system

Abstract

We provide the system. [Solution] A means for generating a response to user input using a generative model, A means for accessing a text database stored in a management device and verifying and correcting the accuracy of the response generated by the generative model, A means of recording the user's learning history and presenting learning content based on that history, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the field of education, incorrect answers or the provision of incomplete information that occur when using a generative model may have an adverse effect on learners. Therefore, it is required to improve the accuracy of the answers of the generative model while providing an efficient and high-quality educational service that meets various learning needs. In addition, it is necessary to eliminate educational disparities due to a shortage of human resources and geographical constraints, and to provide an appropriate educational environment over a wide area including depopulated areas.

Means for Solving the Problems

[0005] This invention provides a system that generates responses based on user input using a generative model. This system refers to a text database stored in a management device to verify the accuracy of the responses generated by the generative model and makes corrections as necessary. It also records the user's learning history and presents learning content optimized for the learner based on that information. Furthermore, it can analyze user progress in real time and provide feedback, thereby improving the overall quality of the educational service.

[0006] A "generative model" is a type of artificial intelligence that uses natural language processing technology to automatically generate human-like responses based on input text.

[0007] A "management device" is a computer system used to manipulate and organize information, including databases and software applications, and to perform specific processes.

[0008] A "text database" is a database system designed to efficiently store text information collected for educational purposes and provide it in a searchable format.

[0009] "User learning history" refers to a dataset that includes records of activities performed and achievements made by the user during the learning process.

[0010] A "feedback generation method" is a process or function that analyzes the user's learning progress and automatically generates appropriate guidance and improvement suggestions based on that analysis. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the 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.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0025] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention is implemented as an educational system that allows users to utilize artificial intelligence technology in the learning process. This system operates through the interaction of a server, terminals, and users, with a generative model at its core. A specific embodiment is described below.

[0033] First, the server hosts the generative model. When this server receives a question, it uses the generative model to generate an answer based on the user's input. The generated answer is validated using a text database prepared by the cram school and corrected as needed to ensure accuracy.

[0034] The terminal is a device that serves as the interface with the user. When the user enters a question about the learning content, the terminal sends that input to the server. When the server returns an answer, the terminal displays it visually to the user.

[0035] Users can input questions and receive answers and feedback via their devices. The system continuously records the problems solved and their results, saving them as learning history on the server. This allows for continuous evaluation of the user's progress and provides personalized instruction.

[0036] As a concrete example, consider a case where a user inputs a math problem, "How to solve a quadratic equation," as a question. The terminal sends this input to the server. The server uses a generative model to generate a detailed answer regarding the solution, and after ensuring its accuracy using the tutoring center's database, it sends it back to the terminal. This allows the user to learn based on accurate information.

[0037] This system is designed to expand educational opportunities in a wide range of areas, including sparsely populated regions, and to efficiently provide learning environments. It functions as an integrated platform that delivers high-quality education while optimizing human resources.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The user starts up their learning device, accesses the login screen, and enters their user ID and password to authenticate their identity.

[0041] Step 2:

[0042] The device sends the entered authentication information to the server and waits for the result of whether authentication was successful. If authentication is successful, the learning session starts.

[0043] Step 3:

[0044] Users enter questions into the terminal about topics they want to learn about or problems they want to solve. For example, "Please explain how to calculate differentiation."

[0045] Step 4:

[0046] The terminal sends the user's question to the server. If the communication with the server is successful, the server receives the content.

[0047] Step 5:

[0048] The server analyzes the received question and uses a generative model to generate an answer for the user. During this process, it constructs the content in a natural style through computational processing.

[0049] Step 6:

[0050] The server compares the generated response with existing information in the database to verify its consistency. If any inaccuracies are found, they are corrected with the correct information.

[0051] Step 7:

[0052] The server sends the verified and corrected answers to the terminal and provides them to the user. Additional explanatory materials and example problems may be included at this time.

[0053] Step 8:

[0054] The device displays the acquired answers to the user, and the user proceeds with learning based on that information.

[0055] Step 9:

[0056] The server records the user's questions and session interactions in a database as learning history. This information is used to personalize the user experience for future visits.

[0057] Step 10:

[0058] At the end of a learning session, the user logs out and exits the system from their terminal. The server disconnects the connection, releases all resources, and completely terminates the session.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] Many learning systems struggle to provide individualized instruction to users, particularly inadequate supply of learning content and accuracy of responses. Furthermore, progress analysis and appropriate feedback are not efficiently conducted, preventing the system from maximizing learning effectiveness. Solving these problems is crucial.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for generating a response to user input using a generative model, means for accessing an information database stored in a data management device to verify and correct the accuracy of the response generated by the generative model, and means for recording the user's learning history and presenting learning content based on that history. This enables personalized learning support and the provision of accurate information to the user.

[0064] A "generative model" is a system that uses artificial intelligence technology to generatively create responses or content in response to specific input data.

[0065] A "data management device" is a computer system used to manage and store information databases and response content.

[0066] An "information database" is a storage device that stores the information and knowledge necessary to verify and correct the responses generated by a generative model.

[0067] A "prompt statement" is a sentence in natural language that a user inputs to a generative model according to their purpose.

[0068] A "terminal device" is hardware that provides an interface for users to access a system and send and receive information.

[0069] "Learning history" refers to data that records the learning activities and results that users have engaged in through the system.

[0070] An "evaluation generation means" is a method or device for analyzing a user's progress and generating appropriate learning suggestions and feedback.

[0071] "Visualization" is the process of displaying generated information and data in a way that is easy for users to understand.

[0072] This invention is a system that allows users to utilize artificial intelligence technology in the learning process. The system operates primarily through interaction between a server, a terminal, and the user.

[0073] The server is the core of the system and hosts the generative model. The server possesses high-performance computing capabilities as hardware and a platform for executing the generative AI model as software. Upon receiving input from the user, the server uses the generative AI model to generate an appropriate response. The generated response is verified against an information database stored in the management device and corrected if necessary. This process ensures the accuracy and reliability of the generated response.

[0074] The terminal is a device that serves as the interface with the user, and can be a tablet, smartphone, or personal computer. The terminal has a user interface as software and provides an environment for the user to input prompts. When the user inputs a question about the learning content, the terminal sends that input to the server. When a response is returned from the server, the terminal displays it visually to the user to help them understand.

[0075] Users can interact with the system via their terminal and progress through their learning. For example, if a user inputs "Please tell me how to solve a quadratic equation" as a prompt, the terminal sends this to the server, which generates a response containing detailed information about the solution. This response is then returned to the terminal, and the user can deepen their learning based on that information.

[0076] This system includes a function to record learning history, continuously tracking user progress. The learning history is stored on a server and forms the basis for providing learning content optimized for each individual user. This enables the delivery of an efficient and personalized learning experience.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The user enters a question related to the learning content as a prompt into the terminal. This action includes text input using a keyboard or touchscreen. An example of the input data might be something like, "Please explain how to solve a quadratic equation." This prompt is then prepared for the next process.

[0080] Step 2:

[0081] The terminal sends the prompt message received from the user to the server. The input here is the prompt message entered in step 1, and the output is a network message to the server. The terminal sends this data to the server via the internet or internal network.

[0082] Step 3:

[0083] The server analyzes the prompt text received from the terminal and generates a response using a generative AI model. The input data is the prompt text, and after going through the natural language generation process by the AI ​​model, the generated response text is obtained as output. The specific operation includes text analysis and generation using natural language processing algorithms.

[0084] Step 4:

[0085] The server verifies the accuracy of the generated response by comparing it with the information database stored in the data management device. Here, the generated response is used as input, and a verified, reliable response is obtained as output. Specifically, the process involves executing a database query and comparing it with the information database.

[0086] Step 5:

[0087] The server sends a verified and corrected response to the terminal. The input is the verified response, which generates a message that is sent to the terminal over the network as output. The server utilizes a communication protocol to do this.

[0088] Step 6:

[0089] The terminal displays responses sent from the server through a user interface. The input is the response message from the server, and the output generates information that is displayed on the screen. Specific operations include rendering text on the screen.

[0090] Step 7:

[0091] The user reviews the displayed answers and, if necessary, enters further questions to continue learning. The input here is the information obtained in step 6, and a new prompt is generated as output. Based on this, the user can plan the next learning step.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] The goal is to enable multiple learners to receive efficient and individually optimized learning instruction, particularly by providing a system that allows for real-time monitoring of users' learning progress via portable devices and offers appropriate feedback and learning plans. This will overcome the resource limitations of traditional educational environments and enable widespread high-quality learning support.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for generating responses to user input using a generative model, means for accessing a text database stored in a management device to verify and correct the accuracy of the responses generated by the generative model, means for recording the user's learning history and presenting learning content based on that history, means for functioning as an interface through a user terminal to acquire user input information, transmit it to the management device with high accuracy for processing, and means for visually presenting the generated answers via a portable device to the learner. This enables learners to receive an optimal learning experience at their own pace.

[0097] A "generative model" is an algorithm that uses artificial intelligence to generate natural language and information based on specific input data.

[0098] "Management device" refers to hardware or software used to store and manage generated data and learning history.

[0099] A "text database" is a database that collects existing text information and is used to verify the accuracy of that information.

[0100] "User learning history" refers to records of the user's learning history and results to date.

[0101] A "user terminal" is a device that a user can use as an interface, utilizing a portable electronic device.

[0102] An "interface" refers to the means or methods used when a user exchanges information with a system in a two-way manner.

[0103] A "portable device" is an electronic device that is easily carried and capable of running educational applications.

[0104] As an embodiment of this invention, a system comprising a server, a user terminal, and a generative model is constructed. The server hosts the generative model and is responsible for providing responses generated based on user input information. This generative model may utilize, for example, natural language processing technology. Specifically, the server can implement OpenAI's GPT or a similar natural language generation algorithm.

[0105] The user terminal functions as a device for learners to operate, and uses portable electronic devices such as smartphones and tablets. The terminal receives questions from the user and transmits that information to the server in real time. WebSocket protocol or HTTP can be used for communication.

[0106] In this system, a user inputs a prompt, such as "Please explain dental implants in detail," expressing a question they have during their learning process. The terminal receives this prompt and sends it to the server. The server utilizes a generative model to generate an explanation for this prompt, verifies its accuracy based on a text database, and then sends the appropriate information back to the user's terminal. As a result, learners receive refined information, enabling effective learning.

[0107] This embodiment realizes a new learning model that enables learners to receive optimal educational support tailored to their individual learning needs, no matter where they are.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The user enters a question via a terminal. The terminal receives the prompt text entered by the user, formats it as input data, and prepares to send it to the server. At this time, the input data is in text format and contains specific questions or doubts related to the user's learning.

[0111] Step 2:

[0112] The terminal sends a prompt message to the server. This data transmission uses the WebSocket or HTTP protocol. When the server receives the prompt message, it prepares to invoke the generative model based on that data. The received data is converted into an appropriate format for input to the generative model.

[0113] Step 3:

[0114] The server uses a generative AI model to generate responses to received prompt sentences. This generative model is based on natural language processing technology and utilizes an algorithm that understands intent from received text data and generates linguistic responses. The generated responses are optimized to include meaningful information from a learning perspective.

[0115] Step 4:

[0116] The server validates the generated response against a text database. Here, it compares the generated response against existing knowledge stored in the database to verify its accuracy. If necessary, the response is corrected based on the validation results. This step involves crucial processing to ensure accurate information is provided.

[0117] Step 5:

[0118] The server sends the verified and corrected response back to the terminal. The terminal formats the received response for visual presentation to the user. This output data is laid out to be displayed in a format that is easy for the user to understand.

[0119] Step 6:

[0120] The user terminal displays the received responses to the user. This allows the user to check the answers to their questions on the terminal, enabling them to progress in their learning more effectively. The generated responses are recorded on the terminal as the user's learning history and used to support future learning.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention is implemented as an educational system combining a generative model and an emotion engine. The system aims to provide a personalized learning experience that takes into account the user's emotional state. Specific embodiments are described below.

[0123] First, the server hosts the generative model and the sentiment engine, coordinating them to support the entire learning process. The server receives questions from the user and generates initial responses using the generative model. At this time, the sentiment engine evaluates the user's emotional state by analyzing the user's input data, which helps in selecting learning content and adjusting responses.

[0124] The terminal interacts with the user, allowing for question input and display of generated responses. Each time the user solves a problem or asks a question, their response is recorded through the terminal and sent to the server. The emotion engine analyzes this data sequentially to identify the user's emotional patterns. For example, if the system determines the user is stressed, it may reduce the learning content or present content designed to increase motivation.

[0125] To give a concrete example, if a user enters "I can't concentrate on studying history" into their device, the server checks the user's current learning history and sentiment data. The sentiment engine determines that the sentiment stems from boredom or impatience, and uses a generative model to generate a response that includes encouragement and specific advice.

[0126] Furthermore, the system records the correlation between the user's past learning history and emotional changes, and uses this data to further optimize learning in subsequent sessions. This mechanism establishes an emotionally responsive learning style tailored to each individual user, maximizing learning effectiveness.

[0127] This system functions effectively in distance education and various learning situations, and can meet diverse educational needs.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] Users log in to their device to begin learning and view their individual dashboard, where they can see their current learning progress and past performance.

[0131] Step 2:

[0132] The device sends login information to the server for user authentication. If authentication is successful, the device retrieves the user's learning history and sentiment data from the server and displays it on the device.

[0133] Step 3:

[0134] Users select a topic they want to learn about and enter specific questions or problems into the device. For example, they might input something like, "I don't understand differential calculus, so could you explain it in detail?"

[0135] Step 4:

[0136] The terminal sends the user's question to the server. If the communication with the server is successful, the server receives the content.

[0137] Step 5:

[0138] The server uses a generative model to generate an initial response to the received question. Additionally, the emotion engine analyzes the user's input to identify their emotional state. This result is used to refine the response.

[0139] Step 6:

[0140] Based on the analysis results of the emotion engine, the server generates responses appropriate to the user's emotional state and makes recommended adjustments to the learning content. For example, if it is determined that the user has difficulty with concentration, it will present a simple problem.

[0141] Step 7:

[0142] The server sends the generated response and corrected learning content to the device.

[0143] Step 8:

[0144] The device displays received responses to the user, helping them to have the best possible learning experience. The displayed content may include advice and additional explanations.

[0145] Step 9:

[0146] Users progress through their learning using the presented learning content, and input additional questions and feedback into their device based on changes in their emotions and level of understanding.

[0147] Step 10:

[0148] The server records learning session data, along with sentiment information, in the learning history. This record is used to personalize the learning process in subsequent sessions.

[0149] Step 11:

[0150] At the end of the learning session, the user logs out, and the device disconnects from the server to end the session. The server releases all resources and confirms that the data has been saved.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0153] Traditional education systems, while presenting learning content based on users' learning history, have not adequately provided responses or learning support that take into account the user's emotional state. As a result, there is a problem where learning effectiveness decreases when users' emotions or motivation decline. It is necessary to solve this problem and provide users with an individualized learning experience.

[0154] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0155] In this invention, the server includes means for generating responses to user input using a generative model, means for analyzing the user's emotional state and adjusting the generated responses based on that state, means for accessing a set of information stored in a management device and verifying and correcting the accuracy of the responses generated by the generative model, and means for recording the user's learning history and emotional state history and presenting learning content based on that history. This enables flexible and effective learning support that is tailored to the user's emotional state.

[0156] A "generative model" is an algorithm or system that takes text data as input and generates a response in natural language form based on it.

[0157] "Emotional state" refers to the emotional response or psychological state that a user exhibits in a particular situation or input.

[0158] A "management device" is a device or system that includes a database for storing and managing information sets and learning histories, and for accessing them as needed.

[0159] An "information set" refers to a collection of data or knowledge that has been organized and classified for a specific purpose.

[0160] A "feedback generation method" refers to a technology or system that analyzes a user's progress and emotional state and generates optimal responses or suggestions based on that analysis.

[0161] "User interface" refers to the screens and means of interaction that users use to interact with a device or program.

[0162] This invention is an advanced educational system that combines a generative model and an emotion engine to provide personalized learning support based on the user's emotional state. Specific embodiments of this system are described below.

[0163] First, the server forms the core of this system, hosting the generative AI model and the emotion engine. The generative AI model receives input text from the user and generates an appropriate response in natural language. This response generation uses existing AI technologies (e.g., natural language processing technologies) and involves complex data processing and calculations.

[0164] Upon receiving user input data, the server activates the emotion engine and analyzes the user's emotional state from the input text. Using text analysis techniques, the emotion engine identifies the user's emotional state and, if the user is experiencing anxiety or low motivation, provides adjustments to the server. Based on the results of the emotion analysis, the generative AI model adjusts the response, providing the user with the most appropriate information and encouraging messages.

[0165] The terminal provides an interface for the user to interact with this system. The user inputs questions through the terminal and receives generated responses. The terminal uses a GUI (Graphical User Interface) for intuitive operation and is designed to allow users to interact with the system smoothly.

[0166] Users inform the server of their state of mind, for example, by typing "I can't concentrate on studying history." The server then considers the user's learning history and sentiment data to ensure that the generative AI model provides the best possible response. This allows users to receive words of encouragement and learning advice, thereby rekindling their motivation to learn.

[0167] A concrete example of a prompt message is, "What kind of encouraging words can be generated when a user gets bored studying history?" In this way, the system can provide a personalized learning experience for the user.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] Users enter questions and comments through their devices. User input is collected in text format, and this contains the initial information regarding the user's intentions and feelings.

[0171] Step 2:

[0172] The terminal sends user input to the server. When the input data is transferred to the server, it is converted to an appropriate format to facilitate processing on the server.

[0173] Step 3:

[0174] The server analyzes the received input data and provides it as input to the generative AI model. The generative AI model processes the input prompt sentence and generates appropriate response text by referring to a relevant knowledge database. At this stage, the input data is analyzed using natural language processing techniques, and response candidates are output.

[0175] Step 4:

[0176] The server inputs the generated response into the emotion engine, which evaluates the user's emotional state. Based on the input data and the generated response, the emotion engine analyzes the user's emotions and readjusts the response as needed to reflect the results. The output is the adjusted response.

[0177] Step 5:

[0178] The server updates the user's learning history and sentiment state history with a refined response. The server adds the new historical data to the database and uses it to optimize future learning sessions.

[0179] Step 6:

[0180] The terminal displays the response received from the server to the user. The generated content is presented on the user interface in a visually organized manner, making it easy for the user to understand and choose their next action.

[0181] (Application Example 2)

[0182] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0183] This invention aims to mitigate the impact of learners' emotional states on learning outcomes in educational content. Current educational systems often fail to consider learners' emotional states, leading to challenges such as stress and decreased motivation hindering learning efficiency. Furthermore, real-time emotion-based feedback and content optimization are difficult, resulting in a lack of personalized learning experiences.

[0184] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0185] In this invention, the server includes means for generating responses to user input using a generative model; means for accessing a text database stored in a management device to verify and correct the accuracy of the responses generated by the generative model; means for recording the user's learning history and emotional state and presenting learning content based on that history and state; means for optimizing the generated responses based on the user's emotions via an emotion analysis device that analyzes the user's emotional information; and means for presenting the optimized information to the user through a visual information display device. This enables the provision of a personalized learning experience that takes into account the user's emotional state and allows for the presentation of educational content optimized in real time according to emotions.

[0186] A "generative model" is an algorithm that automatically generates appropriate responses or information based on input data.

[0187] An "emotion analysis device" is a device that analyzes a user's emotional state and identifies changes in that state in real time.

[0188] A "visual information display device" is a device that visually presents generated information or responses to the user.

[0189] A "text database" is a collection of data stored in text format that is used to verify and correct user information and the responses of generative models.

[0190] "Optimization" refers to adjusting the information and responses provided to a more appropriate state based on the user's emotions and learning history.

[0191] In order to implement this invention, the following system and procedure are necessary.

[0192] The server first generates a response to the user's input using a generative model. The generated initial response is verified using a text database stored in the management device, and the response is corrected as needed. At this time, the sentiment analysis device analyzes the user's emotional information and uses the results to optimize the response. The server records the user's learning history and emotional state, and based on this, optimizes the learning content and presents it to the user.

[0193] The device presents optimized information to the user via a visual information display device. By using the visual information display device, users can access content that matches their emotional state during learning. These devices and systems enable a more personalized learning experience for the user.

[0194] As a concrete example, if a user inputs "I can't concentrate on studying history," the server receives this input and analyzes the user's emotional state via an emotion analysis device. If the analysis results indicate boredom or frustration, a generative model generates a response with encouragement and specific advice. This response is then presented to the user through a visual information display device.

[0195] Examples of prompts to input into the generation AI model include, "If the user's facial expression indicates confusion, generate encouragement and recommended product information," and "Facial expression evaluation: Confusion, Voice tone: Questioning tone, Store environment: Clothing section."

[0196] In this way, real-time optimization that takes emotions into account is performed for each individual user, enabling the provision of a personalized and effective learning experience.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server receives input from the user, which includes questions and problems the user is facing during the learning process. The input data is primarily in text format and is then sent to the generative model for processing.

[0200] Step 2:

[0201] The server processes the received input data into a generative AI model to generate an initial response. At this stage, the generative AI model creates a provisional response to the user's question and returns it to the server as output.

[0202] Step 3:

[0203] The server accesses a text database stored on the management device to verify the accuracy of the initial response generated. If the response is incorrect or inappropriate, corrections are made. Rule-based validation from the text database is performed, and the response is adjusted.

[0204] Step 4:

[0205] The server uses an emotion analysis device to evaluate the user's emotional state. This evaluation is based on data such as the user's voice, facial expressions, and input content, leading to the identification of emotions. The emotion analysis engine processes the data and calculates emotional parameters to obtain the output.

[0206] Step 5:

[0207] The server optimizes the generated response based on the results of the emotion analysis device. Specifically, it adjusts the response to match the user's emotional state to achieve optimal communication. For example, if the user is showing signs of stress, the response will be made gentler and encouraging words will be added.

[0208] Step 6:

[0209] The device displays optimized responses to the user via a visual information display device. This information is presented on the user's display in a visual format, in a way that aids the user's learning.

[0210] Step 7:

[0211] Based on the responses provided, the user decides on the next learning step. At this stage, the user reads and understands the responses and decides whether to continue or ask further questions. The user's responses are recorded and used in the next session.

[0212] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0213] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0214] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0218] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0219] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0220] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0222] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0223] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0224] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0225] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0226] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0227] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0228] This invention is implemented as an educational system that allows users to utilize artificial intelligence technology in the learning process. This system operates through the interaction of a server, terminals, and users, with a generative model at its core. A specific embodiment is described below.

[0229] First, the server hosts the generative model. When this server receives a question, it uses the generative model to generate an answer based on the user's input. The generated answer is validated using a text database prepared by the cram school and corrected as needed to ensure accuracy.

[0230] The terminal is a device that serves as the interface with the user. When the user enters a question about the learning content, the terminal sends that input to the server. When the server returns an answer, the terminal displays it visually to the user.

[0231] Users can input questions and receive answers and feedback via their devices. The system continuously records the problems solved and their results, saving them as learning history on the server. This allows for continuous evaluation of the user's progress and provides personalized instruction.

[0232] As a concrete example, consider a case where a user inputs a math problem, "How to solve a quadratic equation," as a question. The terminal sends this input to the server. The server uses a generative model to generate a detailed answer regarding the solution, and after ensuring its accuracy using the tutoring center's database, it sends it back to the terminal. This allows the user to learn based on accurate information.

[0233] This system is designed to expand educational opportunities in a wide range of areas, including sparsely populated regions, and to efficiently provide learning environments. It functions as an integrated platform that delivers high-quality education while optimizing human resources.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The user starts up their learning device, accesses the login screen, and enters their user ID and password to authenticate their identity.

[0237] Step 2:

[0238] The device sends the entered authentication information to the server and waits for the result of whether authentication was successful. If authentication is successful, the learning session starts.

[0239] Step 3:

[0240] Users enter questions into the terminal about topics they want to learn about or problems they want to solve. For example, "Please explain how to calculate differentiation."

[0241] Step 4:

[0242] The terminal sends the user's question to the server. If the communication with the server is successful, the server receives the content.

[0243] Step 5:

[0244] The server analyzes the received question and uses a generative model to generate an answer for the user. During this process, it constructs the content in a natural style through computational processing.

[0245] Step 6:

[0246] The server compares the generated response with existing information in the database to verify its consistency. If any inaccuracies are found, they are corrected with the correct information.

[0247] Step 7:

[0248] The server sends the verified and corrected answers to the terminal and provides them to the user. Additional explanatory materials and example problems may be included at this time.

[0249] Step 8:

[0250] The device displays the acquired answers to the user, and the user proceeds with learning based on that information.

[0251] Step 9:

[0252] The server records the user's questions and session interactions in a database as learning history. This information is used to personalize the user experience for future visits.

[0253] Step 10:

[0254] At the end of a learning session, the user logs out and exits the system from their terminal. The server disconnects the connection, releases all resources, and completely terminates the session.

[0255] (Example 1)

[0256] Next, we will describe Example 1. 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."

[0257] Many learning systems struggle to provide individualized instruction to users, particularly inadequate supply of learning content and accuracy of responses. Furthermore, progress analysis and appropriate feedback are not efficiently conducted, preventing the system from maximizing learning effectiveness. Solving these problems is crucial.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0259] In this invention, the server includes means for generating a response to user input using a generative model, means for accessing an information database stored in a data management device to verify and correct the accuracy of the response generated by the generative model, and means for recording the user's learning history and presenting learning content based on that history. This enables personalized learning support and the provision of accurate information to the user.

[0260] A "generative model" is a system that uses artificial intelligence technology to generatively create responses or content in response to specific input data.

[0261] A "data management device" is a computer system used to manage and store information databases and response content.

[0262] An "information database" is a storage device that stores the information and knowledge necessary to verify and correct the responses generated by a generative model.

[0263] A "prompt statement" is a sentence in natural language that a user inputs to a generative model according to their purpose.

[0264] A "terminal device" is hardware that provides an interface for users to access a system and send and receive information.

[0265] "Learning history" refers to data that records the learning activities and results that users have engaged in through the system.

[0266] An "evaluation generation means" is a method or device for analyzing a user's progress and generating appropriate learning suggestions and feedback.

[0267] "Visualization" is the process of displaying generated information and data in a way that is easy for users to understand.

[0268] This invention is a system that allows users to utilize artificial intelligence technology in the learning process. The system operates primarily through interaction between a server, a terminal, and the user.

[0269] The server is the core of the system and hosts the generative model. The server possesses high-performance computing capabilities as hardware and a platform for executing the generative AI model as software. Upon receiving input from the user, the server uses the generative AI model to generate an appropriate response. The generated response is verified against an information database stored in the management device and corrected if necessary. This process ensures the accuracy and reliability of the generated response.

[0270] The terminal is a device that serves as the interface with the user, and can be a tablet, smartphone, or personal computer. The terminal has a user interface as software and provides an environment for the user to input prompts. When the user inputs a question about the learning content, the terminal sends that input to the server. When a response is returned from the server, the terminal displays it visually to the user to help them understand.

[0271] Users can interact with the system via their terminal and progress through their learning. For example, if a user inputs "Please tell me how to solve a quadratic equation" as a prompt, the terminal sends this to the server, which generates a response containing detailed information about the solution. This response is then returned to the terminal, and the user can deepen their learning based on that information.

[0272] This system includes a function to record learning history, continuously tracking user progress. The learning history is stored on a server and forms the basis for providing learning content optimized for each individual user. This enables the delivery of an efficient and personalized learning experience.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] The user enters a question related to the learning content as a prompt into the terminal. This action includes text input using a keyboard or touchscreen. An example of the input data might be something like, "Please explain how to solve a quadratic equation." This prompt is then prepared for the next process.

[0276] Step 2:

[0277] The terminal sends the prompt text received from the user to the server. The input here is the prompt text input in Step 1, and as output, a network message to the server is generated. The terminal sends this data to the server via the Internet or an internal network.

[0278] Step 3:

[0279] The server analyzes the prompt text received from the terminal and uses the generative AI model to generate an answer. The input data is the prompt text, and through the natural language generation process by the AI model, the generated answer text is obtained as output. Specific operations include text analysis and generation by natural language processing algorithms.

[0280] Step 4:

[0281] The server compares the generated answer with the information database stored in the data management device to verify its accuracy. Here, the generated answer is used as input, and a verified and reliable response is obtained as output. Specific operations include executing a database query and comparing it with the information database.

[0282] Step 5:

[0283] The server sends the verified and corrected response to the terminal. The input is the response whose accuracy has been verified, and as output, a message is generated that is sent to the terminal via the network. The server uses a communication protocol to do this.

[0284] Step 6:

[0285] The terminal displays the response sent from the server through the user interface. The input is the response message from the server, and as output, information to be displayed on the display is generated. Specific operations include rendering text on the screen.

[0286] Step 7:

[0287] The user checks the displayed answer and, if necessary, enters further questions to continue learning. The input here is the information obtained in step 6, and a new prompt sentence is generated as the output. Based on this, the user can plan the next learning step.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0290] To enable multiple learners to receive learning guidance that is efficient and individually optimized, and in particular, to provide a system that can grasp the learning progress of users in real time via a portable device and provide appropriate feedback and learning plans. This enables high-quality learning support to be widely available beyond the limitations of resources in the conventional educational environment.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0292] In this invention, the server includes means for generating a response to the user's input using a generation model, means for accessing a text database stored in the management device and verifying and correcting the accuracy of the response generated by the generation model, means for recording the user's learning history and presenting learning content based on that history, means for functioning as an interface through the user terminal to obtain the user's input information and transmit it to the management device with high precision for processing, and means for visually presenting the answer generated by the learner via a portable device. As a result, the learner can receive an optimal learning experience at their own pace.

[0293] The "generation model" is an algorithm that uses artificial intelligence to generate natural language and information based on specific input data.

[0294] "Management device" refers to hardware or software used to store and manage generated data and learning history.

[0295] A "text database" is a database that collects existing text information and is used to verify the accuracy of that information.

[0296] "User learning history" refers to records of the user's learning history and results to date.

[0297] A "user terminal" is a device that a user can use as an interface, utilizing a portable electronic device.

[0298] An "interface" refers to the means or methods used when a user exchanges information with a system in a two-way manner.

[0299] A "portable device" is an electronic device that is easily carried and capable of running educational applications.

[0300] As an embodiment of this invention, a system comprising a server, a user terminal, and a generative model is constructed. The server hosts the generative model and provides responses generated based on user input information. This generative model may utilize, for example, natural language processing technology. Specifically, the server can implement OpenAI's GPT or a similar natural language generation algorithm.

[0301] The user terminal functions as a device for learners to operate, and uses portable electronic devices such as smartphones and tablets. The terminal receives questions from the user and transmits that information to the server in real time. WebSocket protocol or HTTP can be used for communication.

[0302] In this system, assume that the user inputs a prompt sentence about doubts in learning, such as "Please tell me more about dental implants." The terminal receives the prompt sentence and sends it to the server. The server utilizes the generation model to generate an explanation for this prompt, verifies its accuracy based on the text database, and then sends appropriate information back to the user terminal. As a result, the learner can obtain refined information and effective learning becomes possible.

[0303] This embodiment realizes a new learning model, enabling learners to receive optimal educational support according to their individual learning needs regardless of their location.

[0304] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0305] Step 1:

[0306] The user inputs a question via the terminal. The terminal receives the prompt sentence input by the user, formats it as input data, and prepares to send it to the server. At this time, the input data is in text format and includes specific questions and doubts related to the user's learning.

[0307] Step 2:

[0308] The terminal sends the prompt sentence to the server. WebSocket or HTTP protocol is used for this data transmission. When the server receives the prompt sentence, it prepares to call the generation model based on the data. The received data is converted into an appropriate format for giving to the generation model.

[0309] Step 3:

[0310] The server uses a generative AI model to generate responses to received prompt sentences. This generative model is based on natural language processing technology and utilizes an algorithm that understands intent from received text data and generates linguistic responses. The generated responses are optimized to include meaningful information from a learning perspective.

[0311] Step 4:

[0312] The server validates the generated response against a text database. Here, it compares the generated response against existing knowledge stored in the database to verify its accuracy. If necessary, the response is corrected based on the validation results. This step involves crucial processing to ensure accurate information is provided.

[0313] Step 5:

[0314] The server sends the verified and corrected response back to the terminal. The terminal formats the received response for visual presentation to the user. This output data is laid out to be displayed in a format that is easy for the user to understand.

[0315] Step 6:

[0316] The user terminal displays the received responses to the user. This allows the user to check the answers to their questions on the terminal, enabling them to progress in their learning more effectively. The generated responses are recorded on the terminal as the user's learning history and used to support future learning.

[0317] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0318] This invention is implemented as an educational system combining a generative model and an emotion engine. The system aims to provide a personalized learning experience that takes into account the user's emotional state. Specific embodiments are described below.

[0319] First, the server hosts the generative model and the sentiment engine, coordinating them to support the entire learning process. The server receives questions from the user and generates initial responses using the generative model. At this time, the sentiment engine evaluates the user's emotional state by analyzing the user's input data, which helps in selecting learning content and adjusting responses.

[0320] The terminal interacts with the user, allowing for question input and display of generated responses. Each time the user solves a problem or asks a question, their response is recorded through the terminal and sent to the server. The emotion engine analyzes this data sequentially to identify the user's emotional patterns. For example, if the system determines the user is stressed, it may reduce the learning content or present content designed to increase motivation.

[0321] To give a concrete example, if a user enters "I can't concentrate on studying history" into their device, the server checks the user's current learning history and sentiment data. The sentiment engine determines that the sentiment stems from boredom or impatience, and uses a generative model to generate a response that includes encouragement and specific advice.

[0322] Furthermore, the system records the correlation between the user's past learning history and emotional changes, and uses this data to further optimize learning in subsequent sessions. This mechanism establishes an emotionally responsive learning style tailored to each individual user, maximizing learning effectiveness.

[0323] This system functions effectively in distance education and various learning situations, and can meet diverse educational needs.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] Users log in to their device to begin learning and view their individual dashboard, where they can see their current learning progress and past performance.

[0327] Step 2:

[0328] The device sends login information to the server for user authentication. If authentication is successful, the device retrieves the user's learning history and sentiment data from the server and displays it on the device.

[0329] Step 3:

[0330] Users select a topic they want to learn about and enter specific questions or problems into the device. For example, they might input something like, "I don't understand differential calculus, so could you explain it in detail?"

[0331] Step 4:

[0332] The terminal sends the user's question to the server. If the communication with the server is successful, the server receives the content.

[0333] Step 5:

[0334] The server uses a generative model to generate an initial response to the received question. Additionally, the emotion engine analyzes the user's input to identify their emotional state. This result is used to refine the response.

[0335] Step 6:

[0336] Based on the analysis results of the emotion engine, the server generates responses appropriate to the user's emotional state and makes recommended adjustments to the learning content. For example, if it is determined that the user has difficulty with concentration, it will present a simple problem.

[0337] Step 7:

[0338] The server sends the generated response and corrected learning content to the device.

[0339] Step 8:

[0340] The device displays received responses to the user, helping them to have the best possible learning experience. The displayed content may include advice and additional explanations.

[0341] Step 9:

[0342] Users progress through their learning using the presented learning content, and input additional questions and feedback into their device based on changes in their emotions and level of understanding.

[0343] Step 10:

[0344] The server records learning session data, along with sentiment information, in the learning history. This record is used to personalize the learning process in subsequent sessions.

[0345] Step 11:

[0346] At the end of the learning session, the user logs out, and the device disconnects from the server to end the session. The server releases all resources and confirms that the data has been saved.

[0347] (Example 2)

[0348] Next, we will describe Example 2. 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".

[0349] Traditional education systems, while presenting learning content based on users' learning history, have not adequately provided responses or learning support that take into account the user's emotional state. As a result, there is a problem where learning effectiveness decreases when users' emotions or motivation decline. It is necessary to solve this problem and provide users with an individualized learning experience.

[0350] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0351] In this invention, the server includes means for generating responses to user input using a generative model, means for analyzing the user's emotional state and adjusting the generated responses based on that state, means for accessing a set of information stored in a management device and verifying and correcting the accuracy of the responses generated by the generative model, and means for recording the user's learning history and emotional state history and presenting learning content based on that history. This enables flexible and effective learning support that is tailored to the user's emotional state.

[0352] A "generative model" is an algorithm or system that takes text data as input and generates a response in natural language form based on it.

[0353] "Emotional state" refers to the emotional response or psychological state that a user exhibits in a particular situation or input.

[0354] A "management device" is a device or system that includes a database for storing and managing information sets and learning histories, and for accessing them as needed.

[0355] An "information set" refers to a collection of data or knowledge that has been organized and classified for a specific purpose.

[0356] A "feedback generation method" refers to a technology or system that analyzes a user's progress and emotional state and generates optimal responses or suggestions based on that analysis.

[0357] "User interface" refers to the screens and means of interaction that users use to interact with a device or program.

[0358] This invention is an advanced educational system that combines a generative model and an emotion engine to provide personalized learning support based on the user's emotional state. Specific embodiments of this system are described below.

[0359] First, the server forms the core of this system, hosting the generative AI model and the emotion engine. The generative AI model receives input text from the user and generates an appropriate response in natural language. This response generation uses existing AI technologies (e.g., natural language processing technologies) and involves complex data processing and calculations.

[0360] Upon receiving user input data, the server activates the emotion engine and analyzes the user's emotional state from the input text. Using text analysis techniques, the emotion engine identifies the user's emotional state and, if the user is experiencing anxiety or low motivation, provides adjustments to the server. Based on the results of the emotion analysis, the generative AI model adjusts the response, providing the user with the most appropriate information and encouraging messages.

[0361] The terminal provides an interface for the user to interact with this system. The user inputs questions through the terminal and receives generated responses. The terminal uses a GUI (Graphical User Interface) for intuitive operation and is designed to allow users to interact with the system smoothly.

[0362] Users inform the server of their state of mind, for example, by typing "I can't concentrate on studying history." The server then considers the user's learning history and sentiment data to ensure that the generative AI model provides the best possible response. This allows users to receive words of encouragement and learning advice, thereby rekindling their motivation to learn.

[0363] A concrete example of a prompt message is, "What kind of encouraging words can be generated when a user gets bored studying history?" In this way, the system can provide a personalized learning experience for the user.

[0364] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0365] Step 1:

[0366] Users enter questions and comments through their devices. User input is collected in text format, and this contains the initial information regarding the user's intentions and feelings.

[0367] Step 2:

[0368] The terminal sends user input to the server. When the input data is transferred to the server, it is converted to an appropriate format to facilitate processing on the server.

[0369] Step 3:

[0370] The server analyzes the received input data and provides it as input to the generative AI model. The generative AI model processes the input prompt sentence and generates appropriate response text by referring to a relevant knowledge database. At this stage, the input data is analyzed using natural language processing techniques, and response candidates are output.

[0371] Step 4:

[0372] The server inputs the generated response into the emotion engine, which evaluates the user's emotional state. Based on the input data and the generated response, the emotion engine analyzes the user's emotions and readjusts the response as needed to reflect the results. The output is the adjusted response.

[0373] Step 5:

[0374] The server updates the user's learning history and sentiment state history with a refined response. The server adds the new historical data to the database and uses it to optimize future learning sessions.

[0375] Step 6:

[0376] The terminal displays the response received from the server to the user. The generated content is presented on the user interface in a visually organized manner, making it easy for the user to understand and choose their next action.

[0377] (Application Example 2)

[0378] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0379] This invention aims to mitigate the impact of learners' emotional states on learning outcomes in educational content. Current educational systems often fail to consider learners' emotional states, leading to challenges such as stress and decreased motivation hindering learning efficiency. Furthermore, real-time emotion-based feedback and content optimization are difficult, resulting in a lack of personalized learning experiences.

[0380] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0381] In this invention, the server includes means for generating responses to user input using a generative model; means for accessing a text database stored in a management device to verify and correct the accuracy of the responses generated by the generative model; means for recording the user's learning history and emotional state and presenting learning content based on that history and state; means for optimizing the generated responses based on the user's emotions via an emotion analysis device that analyzes the user's emotional information; and means for presenting the optimized information to the user through a visual information display device. This enables the provision of a personalized learning experience that takes into account the user's emotional state and allows for the presentation of educational content optimized in real time according to emotions.

[0382] A "generative model" is an algorithm that automatically generates appropriate responses or information based on input data.

[0383] An "emotion analysis device" is a device that analyzes a user's emotional state and identifies changes in that state in real time.

[0384] A "visual information display device" is a device that visually presents generated information or responses to the user.

[0385] A "text database" is a collection of data stored in text format that is used to verify and correct user information and the responses of generative models.

[0386] "Optimization" refers to adjusting the information and responses provided to a more appropriate state based on the user's emotions and learning history.

[0387] In order to implement this invention, the following system and procedure are necessary.

[0388] The server first generates a response to the user's input using a generative model. The generated initial response is verified using a text database stored in the management device, and the response is corrected as needed. At this time, the sentiment analysis device analyzes the user's emotional information and uses the results to optimize the response. The server records the user's learning history and emotional state, and based on this, optimizes the learning content and presents it to the user.

[0389] The device presents optimized information to the user via a visual information display device. By using the visual information display device, users can access content that matches their emotional state during learning. These devices and systems enable a more personalized learning experience for the user.

[0390] As a concrete example, if a user inputs "I can't concentrate on studying history," the server receives this input and analyzes the user's emotional state via an emotion analysis device. If the analysis results indicate boredom or frustration, a generative model generates a response with encouragement and specific advice. This response is then presented to the user through a visual information display device.

[0391] Examples of prompts to input into the generation AI model include, "If the user's facial expression indicates confusion, generate encouragement and recommended product information," and "Facial expression evaluation: Confusion, Voice tone: Questioning tone, Store environment: Clothing section."

[0392] In this way, real-time optimization that takes emotions into account is performed for each individual user, enabling the provision of a personalized and effective learning experience.

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] The server receives input from the user, which includes questions and problems the user is facing during the learning process. The input data is primarily in text format and is then sent to the generative model for processing.

[0396] Step 2:

[0397] The server processes the received input data into a generative AI model to generate an initial response. At this stage, the generative AI model creates a provisional response to the user's question and returns it to the server as output.

[0398] Step 3:

[0399] The server accesses a text database stored on the management device to verify the accuracy of the initial response generated. If the response is incorrect or inappropriate, corrections are made. Rule-based validation from the text database is performed, and the response is adjusted.

[0400] Step 4:

[0401] The server uses an emotion analysis device to evaluate the user's emotional state. This evaluation is based on data such as the user's voice, facial expressions, and input content, leading to the identification of emotions. The emotion analysis engine processes the data and calculates emotional parameters to obtain the output.

[0402] Step 5:

[0403] The server optimizes the generated response based on the results of the emotion analysis device. Specifically, it adjusts the response to match the user's emotional state to achieve optimal communication. For example, if the user is showing signs of stress, the response will be made gentler and encouraging words will be added.

[0404] Step 6:

[0405] The device displays optimized responses to the user via a visual information display device. This information is presented on the user's display in a visual format, in a way that aids the user's learning.

[0406] Step 7:

[0407] Based on the responses provided, the user decides on the next learning step. At this stage, the user reads and understands the responses and decides whether to continue or ask further questions. The user's responses are recorded and used in the next session.

[0408] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0409] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0410] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0411] [Third Embodiment]

[0412] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0413] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0414] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0415] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0416] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0417] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0418] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0419] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0420] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0421] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0422] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0423] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0424] This invention is implemented as an educational system that allows users to utilize artificial intelligence technology in the learning process. This system operates through the interaction of a server, terminals, and users, with a generative model at its core. A specific embodiment is described below.

[0425] First, the server hosts the generative model. When this server receives a question, it uses the generative model to generate an answer based on the user's input. The generated answer is validated using a text database prepared by the cram school and corrected as needed to ensure accuracy.

[0426] The terminal is a device that serves as the interface with the user. When the user enters a question about the learning content, the terminal sends that input to the server. When the server returns an answer, the terminal displays it visually to the user.

[0427] Users can input questions and receive answers and feedback via their devices. The system continuously records the problems solved and their results, saving them as learning history on the server. This allows for continuous evaluation of the user's progress and provides personalized instruction.

[0428] As a concrete example, consider a case where a user inputs a math problem, "How to solve a quadratic equation," as a question. The terminal sends this input to the server. The server uses a generative model to generate a detailed answer regarding the solution, and after ensuring its accuracy using the tutoring center's database, it sends it back to the terminal. This allows the user to learn based on accurate information.

[0429] This system is designed to expand educational opportunities in a wide range of areas, including sparsely populated regions, and to efficiently provide learning environments. It functions as an integrated platform that delivers high-quality education while optimizing human resources.

[0430] The following describes the processing flow.

[0431] Step 1:

[0432] The user starts up their learning device, accesses the login screen, and enters their user ID and password to authenticate their identity.

[0433] Step 2:

[0434] The device sends the entered authentication information to the server and waits for the result of whether authentication was successful. If authentication is successful, the learning session starts.

[0435] Step 3:

[0436] Users enter questions into the terminal about topics they want to learn about or problems they want to solve. For example, "Please explain how to calculate differentiation."

[0437] Step 4:

[0438] The terminal sends the user's question to the server. If the communication with the server is successful, the server receives the content.

[0439] Step 5:

[0440] The server analyzes the received question and uses a generative model to generate an answer for the user. During this process, it constructs the content in a natural style through computational processing.

[0441] Step 6:

[0442] The server compares the generated response with existing information in the database to verify its consistency. If any inaccuracies are found, they are corrected with the correct information.

[0443] Step 7:

[0444] The server sends the verified and corrected answers to the terminal and provides them to the user. Additional explanatory materials and example problems may be included at this time.

[0445] Step 8:

[0446] The device displays the acquired answers to the user, and the user proceeds with learning based on that information.

[0447] Step 9:

[0448] The server records the user's questions and session interactions in a database as learning history. This information is used to personalize the user experience for future visits.

[0449] Step 10:

[0450] At the end of a learning session, the user logs out and exits the system from their terminal. The server disconnects the connection, releases all resources, and completely terminates the session.

[0451] (Example 1)

[0452] Next, we will describe Example 1. 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."

[0453] Many learning systems struggle to provide individualized instruction to users, particularly inadequate supply of learning content and accuracy of responses. Furthermore, progress analysis and appropriate feedback are not efficiently conducted, preventing the system from maximizing learning effectiveness. Solving these problems is crucial.

[0454] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0455] In this invention, the server includes means for generating a response to user input using a generative model, means for accessing an information database stored in a data management device to verify and correct the accuracy of the response generated by the generative model, and means for recording the user's learning history and presenting learning content based on that history. This enables personalized learning support and the provision of accurate information to the user.

[0456] A "generative model" is a system that uses artificial intelligence technology to generatively create responses or content in response to specific input data.

[0457] A "data management device" is a computer system used to manage and store information databases and response content.

[0458] An "information database" is a storage device that stores the information and knowledge necessary to verify and correct the responses generated by a generative model.

[0459] A "prompt statement" is a sentence in natural language that a user inputs to a generative model according to their purpose.

[0460] A "terminal device" is hardware that provides an interface for users to access a system and send and receive information.

[0461] "Learning history" refers to data that records the learning activities and results that users have engaged in through the system.

[0462] An "evaluation generation means" is a method or device for analyzing a user's progress and generating appropriate learning suggestions and feedback.

[0463] "Visualization" is the process of displaying generated information and data in a way that is easy for users to understand.

[0464] This invention is a system that allows users to utilize artificial intelligence technology in the learning process. The system operates primarily through interaction between a server, a terminal, and the user.

[0465] The server is the core of the system and hosts the generative model. The server possesses high-performance computing capabilities as hardware and a platform for executing the generative AI model as software. Upon receiving input from the user, the server uses the generative AI model to generate an appropriate response. The generated response is verified against an information database stored in the management device and corrected if necessary. This process ensures the accuracy and reliability of the generated response.

[0466] The terminal is a device that serves as the interface with the user, and can be a tablet, smartphone, or personal computer. The terminal has a user interface as software and provides an environment for the user to input prompts. When the user inputs a question about the learning content, the terminal sends that input to the server. When a response is returned from the server, the terminal displays it visually to the user to help them understand.

[0467] Users can interact with the system via their terminal and progress through their learning. For example, if a user inputs "Please tell me how to solve a quadratic equation" as a prompt, the terminal sends this to the server, which generates a response containing detailed information about the solution. This response is then returned to the terminal, and the user can deepen their learning based on that information.

[0468] This system includes a function to record learning history, continuously tracking user progress. The learning history is stored on a server and forms the basis for providing learning content optimized for each individual user. This enables the delivery of an efficient and personalized learning experience.

[0469] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0470] Step 1:

[0471] The user enters a question related to the learning content as a prompt into the terminal. This action includes text input using a keyboard or touchscreen. An example of the input data might be something like, "Please explain how to solve a quadratic equation." This prompt is then prepared for the next process.

[0472] Step 2:

[0473] The terminal sends the prompt message received from the user to the server. The input here is the prompt message entered in step 1, and the output is a network message to the server. The terminal sends this data to the server via the internet or internal network.

[0474] Step 3:

[0475] The server analyzes the prompt text received from the terminal and generates a response using a generative AI model. The input data is the prompt text, and after going through the natural language generation process by the AI ​​model, the generated response text is obtained as output. The specific operation includes text analysis and generation using natural language processing algorithms.

[0476] Step 4:

[0477] The server verifies the accuracy of the generated response by comparing it with the information database stored in the data management device. Here, the generated response is used as input, and a verified, reliable response is obtained as output. Specifically, the process involves executing a database query and comparing it with the information database.

[0478] Step 5:

[0479] The server sends a verified and corrected response to the terminal. The input is the verified response, which generates a message that is sent to the terminal over the network as output. The server utilizes a communication protocol to do this.

[0480] Step 6:

[0481] The terminal displays responses sent from the server through a user interface. The input is the response message from the server, and the output generates information that is displayed on the screen. Specific operations include rendering text on the screen.

[0482] Step 7:

[0483] The user reviews the displayed answers and, if necessary, enters further questions to continue learning. The input here is the information obtained in step 6, and a new prompt is generated as output. Based on this, the user can plan the next learning step.

[0484] (Application Example 1)

[0485] Next, we will explain Application Example 1. In the following explanation, 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."

[0486] The goal is to enable multiple learners to receive efficient and individually optimized learning instruction, particularly by providing a system that allows for real-time monitoring of users' learning progress via portable devices and offers appropriate feedback and learning plans. This will overcome the resource limitations of traditional educational environments and enable widespread high-quality learning support.

[0487] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0488] In this invention, the server includes means for generating responses to user input using a generative model, means for accessing a text database stored in a management device to verify and correct the accuracy of the responses generated by the generative model, means for recording the user's learning history and presenting learning content based on that history, means for functioning as an interface through a user terminal to acquire user input information, transmit it to the management device with high accuracy for processing, and means for visually presenting the generated answers via a portable device to the learner. This enables learners to receive an optimal learning experience at their own pace.

[0489] A "generative model" is an algorithm that uses artificial intelligence to generate natural language and information based on specific input data.

[0490] "Management device" refers to hardware or software used to store and manage generated data and learning history.

[0491] A "text database" is a database that collects existing text information and is used to verify the accuracy of that information.

[0492] "User learning history" refers to records of the user's learning history and results to date.

[0493] A "user terminal" is a device that a user can use as an interface, utilizing a portable electronic device.

[0494] An "interface" refers to the means or methods used when a user exchanges information with a system in a two-way manner.

[0495] A "portable device" is an electronic device that is easily carried and capable of running educational applications.

[0496] As an embodiment of this invention, a system comprising a server, a user terminal, and a generative model is constructed. The server hosts the generative model and provides responses generated based on user input information. This generative model may utilize, for example, natural language processing technology. Specifically, the server can implement OpenAI's GPT or a similar natural language generation algorithm.

[0497] The user terminal functions as a device for learners to operate, and uses portable electronic devices such as smartphones and tablets. The terminal receives questions from the user and transmits that information to the server in real time. WebSocket protocol or HTTP can be used for communication.

[0498] In this system, a user inputs a prompt, such as "Please explain dental implants in detail," expressing a question they have during their learning process. The terminal receives this prompt and sends it to the server. The server utilizes a generative model to generate an explanation for this prompt, verifies its accuracy based on a text database, and then sends the appropriate information back to the user's terminal. As a result, learners receive refined information, enabling effective learning.

[0499] This embodiment realizes a new learning model that enables learners to receive optimal educational support tailored to their individual learning needs, no matter where they are.

[0500] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0501] Step 1:

[0502] The user enters a question via a terminal. The terminal receives the prompt text entered by the user, formats it as input data, and prepares to send it to the server. At this time, the input data is in text format and contains specific questions or doubts related to the user's learning.

[0503] Step 2:

[0504] The terminal sends a prompt message to the server. This data transmission uses the WebSocket or HTTP protocol. When the server receives the prompt message, it prepares to invoke the generative model based on that data. The received data is converted into an appropriate format for input to the generative model.

[0505] Step 3:

[0506] The server uses a generative AI model to generate responses to received prompt sentences. This generative model is based on natural language processing technology and utilizes an algorithm that understands intent from received text data and generates linguistic responses. The generated responses are optimized to include meaningful information from a learning perspective.

[0507] Step 4:

[0508] The server validates the generated response against a text database. Here, it compares the generated response against existing knowledge stored in the database to verify its accuracy. If necessary, the response is corrected based on the validation results. This step involves crucial processing to ensure accurate information is provided.

[0509] Step 5:

[0510] The server sends the verified and corrected response back to the terminal. The terminal formats the received response for visual presentation to the user. This output data is laid out to be displayed in a format that is easy for the user to understand.

[0511] Step 6:

[0512] The user terminal displays the received responses to the user. This allows the user to check the answers to their questions on the terminal, enabling them to progress in their learning more effectively. The generated responses are recorded on the terminal as the user's learning history and used to support future learning.

[0513] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0514] This invention is implemented as an educational system combining a generative model and an emotion engine. The system aims to provide a personalized learning experience that takes into account the user's emotional state. Specific embodiments are described below.

[0515] First, the server hosts the generative model and the sentiment engine, coordinating them to support the entire learning process. The server receives questions from the user and generates initial responses using the generative model. At this time, the sentiment engine evaluates the user's emotional state by analyzing the user's input data, which helps in selecting learning content and adjusting responses.

[0516] The terminal interacts with the user, allowing for question input and display of generated responses. Each time the user solves a problem or asks a question, their response is recorded through the terminal and sent to the server. The emotion engine analyzes this data sequentially to identify the user's emotional patterns. For example, if the system determines the user is stressed, it may reduce the learning content or present content designed to increase motivation.

[0517] To give a concrete example, if a user enters "I can't concentrate on studying history" into their device, the server checks the user's current learning history and sentiment data. The sentiment engine determines that the sentiment stems from boredom or impatience, and uses a generative model to generate a response that includes encouragement and specific advice.

[0518] Furthermore, the system records the correlation between the user's past learning history and emotional changes, and uses this data to further optimize learning in subsequent sessions. This mechanism establishes an emotionally responsive learning style tailored to each individual user, maximizing learning effectiveness.

[0519] This system functions effectively in distance education and various learning situations, and can meet diverse educational needs.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] Users log in to their device to begin learning and view their individual dashboard, where they can see their current learning progress and past performance.

[0523] Step 2:

[0524] The device sends login information to the server for user authentication. If authentication is successful, the device retrieves the user's learning history and sentiment data from the server and displays it on the device.

[0525] Step 3:

[0526] Users select a topic they want to learn about and enter specific questions or problems into the device. For example, they might input something like, "I don't understand differential calculus, so could you explain it in detail?"

[0527] Step 4:

[0528] The terminal sends the user's question to the server. If the communication with the server is successful, the server receives the content.

[0529] Step 5:

[0530] The server uses a generative model to generate an initial response to the received question. Additionally, the emotion engine analyzes the user's input to identify their emotional state. This result is used to refine the response.

[0531] Step 6:

[0532] Based on the analysis results of the emotion engine, the server generates responses appropriate to the user's emotional state and makes recommended adjustments to the learning content. For example, if it is determined that the user has difficulty with concentration, it will present a simple problem.

[0533] Step 7:

[0534] The server sends the generated response and corrected learning content to the device.

[0535] Step 8:

[0536] The device displays received responses to the user, helping them to have the best possible learning experience. The displayed content may include advice and additional explanations.

[0537] Step 9:

[0538] Users progress through their learning using the presented learning content, and input additional questions and feedback into their device based on changes in their emotions and level of understanding.

[0539] Step 10:

[0540] The server records learning session data, along with sentiment information, in the learning history. This record is used to personalize the learning process in subsequent sessions.

[0541] Step 11:

[0542] At the end of the learning session, the user logs out, and the device disconnects from the server to end the session. The server releases all resources and confirms that the data has been saved.

[0543] (Example 2)

[0544] Next, we will describe Example 2. 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."

[0545] Traditional education systems, while presenting learning content based on users' learning history, have not adequately provided responses or learning support that take into account the user's emotional state. As a result, there is a problem where learning effectiveness decreases when users' emotions or motivation decline. It is necessary to solve this problem and provide users with an individualized learning experience.

[0546] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0547] In this invention, the server includes means for generating responses to user input using a generative model, means for analyzing the user's emotional state and adjusting the generated responses based on that state, means for accessing a set of information stored in a management device and verifying and correcting the accuracy of the responses generated by the generative model, and means for recording the user's learning history and emotional state history and presenting learning content based on that history. This enables flexible and effective learning support that is tailored to the user's emotional state.

[0548] A "generative model" is an algorithm or system that takes text data as input and generates a response in natural language form based on it.

[0549] "Emotional state" refers to the emotional response or psychological state that a user exhibits in a particular situation or input.

[0550] A "management device" is a device or system that includes a database for storing and managing information sets and learning histories, and for accessing them as needed.

[0551] An "information set" refers to a collection of data or knowledge that has been organized and classified for a specific purpose.

[0552] A "feedback generation method" refers to a technology or system that analyzes a user's progress and emotional state and generates optimal responses or suggestions based on that analysis.

[0553] "User interface" refers to the screens and means of interaction that users use to interact with a device or program.

[0554] This invention is an advanced educational system that combines a generative model and an emotion engine to provide personalized learning support based on the user's emotional state. Specific embodiments of this system are described below.

[0555] First, the server forms the core of this system, hosting the generative AI model and the emotion engine. The generative AI model receives input text from the user and generates an appropriate response in natural language. This response generation uses existing AI technologies (e.g., natural language processing technologies) and involves complex data processing and calculations.

[0556] Upon receiving user input data, the server activates the emotion engine and analyzes the user's emotional state from the input text. Using text analysis techniques, the emotion engine identifies the user's emotional state and, if the user is experiencing anxiety or low motivation, provides adjustments to the server. Based on the results of the emotion analysis, the generative AI model adjusts the response, providing the user with the most appropriate information and encouraging messages.

[0557] The terminal provides an interface for the user to interact with this system. The user inputs questions through the terminal and receives generated responses. The terminal uses a GUI (Graphical User Interface) for intuitive operation and is designed to allow users to interact with the system smoothly.

[0558] Users inform the server of their state of mind, for example, by typing "I can't concentrate on studying history." The server then considers the user's learning history and sentiment data to ensure that the generative AI model provides the best possible response. This allows users to receive words of encouragement and learning advice, thereby rekindling their motivation to learn.

[0559] A concrete example of a prompt message is, "What kind of encouraging words can be generated when a user gets bored studying history?" In this way, the system can provide a personalized learning experience for the user.

[0560] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0561] Step 1:

[0562] Users enter questions and comments through their devices. User input is collected in text format, and this contains the initial information regarding the user's intentions and feelings.

[0563] Step 2:

[0564] The terminal sends user input to the server. When the input data is transferred to the server, it is converted to an appropriate format to facilitate processing on the server.

[0565] Step 3:

[0566] The server analyzes the received input data and provides it as input to the generative AI model. The generative AI model processes the input prompt sentence and generates appropriate response text by referring to a relevant knowledge database. At this stage, the input data is analyzed using natural language processing techniques, and response candidates are output.

[0567] Step 4:

[0568] The server inputs the generated response into the emotion engine, which evaluates the user's emotional state. Based on the input data and the generated response, the emotion engine analyzes the user's emotions and readjusts the response as needed to reflect the results. The output is the adjusted response.

[0569] Step 5:

[0570] The server updates the user's learning history and sentiment state history with a refined response. The server adds the new historical data to the database and uses it to optimize future learning sessions.

[0571] Step 6:

[0572] The terminal displays the response received from the server to the user. The generated content is presented on the user interface in a visually organized manner, making it easy for the user to understand and choose their next action.

[0573] (Application Example 2)

[0574] Next, we will explain application example 2. In the following explanation, 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."

[0575] This invention aims to mitigate the impact of learners' emotional states on learning outcomes in educational content. Current educational systems often fail to consider learners' emotional states, leading to challenges such as stress and decreased motivation hindering learning efficiency. Furthermore, real-time emotion-based feedback and content optimization are difficult, resulting in a lack of personalized learning experiences.

[0576] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0577] In this invention, the server includes means for generating responses to user input using a generative model; means for accessing a text database stored in a management device to verify and correct the accuracy of the responses generated by the generative model; means for recording the user's learning history and emotional state and presenting learning content based on that history and state; means for optimizing the generated responses based on the user's emotions via an emotion analysis device that analyzes the user's emotional information; and means for presenting the optimized information to the user through a visual information display device. This enables the provision of a personalized learning experience that takes into account the user's emotional state and allows for the presentation of educational content optimized in real time according to emotions.

[0578] A "generative model" is an algorithm that automatically generates appropriate responses or information based on input data.

[0579] An "emotion analysis device" is a device that analyzes a user's emotional state and identifies changes in that state in real time.

[0580] A "visual information display device" is a device that visually presents generated information or responses to the user.

[0581] A "text database" is a collection of data stored in text format that is used to verify and correct user information and the responses of generative models.

[0582] "Optimization" refers to adjusting the information and responses provided to a more appropriate state based on the user's emotions and learning history.

[0583] In order to implement this invention, the following system and procedure are necessary.

[0584] The server first generates a response to the user's input using a generative model. The generated initial response is verified using a text database stored in the management device, and the response is corrected as needed. At this time, the sentiment analysis device analyzes the user's emotional information and uses the results to optimize the response. The server records the user's learning history and emotional state, and based on this, optimizes the learning content and presents it to the user.

[0585] The device presents optimized information to the user via a visual information display device. By using the visual information display device, users can access content that matches their emotional state during learning. These devices and systems enable a more personalized learning experience for the user.

[0586] As a concrete example, if a user inputs "I can't concentrate on studying history," the server receives this input and analyzes the user's emotional state via an emotion analysis device. If the analysis results indicate boredom or frustration, a generative model generates a response with encouragement and specific advice. This response is then presented to the user through a visual information display device.

[0587] Examples of prompts to input into the generation AI model include, "If the user's facial expression indicates confusion, generate encouragement and recommended product information," and "Facial expression evaluation: Confusion, Voice tone: Questioning tone, Store environment: Clothing section."

[0588] In this way, real-time optimization that takes emotions into account is performed for each individual user, enabling the provision of a personalized and effective learning experience.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The server receives input from the user, which includes questions and problems the user is facing during the learning process. The input data is primarily in text format and is then sent to the generative model for processing.

[0592] Step 2:

[0593] The server processes the received input data into a generative AI model to generate an initial response. At this stage, the generative AI model creates a provisional response to the user's question and returns it to the server as output.

[0594] Step 3:

[0595] The server accesses a text database stored on the management device to verify the accuracy of the initial response generated. If the response is incorrect or inappropriate, corrections are made. Rule-based validation from the text database is performed, and the response is adjusted.

[0596] Step 4:

[0597] The server uses an emotion analysis device to evaluate the user's emotional state. This evaluation is based on data such as the user's voice, facial expressions, and input content, leading to the identification of emotions. The emotion analysis engine processes the data and calculates emotional parameters to obtain the output.

[0598] Step 5:

[0599] The server optimizes the generated response based on the results of the emotion analysis device. Specifically, it adjusts the response to match the user's emotional state to achieve optimal communication. For example, if the user is showing signs of stress, the response will be made gentler and encouraging words will be added.

[0600] Step 6:

[0601] The device displays optimized responses to the user via a visual information display device. This information is presented on the user's display in a visual format, in a way that aids the user's learning.

[0602] Step 7:

[0603] Based on the responses provided, the user decides on the next learning step. At this stage, the user reads and understands the responses and decides whether to continue or ask further questions. The user's responses are recorded and used in the next session.

[0604] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0605] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0606] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0607] [Fourth Embodiment]

[0608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0609] As shown in Figure 7, the 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.

[0610] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0611] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0612] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0613] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0614] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0615] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0616] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0617] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0618] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0619] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0620] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0621] This invention is implemented as an educational system that allows users to utilize artificial intelligence technology in the learning process. This system operates through the interaction of a server, terminals, and users, with a generative model at its core. A specific embodiment is described below.

[0622] First, the server hosts the generative model. When this server receives a question, it uses the generative model to generate an answer based on the user's input. The generated answer is validated using a text database prepared by the cram school and corrected as needed to ensure accuracy.

[0623] The terminal is a device that serves as the interface with the user. When the user enters a question about the learning content, the terminal sends that input to the server. When the server returns an answer, the terminal displays it visually to the user.

[0624] Users can input questions and receive answers and feedback via their devices. The system continuously records the problems solved and their results, saving them as learning history on the server. This allows for continuous evaluation of the user's progress and provides personalized instruction.

[0625] As a concrete example, consider a case where a user inputs a math problem, "How to solve a quadratic equation," as a question. The terminal sends this input to the server. The server uses a generative model to generate a detailed answer regarding the solution, and after ensuring its accuracy using the tutoring center's database, it sends it back to the terminal. This allows the user to learn based on accurate information.

[0626] This system is designed to expand educational opportunities in a wide range of areas, including sparsely populated regions, and to efficiently provide learning environments. It functions as an integrated platform that delivers high-quality education while optimizing human resources.

[0627] The following describes the processing flow.

[0628] Step 1:

[0629] The user starts up their learning device, accesses the login screen, and enters their user ID and password to authenticate their identity.

[0630] Step 2:

[0631] The device sends the entered authentication information to the server and waits for the result of whether authentication was successful. If authentication is successful, the learning session starts.

[0632] Step 3:

[0633] Users enter questions into the terminal about topics they want to learn about or problems they want to solve. For example, "Please explain how to calculate differentiation."

[0634] Step 4:

[0635] The terminal sends the user's question to the server. If the communication with the server is successful, the server receives the content.

[0636] Step 5:

[0637] The server analyzes the received question and uses a generative model to generate an answer for the user. During this process, it constructs the content in a natural style through computational processing.

[0638] Step 6:

[0639] The server compares the generated response with existing information in the database to verify its consistency. If any inaccuracies are found, they are corrected with the correct information.

[0640] Step 7:

[0641] The server sends the verified and corrected answers to the terminal and provides them to the user. Additional explanatory materials and example problems may be included at this time.

[0642] Step 8:

[0643] The device displays the acquired answers to the user, and the user proceeds with learning based on that information.

[0644] Step 9:

[0645] The server records the user's questions and session interactions in a database as learning history. This information is used to personalize the user experience for future visits.

[0646] Step 10:

[0647] At the end of a learning session, the user logs out and exits the system from their terminal. The server disconnects the connection, releases all resources, and completely terminates the session.

[0648] (Example 1)

[0649] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0650] Many learning systems struggle to provide individualized instruction to users, particularly inadequate supply of learning content and accuracy of responses. Furthermore, progress analysis and appropriate feedback are not efficiently conducted, preventing the system from maximizing learning effectiveness. Solving these problems is crucial.

[0651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0652] In this invention, the server includes means for generating a response to user input using a generative model, means for accessing an information database stored in a data management device to verify and correct the accuracy of the response generated by the generative model, and means for recording the user's learning history and presenting learning content based on that history. This enables personalized learning support and the provision of accurate information to the user.

[0653] A "generative model" is a system that uses artificial intelligence technology to generatively create responses or content in response to specific input data.

[0654] A "data management device" is a computer system used to manage and store information databases and response content.

[0655] An "information database" is a storage device that stores the information and knowledge necessary to verify and correct the responses generated by a generative model.

[0656] A "prompt statement" is a sentence in natural language that a user inputs to a generative model according to their purpose.

[0657] A "terminal device" is hardware that provides an interface for users to access a system and send and receive information.

[0658] "Learning history" refers to data that records the learning activities and results that users have engaged in through the system.

[0659] An "evaluation generation means" is a method or device for analyzing a user's progress and generating appropriate learning suggestions and feedback.

[0660] "Visualization" is the process of displaying generated information and data in a way that is easy for users to understand.

[0661] This invention is a system that allows users to utilize artificial intelligence technology in the learning process. The system operates primarily through interaction between a server, a terminal, and the user.

[0662] The server is the core of the system and hosts the generative model. The server possesses high-performance computing capabilities as hardware and a platform for executing the generative AI model as software. Upon receiving input from the user, the server uses the generative AI model to generate an appropriate response. The generated response is verified against an information database stored in the management device and corrected if necessary. This process ensures the accuracy and reliability of the generated response.

[0663] The terminal is a device that serves as the interface with the user, and can be a tablet, smartphone, or personal computer. The terminal has a user interface as software and provides an environment for the user to input prompts. When the user inputs a question about the learning content, the terminal sends that input to the server. When a response is returned from the server, the terminal displays it visually to the user to help them understand.

[0664] Users can interact with the system via their terminal and progress through their learning. For example, if a user inputs "Please tell me how to solve a quadratic equation" as a prompt, the terminal sends this to the server, which generates a response containing detailed information about the solution. This response is then returned to the terminal, and the user can deepen their learning based on that information.

[0665] This system includes a function to record learning history, continuously tracking user progress. The learning history is stored on a server and forms the basis for providing learning content optimized for each individual user. This enables the delivery of an efficient and personalized learning experience.

[0666] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0667] Step 1:

[0668] The user enters a question related to the learning content as a prompt into the terminal. This action includes text input using a keyboard or touchscreen. An example of the input data might be something like, "Please explain how to solve a quadratic equation." This prompt is then prepared for the next process.

[0669] Step 2:

[0670] The terminal sends the prompt message received from the user to the server. The input here is the prompt message entered in step 1, and the output is a network message to the server. The terminal sends this data to the server via the internet or internal network.

[0671] Step 3:

[0672] The server analyzes the prompt text received from the terminal and generates a response using a generative AI model. The input data is the prompt text, and after going through the natural language generation process by the AI ​​model, the generated response text is obtained as output. The specific operation includes text analysis and generation using natural language processing algorithms.

[0673] Step 4:

[0674] The server verifies the accuracy of the generated response by comparing it with the information database stored in the data management device. Here, the generated response is used as input, and a verified, reliable response is obtained as output. Specifically, the process involves executing a database query and comparing it with the information database.

[0675] Step 5:

[0676] The server sends a verified and corrected response to the terminal. The input is the verified response, which generates a message that is sent to the terminal over the network as output. The server utilizes a communication protocol to do this.

[0677] Step 6:

[0678] The terminal displays responses sent from the server through a user interface. The input is the response message from the server, and the output generates information that is displayed on the screen. Specific operations include rendering text on the screen.

[0679] Step 7:

[0680] The user reviews the displayed answers and, if necessary, enters further questions to continue learning. The input here is the information obtained in step 6, and a new prompt is generated as output. Based on this, the user can plan the next learning step.

[0681] (Application Example 1)

[0682] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0683] The goal is to enable multiple learners to receive efficient and individually optimized learning instruction, particularly by providing a system that allows for real-time monitoring of users' learning progress via portable devices and offers appropriate feedback and learning plans. This will overcome the resource limitations of traditional educational environments and enable widespread high-quality learning support.

[0684] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0685] In this invention, the server includes means for generating responses to user input using a generative model, means for accessing a text database stored in a management device to verify and correct the accuracy of the responses generated by the generative model, means for recording the user's learning history and presenting learning content based on that history, means for functioning as an interface through a user terminal to acquire user input information, transmit it to the management device with high accuracy for processing, and means for visually presenting the generated answers via a portable device to the learner. This enables learners to receive an optimal learning experience at their own pace.

[0686] A "generative model" is an algorithm that uses artificial intelligence to generate natural language and information based on specific input data.

[0687] "Management device" refers to hardware or software used to store and manage generated data and learning history.

[0688] A "text database" is a database that collects existing text information and is used to verify the accuracy of that information.

[0689] "User learning history" refers to records of the user's learning history and results to date.

[0690] A "user terminal" is a device that a user can use as an interface, utilizing a portable electronic device.

[0691] An "interface" refers to the means or methods used when a user exchanges information with a system in a two-way manner.

[0692] A "portable device" is an electronic device that is easily carried and capable of running educational applications.

[0693] As an embodiment of this invention, a system comprising a server, a user terminal, and a generative model is constructed. The server hosts the generative model and provides responses generated based on user input information. This generative model may utilize, for example, natural language processing technology. Specifically, the server can implement OpenAI's GPT or a similar natural language generation algorithm.

[0694] The user terminal functions as a device for learners to operate, and uses portable electronic devices such as smartphones and tablets. The terminal receives questions from the user and transmits that information to the server in real time. WebSocket protocol or HTTP can be used for communication.

[0695] In this system, a user inputs a prompt, such as "Please explain dental implants in detail," expressing a question they have during their learning process. The terminal receives this prompt and sends it to the server. The server utilizes a generative model to generate an explanation for this prompt, verifies its accuracy based on a text database, and then sends the appropriate information back to the user's terminal. As a result, learners receive refined information, enabling effective learning.

[0696] This embodiment realizes a new learning model that enables learners to receive optimal educational support tailored to their individual learning needs, no matter where they are.

[0697] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0698] Step 1:

[0699] The user enters a question via a terminal. The terminal receives the prompt text entered by the user, formats it as input data, and prepares to send it to the server. At this time, the input data is in text format and contains specific questions or doubts related to the user's learning.

[0700] Step 2:

[0701] The terminal sends a prompt message to the server. This data transmission uses the WebSocket or HTTP protocol. When the server receives the prompt message, it prepares to invoke the generative model based on that data. The received data is converted into an appropriate format for input to the generative model.

[0702] Step 3:

[0703] The server uses a generative AI model to generate responses to received prompt sentences. This generative model is based on natural language processing technology and utilizes an algorithm that understands intent from received text data and generates linguistic responses. The generated responses are optimized to include meaningful information from a learning perspective.

[0704] Step 4:

[0705] The server validates the generated response against a text database. Here, it compares the generated response against existing knowledge stored in the database to verify its accuracy. If necessary, the response is corrected based on the validation results. This step involves crucial processing to ensure accurate information is provided.

[0706] Step 5:

[0707] The server sends the verified and corrected response back to the terminal. The terminal formats the received response for visual presentation to the user. This output data is laid out to be displayed in a format that is easy for the user to understand.

[0708] Step 6:

[0709] The user terminal displays the received responses to the user. This allows the user to check the answers to their questions on the terminal, enabling them to progress in their learning more effectively. The generated responses are recorded on the terminal as the user's learning history and used to support future learning.

[0710] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0711] This invention is implemented as an educational system combining a generative model and an emotion engine. The system aims to provide a personalized learning experience that takes into account the user's emotional state. Specific embodiments are described below.

[0712] First, the server hosts the generative model and the sentiment engine, coordinating them to support the entire learning process. The server receives questions from the user and generates initial responses using the generative model. At this time, the sentiment engine evaluates the user's emotional state by analyzing the user's input data, which helps in selecting learning content and adjusting responses.

[0713] The terminal interacts with the user, allowing for question input and display of generated responses. Each time the user solves a problem or asks a question, their response is recorded through the terminal and sent to the server. The emotion engine analyzes this data sequentially to identify the user's emotional patterns. For example, if the system determines the user is stressed, it may reduce the learning content or present content designed to increase motivation.

[0714] To give a concrete example, if a user enters "I can't concentrate on studying history" into their device, the server checks the user's current learning history and sentiment data. The sentiment engine determines that the sentiment stems from boredom or impatience, and uses a generative model to generate a response that includes encouragement and specific advice.

[0715] Furthermore, the system records the correlation between the user's past learning history and emotional changes, and uses this data to further optimize learning in subsequent sessions. This mechanism establishes an emotionally responsive learning style tailored to each individual user, maximizing learning effectiveness.

[0716] This system functions effectively in distance education and various learning situations, and can meet diverse educational needs.

[0717] The following describes the processing flow.

[0718] Step 1:

[0719] Users log in to their device to begin learning and view their individual dashboard, where they can see their current learning progress and past performance.

[0720] Step 2:

[0721] The device sends login information to the server for user authentication. If authentication is successful, the device retrieves the user's learning history and sentiment data from the server and displays it on the device.

[0722] Step 3:

[0723] Users select a topic they want to learn about and enter specific questions or problems into the device. For example, they might input something like, "I don't understand differential calculus, so could you explain it in detail?"

[0724] Step 4:

[0725] The terminal sends the user's question to the server. If the communication with the server is successful, the server receives the content.

[0726] Step 5:

[0727] The server uses a generative model to generate an initial response to the received question. Additionally, the emotion engine analyzes the user's input to identify their emotional state. This result is used to refine the response.

[0728] Step 6:

[0729] Based on the analysis results of the emotion engine, the server generates responses appropriate to the user's emotional state and makes recommended adjustments to the learning content. For example, if it is determined that the user has difficulty with concentration, it will present a simple problem.

[0730] Step 7:

[0731] The server sends the generated response and corrected learning content to the device.

[0732] Step 8:

[0733] The device displays received responses to the user, helping them to have the best possible learning experience. The displayed content may include advice and additional explanations.

[0734] Step 9:

[0735] Users progress through their learning using the presented learning content, and input additional questions and feedback into their device based on changes in their emotions and level of understanding.

[0736] Step 10:

[0737] The server records learning session data, along with sentiment information, in the learning history. This record is used to personalize the learning process in subsequent sessions.

[0738] Step 11:

[0739] At the end of the learning session, the user logs out, and the device disconnects from the server to end the session. The server releases all resources and confirms that the data has been saved.

[0740] (Example 2)

[0741] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0742] Traditional education systems, while presenting learning content based on users' learning history, have not adequately provided responses or learning support that take into account the user's emotional state. As a result, there is a problem where learning effectiveness decreases when users' emotions or motivation decline. It is necessary to solve this problem and provide users with an individualized learning experience.

[0743] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0744] In this invention, the server includes means for generating responses to user input using a generative model, means for analyzing the user's emotional state and adjusting the generated responses based on that state, means for accessing a set of information stored in a management device and verifying and correcting the accuracy of the responses generated by the generative model, and means for recording the user's learning history and emotional state history and presenting learning content based on that history. This enables flexible and effective learning support that is tailored to the user's emotional state.

[0745] A "generative model" is an algorithm or system that takes text data as input and generates a response in natural language form based on it.

[0746] "Emotional state" refers to the emotional response or psychological state that a user exhibits in a particular situation or input.

[0747] A "management device" is a device or system that includes a database for storing and managing information sets and learning histories, and for accessing them as needed.

[0748] An "information set" refers to a collection of data or knowledge that has been organized and classified for a specific purpose.

[0749] A "feedback generation method" refers to a technology or system that analyzes a user's progress and emotional state and generates optimal responses or suggestions based on that analysis.

[0750] "User interface" refers to the screens and means of interaction that users use to interact with a device or program.

[0751] This invention is an advanced educational system that combines a generative model and an emotion engine to provide personalized learning support based on the user's emotional state. Specific embodiments of this system are described below.

[0752] First, the server forms the core of this system, hosting the generative AI model and the emotion engine. The generative AI model receives input text from the user and generates an appropriate response in natural language. This response generation uses existing AI technologies (e.g., natural language processing technologies) and involves complex data processing and calculations.

[0753] Upon receiving user input data, the server activates the emotion engine and analyzes the user's emotional state from the input text. Using text analysis techniques, the emotion engine identifies the user's emotional state and, if the user is experiencing anxiety or low motivation, provides adjustments to the server. Based on the results of the emotion analysis, the generative AI model adjusts the response, providing the user with the most appropriate information and encouraging messages.

[0754] The terminal provides an interface for the user to interact with this system. The user inputs questions through the terminal and receives generated responses. The terminal uses a GUI (Graphical User Interface) for intuitive operation and is designed to allow users to interact with the system smoothly.

[0755] Users inform the server of their state of mind, for example, by typing "I can't concentrate on studying history." The server then considers the user's learning history and sentiment data to ensure that the generative AI model provides the best possible response. This allows users to receive words of encouragement and learning advice, thereby rekindling their motivation to learn.

[0756] A concrete example of a prompt message is, "What kind of encouraging words can be generated when a user gets bored studying history?" In this way, the system can provide a personalized learning experience for the user.

[0757] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0758] Step 1:

[0759] Users enter questions and comments through their devices. User input is collected in text format, and this contains the initial information regarding the user's intentions and feelings.

[0760] Step 2:

[0761] The terminal sends user input to the server. When the input data is transferred to the server, it is converted to an appropriate format to facilitate processing on the server.

[0762] Step 3:

[0763] The server analyzes the received input data and provides it as input to the generative AI model. The generative AI model processes the input prompt sentence and generates appropriate response text by referring to a relevant knowledge database. At this stage, the input data is analyzed using natural language processing techniques, and response candidates are output.

[0764] Step 4:

[0765] The server inputs the generated response into the emotion engine, which evaluates the user's emotional state. Based on the input data and the generated response, the emotion engine analyzes the user's emotions and readjusts the response as needed to reflect the results. The output is the adjusted response.

[0766] Step 5:

[0767] The server updates the user's learning history and sentiment state history with a refined response. The server adds the new historical data to the database and uses it to optimize future learning sessions.

[0768] Step 6:

[0769] The terminal displays the response received from the server to the user. The generated content is presented on the user interface in a visually organized manner, making it easy for the user to understand and choose their next action.

[0770] (Application Example 2)

[0771] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0772] This invention aims to mitigate the impact of learners' emotional states on learning outcomes in educational content. Current educational systems often fail to consider learners' emotional states, leading to challenges such as stress and decreased motivation hindering learning efficiency. Furthermore, real-time emotion-based feedback and content optimization are difficult, resulting in a lack of personalized learning experiences.

[0773] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0774] In this invention, the server includes means for generating responses to user input using a generative model; means for accessing a text database stored in a management device to verify and correct the accuracy of the responses generated by the generative model; means for recording the user's learning history and emotional state and presenting learning content based on that history and state; means for optimizing the generated responses based on the user's emotions via an emotion analysis device that analyzes the user's emotional information; and means for presenting the optimized information to the user through a visual information display device. This enables the provision of a personalized learning experience that takes into account the user's emotional state and allows for the presentation of educational content optimized in real time according to emotions.

[0775] A "generative model" is an algorithm that automatically generates appropriate responses or information based on input data.

[0776] An "emotion analysis device" is a device that analyzes a user's emotional state and identifies changes in that state in real time.

[0777] A "visual information display device" is a device that visually presents generated information or responses to the user.

[0778] A "text database" is a collection of data stored in text format that is used to verify and correct user information and the responses of generative models.

[0779] "Optimization" refers to adjusting the information and responses provided to a more appropriate state based on the user's emotions and learning history.

[0780] In order to implement this invention, the following system and procedure are necessary.

[0781] The server first generates a response to the user's input using a generative model. The generated initial response is verified using a text database stored in the management device, and the response is corrected as needed. At this time, the sentiment analysis device analyzes the user's emotional information and uses the results to optimize the response. The server records the user's learning history and emotional state, and based on this, optimizes the learning content and presents it to the user.

[0782] The device presents optimized information to the user via a visual information display device. By using the visual information display device, users can access content that matches their emotional state during learning. These devices and systems enable a more personalized learning experience for the user.

[0783] As a concrete example, if a user inputs "I can't concentrate on studying history," the server receives this input and analyzes the user's emotional state via an emotion analysis device. If the analysis results indicate boredom or frustration, a generative model generates a response with encouragement and specific advice. This response is then presented to the user through a visual information display device.

[0784] Examples of prompts to input into the generation AI model include, "If the user's facial expression indicates confusion, generate encouragement and recommended product information," and "Facial expression evaluation: Confusion, Voice tone: Questioning tone, Store environment: Clothing section."

[0785] In this way, real-time optimization that takes emotions into account is performed for each individual user, enabling the provision of a personalized and effective learning experience.

[0786] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0787] Step 1:

[0788] The server receives input from the user, which includes questions and problems the user is facing during the learning process. The input data is primarily in text format and is then sent to the generative model for processing.

[0789] Step 2:

[0790] The server processes the received input data into a generative AI model to generate an initial response. At this stage, the generative AI model creates a provisional response to the user's question and returns it to the server as output.

[0791] Step 3:

[0792] The server accesses a text database stored on the management device to verify the accuracy of the initial response generated. If the response is incorrect or inappropriate, corrections are made. Rule-based validation from the text database is performed, and the response is adjusted.

[0793] Step 4:

[0794] The server uses an emotion analysis device to evaluate the user's emotional state. This evaluation is based on data such as the user's voice, facial expressions, and input content, leading to the identification of emotions. The emotion analysis engine processes the data and calculates emotional parameters to obtain the output.

[0795] Step 5:

[0796] The server optimizes the generated response based on the results of the emotion analysis device. Specifically, it adjusts the response to match the user's emotional state to achieve optimal communication. For example, if the user is showing signs of stress, the response will be made gentler and encouraging words will be added.

[0797] Step 6:

[0798] The device displays optimized responses to the user via a visual information display device. This information is presented on the user's display in a visual format, in a way that aids the user's learning.

[0799] Step 7:

[0800] Based on the responses provided, the user decides on the next learning step. At this stage, the user reads and understands the responses and decides whether to continue or ask further questions. The user's responses are recorded and used in the next session.

[0801] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0802] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0803] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0804] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0805] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0806] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0807] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0808] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0809] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0810] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0811] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0812] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0813] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0814] 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.

[0815] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0816] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0817] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0818] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0819] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0820] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0821] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0822] The following is further disclosed regarding the embodiments described above.

[0823] (Claim 1)

[0824] A means for generating a response to user input using a generative model,

[0825] A means for accessing a text database stored in a management device and verifying and correcting the accuracy of the response generated by the generative model,

[0826] A means of recording the user's learning history and presenting learning content based on that history,

[0827] A system that includes this.

[0828] (Claim 2)

[0829] The system according to claim 1, comprising a feedback generation means for analyzing the user's progress and providing optimal suggestions.

[0830] (Claim 3)

[0831] The system according to claim 1, comprising means for displaying the generated response and feedback via an interface on the user terminal.

[0832] "Example 1"

[0833] (Claim 1)

[0834] A means for generating a response to user input using a generative model,

[0835] A means for accessing an information database stored in a data management device, and verifying and correcting the accuracy of the response generated by the generative model,

[0836] A means of recording the user's learning history and presenting learning content based on that history,

[0837] A means for transmitting a prompt message entered via a terminal device to a data processing device,

[0838] A means for visualizing responses generated via terminal devices,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, comprising an evaluation generation means that analyzes the user's progress and makes optimal suggestions.

[0842] (Claim 3)

[0843] The system according to claim 1, further comprising means for displaying the generated response and evaluation via a user interface on the user terminal.

[0844] "Application Example 1"

[0845] (Claim 1)

[0846] A means for generating a response to user input using a generative model,

[0847] A means for accessing a text database stored in a management device and verifying and correcting the accuracy of the response generated by the generative model,

[0848] A means of recording the user's learning history and presenting learning content based on that history,

[0849] A means of functioning as an interface through a user terminal, acquiring user input information, and transmitting it to a management device for processing with high precision,

[0850] A means of visually presenting answers generated by learners via portable devices,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, comprising a feedback generation means for analyzing the user's progress and providing optimal suggestions.

[0854] (Claim 3)

[0855] The system according to claim 1, comprising means for creating and providing a customized educational plan based on learner questions.

[0856] "Example 2 of combining an emotion engine"

[0857] (Claim 1)

[0858] A means for generating a response to user input using a generative model,

[0859] A means for analyzing the emotional state of the user and adjusting the response generated based on that state,

[0860] A means for accessing the information set stored in the management device and verifying and correcting the accuracy of the response generated by the generative model,

[0861] A means for recording the user's learning history and emotional state history, and for presenting learning content based on that history,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, comprising a feedback generation means that analyzes the user's progress and emotional state to provide optimal suggestions.

[0865] (Claim 3)

[0866] The system according to claim 1, comprising means for displaying generated responses and feedback via a user interface on a user terminal.

[0867] "Application example 2 when combining with an emotional engine"

[0868] (Claim 1)

[0869] A means for generating a response to user input using a generative model,

[0870] A means for accessing a text database stored in a management device and verifying and correcting the accuracy of the response generated by the generative model,

[0871] A means for recording the user's learning history and emotional state, and for presenting learning content based on that history and state,

[0872] A means for optimizing the generated response based on the user's emotions, via an emotion analysis device that analyzes the user's emotional information,

[0873] A means of presenting optimized information to the user through a visual information display device,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, comprising a feedback generation means that analyzes the user's progress and emotional state to provide optimal suggestions.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising means for displaying the generated response and feedback via a visual information display device on a user terminal. [Explanation of Symbols]

[0879] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for generating a response to user input using a generative model, A means for accessing a text database stored in a management device and verifying and correcting the accuracy of the response generated by the generative model, A means of recording the user's learning history and presenting learning content based on that history, A system that includes this.

2. The system according to claim 1, comprising a feedback generation means for analyzing the user's progress and making optimal suggestions.

3. The system according to claim 1, further comprising means for displaying the generated response and feedback via an interface on the user terminal.

Images