system

Abstract

We provide the system. [Solution] A means for acquiring the user's learning history information and selecting learning problems optimized for the user, A means for dynamically generating dialogue content based on the selected learning questions, A means for receiving user voice input, converting it into text data, and analyzing the text data, A means of providing feedback to users based on the analysis results, A means for detecting a user's mental stress and providing dialogue content for mental care as needed, A means of recording the user's learning results and updating the learning profile for the next session, 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 recent learning environments, there is a demand for highly personalized learning opportunities and stress reduction through learning, especially for learners preparing for junior high school entrance examinations. However, conventional learning systems have had the problem that it is difficult to achieve both the provision of optimal learning problems corresponding to individual learning needs and psychological support. Therefore, an innovative solution is needed to balance the improvement of learners' academic performance and their mental health.

Means for Solving the Problems

[0005] There seems to be a formatting issue with the "??" line in the original text. It might be a mislabeled or incorrect tag. I've translated it as best as possible while maintaining the integrity of the overall structure. If you can clarify the correct content for that line, it would be helpful for a more accurate translation.This invention provides a means for acquiring a user's learning history information and selecting personalized learning problems. Furthermore, it incorporates a means for generating dynamic dialogue content to present problems to the user in an interactive format based on the selected learning problems. It also includes a means for converting voice input into text data and providing real-time feedback to the user based on the analysis results. In addition, it provides mental support for learners by detecting the user's mental stress using voice recognition technology and providing dialogue for mental care as needed. Furthermore, it includes a means for updating the learning profile for the next session based on this information. This system makes it possible to provide both an optimal learning environment and necessary mental care for the user.

[0006] "User learning history information" refers to information that records the learning content, performance, and progress of a user in the past.

[0007] "Selecting learning questions" is the process of selecting learning questions of appropriate difficulty and content for the user, based on the user's learning history.

[0008] "Dynamic generation of dialogue content" is a method that constructs appropriate conversational questions and hints in real time according to the user's learning progress.

[0009] "Voice input to text data conversion" is a technology in which a system recognizes what a user says and converts it into text data.

[0010] "Feedback based on analysis results" refers to the system analyzing the user's responses and providing appropriate evaluations and advice to the user based on the results.

[0011] "Mental stress detection" is a process that senses psychological burden and stress from the user's voice and behavior.

[0012] "Providing dialogue content for mental care" refers to engaging in conversations with users who have been detected as stressed, in order to promote mental stability and a sense of security.

[0013] "Updating your learning profile" refers to optimizing your future learning plan and content based on your latest learning results and feedback. [Brief explanation of the drawing]

[0014] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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.

[0018] 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.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is an integrated system for personalizing the user's learning experience and providing psychological support. The program's processing flow is described below in natural language.

[0036] Server operation

[0037] The server retrieves the user's learning history information from the database. This allows it to begin analyzing past learning content, performance, and progress. Next, the server selects a set of learning problems that match the user's characteristics and customizes the problems to provide an optimal learning experience tailored to the user's current situation. Problems and related information are dynamically generated by a dialogue content generator and sent to the terminal. Furthermore, the server evaluates the user's responses and adjusts the feedback in real time. If the server detects psychological stress by analyzing the user's voice input, it creates a dialogue for mental care and transfers it to the terminal. Finally, the server saves the learning results and dialogue data to the database and updates the user's latest learning profile.

[0038] Terminal operation

[0039] The device uses speech synthesis technology to present learning questions sent from the server to the user. When the user answers a learning question, the device converts the voice input into text data and sends it back to the server. Once the feedback is received from the server, the device communicates it to the user verbally. In addition, if psychological stress is detected, the device performs a mitigation dialogue to care for the user.

[0040] User actions

[0041] Users answer learning questions presented on their device. Through voice interaction, they receive feedback if they make a mistake and can try the question again. Furthermore, through mental care dialogue, they can continue learning while regaining a sense of relaxation and security. This process aims to maintain the user's motivation to learn and to solidify knowledge while making it enjoyable.

[0042] Through the above process, the system can simultaneously provide users with a customized learning experience and the necessary mental support.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives the user's identification information and retrieves past learning history information from the database based on that information. This information includes problems the user has worked on in the past and their results.

[0046] Step 2:

[0047] The server analyzes the acquired learning history to determine the user's strengths and weaknesses. Based on this, it selects the most suitable learning problems to match the user's learning goals and determines the content to be presented in the next interactive session.

[0048] Step 3:

[0049] The server dynamically generates user interaction content based on the selected learning problem. This interaction content includes the problem statement, hints, and supplementary explanations. The generated interaction content is then sent to the terminal.

[0050] Step 4:

[0051] The terminal uses speech synthesis technology to present the conversation content received from the server to the user. When a question is presented to the user, the terminal waits for the user to answer verbally.

[0052] Step 5:

[0053] The user responds to the questions presented by the device using voice. The device receives this voice input and converts it into text data. This converted data is then sent to the server.

[0054] Step 6:

[0055] The server analyzes the user's text data and determines whether the answer is correct or incorrect. Based on the determination result, it generates feedback in real time and sends the feedback content to the terminal.

[0056] Step 7:

[0057] The device provides the user with voice feedback from the server. If the user answers correctly, they receive a message of praise; if they answer incorrectly, they are offered additional hints or suggestions to try again.

[0058] Step 8:

[0059] The server analyzes the user's voice data and responses to assess their level of mental stress. If high stress levels are detected, it generates a dialogue for mental care and attempts to encourage the user to relax.

[0060] Step 9:

[0061] The device provides users with audio conversations for mental health support. Through these conversations, the aim is to alleviate the user's emotional distress.

[0062] Step 10:

[0063] The server saves the user's learning results and care details to a database. It updates the user's learning profile so that it is reflected in the next learning plan.

[0064] (Example 1)

[0065] 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."

[0066] Conventional learning support systems have struggled to provide an optimal learning experience tailored to the individual characteristics and progress of each learner, and have been particularly inadequate in addressing mental stress. Furthermore, they have faced challenges in providing real-time feedback and adjusting learning content. Additionally, a significant problem exists where many learners lose motivation midway through their studies if support that takes their psychological state into consideration is not provided.

[0067] 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.

[0068] In this invention, the server includes means for acquiring learner history information from information storage and selecting personalized tasks for the learner; means for dynamically generating conversation content based on the selected tasks; and means for receiving the learner's voice input, converting it into text data, and analyzing the text data. This makes it possible to provide learners with a personalized learning experience and emotional support.

[0069] "Information storage" refers to a storage medium that accumulates data such as learners' history, grades, and progress, and makes that data available for retrieval as needed.

[0070] A "learner" refers to an individual user who acquires knowledge and skills by using the system.

[0071] "History information" refers to a collection of data related to an individual learner, including past learning content, grades, and progress.

[0072] "Individualized assignments" are sets of learning problems that have been adjusted and optimized according to the learner's characteristics and past learning history.

[0073] "Dynamically generating conversation content" refers to the process of creating dialogues with learners in real time using generative AI models, etc., and providing flexible content that responds to the situation and responses.

[0074] "Converting speech input to text data" means changing a learner's utterances into text data using speech recognition technology, and then using that text data as the basis for analysis.

[0075] "Mental burden" refers to the stress, anxiety, and mental fatigue that learners may experience during learning activities.

[0076] "Conversation content for psychological support" refers to dialogue designed to reduce the learner's mental burden and provide a sense of security.

[0077] A "learning profile" is a collection of data that is updated based on an individual learner's progress and abilities to provide guidance for future learning activities.

[0078] This invention is an integrated system that provides learners with personalized learning experiences and psychological support. The operation of the system and its embodiments are described below.

[0079] Server operation

[0080] The server uses a database system to retrieve learner history information from information storage. Specifically, it retrieves the learner's past performance and progress using SQL queries. Based on this data, the server utilizes a generative AI model to select personalized tasks. For example, it uses a Python machine learning library to perform data analysis and prepare to present problems optimized for the learner. The generative AI model uses a model with natural language processing capabilities and generates dialogue content by inputting prompts in a specific format. A prompt such as "Create an English vocabulary problem that should be attempted next, based on the user's learning history" can be used. The server sends the generated content to the terminal.

[0081] Terminal operation

[0082] The device transmits learning questions received from the server to the learner using speech synthesis technology. This typically involves using a speech synthesis API. For example, the Google® TTS (Text-to-Speech) API is used to convert text into speech and present it to the learner in combination with visual aids. When the learner responds verbally, the device uses a speech recognition API, such as Google Speech-to-Text, to convert the speech into text data and sends that text data back to the server.

[0083] User actions

[0084] Learners progress through the learning process by answering presented tasks verbally. If they make a mistake, they receive feedback from the server and can try again. Furthermore, if the system perceives mental stress, learners are offered reassurance through mental care dialogues. Relaxation messages, such as "Take a deep breath and relax," are played via speech synthesis.

[0085] Thus, the system of the present invention has embodiments that simultaneously provide learners with a personalized learning experience and appropriate psychological support.

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The server retrieves learner history information from information storage. This input includes the learner's past performance and progress. SQL queries are used to extract this data from the database. The output is the learner's learning history data, which serves as the basis for selecting individualized assignments.

[0089] Step 2:

[0090] The server selects personalized tasks using a generative AI model based on the acquired historical information. The input is the historical data obtained in Step 1. Through data analysis, the learner's strengths and weaknesses are identified, and a personalized set of learning problems is generated as output. Specifically, the analysis is performed using a Python machine learning library.

[0091] Step 3:

[0092] The server dynamically generates conversation content based on the selected task. The input is the set of training questions obtained in step 2. By inputting prompt sentences into the generating AI model, conversation content is created using natural language processing. The output is dynamically generated conversation data, which becomes the content of the task provided to the learner.

[0093] Step 4:

[0094] The server sends the generated conversation content to the terminal. The input is the conversation data obtained in step 3. This is delivered to the terminal via network communication. As output, training questions usable on the terminal are sent.

[0095] Step 5:

[0096] The terminal presents learning questions received from the server to the learner using speech synthesis technology. The input is audio data from the server, which is provided as audio output using the Google TTS API or similar. The output is an audio announcement that the learner can hear.

[0097] Step 6:

[0098] The user answers the presented task using voice. The input is the learner's voice, which the device converts into text data using a speech recognition API. As output, text-formatted answer data is generated and sent back to the server.

[0099] Step 7:

[0100] The server analyzes the user's text data and generates feedback in real time. The input is the text data obtained in step 6. The generation AI model is used again to create feedback based on the analysis results. The output is the conversation content as feedback.

[0101] Step 8:

[0102] The device provides the user with feedback received from the server via speech synthesis. The input is feedback data from the server, which is output as speech using speech synthesis technology. By listening to this audio feedback, the user can check their learning progress.

[0103] Step 9:

[0104] The server analyzes the learner's voice data and assesses their mental burden. The input is the user's voice, and if psychological stress is detected, it uses a generative AI model to generate appropriate mental care conversation content. The output is feedback for mental support.

[0105] Step 10:

[0106] The terminal presents the user with mental health care dialogue content from the server. The input is mental health care data from the server, and speech synthesis technology provides the user with a relaxing voice. The user can gain a sense of security through this voice.

[0107] Step 11:

[0108] The server records the learner's learning results and profile in a database. Inputs include the learner's task performance and generated feedback. This data is used to update the learning profile, contributing to improved accuracy in future individualized learning. The output is the updated learning profile.

[0109] (Application Example 1)

[0110] 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."

[0111] Providing efficient and personalized training for engineers and workers in the field is challenging. Furthermore, operational errors and learning delays can lead to significant mental stress. In this environment, there is a need to provide optimal education and mental support to each individual learner.

[0112] 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.

[0113] In this invention, the server includes means for acquiring user history information and selecting educational questions optimized for the user; means for dynamically generating dialogue content based on the selected educational questions; and means for receiving the user's voice input, converting it into text information, and analyzing the text information. This makes it possible to personalize the learning of engineers in the field and also provide emotional support.

[0114] "History information" refers to data that records a user's past actions and learning progress.

[0115] "Educational questions" are questions used to assess or improve learners' knowledge and skills.

[0116] "Dialogue content" refers to spoken or textual information that enables communication with the user.

[0117] "Voice input" is the process of capturing a user's speech as digital data.

[0118] "Textual information" refers to audio or other data converted into text format.

[0119] An "analytical method" is a technique or process for analyzing data and extracting useful information.

[0120] "Mental tension" refers to a mental state characterized by anxiety or stress experienced by the user.

[0121] "Mental health dialogue content" refers to dialogue designed to improve the user's psychological state and promote relaxation.

[0122] "Learning images" refer to updated profile information that represents the user's learning progress.

[0123] "Machinery and equipment" is a general term referring to machinery used on-site.

[0124] This invention is a system that supports users' learning activities, and is particularly optimized for engineers and workers in the field. The specific operation of the system is shown below.

[0125] The server first retrieves user history information from a database. This data includes past learning content, achievements, and progress. Based on this, it selects the most suitable educational questions for the user. Next, it uses a tool to generate dialogue content based on the selected questions. The dialogue content is dynamically generated using a generative AI model.

[0126] The server accepts the user's voice input and converts it into text. Voice recognition software such as the Google Speech-to-Text API is used. The converted text is analyzed and used to provide appropriate feedback to the user. The feedback is adjusted in real time based on the user's current situation.

[0127] The server also detects mental stress from the user's voice. This involves using a method that evaluates specific stress indicators through voice analysis. If necessary, mental health-related dialogue content is generated and provided to the user to offer mental support.

[0128] When a user interacts with the system, the terminal presents educational questions downloaded from the server in audio format. OpenAI's Whisper model and other speech synthesis technologies are used for speech synthesis. After the user answers the learning questions, their responses are sent to the server for analysis. Based on the analysis, feedback and conversational support are provided to the user, allowing them to continue learning in a relaxed state.

[0129] As a concrete example, this system is used when engineers are learning how to operate newly introduced machinery and equipment. The system adjusts the difficulty level according to the engineer's progress, ensuring they learn safe operating methods. Furthermore, when the engineer feels stressed, it generates relaxing dialogue such as, "Take a deep breath. It's okay to go at your own pace."

[0130] As a concrete example of a prompt, you can instruct the AI ​​model to generate a message such as, "Generate a conversation to help a technician relax when they feel stressed while operating machinery."

[0131] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0132] Step 1:

[0133] The server retrieves user history information from the database. The user ID is used as input, and past learning content, achievements, and progress are obtained as output. Based on this data, the server selects educational questions optimized for the user.

[0134] Step 2:

[0135] The server dynamically generates dialogue content using a generative AI model based on selected educational questions. The input includes the educational questions and the user's current learning progress, and the output is a voice dialogue script. The generated script is then prepared for presentation to the user.

[0136] Step 3:

[0137] The terminal presents the user with a voice dialogue script delivered from the server using speech synthesis software. It receives script data as input and plays the synthesized voice back to the user as output.

[0138] Step 4:

[0139] The user provides answers via voice. The device receives the user's voice input and converts it into text information using speech recognition technology. Voice data is received as input, and text data is generated as output.

[0140] Step 5:

[0141] The server analyzes the text information obtained from voice input and evaluates the user's response. Text data is used as input, and the evaluation result is obtained as output. Based on this result, feedback is generated in real time.

[0142] Step 6:

[0143] The server detects mental stress from the user's voice and generates mental health-promoting dialogue as needed. Voice features are used as input, and a relaxation-oriented dialogue script is output. A generative AI model is used to generate prompts to assist the user.

[0144] Step 7:

[0145] The device provides the user with audio feedback and mental health dialogue scripts received from the server. It receives script data from the server as input and plays synthesized audio as output, allowing the user to continue learning with confidence.

[0146] 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.

[0147] This invention is an interactive learning system that incorporates an emotion engine to improve the user's learning experience and emotional support. This system analyzes the user's emotions in real time and provides a learning experience that is optimally tailored to the individual's emotional state.

[0148] Server operation

[0149] The server uses pre-registered user identification information to retrieve the user's learning history information from the database. Based on this information, it selects learning problems suitable for the user and generates dialogue corresponding to their content. The generated dialogue includes learning problems, hints, and supplementary explanations. Furthermore, the server receives the user's voice input data and performs emotion analysis via an emotion engine. Based on the emotion data, it evaluates the user's stress level and emotional state and provides mental and emotional care as needed.

[0150] Terminal operation

[0151] The device presents the conversation content received from the server to the user using speech synthesis technology. When the user answers a question verbally, the device converts the voice input into text data and sends it to the server. The device also receives feedback from the server and communicates it to the user verbally. Based on the emotional data analyzed by the emotion engine, the device provides appropriate emotional feedback and mental support during the learning process.

[0152] User actions

[0153] Users can answer learning questions presented on the device using voice. The user's responses and voice tone are analyzed by an emotion engine, which evaluates the user's psychological state in real time. If the user experiences high stress levels, the device switches to a conversational mode that provides mental care via a server. In this way, users can progress through their learning while receiving an optimal learning experience and emotional support tailored to their individual learning needs.

[0154] As a concrete example, consider a scenario where a user is working on a math problem and the system detects signs of anxiety from the user's voice. In this case, the server generates a specific care dialogue through its emotion engine, providing the user with reassuring encouragement and additional explanations. This process allows for effective learning outcomes while alleviating user stress.

[0155] This invention is expected to improve the quality of learning by simultaneously providing learners with personalized learning and immediate emotional support.

[0156] The following describes the processing flow.

[0157] Step 1:

[0158] The server receives the user's identification information and accesses the database to retrieve the user's learning history. This information includes past results on problems, response times, and points earned for incorrect answers.

[0159] Step 2:

[0160] The server analyzes the acquired learning history to identify the user's strengths and weaknesses. Based on these results, it automatically selects the most effective learning problems for the user.

[0161] Step 3:

[0162] Based on the selected learning questions, the server generates dialogue content. This generated dialogue includes details about the question, hints to help solve it, and messages to encourage learning. This content is then prepared for transmission to the terminal.

[0163] Step 4:

[0164] The terminal receives the conversation content from the server and outputs it to the user as speech using speech synthesis technology. The user listens to the presented learning questions in audio. The terminal also waits for voice input from the user.

[0165] Step 5:

[0166] The user responds verbally to questions presented by the device. The device converts this voice input into text data. This text data is sent to a server and used for analysis.

[0167] Step 6:

[0168] The server analyzes the received text data and determines whether the user's answer is correct or incorrect. Based on the determination result, it creates feedback and generates customized messages according to the user's learning progress.

[0169] Step 7:

[0170] The device outputs feedback sent from the server as audio to the user. This feedback includes justified answers and explanations to correct misunderstandings.

[0171] Step 8:

[0172] The server uses an emotion engine to analyze the user's emotional state from their voice tone and content. If this analysis detects emotions such as anxiety, stress, or joy, it takes appropriate action.

[0173] Step 9:

[0174] If the user's emotions indicate high levels of stress or anxiety, the server uses an emotion engine to generate mental health support dialogue. The device then communicates this to the user verbally to encourage relaxation.

[0175] Step 10:

[0176] The server stores information about learning results and emotions in a database and updates the user's learning profile. This allows for a more refined learning plan to be suggested for the next session.

[0177] (Example 2)

[0178] 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".

[0179] This invention aims to solve the problem in conventional learning systems where it is difficult to accurately grasp and adjust to the individual learning needs and emotional state of users in real time. In particular, it addresses the problem that learning effectiveness decreases when users are under high stress, and aims to improve the quality of the learning experience by providing individualized mental support.

[0180] 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.

[0181] In this invention, the server includes means for acquiring learning history information using user identification information and selecting educational tasks optimized for the user; means for dynamically generating dialogue content based on the selected educational tasks and presenting it to the user using speech synthesis technology; and means for receiving the user's voice input, converting it into text data, and analyzing the text data. This provides a personalized learning experience and enables mental support tailored to the user's emotional state.

[0182] "Identification information" refers to information used to uniquely identify a user, and includes, for example, user IDs and registered personal information.

[0183] "Learning history information" is a collection of information about the learning content, grades, and progress that a user has undertaken so far, and is used to plan future learning activities.

[0184] "Educational tasks" are specific problems or assignments set up to help users progress in their learning, and are selected according to the user's learning needs.

[0185] "Emotional state" refers to the user's emotional state and is information that evaluates the user's psychological and emotional state detected from voice input and other data.

[0186] "Mental care dialogue content" refers to dialogue content provided by the system that includes encouraging and relaxing messages, with the aim of reducing the user's psychological burden.

[0187] A "generative AI model" is an artificial intelligence model that learns from a large amount of data and is used to generate an output for a given input.

[0188] A "prompt sentence" is a sentence in the form of an instruction or question that is input into a generative AI model to obtain a specific output, and it forms the basis on which the AI ​​generates an appropriate response.

[0189] "Speech synthesis technology" is a technology that converts text data into speech data, and is used to convey the content of a conversation to the user in voice.

[0190] "Speech recognition technology" is a technology that converts speech into text data or a machine-readable format, and is used to process a user's verbal input as digital information.

[0191] This invention provides an interactive learning system that optimizes the user's learning experience and provides emotional support. This system mainly consists of three elements: a server, a terminal, and a user.

[0192] The server receives user identification information and retrieves learning history information from the database. This information is used to select the most appropriate educational tasks based on the user's learning progress. Based on the selected tasks, dialogue content is generated and presented to the user using speech synthesis technology. Specifically, common speech synthesis software such as Google TTS or Amazon Polly can be used for speech synthesis.

[0193] The device has the functionality to present the conversation content sent from the server to the user as audio. When the user provides an audio response, the device uses speech recognition technology (e.g., Google Speech-to-Text) to convert the audio into text data and send it to the server. This process ensures that the user's response is reflected in real time.

[0194] Users verbally respond to presented educational tasks, and the system performs sentiment analysis based on their voice. The server utilizes a generative AI model to analyze the user's voice input and evaluate their emotional state. Based on the analysis results, the server generates mental care dialogues as needed and provides adaptive feedback. An example of a prompt to the generative AI model is, "Generate an appropriate message to alleviate the stress the user is feeling." This allows the user to concentrate on learning with a sense of security.

[0195] As a concrete example, let's explain how the system behaves when it detects anxiety from the user's voice while they are working on a math problem. In this case, the server uses a generative AI model to generate a mental support dialogue such as, "It's okay, there's no need to rush. Let's solve it little by little," and provides it to the user through the terminal. This process reduces the user's stress and provides an effective learning experience.

[0196] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0197] Step 1:

[0198] The server receives user identification information, accesses the database, and retrieves learning history information. The input is the user's identification information, and the output is the user's past learning history information. This data serves as the basis for selecting the most suitable educational tasks for the user. Specifically, the server executes a database query using the identification information as the key and extracts the corresponding learning history.

[0199] Step 2:

[0200] The server analyzes the acquired learning history information and selects educational tasks appropriate to the user's current learning stage. The input is learning history information, and the output is educational tasks optimized for the user. In this process, the server dynamically determines appropriate tasks by considering the user's strengths and weaknesses. Specifically, it uses an algorithm to select tasks, taking into account past performance and the passage of time.

[0201] Step 3:

[0202] The server generates dialogue content based on the selected educational task and creates a dialogue script to present to the user using a generative AI model. The input is the educational task, and the output is the dialogue content. Specifically, by inputting prompt sentences into the AI ​​model, a script in a natural dialogue format is generated.

[0203] Step 4:

[0204] The server sends the generated dialogue content to the terminal. The input is the dialogue content, and the output is the transmission of data to the terminal. Specifically, it sends the data in packet format to the terminal via the network and confirms receipt.

[0205] Step 5:

[0206] The terminal converts received dialogue into speech and presents it to the user. The input is the dialogue from the server, and the output is the speech that the user can hear. Specifically, speech synthesis technology is used to convert text into speech data, which is then output through the speaker.

[0207] Step 6:

[0208] The user responds to the presented educational task verbally. The input is the user's verbal response, and the output is audio data recorded on the device. This response is processed as text in the next step.

[0209] Step 7:

[0210] The terminal converts the user's voice into text data and sends it to the server. The input is the user's voice data, and the output is text data. Specifically, it uses speech recognition software to convert the voice to text and sends it to the server as text data.

[0211] Step 8:

[0212] The server analyzes the received text data and evaluates the user's emotional state. The input is text data, and the output is the result of the emotional analysis. Specifically, a generative AI model is used to analyze the text and quantify the emotional state.

[0213] Step 9:

[0214] The server generates necessary mental care dialogues based on the emotion analysis results. The input is data on the emotional state, and the output is the mental care dialogue. Specifically, prompts corresponding to the emotional state are input to the AI ​​model, which then generates appropriate feedback messages.

[0215] Step 10:

[0216] The terminal converts mental health care dialogues from the server into audio and presents them to the user. The input is mental health care dialogue data, and the output is an audio message presented to the user audibly. This step is also achieved using speech synthesis technology.

[0217] (Application Example 2)

[0218] 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 device 14 will be referred to as the "terminal."

[0219] Conventional learning support systems have struggled to provide individualized learning experiences and to adequately alleviate users' mental pressure while providing support. Furthermore, in the in-store purchasing experience, there is a lack of means to suggest products that take into account the emotions and mental state of customers, resulting in a challenge in stimulating sufficient purchasing intent.

[0220] 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.

[0221] In this invention, the server includes means for acquiring the user's learning history information and selecting learning content optimized for the user; means for dynamically generating dialogue content based on the selected learning content; means for receiving the user's voice input, converting it into text data, and analyzing the text data; means for providing feedback to the user based on the analysis results; means for detecting the user's mental pressure and providing dialogue content for mental care as needed; means for presenting optimized product information based on the user's purchasing behavior; means for analyzing the user's mental pressure and emotional state in real time and making appropriate product suggestions; and means for generating prompt sentences using a generation AI model according to the user's selection.

[0222] This allows users to receive a personalized learning experience while reducing mental pressure, and furthermore, receiving emotionally resonant product suggestions in physical stores can stimulate their desire to purchase.

[0223] "Learning history information" refers to information that records what a user has learned in the past and their progress.

[0224] "Learning content" refers to the assignments and learning materials that users use for their studies.

[0225] "Dialogue content" refers to the content of communication exchanged between the user and the system, which is generated according to the purpose of learning or support.

[0226] "Voice input" refers to the audio data that users use to give instructions or responses to a system.

[0227] "Text data" refers to data obtained by converting voice input into a written format for analysis and understanding.

[0228] "Feedback" refers to the system's response and evaluation of user behavior and learning, and is intended to support user learning.

[0229] "Mental pressure" refers to the psychological burden and stress that users experience.

[0230] "Mental care" refers to the support and assistance provided to users to alleviate their mental stress and maintain their mental health.

[0231] "Purchasing behavior" refers to the series of actions a user takes when purchasing goods inside or outside a store.

[0232] "Product information" refers to information about products offered in physical stores or online, including their characteristics, specifications, price, and intended use.

[0233] A "generative AI model" refers to artificial intelligence technology that dynamically generates content according to the user's requests and objectives.

[0234] A "prompt statement" is a guidance statement created to give instructions or commands to a generative AI model so that it can function properly.

[0235] The system for realizing this invention consists of a server, a terminal, and a user who operates them. The server first acquires the user's learning history information and selects optimized learning content. Based on this selected learning content, it dynamically generates dialogue content. Data entered by the user via voice is received by the terminal and converted into text data via a speech recognition engine. These processes utilize terminals equipped with high-performance microphones and speech recognition technology using Nvidia Jetson.

[0236] Based on the analysis results, the server generates feedback and provides it to the user. If the user's mental stress is detected, it automatically generates dialogue content for mental care and provides immediate feedback. It also analyzes the user's purchasing behavior and presents product information that reflects their emotional state in real time. Specifically, it captures the customer's facial expressions with a camera and evaluates their emotions using facial expression analysis technologies such as Microsoft® Azure® Emotion API.

[0237] Furthermore, the system constructs prompt messages based on a generative AI model, providing optimal information tailored to the user's choices and requests. This allows users to customize their learning and purchasing experience while stimulating their interest. For example, by analyzing a customer's prolonged viewing of a particular product, the system can offer customer service with a prompt such as, "It appears you are interested in this product; do you have any questions?"

[0238] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0239] Step 1:

[0240] The server retrieves the user's learning history information from the database. Based on this input information, it selects learning content optimized for the user. This selection process analyzes the user's past learning trends and performance to determine the most effective content. As a result, appropriate learning content is output.

[0241] Step 2:

[0242] The server dynamically generates dialogue content based on the selected learning content. Using a generation AI model, it creates the learning flow, hints, and supplementary explanations to present to the user, depending on the input learning content. Prompts designed to enhance the user's motivation are also set here. This output is dialogue content data for use on the terminal.

[0243] Step 3:

[0244] The user provides voice input to the device. The device receives this voice data and converts it into text data using speech recognition technology. The speech recognition engine, using Nvidia Jetson, analyzes the input voice data and obtains the corresponding text output. The converted text data is sent to the server.

[0245] Step 4:

[0246] The server analyzes text data to understand user responses. This analysis utilizes natural language processing techniques, including grasping the intent and emotions contained in the user's answers. Based on the analysis results, the server generates feedback for the user and sends it to their device. This feedback supports the user's learning and facilitates a better learning experience.

[0247] Step 5:

[0248] The device receives feedback from the server and presents it to the user verbally using speech synthesis technology. It also collects the user's facial expressions and voice tone using a camera and microphone to monitor their emotional state in real time. Using the Microsoft Azure Emotion API, it analyzes the input image and audio data to evaluate their emotional state. Based on this, necessary mental health support dialogues are simultaneously generated and provided as feedback to the user.

[0249] Step 6:

[0250] The device observes user purchasing behavior and analyzes customer interests through its camera. Based on the input video data, it evaluates customer gaze and pacing time, and provides real-time product information in combination with sentiment analysis. The selected product information is generated as prompt text using an AI model and output to the user via voice or display.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] [Second Embodiment]

[0255] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0256] 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.

[0257] 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).

[0258] 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.

[0259] 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.

[0260] 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).

[0261] 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.

[0262] 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.

[0263] 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.

[0264] 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.

[0265] 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.

[0266] 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".

[0267] This invention is an integrated system for personalizing the user's learning experience and providing psychological support. The program's processing flow is described below in natural language.

[0268] Server operation

[0269] The server retrieves the user's learning history information from the database. This allows it to begin analyzing past learning content, performance, and progress. Next, the server selects a set of learning problems that match the user's characteristics and customizes the problems to provide an optimal learning experience tailored to the user's current situation. Problems and related information are dynamically generated by a dialogue content generator and sent to the terminal. Furthermore, the server evaluates the user's responses and adjusts the feedback in real time. If the server detects psychological stress by analyzing the user's voice input, it creates a dialogue for mental care and transfers it to the terminal. Finally, the server saves the learning results and dialogue data to the database and updates the user's latest learning profile.

[0270] Terminal operation

[0271] The device uses speech synthesis technology to present learning questions sent from the server to the user. When the user answers a learning question, the device converts the voice input into text data and sends it back to the server. Once the feedback is received from the server, the device communicates it to the user verbally. In addition, if psychological stress is detected, the device performs a mitigation dialogue to care for the user.

[0272] User actions

[0273] Users answer learning questions presented on their device. Through voice interaction, they receive feedback if they make a mistake and can try the question again. Furthermore, through mental care dialogue, they can continue learning while regaining a sense of relaxation and security. This process aims to maintain the user's motivation to learn and to solidify knowledge while making it enjoyable.

[0274] Through the above process, the system can simultaneously provide users with a customized learning experience and the necessary mental support.

[0275] The following describes the processing flow.

[0276] Step 1:

[0277] The server receives the user's identification information and obtains the past learning history information from the database based on this information. This information includes the problems the user has worked on in the past and the results thereof.

[0278] Step 2:

[0279] The server analyzes the acquired learning history to determine the user's strong and weak areas. Based on this, it selects the optimal learning problems that match the user's learning goals and determines the content to be presented in the next dialogue session.

[0280] Step 3:

[0281] Based on the selected learning problems, the server dynamically generates the content of the dialogue with the user. The content of this dialogue should include the problem statement, hints, and supplementary explanations. The generated dialogue content is transmitted to the terminal.

[0282] Step 4:

[0283] The terminal presents the dialogue content received from the server to the user using speech synthesis technology. When a problem is presented to the user, the terminal waits for the user to answer by voice.

[0284] Step 5:

[0285] The user answers the problem presented by the terminal by voice. The terminal receives the voice input and converts it into text data. This converted data is transmitted to the server.

[0286] Step 6:

[0287] The server analyzes the received text data of the user to determine correct or incorrect answers. Based on the determination result, it generates real-time feedback and sends the feedback content to the terminal. <00E00910> Step 7:

[0289] The device provides the user with voice feedback from the server. If the user answers correctly, they receive a message of praise; if they answer incorrectly, they are offered additional hints or suggestions to try again.

[0290] Step 8:

[0291] The server analyzes the user's voice data and responses to assess their level of mental stress. If high stress levels are detected, it generates a dialogue for mental care and attempts to encourage the user to relax.

[0292] Step 9:

[0293] The device provides users with audio conversations for mental health support. Through these conversations, the aim is to alleviate the user's emotional distress.

[0294] Step 10:

[0295] The server saves the user's learning results and care details to a database. It updates the user's learning profile so that it is reflected in the next learning plan.

[0296] (Example 1)

[0297] 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."

[0298] Conventional learning support systems have struggled to provide an optimal learning experience tailored to the individual characteristics and progress of each learner, and have been particularly inadequate in addressing mental stress. Furthermore, they have faced challenges in providing real-time feedback and adjusting learning content. Additionally, a significant problem exists where many learners lose motivation midway through their studies if support that takes their psychological state into consideration is not provided.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0300] In this invention, the server includes means for acquiring the learner's history information from the information storage and selecting an individualized task for the learner, means for dynamically generating conversation content based on the selected task, and means for receiving the learner's voice input, converting it into character data, and analyzing the character data. Thereby, it becomes possible to provide an individualized learning experience for the learner and supply mental support.

[0301] "Information storage" is a storage medium for accumulating data such as the learner's history information, grades, progress status, etc., and enabling acquisition of those data as needed.

[0302] "Learner" refers to an individual user who acquires knowledge and skills using the system.

[0303] "History information" is a collection of data related to an individual learner, including past learning content, grades, and progress status.

[0304] "Individualized task" is a set of learning problems adjusted and optimized according to the learner's characteristics and past learning history.

[0305] "Dynamically generating conversation content" refers to the process of creating a conversation with the learner in real time using a generation AI model or the like and providing flexible content according to the situation and response.

[0306] "Converting voice input into character data" means changing the learner's utterance into text data by voice recognition technology, which is a process based on the text data for analysis.

[0307] "Mental burden" refers to stress, uneasiness, and mental fatigue that a learner may experience during learning activities.

[0308] "Conversation content for psychological support" refers to dialogue designed to reduce the learner's mental burden and provide a sense of security.

[0309] A "learning profile" is a collection of data that is updated based on an individual learner's progress and abilities to provide guidance for future learning activities.

[0310] This invention is an integrated system that provides learners with personalized learning experiences and psychological support. The operation of the system and its embodiments are described below.

[0311] Server operation

[0312] The server uses a database system to retrieve learner history information from information storage. Specifically, it retrieves the learner's past performance and progress using SQL queries. Based on this data, the server utilizes a generative AI model to select personalized tasks. For example, it uses a Python machine learning library to perform data analysis and prepare to present problems optimized for the learner. The generative AI model uses a model with natural language processing capabilities and generates dialogue content by inputting prompts in a specific format. A prompt such as "Create an English vocabulary problem that should be attempted next, based on the user's learning history" can be used. The server sends the generated content to the terminal.

[0313] Terminal operation

[0314] The device transmits learning questions received from the server to the learner using speech synthesis technology. This typically involves using a speech synthesis API. For example, the Google TTS (Text-to-Speech) API is used to convert text into speech and present it to the learner in combination with visual aids. When the learner responds verbally, the device uses a speech recognition API, such as Google Speech-to-Text, to convert the speech into text data and sends that text data back to the server.

[0315] User actions

[0316] Learners progress through the learning process by answering presented tasks verbally. If they make a mistake, they receive feedback from the server and can try again. Furthermore, if the system perceives mental stress, learners are offered reassurance through mental care dialogues. Relaxation messages, such as "Take a deep breath and relax," are played via speech synthesis.

[0317] Thus, the system of the present invention has embodiments that simultaneously provide learners with a personalized learning experience and appropriate psychological support.

[0318] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0319] Step 1:

[0320] The server retrieves learner history information from information storage. This input includes the learner's past performance and progress. SQL queries are used to extract this data from the database. The output is the learner's learning history data, which serves as the basis for selecting individualized assignments.

[0321] Step 2:

[0322] The server selects personalized tasks using a generative AI model based on the acquired historical information. The input is the historical data obtained in Step 1. Through data analysis, the learner's strengths and weaknesses are identified, and a personalized set of learning problems is generated as output. Specifically, the analysis is performed using a Python machine learning library.

[0323] Step 3:

[0324] The server dynamically generates conversation content based on the selected task. The input is the set of training questions obtained in step 2. By inputting prompt sentences into the generating AI model, conversation content is created using natural language processing. The output is dynamically generated conversation data, which becomes the content of the task provided to the learner.

[0325] Step 4:

[0326] The server sends the generated conversation content to the terminal. The input is the conversation data obtained in step 3. This is delivered to the terminal via network communication. As output, training questions usable on the terminal are sent.

[0327] Step 5:

[0328] The terminal presents learning questions received from the server to the learner using speech synthesis technology. The input is audio data from the server, which is provided as audio output using the Google TTS API or similar. The output is an audio announcement that the learner can hear.

[0329] Step 6:

[0330] The user answers the presented task using voice. The input is the learner's voice, which the device converts into text data using a speech recognition API. As output, text-formatted answer data is generated and sent back to the server.

[0331] Step 7:

[0332] The server analyzes the user's text data and generates feedback in real time. The input is the text data obtained in step 6. The generation AI model is used again to create feedback based on the analysis results. The output is the conversation content as feedback.

[0333] Step 8:

[0334] The device provides the user with feedback received from the server via speech synthesis. The input is feedback data from the server, which is output as speech using speech synthesis technology. By listening to this audio feedback, the user can check their learning progress.

[0335] Step 9:

[0336] The server analyzes the learner's voice data and assesses their mental burden. The input is the user's voice, and if psychological stress is detected, it uses a generative AI model to generate appropriate mental care conversation content. The output is feedback for mental support.

[0337] Step 10:

[0338] The terminal presents the user with mental health care dialogue content from the server. The input is mental health care data from the server, and speech synthesis technology provides the user with a relaxing voice. The user can gain a sense of security through this voice.

[0339] Step 11:

[0340] The server records the learner's learning results and profile in a database. Inputs include the learner's task performance and generated feedback. This data is used to update the learning profile, contributing to improved accuracy in future individualized learning. The output is the updated learning profile.

[0341] (Application Example 1)

[0342] 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 glasses 214 will be referred to as the "terminal."

[0343] Providing efficient and personalized training for engineers and workers in the field is challenging. Furthermore, operational errors and learning delays can lead to significant mental stress. In this environment, there is a need to provide optimal education and mental support to each individual learner.

[0344] 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.

[0345] In this invention, the server includes means for acquiring user history information and selecting educational questions optimized for the user; means for dynamically generating dialogue content based on the selected educational questions; and means for receiving the user's voice input, converting it into text information, and analyzing the text information. This makes it possible to personalize the learning of engineers in the field and also provide emotional support.

[0346] "History information" refers to data that records a user's past actions and learning progress.

[0347] "Educational questions" are questions used to assess or improve learners' knowledge and skills.

[0348] "Dialogue content" refers to spoken or textual information that enables communication with the user.

[0349] "Voice input" is the process of capturing a user's speech as digital data.

[0350] "Textual information" refers to audio or other data converted into text format.

[0351] An "analytical method" is a technique or process for analyzing data and extracting useful information.

[0352] "Mental tension" refers to a mental state characterized by anxiety or stress experienced by the user.

[0353] "Mental health dialogue content" refers to dialogue designed to improve the user's psychological state and promote relaxation.

[0354] "Learning images" refer to updated profile information that represents the user's learning progress.

[0355] "Machinery and equipment" is a general term referring to machinery used on-site.

[0356] This invention is a system that supports users' learning activities, and is particularly optimized for engineers and workers in the field. The specific operation of the system is shown below.

[0357] The server first retrieves user history information from a database. This data includes past learning content, achievements, and progress. Based on this, it selects the most suitable educational questions for the user. Next, it uses a tool to generate dialogue content based on the selected questions. The dialogue content is dynamically generated using a generative AI model.

[0358] The server accepts the user's voice input and converts it into text. Voice recognition software such as the Google Speech-to-Text API is used. The converted text is analyzed and used to provide appropriate feedback to the user. The feedback is adjusted in real time based on the user's current situation.

[0359] The server also detects mental stress from the user's voice. This involves using a method that evaluates specific stress indicators through voice analysis. If necessary, mental health-related dialogue content is generated and provided to the user to offer mental support.

[0360] When a user interacts with the system, the terminal presents educational questions downloaded from the server in audio format. OpenAI's Whisper model and other speech synthesis technologies are used for speech synthesis. After the user answers the learning questions, their responses are sent to the server for analysis. Based on the analysis, feedback and conversational support are provided to the user, allowing them to continue learning in a relaxed state.

[0361] As a concrete example, this system is used when engineers are learning how to operate newly introduced machinery and equipment. The system adjusts the difficulty level according to the engineer's progress, ensuring they learn safe operating methods. Furthermore, when the engineer feels stressed, it generates relaxing dialogue such as, "Take a deep breath. It's okay to go at your own pace."

[0362] As a concrete example of a prompt, you can instruct the AI ​​model to generate a message such as, "Generate a conversation to help a technician relax when they feel stressed while operating machinery."

[0363] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0364] Step 1:

[0365] The server retrieves user history information from the database. The user ID is used as input, and past learning content, achievements, and progress are obtained as output. Based on this data, the server selects educational questions optimized for the user.

[0366] Step 2:

[0367] The server dynamically generates dialogue content using a generative AI model based on selected educational questions. The input includes the educational questions and the user's current learning progress, and the output is a voice dialogue script. The generated script is then prepared for presentation to the user.

[0368] Step 3:

[0369] The terminal presents the user with a voice dialogue script delivered from the server using speech synthesis software. It receives script data as input and plays the synthesized voice back to the user as output.

[0370] Step 4:

[0371] The user provides answers via voice. The device receives the user's voice input and converts it into text information using speech recognition technology. Voice data is received as input, and text data is generated as output.

[0372] Step 5:

[0373] The server analyzes the text information obtained from voice input and evaluates the user's response. Text data is used as input, and the evaluation result is obtained as output. Based on this result, feedback is generated in real time.

[0374] Step 6:

[0375] The server detects mental stress from the user's voice and generates mental health-promoting dialogue as needed. Voice features are used as input, and a relaxation-oriented dialogue script is output. A generative AI model is used to generate prompts to assist the user.

[0376] Step 7:

[0377] The device provides the user with audio feedback and mental health dialogue scripts received from the server. It receives script data from the server as input and plays synthesized audio as output, allowing the user to continue learning with confidence.

[0378] 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.

[0379] This invention is an interactive learning system that incorporates an emotion engine to improve the user's learning experience and emotional support. This system analyzes the user's emotions in real time and provides a learning experience that is optimally tailored to the individual's emotional state.

[0380] Server operation

[0381] The server uses pre-registered user identification information to retrieve the user's learning history information from the database. Based on this information, it selects learning problems suitable for the user and generates dialogue corresponding to their content. The generated dialogue includes learning problems, hints, and supplementary explanations. Furthermore, the server receives the user's voice input data and performs emotion analysis via an emotion engine. Based on the emotion data, it evaluates the user's stress level and emotional state and provides mental and emotional care as needed.

[0382] Terminal operation

[0383] The device presents the conversation content received from the server to the user using speech synthesis technology. When the user answers a question verbally, the device converts the voice input into text data and sends it to the server. The device also receives feedback from the server and communicates it to the user verbally. Based on the emotional data analyzed by the emotion engine, the device provides appropriate emotional feedback and mental support during the learning process.

[0384] User actions

[0385] Users can answer learning questions presented on the device using voice. The user's responses and voice tone are analyzed by an emotion engine, which evaluates the user's psychological state in real time. If the user experiences high stress levels, the device switches to a conversational mode that provides mental care via a server. In this way, users can progress through their learning while receiving an optimal learning experience and emotional support tailored to their individual learning needs.

[0386] As a concrete example, consider a scenario where a user is working on a math problem and the system detects signs of anxiety from the user's voice. In this case, the server generates a specific care dialogue through its emotion engine, providing the user with reassuring encouragement and additional explanations. This process allows for effective learning outcomes while alleviating user stress.

[0387] This invention is expected to improve the quality of learning by simultaneously providing learners with personalized learning and immediate emotional support.

[0388] The following describes the processing flow.

[0389] Step 1:

[0390] The server receives the user's identification information and accesses the database to retrieve the user's learning history. This information includes past results on problems, response times, and points earned for incorrect answers.

[0391] Step 2:

[0392] The server analyzes the acquired learning history to identify the user's strengths and weaknesses. Based on these results, it automatically selects the most effective learning problems for the user.

[0393] Step 3:

[0394] Based on the selected learning questions, the server generates dialogue content. This generated dialogue includes details about the question, hints to help solve it, and messages to encourage learning. This content is then prepared for transmission to the terminal.

[0395] Step 4:

[0396] The terminal receives the conversation content from the server and outputs it to the user as speech using speech synthesis technology. The user listens to the presented learning questions in audio. The terminal also waits for voice input from the user.

[0397] Step 5:

[0398] The user responds verbally to questions presented by the device. The device converts this voice input into text data. This text data is sent to a server and used for analysis.

[0399] Step 6:

[0400] The server analyzes the received text data and determines whether the user's answer is correct or incorrect. Based on the determination result, it creates feedback and generates customized messages according to the user's learning progress.

[0401] Step 7:

[0402] The device outputs feedback sent from the server as audio to the user. This feedback includes justified answers and explanations to correct misunderstandings.

[0403] Step 8:

[0404] The server uses an emotion engine to analyze the user's emotional state from their voice tone and content. If this analysis detects emotions such as anxiety, stress, or joy, it takes appropriate action.

[0405] Step 9:

[0406] If the user's emotions indicate high levels of stress or anxiety, the server uses an emotion engine to generate mental health support dialogue. The device then communicates this to the user verbally to encourage relaxation.

[0407] Step 10:

[0408] The server stores information about learning results and emotions in a database and updates the user's learning profile. This allows for a more refined learning plan to be suggested for the next session.

[0409] (Example 2)

[0410] 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".

[0411] This invention aims to solve the problem in conventional learning systems where it is difficult to accurately grasp and adjust to the individual learning needs and emotional state of users in real time. In particular, it addresses the problem that learning effectiveness decreases when users are under high stress, and aims to improve the quality of the learning experience by providing individualized mental support.

[0412] 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.

[0413] In this invention, the server includes means for acquiring learning history information using user identification information and selecting educational tasks optimized for the user; means for dynamically generating dialogue content based on the selected educational tasks and presenting it to the user using speech synthesis technology; and means for receiving the user's voice input, converting it into text data, and analyzing the text data. This provides a personalized learning experience and enables mental support tailored to the user's emotional state.

[0414] "Identification information" refers to information used to uniquely identify a user, and includes, for example, user IDs and registered personal information.

[0415] "Learning history information" is a collection of information about the learning content, grades, and progress that a user has undertaken so far, and is used to plan future learning activities.

[0416] "Educational tasks" are specific problems or assignments set up to help users progress in their learning, and are selected according to the user's learning needs.

[0417] "Emotional state" refers to the user's emotional state and is information that evaluates the user's psychological and emotional state detected from voice input and other data.

[0418] "Mental care dialogue content" refers to dialogue content provided by the system that includes encouraging and relaxing messages, with the aim of reducing the user's psychological burden.

[0419] A "generative AI model" is an artificial intelligence model that learns from a large amount of data and is used to generate an output for a given input.

[0420] A "prompt sentence" is a sentence in the form of an instruction or question that is input into a generative AI model to obtain a specific output, and it forms the basis on which the AI ​​generates an appropriate response.

[0421] "Speech synthesis technology" is a technology that converts text data into speech data, and is used to convey the content of a conversation to the user in voice.

[0422] "Speech recognition technology" is a technology that converts speech into text data or a machine-readable format, and is used to process a user's verbal input as digital information.

[0423] This invention provides an interactive learning system that optimizes the user's learning experience and provides emotional support. This system mainly consists of three elements: a server, a terminal, and a user.

[0424] The server receives user identification information and retrieves learning history information from the database. This information is used to select the most appropriate educational tasks based on the user's learning progress. Based on the selected tasks, dialogue content is generated and presented to the user using speech synthesis technology. Specifically, common speech synthesis software such as Google TTS or Amazon Polly can be used for speech synthesis.

[0425] The device has the functionality to present the conversation content sent from the server to the user as audio. When the user provides an audio response, the device uses speech recognition technology (e.g., Google Speech-to-Text) to convert the audio into text data and send it to the server. This process ensures that the user's response is reflected in real time.

[0426] Users verbally respond to presented educational tasks, and the system performs sentiment analysis based on their voice. The server utilizes a generative AI model to analyze the user's voice input and evaluate their emotional state. Based on the analysis results, the server generates mental care dialogues as needed and provides adaptive feedback. An example of a prompt to the generative AI model is, "Generate an appropriate message to alleviate the stress the user is feeling." This allows the user to concentrate on learning with a sense of security.

[0427] As a concrete example, let's explain how the system behaves when it detects anxiety from the user's voice while they are working on a math problem. In this case, the server uses a generative AI model to generate a mental support dialogue such as, "It's okay, there's no need to rush. Let's solve it little by little," and provides it to the user through the terminal. This process reduces the user's stress and provides an effective learning experience.

[0428] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0429] Step 1:

[0430] The server receives user identification information, accesses the database, and retrieves learning history information. The input is the user's identification information, and the output is the user's past learning history information. This data serves as the basis for selecting the most suitable educational tasks for the user. Specifically, the server executes a database query using the identification information as the key and extracts the corresponding learning history.

[0431] Step 2:

[0432] The server analyzes the acquired learning history information and selects educational tasks appropriate to the user's current learning stage. The input is learning history information, and the output is educational tasks optimized for the user. In this process, the server dynamically determines appropriate tasks by considering the user's strengths and weaknesses. Specifically, it uses an algorithm to select tasks, taking into account past performance and the passage of time.

[0433] Step 3:

[0434] The server generates dialogue content based on the selected educational task and creates a dialogue script to present to the user using a generative AI model. The input is the educational task, and the output is the dialogue content. Specifically, by inputting prompt sentences into the AI ​​model, a script in a natural dialogue format is generated.

[0435] Step 4:

[0436] The server sends the generated dialogue content to the terminal. The input is the dialogue content, and the output is the transmission of data to the terminal. Specifically, it sends the data in packet format to the terminal via the network and confirms receipt.

[0437] Step 5:

[0438] The terminal converts received dialogue into speech and presents it to the user. The input is the dialogue from the server, and the output is the speech that the user can hear. Specifically, speech synthesis technology is used to convert text into speech data, which is then output through the speaker.

[0439] Step 6:

[0440] The user responds to the presented educational task verbally. The input is the user's verbal response, and the output is audio data recorded on the device. This response is processed as text in the next step.

[0441] Step 7:

[0442] The terminal converts the user's voice into text data and sends it to the server. The input is the user's voice data, and the output is text data. Specifically, it uses speech recognition software to convert the voice to text and sends it to the server as text data.

[0443] Step 8:

[0444] The server analyzes the received text data and evaluates the user's emotional state. The input is text data, and the output is the result of the emotional analysis. Specifically, a generative AI model is used to analyze the text and quantify the emotional state.

[0445] Step 9:

[0446] The server generates necessary mental care dialogues based on the emotion analysis results. The input is data on the emotional state, and the output is the mental care dialogue. Specifically, prompts corresponding to the emotional state are input to the AI ​​model, which then generates appropriate feedback messages.

[0447] Step 10:

[0448] The terminal converts mental health care dialogues from the server into audio and presents them to the user. The input is mental health care dialogue data, and the output is an audio message presented to the user audibly. This step is also achieved using speech synthesis technology.

[0449] (Application Example 2)

[0450] 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."

[0451] Conventional learning support systems have struggled to provide individualized learning experiences and to adequately alleviate users' mental pressure while providing support. Furthermore, in the in-store purchasing experience, there is a lack of means to suggest products that take into account the emotions and mental state of customers, resulting in a challenge in stimulating sufficient purchasing intent.

[0452] 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.

[0453] In this invention, the server includes means for acquiring the user's learning history information and selecting learning content optimized for the user; means for dynamically generating dialogue content based on the selected learning content; means for receiving the user's voice input, converting it into text data, and analyzing the text data; means for providing feedback to the user based on the analysis results; means for detecting the user's mental pressure and providing dialogue content for mental care as needed; means for presenting optimized product information based on the user's purchasing behavior; means for analyzing the user's mental pressure and emotional state in real time and making appropriate product suggestions; and means for generating prompt sentences using a generation AI model according to the user's selection.

[0454] This allows users to receive a personalized learning experience while reducing mental pressure, and furthermore, receiving emotionally resonant product suggestions in physical stores can stimulate their desire to purchase.

[0455] "Learning history information" refers to information that records what a user has learned in the past and their progress.

[0456] "Learning content" refers to the assignments and learning materials that users use for their studies.

[0457] "Dialogue content" refers to the content of communication exchanged between the user and the system, which is generated according to the purpose of learning or support.

[0458] "Voice input" refers to the audio data that users use to give instructions or responses to a system.

[0459] "Text data" refers to data obtained by converting voice input into a written format for analysis and understanding.

[0460] "Feedback" refers to the system's response and evaluation of user behavior and learning, and is intended to support user learning.

[0461] "Mental pressure" refers to the psychological burden and stress that users experience.

[0462] "Mental care" refers to the support and assistance provided to users to alleviate their mental stress and maintain their mental health.

[0463] "Purchasing behavior" refers to the series of actions a user takes when purchasing goods inside or outside a store.

[0464] "Product information" refers to information about products offered in physical stores or online, including their characteristics, specifications, price, and intended use.

[0465] A "generative AI model" refers to artificial intelligence technology that dynamically generates content according to the user's requests and objectives.

[0466] A "prompt statement" is a guidance statement created to give instructions or commands to a generative AI model so that it can function properly.

[0467] The system for realizing this invention consists of a server, a terminal, and a user who operates them. The server first acquires the user's learning history information and selects optimized learning content. Based on this selected learning content, it dynamically generates dialogue content. Data entered by the user via voice is received by the terminal and converted into text data via a speech recognition engine. These processes utilize terminals equipped with high-performance microphones and speech recognition technology using Nvidia Jetson.

[0468] Based on the analysis results, the server generates feedback and provides it to the user. If the user's mental stress is detected, it automatically generates dialogue content for mental care and provides immediate feedback. It also analyzes the user's purchasing behavior and presents product information that reflects their emotional state in real time. Specifically, it captures the customer's facial expressions with a camera and evaluates their emotions using facial expression analysis technologies such as the Microsoft Azure Emotion API.

[0469] Furthermore, the system constructs prompt messages based on a generative AI model, providing optimal information tailored to the user's choices and requests. This allows users to customize their learning and purchasing experience while stimulating their interest. For example, by analyzing a customer's prolonged viewing of a particular product, the system can offer customer service with a prompt such as, "It appears you are interested in this product; do you have any questions?"

[0470] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0471] Step 1:

[0472] The server retrieves the user's learning history information from the database. Based on this input information, it selects learning content optimized for the user. This selection process analyzes the user's past learning trends and performance to determine the most effective content. As a result, appropriate learning content is output.

[0473] Step 2:

[0474] The server dynamically generates dialogue content based on the selected learning content. Using a generation AI model, it creates the learning flow, hints, and supplementary explanations to present to the user, depending on the input learning content. Prompts designed to enhance the user's motivation are also set here. This output is dialogue content data for use on the terminal.

[0475] Step 3:

[0476] The user provides voice input to the device. The device receives this voice data and converts it into text data using speech recognition technology. The speech recognition engine, using Nvidia Jetson, analyzes the input voice data and obtains the corresponding text output. The converted text data is sent to the server.

[0477] Step 4:

[0478] The server analyzes text data to understand user responses. This analysis utilizes natural language processing techniques, including grasping the intent and emotions contained in the user's answers. Based on the analysis results, the server generates feedback for the user and sends it to their device. This feedback supports the user's learning and facilitates a better learning experience.

[0479] Step 5:

[0480] The device receives feedback from the server and presents it to the user verbally using speech synthesis technology. It also collects the user's facial expressions and voice tone using a camera and microphone to monitor their emotional state in real time. Using the Microsoft Azure Emotion API, it analyzes the input image and audio data to evaluate their emotional state. Based on this, necessary mental health support dialogues are simultaneously generated and provided as feedback to the user.

[0481] Step 6:

[0482] The device observes user purchasing behavior and analyzes customer interests through its camera. Based on the input video data, it evaluates customer gaze and pacing time, and provides real-time product information in combination with sentiment analysis. The selected product information is generated as prompt text using an AI model and output to the user via voice or display.

[0483] 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.

[0484] 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.

[0485] 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.

[0486] [Third Embodiment]

[0487] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0488] 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.

[0489] 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).

[0490] 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.

[0491] 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.

[0492] 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).

[0493] 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.

[0494] 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.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] 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".

[0499] This invention is an integrated system for personalizing the user's learning experience and providing psychological support. The program's processing flow is described below in natural language.

[0500] Server operation

[0501] The server retrieves the user's learning history information from the database. This allows it to begin analyzing past learning content, performance, and progress. Next, the server selects a set of learning problems that match the user's characteristics and customizes the problems to provide an optimal learning experience tailored to the user's current situation. Problems and related information are dynamically generated by a dialogue content generator and sent to the terminal. Furthermore, the server evaluates the user's responses and adjusts the feedback in real time. If the server detects psychological stress by analyzing the user's voice input, it creates a dialogue for mental care and transfers it to the terminal. Finally, the server saves the learning results and dialogue data to the database and updates the user's latest learning profile.

[0502] Terminal operation

[0503] The device uses speech synthesis technology to present learning questions sent from the server to the user. When the user answers a learning question, the device converts the voice input into text data and sends it back to the server. Once the feedback is received from the server, the device communicates it to the user verbally. In addition, if psychological stress is detected, the device performs a mitigation dialogue to care for the user.

[0504] User actions

[0505] Users answer learning questions presented on their device. Through voice interaction, they receive feedback if they make a mistake and can try the question again. Furthermore, through mental care dialogue, they can continue learning while regaining a sense of relaxation and security. This process aims to maintain the user's motivation to learn and to solidify knowledge while making it enjoyable.

[0506] Through the above process, the system can simultaneously provide users with a customized learning experience and the necessary mental support.

[0507] The following describes the processing flow.

[0508] Step 1:

[0509] The server receives the user's identification information and retrieves past learning history information from the database based on that information. This information includes problems the user has worked on in the past and their results.

[0510] Step 2:

[0511] The server analyzes the acquired learning history to determine the user's strengths and weaknesses. Based on this, it selects the most suitable learning problems to match the user's learning goals and determines the content to be presented in the next interactive session.

[0512] Step 3:

[0513] The server dynamically generates user interaction content based on the selected learning problem. This interaction content includes the problem statement, hints, and supplementary explanations. The generated interaction content is then sent to the terminal.

[0514] Step 4:

[0515] The terminal uses speech synthesis technology to present the conversation content received from the server to the user. When a question is presented to the user, the terminal waits for the user to answer verbally.

[0516] Step 5:

[0517] The user responds to the questions presented by the device using voice. The device receives this voice input and converts it into text data. This converted data is then sent to the server.

[0518] Step 6:

[0519] The server analyzes the user's text data and determines whether the answer is correct or incorrect. Based on the determination result, it generates feedback in real time and sends the feedback content to the terminal.

[0520] Step 7:

[0521] The device provides the user with voice feedback from the server. If the user answers correctly, they receive a message of praise; if they answer incorrectly, they are offered additional hints or suggestions to try again.

[0522] Step 8:

[0523] The server analyzes the user's voice data and responses to assess their level of mental stress. If high stress levels are detected, it generates a dialogue for mental care and attempts to encourage the user to relax.

[0524] Step 9:

[0525] The device provides users with audio conversations for mental health support. Through these conversations, the aim is to alleviate the user's emotional distress.

[0526] Step 10:

[0527] The server saves the user's learning results and care details to a database. It updates the user's learning profile so that it is reflected in the next learning plan.

[0528] (Example 1)

[0529] 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."

[0530] Conventional learning support systems have struggled to provide an optimal learning experience tailored to the individual characteristics and progress of each learner, and have been particularly inadequate in addressing mental stress. Furthermore, they have faced challenges in providing real-time feedback and adjusting learning content. Additionally, a significant problem exists where many learners lose motivation midway through their studies if support that takes their psychological state into consideration is not provided.

[0531] 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.

[0532] In this invention, the server includes means for acquiring learner history information from information storage and selecting personalized tasks for the learner; means for dynamically generating conversation content based on the selected tasks; and means for receiving the learner's voice input, converting it into text data, and analyzing the text data. This makes it possible to provide learners with a personalized learning experience and emotional support.

[0533] "Information storage" refers to a storage medium that accumulates data such as learners' history, grades, and progress, and makes that data available for retrieval as needed.

[0534] A "learner" refers to an individual user who acquires knowledge and skills by using the system.

[0535] "History information" refers to a collection of data related to an individual learner, including past learning content, grades, and progress.

[0536] "Individualized assignments" are sets of learning problems that have been adjusted and optimized according to the learner's characteristics and past learning history.

[0537] "Dynamically generating conversation content" refers to the process of creating dialogues with learners in real time using generative AI models, etc., and providing flexible content that responds to the situation and responses.

[0538] "Converting speech input to text data" means changing a learner's utterances into text data using speech recognition technology, and then using that text data as the basis for analysis.

[0539] "Mental burden" refers to the stress, anxiety, and mental fatigue that learners may experience during learning activities.

[0540] "Conversation content for psychological support" refers to dialogue designed to reduce the learner's mental burden and provide a sense of security.

[0541] A "learning profile" is a collection of data that is updated based on an individual learner's progress and abilities to provide guidance for future learning activities.

[0542] This invention is an integrated system that provides learners with personalized learning experiences and psychological support. The operation of the system and its embodiments are described below.

[0543] Server operation

[0544] The server uses a database system to retrieve learner history information from information storage. Specifically, it retrieves the learner's past performance and progress using SQL queries. Based on this data, the server utilizes a generative AI model to select personalized tasks. For example, it uses a Python machine learning library to perform data analysis and prepare to present problems optimized for the learner. The generative AI model uses a model with natural language processing capabilities and generates dialogue content by inputting prompts in a specific format. A prompt such as "Create an English vocabulary problem that should be attempted next, based on the user's learning history" can be used. The server sends the generated content to the terminal.

[0545] Terminal operation

[0546] The device transmits learning questions received from the server to the learner using speech synthesis technology. This typically involves using a speech synthesis API. For example, the Google TTS (Text-to-Speech) API is used to convert text into speech and present it to the learner in combination with visual aids. When the learner responds verbally, the device uses a speech recognition API, such as Google Speech-to-Text, to convert the speech into text data and sends that text data back to the server.

[0547] User actions

[0548] Learners progress through the learning process by answering presented tasks verbally. If they make a mistake, they receive feedback from the server and can try again. Furthermore, if the system perceives mental stress, learners are offered reassurance through mental care dialogues. Relaxation messages, such as "Take a deep breath and relax," are played via speech synthesis.

[0549] Thus, the system of the present invention has embodiments that simultaneously provide learners with a personalized learning experience and appropriate psychological support.

[0550] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0551] Step 1:

[0552] The server retrieves learner history information from information storage. This input includes the learner's past performance and progress. SQL queries are used to extract this data from the database. The output is the learner's learning history data, which serves as the basis for selecting individualized assignments.

[0553] Step 2:

[0554] The server selects personalized tasks using a generative AI model based on the acquired historical information. The input is the historical data obtained in Step 1. Through data analysis, the learner's strengths and weaknesses are identified, and a personalized set of learning problems is generated as output. Specifically, the analysis is performed using a Python machine learning library.

[0555] Step 3:

[0556] The server dynamically generates conversation content based on the selected task. The input is the set of training questions obtained in step 2. By inputting prompt sentences into the generating AI model, conversation content is created using natural language processing. The output is dynamically generated conversation data, which becomes the content of the task provided to the learner.

[0557] Step 4:

[0558] The server sends the generated conversation content to the terminal. The input is the conversation data obtained in step 3. This is delivered to the terminal via network communication. As output, training questions usable on the terminal are sent.

[0559] Step 5:

[0560] The terminal presents learning questions received from the server to the learner using speech synthesis technology. The input is audio data from the server, which is provided as audio output using the Google TTS API or similar. The output is an audio announcement that the learner can hear.

[0561] Step 6:

[0562] The user answers the presented task using voice. The input is the learner's voice, which the device converts into text data using a speech recognition API. As output, text-formatted answer data is generated and sent back to the server.

[0563] Step 7:

[0564] The server analyzes the user's text data and generates feedback in real time. The input is the text data obtained in step 6. The generation AI model is used again to create feedback based on the analysis results. The output is the conversation content as feedback.

[0565] Step 8:

[0566] The device provides the user with feedback received from the server via speech synthesis. The input is feedback data from the server, which is output as speech using speech synthesis technology. By listening to this audio feedback, the user can check their learning progress.

[0567] Step 9:

[0568] The server analyzes the learner's voice data and assesses their mental burden. The input is the user's voice, and if psychological stress is detected, it uses a generative AI model to generate appropriate mental care conversation content. The output is feedback for mental support.

[0569] Step 10:

[0570] The terminal presents the user with mental health care dialogue content from the server. The input is mental health care data from the server, and speech synthesis technology provides the user with a relaxing voice. The user can gain a sense of security through this voice.

[0571] Step 11:

[0572] The server records the learner's learning results and profile in a database. Inputs include the learner's task performance and generated feedback. This data is used to update the learning profile, contributing to improved accuracy in future individualized learning. The output is the updated learning profile.

[0573] (Application Example 1)

[0574] 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."

[0575] Providing efficient and personalized training for engineers and workers in the field is challenging. Furthermore, operational errors and learning delays can lead to significant mental stress. In this environment, there is a need to provide optimal education and mental support to each individual learner.

[0576] 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.

[0577] In this invention, the server includes means for acquiring user history information and selecting educational questions optimized for the user; means for dynamically generating dialogue content based on the selected educational questions; and means for receiving the user's voice input, converting it into text information, and analyzing the text information. This makes it possible to personalize the learning of engineers in the field and also provide emotional support.

[0578] "History information" refers to data that records a user's past actions and learning progress.

[0579] "Educational questions" are questions used to assess or improve learners' knowledge and skills.

[0580] "Dialogue content" refers to spoken or textual information that enables communication with the user.

[0581] "Voice input" is the process of capturing a user's speech as digital data.

[0582] "Textual information" refers to audio or other data converted into text format.

[0583] An "analytical method" is a technique or process for analyzing data and extracting useful information.

[0584] "Mental tension" refers to a mental state characterized by anxiety or stress experienced by the user.

[0585] "Mental health dialogue content" refers to dialogue designed to improve the user's psychological state and promote relaxation.

[0586] "Learning images" refer to updated profile information that represents the user's learning progress.

[0587] "Machinery and equipment" is a general term referring to machinery used on-site.

[0588] This invention is a system that supports users' learning activities, and is particularly optimized for engineers and workers in the field. The specific operation of the system is shown below.

[0589] The server first retrieves user history information from a database. This data includes past learning content, achievements, and progress. Based on this, it selects the most suitable educational questions for the user. Next, it uses a tool to generate dialogue content based on the selected questions. The dialogue content is dynamically generated using a generative AI model.

[0590] The server accepts the user's voice input and converts it into text. Voice recognition software such as the Google Speech-to-Text API is used. The converted text is analyzed and used to provide appropriate feedback to the user. The feedback is adjusted in real time based on the user's current situation.

[0591] The server also detects mental stress from the user's voice. This involves using a method that evaluates specific stress indicators through voice analysis. If necessary, mental health-related dialogue content is generated and provided to the user to offer mental support.

[0592] When a user interacts with the system, the terminal presents educational questions downloaded from the server in audio format. OpenAI's Whisper model and other speech synthesis technologies are used for speech synthesis. After the user answers the learning questions, their responses are sent to the server for analysis. Based on the analysis, feedback and conversational support are provided to the user, allowing them to continue learning in a relaxed state.

[0593] As a concrete example, this system is used when engineers are learning how to operate newly introduced machinery and equipment. The system adjusts the difficulty level according to the engineer's progress, ensuring they learn safe operating methods. Furthermore, when the engineer feels stressed, it generates relaxing dialogue such as, "Take a deep breath. It's okay to go at your own pace."

[0594] As a concrete example of a prompt, you can instruct the AI ​​model to generate a message such as, "Generate a conversation to help a technician relax when they feel stressed while operating machinery."

[0595] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0596] Step 1:

[0597] The server retrieves user history information from the database. The user ID is used as input, and past learning content, achievements, and progress are obtained as output. Based on this data, the server selects educational questions optimized for the user.

[0598] Step 2:

[0599] The server dynamically generates dialogue content using a generative AI model based on selected educational questions. The input includes the educational questions and the user's current learning progress, and the output is a voice dialogue script. The generated script is then prepared for presentation to the user.

[0600] Step 3:

[0601] The terminal presents the user with a voice dialogue script delivered from the server using speech synthesis software. It receives script data as input and plays the synthesized voice back to the user as output.

[0602] Step 4:

[0603] The user provides answers via voice. The device receives the user's voice input and converts it into text information using speech recognition technology. Voice data is received as input, and text data is generated as output.

[0604] Step 5:

[0605] The server analyzes the text information obtained from voice input and evaluates the user's response. Text data is used as input, and the evaluation result is obtained as output. Based on this result, feedback is generated in real time.

[0606] Step 6:

[0607] The server detects mental stress from the user's voice and generates mental health-promoting dialogue as needed. Voice features are used as input, and a relaxation-oriented dialogue script is output. A generative AI model is used to generate prompts to assist the user.

[0608] Step 7:

[0609] The device provides the user with audio feedback and mental health dialogue scripts received from the server. It receives script data from the server as input and plays synthesized audio as output, allowing the user to continue learning with confidence.

[0610] 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.

[0611] This invention is an interactive learning system that incorporates an emotion engine to improve the user's learning experience and emotional support. This system analyzes the user's emotions in real time and provides a learning experience that is optimally tailored to the individual's emotional state.

[0612] Server operation

[0613] The server uses pre-registered user identification information to retrieve the user's learning history information from the database. Based on this information, it selects learning problems suitable for the user and generates dialogue corresponding to their content. The generated dialogue includes learning problems, hints, and supplementary explanations. Furthermore, the server receives the user's voice input data and performs emotion analysis via an emotion engine. Based on the emotion data, it evaluates the user's stress level and emotional state and provides mental and emotional care as needed.

[0614] Terminal operation

[0615] The device presents the conversation content received from the server to the user using speech synthesis technology. When the user answers a question verbally, the device converts the voice input into text data and sends it to the server. The device also receives feedback from the server and communicates it to the user verbally. Based on the emotional data analyzed by the emotion engine, the device provides appropriate emotional feedback and mental support during the learning process.

[0616] User actions

[0617] Users can answer learning questions presented on the device using voice. The user's responses and voice tone are analyzed by an emotion engine, which evaluates the user's psychological state in real time. If the user experiences high stress levels, the device switches to a conversational mode that provides mental care via a server. In this way, users can progress through their learning while receiving an optimal learning experience and emotional support tailored to their individual learning needs.

[0618] As a concrete example, consider a scenario where a user is working on a math problem and the system detects signs of anxiety from the user's voice. In this case, the server generates a specific care dialogue through its emotion engine, providing the user with reassuring encouragement and additional explanations. This process allows for effective learning outcomes while alleviating user stress.

[0619] This invention is expected to improve the quality of learning by simultaneously providing learners with personalized learning and immediate emotional support.

[0620] The following describes the processing flow.

[0621] Step 1:

[0622] The server receives the user's identification information and accesses the database to retrieve the user's learning history. This information includes past results on problems, response times, and points earned for incorrect answers.

[0623] Step 2:

[0624] The server analyzes the acquired learning history to identify the user's strengths and weaknesses. Based on these results, it automatically selects the most effective learning problems for the user.

[0625] Step 3:

[0626] Based on the selected learning questions, the server generates dialogue content. This generated dialogue includes details about the question, hints to help solve it, and messages to encourage learning. This content is then prepared for transmission to the terminal.

[0627] Step 4:

[0628] The terminal receives the conversation content from the server and outputs it to the user as speech using speech synthesis technology. The user listens to the presented learning questions in audio. The terminal also waits for voice input from the user.

[0629] Step 5:

[0630] The user responds verbally to questions presented by the device. The device converts this voice input into text data. This text data is sent to a server and used for analysis.

[0631] Step 6:

[0632] The server analyzes the received text data and determines whether the user's answer is correct or incorrect. Based on the determination result, it creates feedback and generates customized messages according to the user's learning progress.

[0633] Step 7:

[0634] The device outputs feedback sent from the server as audio to the user. This feedback includes justified answers and explanations to correct misunderstandings.

[0635] Step 8:

[0636] The server uses an emotion engine to analyze the user's emotional state from their voice tone and content. If this analysis detects emotions such as anxiety, stress, or joy, it takes appropriate action.

[0637] Step 9:

[0638] If the user's emotions indicate high levels of stress or anxiety, the server uses an emotion engine to generate mental health support dialogue. The device then communicates this to the user verbally to encourage relaxation.

[0639] Step 10:

[0640] The server stores information about learning results and emotions in a database and updates the user's learning profile. This allows for a more refined learning plan to be suggested for the next session.

[0641] (Example 2)

[0642] 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."

[0643] This invention aims to solve the problem in conventional learning systems where it is difficult to accurately grasp and adjust to the individual learning needs and emotional state of users in real time. In particular, it addresses the problem that learning effectiveness decreases when users are under high stress, and aims to improve the quality of the learning experience by providing individualized mental support.

[0644] 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.

[0645] In this invention, the server includes means for acquiring learning history information using user identification information and selecting educational tasks optimized for the user; means for dynamically generating dialogue content based on the selected educational tasks and presenting it to the user using speech synthesis technology; and means for receiving the user's voice input, converting it into text data, and analyzing the text data. This provides a personalized learning experience and enables mental support tailored to the user's emotional state.

[0646] "Identification information" refers to information used to uniquely identify a user, and includes, for example, user IDs and registered personal information.

[0647] "Learning history information" is a collection of information about the learning content, grades, and progress that a user has undertaken so far, and is used to plan future learning activities.

[0648] "Educational tasks" are specific problems or assignments set up to help users progress in their learning, and are selected according to the user's learning needs.

[0649] "Emotional state" refers to the user's emotional state and is information that evaluates the user's psychological and emotional state detected from voice input and other data.

[0650] "Mental care dialogue content" refers to dialogue content provided by the system that includes encouraging and relaxing messages, with the aim of reducing the user's psychological burden.

[0651] A "generative AI model" is an artificial intelligence model that learns from a large amount of data and is used to generate an output for a given input.

[0652] A "prompt sentence" is a sentence in the form of an instruction or question that is input into a generative AI model to obtain a specific output, and it forms the basis on which the AI ​​generates an appropriate response.

[0653] "Speech synthesis technology" is a technology that converts text data into speech data, and is used to convey the content of a conversation to the user in voice.

[0654] "Speech recognition technology" is a technology that converts speech into text data or a machine-readable format, and is used to process a user's verbal input as digital information.

[0655] This invention provides an interactive learning system that optimizes the user's learning experience and provides emotional support. This system mainly consists of three elements: a server, a terminal, and a user.

[0656] The server receives user identification information and retrieves learning history information from the database. This information is used to select the most appropriate educational tasks based on the user's learning progress. Based on the selected tasks, dialogue content is generated and presented to the user using speech synthesis technology. Specifically, common speech synthesis software such as Google TTS or Amazon Polly can be used for speech synthesis.

[0657] The device has the functionality to present the conversation content sent from the server to the user as audio. When the user provides an audio response, the device uses speech recognition technology (e.g., Google Speech-to-Text) to convert the audio into text data and send it to the server. This process ensures that the user's response is reflected in real time.

[0658] Users verbally respond to presented educational tasks, and the system performs sentiment analysis based on their voice. The server utilizes a generative AI model to analyze the user's voice input and evaluate their emotional state. Based on the analysis results, the server generates mental care dialogues as needed and provides adaptive feedback. An example of a prompt to the generative AI model is, "Generate an appropriate message to alleviate the stress the user is feeling." This allows the user to concentrate on learning with a sense of security.

[0659] As a concrete example, let's explain how the system behaves when it detects anxiety from the user's voice while they are working on a math problem. In this case, the server uses a generative AI model to generate a mental support dialogue such as, "It's okay, there's no need to rush. Let's solve it little by little," and provides it to the user through the terminal. This process reduces the user's stress and provides an effective learning experience.

[0660] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0661] Step 1:

[0662] The server receives user identification information, accesses the database, and retrieves learning history information. The input is the user's identification information, and the output is the user's past learning history information. This data serves as the basis for selecting the most suitable educational tasks for the user. Specifically, the server executes a database query using the identification information as the key and extracts the corresponding learning history.

[0663] Step 2:

[0664] The server analyzes the acquired learning history information and selects educational tasks appropriate to the user's current learning stage. The input is learning history information, and the output is educational tasks optimized for the user. In this process, the server dynamically determines appropriate tasks by considering the user's strengths and weaknesses. Specifically, it uses an algorithm to select tasks, taking into account past performance and the passage of time.

[0665] Step 3:

[0666] The server generates dialogue content based on the selected educational task and creates a dialogue script to present to the user using a generative AI model. The input is the educational task, and the output is the dialogue content. Specifically, by inputting prompt sentences into the AI ​​model, a script in a natural dialogue format is generated.

[0667] Step 4:

[0668] The server sends the generated dialogue content to the terminal. The input is the dialogue content, and the output is the transmission of data to the terminal. Specifically, it sends the data in packet format to the terminal via the network and confirms receipt.

[0669] Step 5:

[0670] The terminal converts received dialogue into speech and presents it to the user. The input is the dialogue from the server, and the output is the speech that the user can hear. Specifically, speech synthesis technology is used to convert text into speech data, which is then output through the speaker.

[0671] Step 6:

[0672] The user responds to the presented educational task verbally. The input is the user's verbal response, and the output is audio data recorded on the device. This response is processed as text in the next step.

[0673] Step 7:

[0674] The terminal converts the user's voice into text data and sends it to the server. The input is the user's voice data, and the output is text data. Specifically, it uses speech recognition software to convert the voice to text and sends it to the server as text data.

[0675] Step 8:

[0676] The server analyzes the received text data and evaluates the user's emotional state. The input is text data, and the output is the result of the emotional analysis. Specifically, a generative AI model is used to analyze the text and quantify the emotional state.

[0677] Step 9:

[0678] The server generates necessary mental care dialogues based on the emotion analysis results. The input is data on the emotional state, and the output is the mental care dialogue. Specifically, prompts corresponding to the emotional state are input to the AI ​​model, which then generates appropriate feedback messages.

[0679] Step 10:

[0680] The terminal converts mental health care dialogues from the server into audio and presents them to the user. The input is mental health care dialogue data, and the output is an audio message presented to the user audibly. This step is also achieved using speech synthesis technology.

[0681] (Application Example 2)

[0682] 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."

[0683] Conventional learning support systems have struggled to provide individualized learning experiences and to adequately alleviate users' mental pressure while providing support. Furthermore, in the in-store purchasing experience, there is a lack of means to suggest products that take into account the emotions and mental state of customers, resulting in a challenge in stimulating sufficient purchasing intent.

[0684] 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.

[0685] In this invention, the server includes means for acquiring the user's learning history information and selecting learning content optimized for the user; means for dynamically generating dialogue content based on the selected learning content; means for receiving the user's voice input, converting it into text data, and analyzing the text data; means for providing feedback to the user based on the analysis results; means for detecting the user's mental pressure and providing dialogue content for mental care as needed; means for presenting optimized product information based on the user's purchasing behavior; means for analyzing the user's mental pressure and emotional state in real time and making appropriate product suggestions; and means for generating prompt sentences using a generation AI model according to the user's selection.

[0686] This allows users to receive a personalized learning experience while reducing mental pressure, and furthermore, receiving emotionally resonant product suggestions in physical stores can stimulate their desire to purchase.

[0687] "Learning history information" refers to information that records what a user has learned in the past and their progress.

[0688] "Learning content" refers to the assignments and learning materials that users use for their studies.

[0689] "Dialogue content" refers to the content of communication exchanged between the user and the system, which is generated according to the purpose of learning or support.

[0690] "Voice input" refers to the audio data that users use to give instructions or responses to a system.

[0691] "Text data" refers to data obtained by converting voice input into a written format for analysis and understanding.

[0692] "Feedback" refers to the system's response and evaluation of user behavior and learning, and is intended to support user learning.

[0693] "Mental pressure" refers to the psychological burden and stress that users experience.

[0694] "Mental care" refers to the support and assistance provided to users to alleviate their mental stress and maintain their mental health.

[0695] "Purchasing behavior" refers to the series of actions a user takes when purchasing goods inside or outside a store.

[0696] "Product information" refers to information about products offered in physical stores or online, including their characteristics, specifications, price, and intended use.

[0697] A "generative AI model" refers to artificial intelligence technology that dynamically generates content according to the user's requests and objectives.

[0698] A "prompt statement" is a guidance statement created to give instructions or commands to a generative AI model so that it can function properly.

[0699] The system for realizing this invention consists of a server, a terminal, and a user who operates them. The server first acquires the user's learning history information and selects optimized learning content. Based on this selected learning content, it dynamically generates dialogue content. Data entered by the user via voice is received by the terminal and converted into text data via a speech recognition engine. These processes utilize terminals equipped with high-performance microphones and speech recognition technology using Nvidia Jetson.

[0700] Based on the analysis results, the server generates feedback and provides it to the user. If the user's mental stress is detected, it automatically generates dialogue content for mental care and provides immediate feedback. It also analyzes the user's purchasing behavior and presents product information that reflects their emotional state in real time. Specifically, it captures the customer's facial expressions with a camera and evaluates their emotions using facial expression analysis technologies such as the Microsoft Azure Emotion API.

[0701] Furthermore, the system constructs prompt messages based on a generative AI model, providing optimal information tailored to the user's choices and requests. This allows users to customize their learning and purchasing experience while stimulating their interest. For example, by analyzing a customer's prolonged viewing of a particular product, the system can offer customer service with a prompt such as, "It appears you are interested in this product; do you have any questions?"

[0702] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0703] Step 1:

[0704] The server retrieves the user's learning history information from the database. Based on this input information, it selects learning content optimized for the user. This selection process analyzes the user's past learning trends and performance to determine the most effective content. As a result, appropriate learning content is output.

[0705] Step 2:

[0706] The server dynamically generates dialogue content based on the selected learning content. Using a generation AI model, it creates the learning flow, hints, and supplementary explanations to present to the user, depending on the input learning content. Prompts designed to enhance the user's motivation are also set here. This output is dialogue content data for use on the terminal.

[0707] Step 3:

[0708] The user provides voice input to the device. The device receives this voice data and converts it into text data using speech recognition technology. The speech recognition engine, using Nvidia Jetson, analyzes the input voice data and obtains the corresponding text output. The converted text data is sent to the server.

[0709] Step 4:

[0710] The server analyzes text data to understand user responses. This analysis utilizes natural language processing techniques, including grasping the intent and emotions contained in the user's answers. Based on the analysis results, the server generates feedback for the user and sends it to their device. This feedback supports the user's learning and facilitates a better learning experience.

[0711] Step 5:

[0712] The device receives feedback from the server and presents it to the user verbally using speech synthesis technology. It also collects the user's facial expressions and voice tone using a camera and microphone to monitor their emotional state in real time. Using the Microsoft Azure Emotion API, it analyzes the input image and audio data to evaluate their emotional state. Based on this, necessary mental health support dialogues are simultaneously generated and provided as feedback to the user.

[0713] Step 6:

[0714] The device observes user purchasing behavior and analyzes customer interests through its camera. Based on the input video data, it evaluates customer gaze and pacing time, and provides real-time product information in combination with sentiment analysis. The selected product information is generated as prompt text using an AI model and output to the user via voice or display.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] [Fourth Embodiment]

[0719] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0720] 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.

[0721] 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).

[0722] 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.

[0723] 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.

[0724] 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).

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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".

[0732] This invention is an integrated system for personalizing the user's learning experience and providing psychological support. The program's processing flow is described below in natural language.

[0733] Server operation

[0734] The server retrieves the user's learning history information from the database. This allows it to begin analyzing past learning content, performance, and progress. Next, the server selects a set of learning problems that match the user's characteristics and customizes the problems to provide an optimal learning experience tailored to the user's current situation. Problems and related information are dynamically generated by a dialogue content generator and sent to the terminal. Furthermore, the server evaluates the user's responses and adjusts the feedback in real time. If the server detects psychological stress by analyzing the user's voice input, it creates a dialogue for mental care and transfers it to the terminal. Finally, the server saves the learning results and dialogue data to the database and updates the user's latest learning profile.

[0735] Terminal operation

[0736] The device uses speech synthesis technology to present learning questions sent from the server to the user. When the user answers a learning question, the device converts the voice input into text data and sends it back to the server. Once the feedback is received from the server, the device communicates it to the user verbally. In addition, if psychological stress is detected, the device performs a mitigation dialogue to care for the user.

[0737] User actions

[0738] Users answer learning questions presented on their device. Through voice interaction, they receive feedback if they make a mistake and can try the question again. Furthermore, through mental care dialogue, they can continue learning while regaining a sense of relaxation and security. This process aims to maintain the user's motivation to learn and to solidify knowledge while making it enjoyable.

[0739] Through the above process, the system can simultaneously provide users with a customized learning experience and the necessary mental support.

[0740] The following describes the processing flow.

[0741] Step 1:

[0742] The server receives the user's identification information and retrieves past learning history information from the database based on that information. This information includes problems the user has worked on in the past and their results.

[0743] Step 2:

[0744] The server analyzes the acquired learning history to determine the user's strengths and weaknesses. Based on this, it selects the most suitable learning problems to match the user's learning goals and determines the content to be presented in the next interactive session.

[0745] Step 3:

[0746] The server dynamically generates user interaction content based on the selected learning problem. This interaction content includes the problem statement, hints, and supplementary explanations. The generated interaction content is then sent to the terminal.

[0747] Step 4:

[0748] The terminal uses speech synthesis technology to present the conversation content received from the server to the user. When a question is presented to the user, the terminal waits for the user to answer verbally.

[0749] Step 5:

[0750] The user responds to the questions presented by the device using voice. The device receives this voice input and converts it into text data. This converted data is then sent to the server.

[0751] Step 6:

[0752] The server analyzes the user's text data and determines whether the answer is correct or incorrect. Based on the determination result, it generates feedback in real time and sends the feedback content to the terminal.

[0753] Step 7:

[0754] The device provides the user with voice feedback from the server. If the user answers correctly, they receive a message of praise; if they answer incorrectly, they are offered additional hints or suggestions to try again.

[0755] Step 8:

[0756] The server analyzes the user's voice data and responses to assess their level of mental stress. If high stress levels are detected, it generates a dialogue for mental care and attempts to encourage the user to relax.

[0757] Step 9:

[0758] The device provides users with audio conversations for mental health support. Through these conversations, the aim is to alleviate the user's emotional distress.

[0759] Step 10:

[0760] The server saves the user's learning results and care details to a database. It updates the user's learning profile so that it is reflected in the next learning plan.

[0761] (Example 1)

[0762] 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".

[0763] Conventional learning support systems have struggled to provide an optimal learning experience tailored to the individual characteristics and progress of each learner, and have been particularly inadequate in addressing mental stress. Furthermore, they have faced challenges in providing real-time feedback and adjusting learning content. Additionally, a significant problem exists where many learners lose motivation midway through their studies if support that takes their psychological state into consideration is not provided.

[0764] 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.

[0765] In this invention, the server includes means for acquiring learner history information from information storage and selecting personalized tasks for the learner; means for dynamically generating conversation content based on the selected tasks; and means for receiving the learner's voice input, converting it into text data, and analyzing the text data. This makes it possible to provide learners with a personalized learning experience and emotional support.

[0766] "Information storage" refers to a storage medium that accumulates data such as learners' history, grades, and progress, and makes that data available for retrieval as needed.

[0767] A "learner" refers to an individual user who acquires knowledge and skills by using the system.

[0768] "History information" refers to a collection of data related to an individual learner, including past learning content, grades, and progress.

[0769] "Individualized assignments" are sets of learning problems that have been adjusted and optimized according to the learner's characteristics and past learning history.

[0770] "Dynamically generating conversation content" refers to the process of creating dialogues with learners in real time using generative AI models, etc., and providing flexible content that responds to the situation and responses.

[0771] "Converting speech input to text data" means changing a learner's utterances into text data using speech recognition technology, and then using that text data as the basis for analysis.

[0772] "Mental burden" refers to the stress, anxiety, and mental fatigue that learners may experience during learning activities.

[0773] "Conversation content for psychological support" refers to dialogue designed to reduce the learner's mental burden and provide a sense of security.

[0774] A "learning profile" is a collection of data that is updated based on an individual learner's progress and abilities to provide guidance for future learning activities.

[0775] This invention is an integrated system that provides learners with personalized learning experiences and psychological support. The operation of the system and its embodiments are described below.

[0776] Server operation

[0777] The server uses a database system to retrieve learner history information from information storage. Specifically, it retrieves the learner's past performance and progress using SQL queries. Based on this data, the server utilizes a generative AI model to select personalized tasks. For example, it uses a Python machine learning library to perform data analysis and prepare to present problems optimized for the learner. The generative AI model uses a model with natural language processing capabilities and generates dialogue content by inputting prompts in a specific format. A prompt such as "Create an English vocabulary problem that should be attempted next, based on the user's learning history" can be used. The server sends the generated content to the terminal.

[0778] Terminal operation

[0779] The device transmits learning questions received from the server to the learner using speech synthesis technology. This typically involves using a speech synthesis API. For example, the Google TTS (Text-to-Speech) API is used to convert text into speech and present it to the learner in combination with visual aids. When the learner responds verbally, the device uses a speech recognition API, such as Google Speech-to-Text, to convert the speech into text data and sends that text data back to the server.

[0780] User actions

[0781] Learners progress through the learning process by answering presented tasks verbally. If they make a mistake, they receive feedback from the server and can try again. Furthermore, if the system perceives mental stress, learners are offered reassurance through mental care dialogues. Relaxation messages, such as "Take a deep breath and relax," are played via speech synthesis.

[0782] Thus, the system of the present invention has embodiments that simultaneously provide learners with a personalized learning experience and appropriate psychological support.

[0783] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0784] Step 1:

[0785] The server retrieves learner history information from information storage. This input includes the learner's past performance and progress. SQL queries are used to extract this data from the database. The output is the learner's learning history data, which serves as the basis for selecting individualized assignments.

[0786] Step 2:

[0787] The server selects personalized tasks using a generative AI model based on the acquired historical information. The input is the historical data obtained in Step 1. Through data analysis, the learner's strengths and weaknesses are identified, and a personalized set of learning problems is generated as output. Specifically, the analysis is performed using a Python machine learning library.

[0788] Step 3:

[0789] The server dynamically generates conversation content based on the selected task. The input is the set of training questions obtained in step 2. By inputting prompt sentences into the generating AI model, conversation content is created using natural language processing. The output is dynamically generated conversation data, which becomes the content of the task provided to the learner.

[0790] Step 4:

[0791] The server sends the generated conversation content to the terminal. The input is the conversation data obtained in step 3. This is delivered to the terminal via network communication. As output, training questions usable on the terminal are sent.

[0792] Step 5:

[0793] The terminal presents learning questions received from the server to the learner using speech synthesis technology. The input is audio data from the server, which is provided as audio output using the Google TTS API or similar. The output is an audio announcement that the learner can hear.

[0794] Step 6:

[0795] The user answers the presented task using voice. The input is the learner's voice, which the device converts into text data using a speech recognition API. As output, text-formatted answer data is generated and sent back to the server.

[0796] Step 7:

[0797] The server analyzes the user's text data and generates feedback in real time. The input is the text data obtained in step 6. The generation AI model is used again to create feedback based on the analysis results. The output is the conversation content as feedback.

[0798] Step 8:

[0799] The device provides the user with feedback received from the server via speech synthesis. The input is feedback data from the server, which is output as speech using speech synthesis technology. By listening to this audio feedback, the user can check their learning progress.

[0800] Step 9:

[0801] The server analyzes the learner's voice data and assesses their mental burden. The input is the user's voice, and if psychological stress is detected, it uses a generative AI model to generate appropriate mental care conversation content. The output is feedback for mental support.

[0802] Step 10:

[0803] The terminal presents the user with mental health care dialogue content from the server. The input is mental health care data from the server, and speech synthesis technology provides the user with a relaxing voice. The user can gain a sense of security through this voice.

[0804] Step 11:

[0805] The server records the learner's learning results and profile in a database. Inputs include the learner's task performance and generated feedback. This data is used to update the learning profile, contributing to improved accuracy in future individualized learning. The output is the updated learning profile.

[0806] (Application Example 1)

[0807] 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".

[0808] Providing efficient and personalized training for engineers and workers in the field is challenging. Furthermore, operational errors and learning delays can lead to significant mental stress. In this environment, there is a need to provide optimal education and mental support to each individual learner.

[0809] 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.

[0810] In this invention, the server includes means for acquiring user history information and selecting educational questions optimized for the user; means for dynamically generating dialogue content based on the selected educational questions; and means for receiving the user's voice input, converting it into text information, and analyzing the text information. This makes it possible to personalize the learning of engineers in the field and also provide emotional support.

[0811] "History information" refers to data that records a user's past actions and learning progress.

[0812] "Educational questions" are questions used to assess or improve learners' knowledge and skills.

[0813] "Dialogue content" refers to spoken or textual information that enables communication with the user.

[0814] "Voice input" is the process of capturing a user's speech as digital data.

[0815] "Textual information" refers to audio or other data converted into text format.

[0816] An "analytical method" is a technique or process for analyzing data and extracting useful information.

[0817] "Mental tension" refers to a mental state characterized by anxiety or stress experienced by the user.

[0818] "Mental health dialogue content" refers to dialogue designed to improve the user's psychological state and promote relaxation.

[0819] "Learning images" refer to updated profile information that represents the user's learning progress.

[0820] "Machinery and equipment" is a general term referring to machinery used on-site.

[0821] This invention is a system that supports users' learning activities, and is particularly optimized for engineers and workers in the field. The specific operation of the system is shown below.

[0822] The server first retrieves user history information from a database. This data includes past learning content, achievements, and progress. Based on this, it selects the most suitable educational questions for the user. Next, it uses a tool to generate dialogue content based on the selected questions. The dialogue content is dynamically generated using a generative AI model.

[0823] The server accepts the user's voice input and converts it into text. Voice recognition software such as the Google Speech-to-Text API is used. The converted text is analyzed and used to provide appropriate feedback to the user. The feedback is adjusted in real time based on the user's current situation.

[0824] The server also detects mental stress from the user's voice. This involves using a method that evaluates specific stress indicators through voice analysis. If necessary, mental health-related dialogue content is generated and provided to the user to offer mental support.

[0825] When a user interacts with the system, the terminal presents educational questions downloaded from the server in audio format. OpenAI's Whisper model and other speech synthesis technologies are used for speech synthesis. After the user answers the learning questions, their responses are sent to the server for analysis. Based on the analysis, feedback and conversational support are provided to the user, allowing them to continue learning in a relaxed state.

[0826] As a concrete example, this system is used when engineers are learning how to operate newly introduced machinery and equipment. The system adjusts the difficulty level according to the engineer's progress, ensuring they learn safe operating methods. Furthermore, when the engineer feels stressed, it generates relaxing dialogue such as, "Take a deep breath. It's okay to go at your own pace."

[0827] As a concrete example of a prompt, you can instruct the AI ​​model to generate a message such as, "Generate a conversation to help a technician relax when they feel stressed while operating machinery."

[0828] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0829] Step 1:

[0830] The server retrieves user history information from the database. The user ID is used as input, and past learning content, achievements, and progress are obtained as output. Based on this data, the server selects educational questions optimized for the user.

[0831] Step 2:

[0832] The server dynamically generates dialogue content using a generative AI model based on selected educational questions. The input includes the educational questions and the user's current learning progress, and the output is a voice dialogue script. The generated script is then prepared for presentation to the user.

[0833] Step 3:

[0834] The terminal presents the user with a voice dialogue script delivered from the server using speech synthesis software. It receives script data as input and plays the synthesized voice back to the user as output.

[0835] Step 4:

[0836] The user provides answers via voice. The device receives the user's voice input and converts it into text information using speech recognition technology. Voice data is received as input, and text data is generated as output.

[0837] Step 5:

[0838] The server analyzes the text information obtained from voice input and evaluates the user's response. Text data is used as input, and the evaluation result is obtained as output. Based on this result, feedback is generated in real time.

[0839] Step 6:

[0840] The server detects mental stress from the user's voice and generates mental health-promoting dialogue as needed. Voice features are used as input, and a relaxation-oriented dialogue script is output. A generative AI model is used to generate prompts to assist the user.

[0841] Step 7:

[0842] The device provides the user with audio feedback and mental health dialogue scripts received from the server. It receives script data from the server as input and plays synthesized audio as output, allowing the user to continue learning with confidence.

[0843] 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.

[0844] This invention is an interactive learning system that incorporates an emotion engine to improve the user's learning experience and emotional support. This system analyzes the user's emotions in real time and provides a learning experience that is optimally tailored to the individual's emotional state.

[0845] Server operation

[0846] The server uses pre-registered user identification information to retrieve the user's learning history information from the database. Based on this information, it selects learning problems suitable for the user and generates dialogue corresponding to their content. The generated dialogue includes learning problems, hints, and supplementary explanations. Furthermore, the server receives the user's voice input data and performs emotion analysis via an emotion engine. Based on the emotion data, it evaluates the user's stress level and emotional state and provides mental and emotional care as needed.

[0847] Terminal operation

[0848] The device presents the conversation content received from the server to the user using speech synthesis technology. When the user answers a question verbally, the device converts the voice input into text data and sends it to the server. The device also receives feedback from the server and communicates it to the user verbally. Based on the emotional data analyzed by the emotion engine, the device provides appropriate emotional feedback and mental support during the learning process.

[0849] User actions

[0850] Users can answer learning questions presented on the device using voice. The user's responses and voice tone are analyzed by an emotion engine, which evaluates the user's psychological state in real time. If the user experiences high stress levels, the device switches to a conversational mode that provides mental care via a server. In this way, users can progress through their learning while receiving an optimal learning experience and emotional support tailored to their individual learning needs.

[0851] As a concrete example, consider a scenario where a user is working on a math problem and the system detects signs of anxiety from the user's voice. In this case, the server generates a specific care dialogue through its emotion engine, providing the user with reassuring encouragement and additional explanations. This process allows for effective learning outcomes while alleviating user stress.

[0852] This invention is expected to improve the quality of learning by simultaneously providing learners with personalized learning and immediate emotional support.

[0853] The following describes the processing flow.

[0854] Step 1:

[0855] The server receives the user's identification information and accesses the database to retrieve the user's learning history. This information includes past results on problems, response times, and points earned for incorrect answers.

[0856] Step 2:

[0857] The server analyzes the acquired learning history to identify the user's strengths and weaknesses. Based on these results, it automatically selects the most effective learning problems for the user.

[0858] Step 3:

[0859] Based on the selected learning questions, the server generates dialogue content. This generated dialogue includes details about the question, hints to help solve it, and messages to encourage learning. This content is then prepared for transmission to the terminal.

[0860] Step 4:

[0861] The terminal receives the conversation content from the server and outputs it to the user as speech using speech synthesis technology. The user listens to the presented learning questions in audio. The terminal also waits for voice input from the user.

[0862] Step 5:

[0863] The user responds verbally to questions presented by the device. The device converts this voice input into text data. This text data is sent to a server and used for analysis.

[0864] Step 6:

[0865] The server analyzes the received text data and determines whether the user's answer is correct or incorrect. Based on the determination result, it creates feedback and generates customized messages according to the user's learning progress.

[0866] Step 7:

[0867] The device outputs feedback sent from the server as audio to the user. This feedback includes justified answers and explanations to correct misunderstandings.

[0868] Step 8:

[0869] The server uses an emotion engine to analyze the user's emotional state from their voice tone and content. If this analysis detects emotions such as anxiety, stress, or joy, it takes appropriate action.

[0870] Step 9:

[0871] If the user's emotions indicate high levels of stress or anxiety, the server uses an emotion engine to generate mental health support dialogue. The device then communicates this to the user verbally to encourage relaxation.

[0872] Step 10:

[0873] The server stores information about learning results and emotions in a database and updates the user's learning profile. This allows for a more refined learning plan to be suggested for the next session.

[0874] (Example 2)

[0875] 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".

[0876] This invention aims to solve the problem in conventional learning systems where it is difficult to accurately grasp and adjust to the individual learning needs and emotional state of users in real time. In particular, it addresses the problem that learning effectiveness decreases when users are under high stress, and aims to improve the quality of the learning experience by providing individualized mental support.

[0877] 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.

[0878] In this invention, the server includes means for acquiring learning history information using user identification information and selecting educational tasks optimized for the user; means for dynamically generating dialogue content based on the selected educational tasks and presenting it to the user using speech synthesis technology; and means for receiving the user's voice input, converting it into text data, and analyzing the text data. This provides a personalized learning experience and enables mental support tailored to the user's emotional state.

[0879] "Identification information" refers to information used to uniquely identify a user, and includes, for example, user IDs and registered personal information.

[0880] "Learning history information" is a collection of information about the learning content, grades, and progress that a user has undertaken so far, and is used to plan future learning activities.

[0881] "Educational tasks" are specific problems or assignments set up to help users progress in their learning, and are selected according to the user's learning needs.

[0882] "Emotional state" refers to the user's emotional state and is information that evaluates the user's psychological and emotional state detected from voice input and other data.

[0883] "Mental care dialogue content" refers to dialogue content provided by the system that includes encouraging and relaxing messages, with the aim of reducing the user's psychological burden.

[0884] A "generative AI model" is an artificial intelligence model that learns from a large amount of data and is used to generate an output for a given input.

[0885] A "prompt sentence" is a sentence in the form of an instruction or question that is input into a generative AI model to obtain a specific output, and it forms the basis on which the AI ​​generates an appropriate response.

[0886] "Speech synthesis technology" is a technology that converts text data into speech data, and is used to convey the content of a conversation to the user in voice.

[0887] "Speech recognition technology" is a technology that converts speech into text data or a machine-readable format, and is used to process a user's verbal input as digital information.

[0888] This invention provides an interactive learning system that optimizes the user's learning experience and provides emotional support. This system mainly consists of three elements: a server, a terminal, and a user.

[0889] The server receives user identification information and retrieves learning history information from the database. This information is used to select the most appropriate educational tasks based on the user's learning progress. Based on the selected tasks, dialogue content is generated and presented to the user using speech synthesis technology. Specifically, common speech synthesis software such as Google TTS or Amazon Polly can be used for speech synthesis.

[0890] The device has the functionality to present the conversation content sent from the server to the user as audio. When the user provides an audio response, the device uses speech recognition technology (e.g., Google Speech-to-Text) to convert the audio into text data and send it to the server. This process ensures that the user's response is reflected in real time.

[0891] Users verbally respond to presented educational tasks, and the system performs sentiment analysis based on their voice. The server utilizes a generative AI model to analyze the user's voice input and evaluate their emotional state. Based on the analysis results, the server generates mental care dialogues as needed and provides adaptive feedback. An example of a prompt to the generative AI model is, "Generate an appropriate message to alleviate the stress the user is feeling." This allows the user to concentrate on learning with a sense of security.

[0892] As a concrete example, let's explain how the system behaves when it detects anxiety from the user's voice while they are working on a math problem. In this case, the server uses a generative AI model to generate a mental support dialogue such as, "It's okay, there's no need to rush. Let's solve it little by little," and provides it to the user through the terminal. This process reduces the user's stress and provides an effective learning experience.

[0893] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0894] Step 1:

[0895] The server receives user identification information, accesses the database, and retrieves learning history information. The input is the user's identification information, and the output is the user's past learning history information. This data serves as the basis for selecting the most suitable educational tasks for the user. Specifically, the server executes a database query using the identification information as the key and extracts the corresponding learning history.

[0896] Step 2:

[0897] The server analyzes the acquired learning history information and selects educational tasks appropriate to the user's current learning stage. The input is learning history information, and the output is educational tasks optimized for the user. In this process, the server dynamically determines appropriate tasks by considering the user's strengths and weaknesses. Specifically, it uses an algorithm to select tasks, taking into account past performance and the passage of time.

[0898] Step 3:

[0899] The server generates dialogue content based on the selected educational task and creates a dialogue script to present to the user using a generative AI model. The input is the educational task, and the output is the dialogue content. Specifically, by inputting prompt sentences into the AI ​​model, a script in a natural dialogue format is generated.

[0900] Step 4:

[0901] The server sends the generated dialogue content to the terminal. The input is the dialogue content, and the output is the transmission of data to the terminal. Specifically, it sends the data in packet format to the terminal via the network and confirms receipt.

[0902] Step 5:

[0903] The terminal converts received dialogue into speech and presents it to the user. The input is the dialogue from the server, and the output is the speech that the user can hear. Specifically, speech synthesis technology is used to convert text into speech data, which is then output through the speaker.

[0904] Step 6:

[0905] The user responds to the presented educational task verbally. The input is the user's verbal response, and the output is audio data recorded on the device. This response is processed as text in the next step.

[0906] Step 7:

[0907] The terminal converts the user's voice into text data and sends it to the server. The input is the user's voice data, and the output is text data. Specifically, it uses speech recognition software to convert the voice to text and sends it to the server as text data.

[0908] Step 8:

[0909] The server analyzes the received text data and evaluates the user's emotional state. The input is text data, and the output is the result of the emotional analysis. Specifically, a generative AI model is used to analyze the text and quantify the emotional state.

[0910] Step 9:

[0911] The server generates necessary mental care dialogues based on the emotion analysis results. The input is data on the emotional state, and the output is the mental care dialogue. Specifically, prompts corresponding to the emotional state are input to the AI ​​model, which then generates appropriate feedback messages.

[0912] Step 10:

[0913] The terminal converts mental health care dialogues from the server into audio and presents them to the user. The input is mental health care dialogue data, and the output is an audio message presented to the user audibly. This step is also achieved using speech synthesis technology.

[0914] (Application Example 2)

[0915] 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".

[0916] Conventional learning support systems have struggled to provide individualized learning experiences and to adequately alleviate users' mental pressure while providing support. Furthermore, in the in-store purchasing experience, there is a lack of means to suggest products that take into account the emotions and mental state of customers, resulting in a challenge in stimulating sufficient purchasing intent.

[0917] 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.

[0918] In this invention, the server includes means for acquiring the user's learning history information and selecting learning content optimized for the user; means for dynamically generating dialogue content based on the selected learning content; means for receiving the user's voice input, converting it into text data, and analyzing the text data; means for providing feedback to the user based on the analysis results; means for detecting the user's mental pressure and providing dialogue content for mental care as needed; means for presenting optimized product information based on the user's purchasing behavior; means for analyzing the user's mental pressure and emotional state in real time and making appropriate product suggestions; and means for generating prompt sentences using a generation AI model according to the user's selection.

[0919] This allows users to receive a personalized learning experience while reducing mental pressure, and furthermore, receiving emotionally resonant product suggestions in physical stores can stimulate their desire to purchase.

[0920] "Learning history information" refers to information that records what a user has learned in the past and their progress.

[0921] "Learning content" refers to the assignments and learning materials that users use for their studies.

[0922] "Dialogue content" refers to the content of communication exchanged between the user and the system, which is generated according to the purpose of learning or support.

[0923] "Voice input" refers to the audio data that users use to give instructions or responses to a system.

[0924] "Text data" refers to data obtained by converting voice input into a written format for analysis and understanding.

[0925] "Feedback" refers to the system's response and evaluation of user behavior and learning, and is intended to support user learning.

[0926] "Mental pressure" refers to the psychological burden and stress that users experience.

[0927] "Mental care" refers to the support and assistance provided to users to alleviate their mental stress and maintain their mental health.

[0928] "Purchasing behavior" refers to the series of actions a user takes when purchasing goods inside or outside a store.

[0929] "Product information" refers to information about products offered in physical stores or online, including their characteristics, specifications, price, and intended use.

[0930] A "generative AI model" refers to artificial intelligence technology that dynamically generates content according to the user's requests and objectives.

[0931] A "prompt statement" is a guidance statement created to give instructions or commands to a generative AI model so that it can function properly.

[0932] The system for realizing this invention consists of a server, a terminal, and a user who operates them. The server first acquires the user's learning history information and selects optimized learning content. Based on this selected learning content, it dynamically generates dialogue content. Data entered by the user via voice is received by the terminal and converted into text data via a speech recognition engine. These processes utilize terminals equipped with high-performance microphones and speech recognition technology using Nvidia Jetson.

[0933] Based on the analysis results, the server generates feedback and provides it to the user. If the user's mental stress is detected, it automatically generates dialogue content for mental care and provides immediate feedback. It also analyzes the user's purchasing behavior and presents product information that reflects their emotional state in real time. Specifically, it captures the customer's facial expressions with a camera and evaluates their emotions using facial expression analysis technologies such as the Microsoft Azure Emotion API.

[0934] Furthermore, the system constructs prompt messages based on a generative AI model, providing optimal information tailored to the user's choices and requests. This allows users to customize their learning and purchasing experience while stimulating their interest. For example, by analyzing a customer's prolonged viewing of a particular product, the system can offer customer service with a prompt such as, "It appears you are interested in this product; do you have any questions?"

[0935] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0936] Step 1:

[0937] The server retrieves the user's learning history information from the database. Based on this input information, it selects learning content optimized for the user. This selection process analyzes the user's past learning trends and performance to determine the most effective content. As a result, appropriate learning content is output.

[0938] Step 2:

[0939] The server dynamically generates dialogue content based on the selected learning content. Using a generation AI model, it creates the learning flow, hints, and supplementary explanations to present to the user, depending on the input learning content. Prompts designed to enhance the user's motivation are also set here. This output is dialogue content data for use on the terminal.

[0940] Step 3:

[0941] The user provides voice input to the device. The device receives this voice data and converts it into text data using speech recognition technology. The speech recognition engine, using Nvidia Jetson, analyzes the input voice data and obtains the corresponding text output. The converted text data is sent to the server.

[0942] Step 4:

[0943] The server analyzes text data to understand user responses. This analysis utilizes natural language processing techniques, including grasping the intent and emotions contained in the user's answers. Based on the analysis results, the server generates feedback for the user and sends it to their device. This feedback supports the user's learning and facilitates a better learning experience.

[0944] Step 5:

[0945] The device receives feedback from the server and presents it to the user verbally using speech synthesis technology. It also collects the user's facial expressions and voice tone using a camera and microphone to monitor their emotional state in real time. Using the Microsoft Azure Emotion API, it analyzes the input image and audio data to evaluate their emotional state. Based on this, necessary mental health support dialogues are simultaneously generated and provided as feedback to the user.

[0946] Step 6:

[0947] The device observes user purchasing behavior and analyzes customer interests through its camera. Based on the input video data, it evaluates customer gaze and pacing time, and provides real-time product information in combination with sentiment analysis. The selected product information is generated as prompt text using an AI model and output to the user via voice or display.

[0948] 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.

[0949] 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.

[0950] 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 robot 414.

[0951] 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.

[0952] 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.

[0953] 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.

[0954] 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.

[0955] 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.

[0956] 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."

[0957] 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.

[0958] 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.

[0959] 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.

[0960] 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.

[0961] 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.

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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 as being incorporated by reference.

[0969] The following is further disclosed regarding the embodiments described above.

[0970] (Claim 1)

[0971] A means for acquiring the user's learning history information and selecting learning problems optimized for the user,

[0972] A means for dynamically generating dialogue content based on the selected learning questions,

[0973] A means for receiving user voice input, converting it into text data, and analyzing the text data,

[0974] A means of providing feedback to users based on the analysis results,

[0975] A means for detecting a user's mental stress and providing dialogue content for mental care as needed,

[0976] A means of recording the user's learning results and updating the learning profile for the next session,

[0977] A system that includes this.

[0978] (Claim 2)

[0979] The system according to claim 1, configured to adjust the content of feedback in real time based on the user's response.

[0980] (Claim 3)

[0981] The system according to claim 1, configured to use speech recognition and analysis techniques in detecting the user's mental stress.

[0982] "Example 1"

[0983] (Claim 1)

[0984] A means for obtaining learner history information from information storage and selecting personalized tasks for the learner,

[0985] A means for dynamically generating conversation content based on the selected topic,

[0986] A means for receiving voice input from learners, converting it into text data, and analyzing the text data,

[0987] Means of providing information to learners based on the analysis results,

[0988] A means of detecting learners' mental burden and providing conversational content for psychological support as needed,

[0989] A means of recording learner performance and updating learning profiles for subsequent sessions,

[0990] A system that includes this.

[0991] (Claim 2)

[0992] The system according to claim 1, configured to adjust information in real time based on learner responses.

[0993] (Claim 3)

[0994] The system according to claim 1, configured to use speech recognition and analysis techniques in detecting the mental burden on learners.

[0995] "Application Example 1"

[0996] (Claim 1)

[0997] A means for acquiring user history information and selecting educational questions optimized for the user,

[0998] A means for dynamically generating dialogue content based on the selected educational questions,

[0999] A means for receiving user voice input, converting it into text information, and analyzing the text information,

[1000] A means of providing a response to the user based on the analysis results,

[1001] A means for detecting the user's mental stress and providing mental health-related dialogue content as needed,

[1002] A means of recording the user's learning progress and updating the learning images for the next interaction,

[1003] A means of implementing this system in machinery and equipment intended to support the learning and mental well-being of on-site workers,

[1004] A system that includes this.

[1005] (Claim 2)

[1006] The system according to claim 1, configured to adjust the response content in real time based on the user's response.

[1007] (Claim 3)

[1008] The system according to claim 1, configured to use speech recognition and analysis methods for detecting the user's mental tension.

[1009] "Example 2 of combining an emotion engine"

[1010] (Claim 1)

[1011] A means for obtaining learning history information using user identification information and selecting educational tasks optimized for the user,

[1012] A means for dynamically generating dialogue content based on the selected educational topics and presenting it to the user using speech synthesis technology,

[1013] A means for receiving user voice input, converting it into text data, and analyzing the text data,

[1014] A means to evaluate the user's emotional state based on the analysis results and measure their stress level,

[1015] A means of adaptively providing mental care dialogue content according to the user's emotional state and adjusting feedback in real time,

[1016] A means of recording the user's learning results and emotional state, and updating the learning profile for the next session,

[1017] A system that includes this.

[1018] (Claim 2)

[1019] The system according to claim 1, which uses a generative AI model to analyze voice input and applies prompt sentences to generate feedback content.

[1020] (Claim 3)

[1021] The system according to claim 1, which utilizes speech recognition technology when performing emotion analysis from user voice data.

[1022] "Application example 2 of combining emotional engines"

[1023] (Claim 1)

[1024] A means for acquiring a user's learning history information and selecting learning content optimized for the user,

[1025] A means for dynamically generating dialogue content based on the selected learning content,

[1026] A means for receiving user voice input, converting it into text data, and analyzing the text data,

[1027] A means of providing feedback to users based on the analysis results,

[1028] A means for detecting the user's mental pressure and providing dialogue content for mental care as needed,

[1029] A means of presenting optimized product information based on the user's purchasing behavior,

[1030] A means of analyzing the user's mental pressure and emotional state in real time and making appropriate product recommendations,

[1031] A means of generating prompt sentences using a generation AI model according to the user's selection,

[1032] A system that includes this.

[1033] (Claim 2)

[1034] The system according to claim 1, configured to adjust feedback content in real time based on user responses and to provide product information based on purchase intent.

[1035] (Claim 3)

[1036] The system according to claim 1, configured to use speech recognition and facial expression analysis technology in detecting the user's mental pressure. [Explanation of Symbols]

[1037] 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 acquiring the user's learning history information and selecting learning problems optimized for the user, A means for dynamically generating dialogue content based on the selected learning questions, A means for receiving user voice input, converting it into text data, and analyzing the text data, A means of providing feedback to users based on the analysis results, A means for detecting a user's mental stress and providing dialogue content for mental care as needed, A means of recording the user's learning results and updating the learning profile for the next session, A system that includes this.

2. The system according to claim 1, configured to adjust the content of feedback in real time based on the user's response.

3. The system according to claim 1, configured to use speech recognition and analysis techniques for detecting the user's mental stress.

Images