TTS) engine.

[1924] Step 11:

[1925] The server invokes a character generation process to generate a character based on the character style selected by the user (e.g., an ancient Roman soldier or a modern doctor).

[1926] Step 12:

[1927] The server integrates the generated text, images, audio, and character animations and packages them as learning materials.

[1928] Step 13:

[1929] The server sends the integrated learning material package to the terminal, using a communication protocol such as the Internet.

[1930] Step 14:

[1931] The device displays the received learning material on the user's screen and plays the audio. Images, text, audio, and characters are arranged and played appropriately, and the user can begin learning.

[1932] Step 15:

[1933] The device continues to collect emotional data in real time while learning, and if the user's emotional state changes, the data is also sent to the server.

[1934] Step 16:

[1935] The server dynamically adjusts the learning material based on the latest emotional data it receives, for example, by adding more engaging content or images if the user is losing interest.

[1936] Step 17:

[1937] The server then sends the modified or adjusted learning material back to the device, which then displays the new material and plays the audio.

[1938] In this way, the system supports effective learning by providing and dynamically adjusting learning materials that are individually customized based on the user's preferences, learning style, and even emotional state.

[1939] Example 2

[1940] 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."

[1941] Conventional learning systems have difficulty customizing learning materials to suit individual users' preferences and learning styles, and have been unable to provide appropriate learning materials according to the user's emotional state. This has resulted in problems with users not being able to fully achieve their learning goals.

[1942] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1943] In this invention, the server includes means for collecting user preferences and learning styles, means for saving the collected user data, means for collecting emotional data from the user's facial expressions and voice using devices such as a camera and microphone and analyzing the emotional data, means for saving the collected emotional data, means for using a generative AI model to generate individually customized learning materials based on the saved user data and emotional data, means for transmitting the generated learning materials to the user's device, and means for collecting emotional data in real time even during learning and dynamically adjusting the learning materials, thereby making it possible to provide optimal learning materials according to the user's preferences and emotional state.

[1944] "User preferences and learning style" refers to the user's preferred content format, difficulty level, frequency of use, visual and auditory elements, and preferred learning methods.

[1945] "Customized learning materials" refers to educational content generated based on a user's preferences, learning style, and real-time emotional data.

[1946] "Emotional Data" refers to data about a user's current emotional state collected from the user's facial expressions and voice using devices such as a camera or microphone.

[1947] "Generative AI models" refer to artificial intelligence algorithms that generate learning materials based on collected user and emotional data. Specifically, they include AI models that perform natural language processing and image generation.

[1948] "Means for dynamic adjustment" refers to the function of analyzing the user's emotional data in real time and updating or changing the content of the learning material as needed.

[1949] "Terminal" refers to any device that a user accesses, including, for example, a PC, smartphone, or tablet.

[1950] "Server" refers to a remote computer system that stores and processes user data and sentiment data, including databases and infrastructure for running AI models.

[1951] "Survey data" refers to the response data to questions about preferences and learning styles that users answer when they first access the system.

[1952] An "emotion engine" refers to software or algorithms that analyze user data acquired through a camera or microphone and identify their emotional state.

[1953] The embodiment of the present invention is a system that provides individually customized learning materials to enable users to study effectively, recognizes the user's emotions in real time, and adjusts the learning materials appropriately based on that information. This system is described in detail below.

[1954] Collecting user preferences and learning styles

[1955] When a user first accesses the system, the device displays a questionnaire about preferences and learning style through a user interface. This questionnaire includes the level of difficulty of the text, the frequency of image use, the style of the images, the characteristics of the voice, and the preference of explanatory characters. When the user answers the questionnaire, the device collects the data and sends it to a server. The device uses a user interface that runs on a web browser or a mobile app.

[1956] Store and manage user data

[1957] The server stores the received survey data in a relational database (e.g., MySQL, PostgreSQL), and also records user profile information.

[1958] Emotion Recognition and Data Collection

[1959] The device uses a camera and microphone to collect emotion data from the user's facial expressions and voice in real time. The devices used here include a PC's built-in camera, an external webcam, and a microphone. The collected emotion data is analyzed by the device, and the user's emotional state is identified using an emotion engine (e.g., Microsoft Azure Face API, Google Cloud Speech-to-Text API). The identified emotion data is sent from the device to a server, which stores it in a database.

[1960] Generate customized learning materials

[1961] The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate training materials based on the stored user data and emotion data. The generated training materials include the following elements:

[1962] Text content according to the level of difficulty

[1963] Image styles to suit user preferences (anime, movie, etc.)

[1964] Voice generated by selected voice actors

[1965] Explanation animation by user-defined characters

[1966] Delivery of learning materials

[1967] The server integrates the generated learning materials and sends them as a package to the device, which then displays the received learning materials on the screen and plays the audio.

[1968] Dynamic Adjustment

[1969] The device continues to collect emotional data in real time while learning and sends it to the server. The server dynamically adjusts the content of the learning materials based on the latest emotional data and sends them back to the device. This allows the device to provide optimal learning materials according to the user's emotional state.

[1970] Specific examples

[1971] Example 1: English language learning for primary school students

[1972] 1. A user (elementary school student) accesses the system for the first time and answers the questionnaire with the following options: "Text difficulty: for elementary school students," "Frequency of image use: high," "Image style: anime-style," "Audio characteristics: child's voice," and "Explanatory character: animal character."

[1973] 2. The terminal sends the survey data to the server, which stores the data in a database.

[1974] 3. The device uses a camera and microphone to collect emotional data from facial expressions and voice, and then uses an emotion engine to identify the emotional state.

[1975] 4. The device sends the emotion data to the server, which stores it in a database.

[1976] 5. Based on the saved data, the server generates English textbooks for elementary school students, featuring a wide range of cartoon-style images. Audio is recorded using children's voices, and animations featuring animal characters are created.

[1977] 6. The server consolidates the generated learning materials and sends them to the terminal.

[1978] 7. The device displays the learning material on the screen and plays the audio.

[1979] 8. The device collects emotional data during learning and sends the information to the server as needed.

[1980] 9. The server dynamically adjusts the learning material and sends it back to the device.

[1981] Prompt Sentence Examples

[1982] "Generate an anime-style English learning textbook for elementary school students. Images should be used frequently, with children's voices and animal characters as explanatory characters."

[1983] Example 2: History study for high school graduation exams

[1984] 1. The user (high school student) accesses the system and answers the questionnaire with the following options: "Text difficulty: for high school students," "Image use frequency: medium," "Image style: realistic," "Audio characteristics: male voice actor," and "Explanatory character: historical figure style."

[1985] 2. The terminal sends the survey data to the server, which stores the data in a database.

[1986] 3. The device uses a camera and microphone to collect emotional data from facial expressions and voice, and then uses an emotion engine to identify the emotional state.

[1987] 4. The device sends the emotion data to the server, which stores it in a database.

[1988] 5. Based on the saved data, the server generates historical textbooks for high school students using realistic images. Audio is recorded by male voice actors, and animated characters that resemble historical figures are created.

[1989] 6. The server consolidates the generated learning materials and sends them to the terminal.

[1990] 7. The device displays the learning material on the screen and plays the audio.

[1991] 8. The device collects emotional data during learning and sends the information to the server as needed.

[1992] 9. The server dynamically adjusts the learning material and sends it back to the device.

[1993] Prompt Sentence Examples

[1994] "Generate a realistic history textbook for high school students. Images should be used moderately, audio should be provided by a male voice actor, and explanatory characters should look like historical figures."

[1995] In this way, the present invention is a system that provides learning materials that are individually customized based on the user's preferences, learning style, and emotions, helping the user achieve high learning effectiveness. This provides a highly accurate learning experience that could not be achieved with conventional, uniform learning materials.

[1996] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1997] Step 1: Collect user surveys

[1998] 1-1. The user accesses the system for the first time. The questionnaire includes questions about the difficulty of the text, the frequency of image use, the style of the image, the characteristics of the voice, and the preference for the explanatory character.

[1999] Input: The user answers the survey items.

[2000] Operation: A questionnaire screen is displayed and the user answers each item.

[2001] Output: User response data.

[2002] 1-2. The device collects the user's response data and sends it to the server.

[2003] Input: User response data.

[2004] Operation: The device sends the response data to the server.

[2005] Output: Survey data sent to the server.

[2006] Step 2: Save user data

[2007] 2-1. The server stores the received survey data in a relational database, such as MySQL or PostgreSQL.

[2008] Input: Survey data.

[2009] How it works: The server saves the survey data in a database.

[2010] Output: Survey data stored in a database.

[2011] 2-2. The server also records the user's profile information.

[2012] Input: User's personal information.

[2013] How it works: The server stores user profile information in a database.

[2014] Output: User profile information stored in a database.

[2015] Step 3: Collecting emotion data

[2016] 3-1. The device uses a camera and microphone to collect emotional data from the user's facial expressions and voice in real time. The devices used include the PC's built-in camera, an external webcam, and a microphone.

[2017] Input: User facial expressions and voice collected by camera and microphone.

[2018] What it does: Your device collects data through its camera and microphone.

[2019] Output: Collected emotion data.

[2020] 3-2. The device analyzes the collected emotion data and identifies the user's current emotional state using an emotion engine, such as the Microsoft Azure Face API or the Google Cloud Speech-to-Text API.

[2021] Input: Collected emotion data.

[2022] How it works: The emotion engine analyzes the emotion data and identifies the user's emotional state.

[2023] Output: Identified emotion data.

[2024] 3-3. The device sends the identified emotion data to the server.

[2025] Input: Identified emotion data.

[2026] Operation: The device sends emotion data to the server.

[2027] Output: Emotion data sent to the server.

[2028] 3-4. The server stores the received emotion data in a database.

[2029] Input: Emotion data.

[2030] How it works: The server stores emotion data in a database.

[2031] Output: Emotion data stored in a database.

[2032] Step 4: Generate customized learning materials

[2033] 4-1. The server uses a generative AI model (e.g., GPT-4 or an image generation model) to generate learning materials based on the stored user data and emotion data.

[2034] Input: User data and emotion data.

[2035] How it works: The AI ​​model analyzes the data and generates optimal learning materials for the user.

[2036] Output: The generated learning material.

[2037] 4-2. The generated learning materials include the following elements:

[2038] Text content according to the level of difficulty

[2039] Image styles to suit user preferences (anime, movie, etc.)

[2040] Voice generated by selected voice actors

[2041] Explanation animation by user-defined characters

[2042] Input: Individual elements of user data (e.g. difficulty of text, frequency of image use, etc.).

[2043] How it works: The AI ​​model generates materials based on each element.

[2044] Output: Each element of the customized learning material.

[2045] Step 5: Deliver learning materials

[2046] 5-1. The server integrates the generated learning materials and sends them to the terminal as a package.

[2047] Input: Generated learning material.

[2048] How it works: The server collects the material into a single package and sends it to the device.

[2049] Output: The learning material package sent to the device.

[2050] 5-2. The device displays the received learning material on the screen and plays the audio.

[2051] Input: Received learning material package.

[2052] What it does: The device displays the material on the screen and plays the audio.

[2053] Output: Learning material that is visible and audible to the user.

[2054] Step 6: Dynamic adjustment

[2055] 6-1. The device continues to collect emotional data in real time even during learning, and if adjustments are needed to suit different conditions, it sends that information to the server.

[2056] Input: Emotion data collected in real time.

[2057] Operation: The device continues to collect emotion data and transmits it to the server.

[2058] Output: The latest emotion data sent to the server.

[2059] 6-2. The server dynamically adjusts the content of the learning material based on the latest emotional data received and sends it back to the device.

[2060] Input: Latest emotion data.

[2061] How it works: The server analyzes the emotion data and adjusts the learning material as needed.

[2062] Output: Dynamically adjusted learning material.

[2063] (Application example 2)

[2064] 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."

[2065] With current learning systems, it is difficult to customize learning materials to suit each user's preferences and learning style. It is also extremely difficult to grasp the user's emotional state in real time while learning and instantly adjust the learning materials. This results in problems such as users being unable to study effectively and reduced learning efficiency.

[2066] 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.

[2067] In this invention, the server includes means for collecting user preferences and learning styles, means for storing the collected user data, means for generating individually customized learning materials based on the stored data and the user's emotional data, means for transmitting the generated learning materials to the user's terminal, and means for collecting emotional data in real time during learning and dynamically adjusting the materials. This allows the server to provide individually customized learning materials, enabling users to achieve high learning effectiveness.

[2068] "Preferences" refer to the types and formats of learning content that a user particularly prefers.

[2069] "Learning style" refers to a particular learning method or approach that a user takes to effectively learn.

[2070] "Emotion data" is data that indicates the user's current emotional state, extracted from the user's facial expressions and voice.

[2071] "Customized learning materials" refers to learning content that is individually tailored to a user based on their preferences, learning style, and emotional data.

[2072] "Collecting in real time" means that data is collected continuously while the user is studying.

[2073] "Dynamic adjustment" refers to changing the content of learning materials on the fly based on collected data.

[2074] "Terminal" refers to a device used by a user, such as a smartphone or smart glasses.

[2075] "Server" refers to the central computing system that stores user data and generates and delivers learning materials.

[2076] System configuration explanation

[2077] The system of the present invention mainly includes means for collecting user preferences and learning styles, means for collecting emotional data in real time, means for generating individually customized learning materials based on the stored data and the user's emotional data, and means for transmitting the generated learning materials to a terminal.

[2078] Hardware and software used

[2079] The system uses the following hardware and software:

[2080] Device: The smartphone or smart glasses used by the user, including the camera, microphone, and other input devices.

[2081] Server: A high-performance computing system, either on cloud or on-premise, that stores user data and generates and delivers learning materials.

[2082] Emotion recognition software: Facial expression recognition libraries and voice analysis tools (e.g., EmotionRecognizer).

[2083] Generative AI models: High-performance text and image generation models such as GPT-4.

[2084] Program processing overview

[2085] 1. The device initially collects data by conducting a survey about the user's preferences and learning style.

[2086] 2. The device sends the collected data to the server, which stores it in a database.

[2087] 3. The device uses a camera and microphone to collect and analyze emotional data from the user's facial expressions and voice in real time.

[2088] 4. The device sends the analyzed emotion data to the server, which stores it in a database.

[2089] 5. The server generates customized learning materials using a generative AI model based on the stored user data and emotion data.

[2090] 6. The server sends the generated learning material to the terminal, which displays or plays it to the user.

[2091] 7. The device continues to collect emotional data in real time during training and transmits the information to the server as needed.

[2092] 8. The server dynamically adjusts the learning material based on the latest emotional data and sends it back to the device.

[2093] Specific examples

[2094] For example, when a user visits a store, they put on the smart glasses and the learning process proceeds as follows:

[2095] 1. Survey collection: The user answers the survey and enters information such as "Image usage frequency: high frequency," "Image style: realistic," and "Audio characteristics: male voice."

[2096] 2. Data storage: The survey results are sent to the server and stored in the database.

[2097] 3. Emotion data collection: The camera in the smart glasses captures facial expressions and analyzes them in real time.

[2098] 4. Learning material generation: The server uses the generative AI model to create customized learning content.

[2099] 5. Content delivery: The learning content is sent to the device and the user begins learning.

[2100] 6. Real-time adjustment: Materials are dynamically adjusted according to the user's emotional state.

[2101] Prompt Sentence Examples

[2102] "User profile: They frequently use realistic images and prefer characters with male voices."

[2103] "Sentiment data: Interest is currently waning. Use this information to provide more engaging content."

[2104] This system allows users to receive individually customized learning materials on the spot, resulting in higher learning effectiveness.

[2105] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2106] Step 1:

[2107] A user accesses the system using a terminal (smartphone or smart glasses). The terminal displays a questionnaire to the user about their preferences and learning style. The user answers the questionnaire and enters the data. The user's questionnaire data is entered into the terminal. The terminal collects this data and sends it to the server.

[2108] Step 2:

[2109] The server receives the survey data sent from the device. The received data is stored in a database. The server stores the user's profile information, as well as their preferences and learning style data, for a long period of time. The input is the survey data, and the output is the stored data.

[2110] Step 3:

[2111] The device collects the user's facial expressions and voice in real time using a camera and microphone. The collected data is analyzed using a facial expression recognition library and a voice analysis tool (e.g., EmotionRecognizer). The device then sends the analyzed emotion data to a server. The input is facial expression and voice data, and the output is the analyzed emotion data.

[2112] Step 4:

[2113] The server receives the emotion data sent from the device. The received data is stored in a database. The server identifies and records the user's current emotional state. The input is the emotion data, and the output is the stored emotion data.

[2114] Step 5:

[2115] The server generates customized learning materials using a generative AI model (e.g., GPT-4) based on the stored user data and emotional data. Learning content, such as text, images, and audio, is created based on prompts input to the generative AI model. The input is user data and emotional data, and the output is customized learning materials.

[2116] Step 6:

[2117] The server integrates the generated learning materials and sends them to the terminal. The learning materials are optimized for easy understanding by the user. The input is the generated learning materials, and the output is the learning materials delivered to the terminal.

[2118] Step 7:

[2119] The terminal receives learning materials sent from the server. The terminal displays and plays these materials to the user. The user then uses the customized learning materials to progress through their learning. The input is the delivered learning materials, and the output is the user's execution of the learning.

[2120] Step 8:

[2121] During training, the device continues to collect the user's facial expressions and voice in real time using a camera and microphone. If the emotional data changes, it sends that data to the server. The input is the continuously collected emotional data, and the output is the updated emotional data.

[2122] Step 9:

[2123] The server dynamically adjusts the learning materials accordingly based on the latest emotional data. The generative AI model is again used to update the content based on the new prompt. The input is the latest emotional data, and the output is the dynamically adjusted learning materials.

[2124] Step 10:

[2125] The server sends the adjusted learning materials back to the terminal. The terminal displays and plays these materials again to the user. The user continues learning adapted to the new conditions. The input is the adjusted learning materials, and the output is the user's continued learning.

[2126] This allows users to use individually customized learning materials and enjoy a learning environment that adapts in real time as they learn.

[2127] 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.

[2128] 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.

[2129] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2130] 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.

[2131] 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.

[2132] 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.

[2133] 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).

[2134] 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.

[2135] 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."

[2136] 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.

[2137] 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).

[2138] 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.

[2139] 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.

[2140] 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.

[2141] 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.

[2142] 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.

[2143] 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.

[2144] 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.

[2145] 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.

[2146] 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 ...

Claims

1. a means for collecting user preferences and learning styles; a means for storing collected user data; A means for generating individually customized learning materials based on the stored data; The system includes a means for transmitting the generated learning material to a user's terminal.

2. 2. The system according to claim 1, wherein the difficulty level of the text, the frequency of use of images, the style of the images, the characteristics of the voice, and the characteristics of the explanatory characters can be customized in generating learning materials.

3. 10. The system of claim 1, further comprising means for collecting feedback from the user and adjusting the learning material based on the collected feedback.

Images