system

Abstract

We provide the system. [Solution] A means of collecting and analyzing data from multiple learners, A means for organizing the learners into optimal groups based on the above analysis, A means of providing topics to facilitate communication among the aforementioned group, A means of searching for and providing hints and reference materials for the problem, A means of monitoring messages between learners and detecting signs of trouble, 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 as a 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 a conventional educational environment, insufficient communication among students and imbalance in group learning activities often pose problems. Also, the burden on teachers to manage the progress of collaborative learning is large, and furthermore, it is difficult to detect early signs of trouble or bullying among students, so it is required to solve this problem and cultivate the social skills of students.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for collecting and analyzing data from multiple learners. This system has means for organizing learners into optimal groups based on the analysis and means for providing topics to facilitate communication. Furthermore, it has means for searching for and providing hints and reference materials for tasks, and means for monitoring messages between learners and detecting signs of trouble, thereby enabling early detection of problems and notification to educators, and solving the aforementioned problems by providing guides to encourage learners to solve problems themselves.

[0006] The term "learner" refers to students or pupils who engage in learning activities at an educational institution.

[0007] "Data collection" refers to the process of electronically gathering information about learners, including their learning progress, interests, and past activity history.

[0008] "Analysis" is the process of transforming collected data into meaningful information to understand the characteristics and needs of learners.

[0009] "Group formation" is the act of organizing optimal learning groups based on the results of learner data analysis, with the aim of maximizing learning effectiveness.

[0010] A "communication topic" refers to a subject or theme provided to facilitate dialogue and discussion among learners.

[0011] A "hint" is information or instructions that help learners solve a problem.

[0012] "Reference materials" refer to literature and content that supplement the knowledge and information related to the assignment.

[0013] "Monitoring" is a method of monitoring the communication and behavior among learners to detect early signs of unexpected problems or troubles.

[0014] "Trouble" refers to an undesirable situation that includes problems and bullying that occur among learners.

[0015] "Self - solution guide" refers to the guidelines and support information provided to assist learners in solving problems on their own.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It 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

[0017] 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.

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] 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.

[0021] 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

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

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system designed to facilitate learner communication and enable effective collaborative learning. At the core of the system is an AI agent that collects and analyzes data from multiple learners, providing optimal group formation and smooth communication. This agent operates on a server and provides services to learners in real time as needed.

[0038] Data collection and analysis

[0039] Server: Retrieves learning history and interest data accumulated through learners' accounts. This data is stored in cloud storage and managed securely.

[0040] Device: Learners can input data through an intuitive UI for setting interests and goals. The input data is sent to the server and automatically added to the learner's profile.

[0041] Group Formation

[0042] Server: Using an AI algorithm, the server automatically creates optimal group formations based on each learner's data. Here, it considers learners' interests and the results of previous group activities to create well-balanced groups.

[0043] Communication support

[0044] Devices: Each learner's device displays discussion topics designed to facilitate effective communication within the group. These topics are generated based on daily news and the learners' interests.

[0045] User: Learners can engage in discussions and deepen their interactions based on the provided themes. The AI ​​provides additional questions and relevant information in real time to further stimulate the conversation.

[0046] Support for problem solving

[0047] Server: Searches for relevant textbooks and reference materials in response to assignments entered by learners. The AI ​​understands the context and presents the most relevant information.

[0048] Device: Links to helpful hints and resources for assignments are displayed, allowing learners to use them to progress autonomously in their studies.

[0049] Trouble detection and response

[0050] Server: Monitors chat content using natural language processing technology and immediately notifies educators if there are signs of trouble such as bullying or conflict.

[0051] Device: For minor issues, the system automatically provides guides to help learners resolve the problem themselves.

[0052] This system allows learners to engage in group activities through smooth communication and deepen their understanding of the assigned tasks. In addition, it reduces the burden on educators of monitoring student relationships and activities, enabling them to carry out their teaching duties more efficiently.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] The server collects learner basic information, learning history, and interest data from a cloud database and updates the data to the latest state. It also adds data for new learners if available.

[0056] Step 2:

[0057] The device displays a question form to the learner regarding their interests and learning goals, and sends the entered data to the server. This keeps the learner's profile up-to-date.

[0058] Step 3:

[0059] The server then uses the collected data to begin analysis with an AI algorithm. It evaluates each learner's learning style and interests, and extracts the information necessary for group formation.

[0060] Step 4:

[0061] The server organizes learners into optimal groups based on the analysis results. Here, it determines combinations that maximize the balance and learning effectiveness of each learner.

[0062] Step 5:

[0063] The device notifies learners of the new group's member list and the topic for group discussion. This allows learners to check their group and prepare to engage in the activity.

[0064] Step 6:

[0065] The learners, as users, begin activities to exchange ideas and engage in discussions within their groups based on the provided topic. This stimulates communication among learners.

[0066] Step 7:

[0067] The server monitors the content and flow of the discussion and generates and provides additional questions and support information to ensure smooth communication.

[0068] Step 8:

[0069] The server searches databases and external resources for relevant information regarding the submitted problem and selects hints and reference materials that can help solve it.

[0070] Step 9:

[0071] The device displays selected hints and materials to the learner, supporting them in independently working on problem-solving.

[0072] Step 10:

[0073] The server analyzes chat content using natural language processing technology to detect signs of trouble and terms related to bullying. If a problem is detected, it notifies the educator without delay.

[0074] Step 11:

[0075] For minor issues, the device will provide learners with individual self-help guides to support them in proactively resolving problems.

[0076] Through these steps, the PeerConnect system supports smooth communication among learners, promotes improved collaborative learning outcomes, and prevents problems from occurring.

[0077] (Example 1)

[0078] 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."

[0079] This invention aims to solve the problems of conventional collaborative learning systems, such as insufficient communication among learners and difficulty in forming groups appropriate to the learning progress. It also aims to support educators in quickly detecting problems among learners and responding appropriately.

[0080] 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.

[0081] In this invention, the server includes means for collecting and analyzing learner information, means for organizing the learners into optimal groups based on the analysis, and means for providing topics to promote interaction among the groups. This enables smooth communication among learners, realizes an optimal collaborative learning environment, and allows for early response in the event of trouble.

[0082] A "learner" refers to an individual who participates in an educational program and seeks to acquire knowledge.

[0083] "Means for collecting and analyzing information" refers to a system that collects data obtained from learners and analyzes it using analytical algorithms.

[0084] "Methods for forming optimal groups" refers to algorithms that automatically form groups based on learners' characteristics and interests.

[0085] "Means of providing topics to promote interaction" refers to a mechanism that presents relevant themes and discussion topics to stimulate communication among learners.

[0086] "Means for detecting signs of problems" refers to technologies that monitor the content of communication between learners and detect the occurrence of troubles or conflicts at an early stage.

[0087] "Educational personnel" refers to teachers and educational staff who are responsible for guiding and supporting learners.

[0088] "Means of displaying guidance" refers to interfaces and methods for presenting information and procedures that are helpful when learners attempt to solve problems on their own.

[0089] This invention is a system for facilitating collaborative learning among learners, and it functions through the combination of server, terminal, and user elements. An embodiment of this system is shown below.

[0090] The server uses a cloud platform to collect and manage learner information. Specifically, it uses a general-purpose cloud storage service to securely store learner account information and learning history. For information analysis, it uses machine learning frameworks such as TENSORFLOW® or PyTorch to perform data calculations to classify learners' interests and characteristics based on the data obtained.

[0091] The device provides an interface with the learner, using front-end frameworks such as React and Angular to provide an intuitive and user-friendly environment. This allows learners to easily set their goals and interests on the device, and this information is sent to the server in real time, contributing to profile updates.

[0092] Based on the information above, the server uses an AI algorithm to organize learners into optimal groups. An example of such an algorithm is the K-Nearest Neighbors (KNN) method, which analyzes the similarity of learners' attributes to form balanced groups.

[0093] Furthermore, discussion topics generated using a generative AI model are displayed on the device, allowing learners to interact based on those topics. For example, a prompt such as, "What efforts do you think are necessary to reduce the impacts of global warming?" might be used.

[0094] In communication between users, i.e., learners, the system uses natural language processing technology to monitor conversation content and notifies educators if there are signs of trouble. Furthermore, for minor issues, the system displays guidance on the terminal to encourage self-resolution, supporting learners in developing their independent problem-solving abilities.

[0095] Thus, the present invention provides an integrated system for facilitating smooth communication and collaborative learning among learners, enabling its effective use in educational settings.

[0096] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0097] Step 1:

[0098] The server receives account information, learning history, and interest data sent from the learner's device and stores it in cloud storage. Based on this input, the server encrypts and securely manages the data. The output is learner information stored in encrypted format.

[0099] Step 2:

[0100] The server analyzes the stored data. This analysis uses a machine learning framework to perform data calculations that identify the learner's interests and characteristics. Specifically, a model using TensorFlow performs data clustering. The input is the learner's historical data, and the output is a profile based on interests and characteristics.

[0101] Step 3:

[0102] The server uses an AI algorithm based on the analysis to form the optimal learning groups. Here, the K-Nearest Neighbors (KNN) algorithm is used to compare the attributes of the learners and determine the most suitable group for each of them. The input is profile information, and the output is the group formation result.

[0103] Step 4:

[0104] The terminal receives group information sent from the server and notifies the user. It then displays discussion themes generated by a generative AI model. Specifically, it uses natural language processing to construct highly relevant themes and provides them as prompts. The input is group information, and the output is the displayed discussion themes.

[0105] Step 5:

[0106] Users engage in discussions with other learners based on themes provided via their devices. During this process, AI provides additional prompts to encourage further dialogue. The input is the discussion theme, and the output is the communication between users.

[0107] Step 6:

[0108] The server constantly monitors user communication and uses natural language processing to detect signs of trouble. If a problem is detected, a notification is sent to the educator. For minor issues, instructions are displayed on the device to encourage self-resolution. Input is communication data, and output is trouble detection and notification, or presentation of instructions.

[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] Traditional learning platforms struggle to effectively facilitate interaction and collaborative learning among learners. Furthermore, they lack the functionality to proactively detect and appropriately address communication imbalances and problems that may arise during group learning. Additionally, there is a current lack of support for learners to deepen discussions based on their own interests and to effectively advance their learning.

[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 collecting and analyzing information on multiple users, means for organizing the users into an optimal group based on the analysis, means for providing topics to facilitate interaction among the groups, means for searching for and providing advice and reference information on tasks, and means for generating questions to stimulate discussion based on the presented topics. This enables learners to achieve deep learning through smooth communication and to effectively conduct group activities. Furthermore, by detecting signs of problems early and taking appropriate action, a safe and secure learning environment can be provided.

[0114] "Users" refers to individuals or groups that use the system, and in this case, it means people who participate in learning activities.

[0115] "Information" refers to data that users provide to the system, including their interests, the activities they participate in, and their past learning history.

[0116] "Analysis" is the process of evaluating collected information and understanding the characteristics and needs of users.

[0117] A "group" is a collection of users with common interests or goals that are formed when a system optimally organizes its user groups.

[0118] "Interaction" refers to communication, information sharing, and exchange of opinions among users, and the system aims to facilitate these activities.

[0119] "Topics" refer to themes and topics provided by the system to stimulate dialogue among users.

[0120] "Advice" refers to specific suggestions or methods that the system provides to users to help them solve problems.

[0121] "Reference information" refers to relevant materials and information that the system collects and presents to support the user's learning activities.

[0122] "Generating questions" is the process by which a system automatically creates relevant questions to deepen the discussion among users.

[0123] "Signs of a problem" refers to potential troubles lurking in communication between users, and detecting these is part of the system's monitoring function.

[0124] The main components of the system implementing this invention are a server, a terminal, and an AI agent. The server is built using Flask in Python and uses Pandas or Scikit-learn for data collection and analysis. The AI ​​agent generates a natural language processing model using TensorFlow or PyTorch. In this system, the server collects information from multiple users and stores it in a database. This aggregates the interests and past learning history of each individual user.

[0125] The server analyzes the collected data and uses Scikit-learn to organize users into optimal groups. These groups consist of users with common interests and goals, promoting effective collaborative learning. Furthermore, the server provides topics to encourage interaction among the devices, facilitating the initiation of natural communication.

[0126] The device uses a generative AI model to generate questions to stimulate discussion based on the provided topic. This model understands the context and presents topics that are easy for the user to talk about and that are of interest to them. For example, using a prompt such as "Please provide appropriate questions and information to discuss global warming based on the latest news" enables the generation of appropriate questions.

[0127] The terminal further searches for and provides advice and reference information related to tasks. By utilizing the provided reference information, users can develop problem-solving skills and proceed with learning autonomously. In addition, by monitoring communication between users and detecting signs of problems, a safe and secure learning environment can be provided. This system enables users to achieve deep learning through smooth communication and to conduct group activities effectively.

[0128] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0129] Step 1:

[0130] The server collects information from the user's device. It receives data such as the user's interests, goals, and past learning history as input, and stores it in a cloud database. At this stage, data transformation and cleansing are performed, and the data is stored in a standardized format.

[0131] Step 2:

[0132] The server analyzes the aggregated data. The input is the user data collected in Step 1, and a clustering algorithm is performed using Pandas and Scikit-learn. This identifies patterns in the user data and outputs the optimal grouping based on similarity.

[0133] Step 3:

[0134] The server selects topics to facilitate interaction among the generated group and sends them to the terminal. Input consists of current events and user profile information, and the AI ​​model uses this information to select relevant topics. The output is content presented to the user's terminal as part of that topic.

[0135] Step 4:

[0136] The terminal uses a generative AI model to generate questions to stimulate discussion based on the presented topic. The input is a topic sent from the server, and the output is the generated related questions presented to the user. The generative AI model utilizes natural language processing techniques to automatically create contextually appropriate questions.

[0137] Step 5:

[0138] The terminal accesses the server to search for helpful advice and reference information for the problem and provides it to the user. The input is the problem the user wants to solve, and the output is related materials and information links displayed on the terminal. The server processes the search query in response and selects the most relevant information.

[0139] Step 6:

[0140] The server monitors communication between users and detects signs of problems. Its input is real-time chat logs, and it uses a natural language processing model to detect issues. When a problem is detected, it notifies the instructor and prompts intervention if necessary.

[0141] 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.

[0142] This invention is a technology that facilitates smoother communication among learners by using a system that implements an emotion engine. This system is deployed on a server in the cloud and on the learner's terminal, and is designed to allow for real-time monitoring of learning progress and emotional state.

[0143] Data collection and emotion recognition

[0144] The server continuously collects and stores data such as learners' basic information, interests, and past learning history for analysis. In addition to this data, the emotion engine analyzes each learner's facial expressions, tone of voice, and input content to recognize their current emotional state in real time.

[0145] The device provides an interface for acquiring learner emotion data through voice and camera input. The acquired data is sent to a server and evaluated by an emotion engine.

[0146] Group formation and communication support

[0147] The server organizes optimal learning groups based on each learner's emotional state, interest data, and learning history. This process involves creating groups with balanced emotional states to facilitate smooth communication.

[0148] The device notifies learners of new group information and discussion topics tailored to their emotional state. For example, if the emotion engine detects that the learner is "happy," a positive topic such as "Let's share something funny that happened recently" will be provided.

[0149] Problem solving and emotional management

[0150] The learner, as the user, can work on assigned tasks and search for related information through their device. The server checks their emotional state and, if it determines they are experiencing stress, provides more easily understandable hints.

[0151] Trouble detection and emotional support

[0152] The server uses natural language processing technology to monitor messages between learners. If signs of trouble or negative emotions are detected, it immediately notifies the educator and prompts mediation as needed.

[0153] The device effectively supports self-reliance by displaying encouraging messages and positive feedback to alleviate negative emotions identified by the emotion engine in the learner.

[0154] This system allows learners to engage in collaborative learning in an environment that takes individual emotions into consideration, and enables educators to understand students' emotional states and group dynamics, thereby conducting educational activities more effectively.

[0155] The following describes the processing flow.

[0156] Step 1:

[0157] The server retrieves learner's basic information, learning history data, and interest profiles from a cloud database and prepares them for analysis.

[0158] Step 2:

[0159] The device uses a camera and microphone to capture the learner's facial expressions and voice, and transmits this data to a server in real time. This data is then analyzed by an emotion engine.

[0160] Step 3:

[0161] The server uses an emotion engine to analyze received facial and voice data and assess the learner's current emotional state. The results are reflected in each learner's profile.

[0162] Step 4:

[0163] The server applies an optimization algorithm to organize learning groups based on emotional states and other learning parameters. In this process, members are selected while considering emotional balance.

[0164] Step 5:

[0165] The device notifies the learner of the group they belong to and the associated communication topics. Topics are dynamically selected, taking into account the learner's emotional state.

[0166] Step 6:

[0167] The learner user initiates a discussion within the group based on a topic provided through their device. If the emotion engine detects positive emotions, the server may recommend additional positive events.

[0168] Step 7:

[0169] The server monitors the discussion content and uses natural language processing to detect signs of trouble or negative emotional expression. In cases where necessary, it sends notifications to educators.

[0170] Step 8:

[0171] The device uses an emotion engine to display suggestion messages and positive feedback to alleviate negative emotions and support learners.

[0172] Step 9:

[0173] When users work on assignments, they can access reference materials and hints sent from the server via their device, deepening their learning at their own pace. The emotion engine, if it detects stress, instructs the server to provide further hints.

[0174] These processing steps allow learners to enjoy an emotionally sensitive collaborative learning environment, and enable educators to grasp students' emotional developments in a timely manner.

[0175] (Example 2)

[0176] 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".

[0177] Traditional education systems have struggled to provide an effective collaborative learning environment that takes learners' emotional states into account. As a result, there have been problems such as poor communication among learners and limited learning effectiveness. Furthermore, there have been insufficient mechanisms for early detection of troubles and signs of problems and for appropriate intervention.

[0178] 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.

[0179] In this invention, the server includes means for acquiring and analyzing information on multiple learners, means for placing the learners into the most suitable group based on the analysis, and means for monitoring messages between learners and detecting signs of problems. This makes it possible to recognize the emotional state of learners in real time and provide support that is appropriate to their emotions.

[0180] "Educational participant" refers to an individual who participates in educational activities and engages in learning.

[0181] "Means of acquiring and analyzing information" refers to the process of collecting data on educational participants and processing and analyzing that data to understand the attributes and status of the participants.

[0182] "Methods for group placement" refers to the process of organizing educational participants into the most suitable groups based on the analysis results, thereby promoting collaborative learning.

[0183] "Means of monitoring messages and detecting early signs of problems" refers to a process of monitoring communication among trainees to detect potential troubles or problems early on.

[0184] "Means of recognizing emotional states" refers to a process that determines the emotions of trainees in real time by analyzing their facial expressions, voice, and input content.

[0185] "Means of providing support tailored to emotions" refers to the process of providing appropriate guidance and feedback to individual participants based on their recognized emotional state.

[0186] This invention is a system designed to recognize the emotions of learners in real time and optimize their learning. This system consists of a server and terminals and supports collaborative learning among learners.

[0187] The server collects and analyzes a wide range of information about the students, including their basic information, learning history, interests, and real-time input data. This analysis utilizes an emotion engine, which implements algorithms to analyze the students' facial expressions, voice, and input in real time. This emotion engine includes an emotion analysis algorithm written in Python, which classifies the students' emotions into states such as "happy," "sad," and "stressed."

[0188] The device uses a camera and microphone interface to capture the facial expressions and voices of the learners. This data is sent to a server for analysis by an emotion engine. The device also serves to notify learners of new group information and recommended discussion topics. For example, a learner judged to be enjoying themselves might be presented with a discussion topic such as "Let's share something funny."

[0189] The users, who are educational learners, can work on assignments provided by the server. The server monitors the learners' emotional state and provides easy-to-understand hints if it determines that they are experiencing stress. This entire process allows learners to learn efficiently in an emotionally responsive environment.

[0190] Specific examples of using the generative AI model include prompts such as, "Please suggest countermeasures for when the user is feeling stressed," and "Please suggest topics to facilitate a smooth group discussion." In this way, the system can provide support tailored to each participant in real time.

[0191] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0192] Step 1:

[0193] The device acquires information about the student using its camera and microphone. Input includes facial image data and audio data of the student. This data is collected and sent to a server. Specifically, the camera captures images every second, and the microphone records audio. This data is then processed by an emotion engine.

[0194] Step 2:

[0195] The server inputs received facial image and audio data into an emotion engine, which analyzes the emotional state in real time. The emotion engine uses a Python algorithm to perform the analysis and classify the participant's emotions into categories such as "happy," "sad," and "stressed." The output is the analyzed emotional state. Specifically, the server automatically registers the analysis results in a database.

[0196] Step 3:

[0197] The server sends prompt messages to the generative AI model based on the analysis results, and then organizes the optimal learning groups. The input includes the learners' emotional states and past learning history. The generative AI model analyzes the prompts and generates the optimal group configuration as output. Specifically, the server updates the group information based on the generated results.

[0198] Step 4:

[0199] The device notifies participants of newly formed group information and presents discussion topics tailored to their emotional state. Input includes group composition and topic information received from the server. Output consists of notifications and topics displayed on the user interface. Specifically, the device generates a push notification and displays the topic as a pop-up on the screen.

[0200] Step 5:

[0201] Users can work on tasks presented through their devices. While solving problems, they use their devices to search for necessary information. Input includes the task content and hints from the server. Output consists of guidelines and supplementary information to help complete the task without difficulty. Specifically, the server searches for and provides additional materials based on the task selected by the user.

[0202] Step 6:

[0203] The server monitors messages between students and uses natural language processing to detect negative emotions and signs of trouble. The input is chat data, which the monitoring system analyzes. The output is an alert notification to the education support staff. Specifically, keyword-based triggers are built, and notifications are sent immediately when a problem is detected.

[0204] (Application Example 2)

[0205] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0206] In today's learning environment, learners may experience difficulties communicating effectively due to changes in their emotional state. Furthermore, learning programs lacking appropriate task presentation and teaching methods can lead to decreased learner motivation and poor results. Because educators often struggle to understand the emotional states of individual learners and group dynamics, there is a need for support in conducting more effective educational activities.

[0207] 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.

[0208] In this invention, the server includes means for collecting and analyzing user emotional data, means for organizing users into optimal groups based on the analysis, and means for providing topics to facilitate communication among the groups. This enables the provision of an optimal learning environment tailored to the emotional state of learners, and allows educators to conduct effective educational activities while understanding the emotional state of individual learners.

[0209] "User" refers to a learner or individual in an educational environment who utilizes the system of the present invention.

[0210] "Emotional data" refers to information such as facial expressions, tone of voice, and input content that represent the user's emotional state.

[0211] "Means of analysis" refers to the technology that performs a process to interpret the user's emotional state and tendencies based on the emotional data collected.

[0212] "Methods for organizing into groups" refer to methods for organizing users into optimal groups based on analysis results, thereby promoting communication.

[0213] "Topics to facilitate communication" are topics that support active information exchange and opinion sharing among users within a group.

[0214] A "terminal" is a device that the user directly operates and is hardware used for collecting and providing emotional data.

[0215] A "server" is a computer system that serves as the core of the entire system, processing, analyzing, storing, and directing emotional data.

[0216] An "educator" is an individual who acts as a leader in a learning environment and conducts educational activities based on information provided by the system.

[0217] The system for realizing this invention is primarily composed of a server and terminals. In the embodiment of the invention, the server is located on the cloud and collects emotional data from multiple users, processing and analyzing it in real time. The server analyzes emotional data such as the user's facial expressions and voice tone, and uses advanced image processing libraries such as OpenCV and speech analysis technology to evaluate their emotional state.

[0218] The terminal is a device such as a smartphone or smart glasses, which, through direct user operation, collects emotional data via sensors such as cameras and microphones. The collected data is transmitted to a server via the terminal.

[0219] Specifically, the server analyzes the transmitted data and makes decisions to group users into the most suitable learning groups. Furthermore, to facilitate communication among users, it suggests topics based on their interests, and this information is fed back from the server to the terminals.

[0220] For example, by implementing this system in an educational institution, it is possible to analyze the emotional state of each learner. Based on these analysis results, learners with stable emotions can be grouped together, creating an environment where learning activities can proceed smoothly.

[0221] For example, by inputting a prompt such as "Design an AI algorithm that selects topics based on the learner's emotions" into a generating AI model, effective suggestions for learning topics can be achieved.

[0222] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0223] Step 1:

[0224] The device uses a camera and microphone to capture the user's facial expressions and voice tone, collecting emotional data. The input is real-time image and audio data, which is converted into numerical features using an external library (e.g., OpenCV). The output is numerical data of facial expressions and voice tone.

[0225] Step 2:

[0226] The terminal transmits digitized emotional data to the server. The input is the emotional data obtained in step 1, and the output is the data provided to the server in the cloud. Specifically, the Internet protocol is used for data transmission to ensure that the data is transferred securely.

[0227] Step 3:

[0228] The server analyzes the received emotional data to recognize the user's emotional state. The input is emotional data transmitted from the terminal, which is then analyzed using natural language processing techniques and machine learning algorithms. The output is an evaluation result indicating the user's emotional state.

[0229] Step 4:

[0230] The server organizes users into optimal learning groups based on their analyzed emotional states. The input is the evaluation result of the emotional state obtained in step 3, and the output is the group organization decision. Specifically, it uses a database to consider each user's attributes and places them in the most suitable group.

[0231] Step 5:

[0232] The server generates prompt sentences to suggest the most appropriate topics and feeds this information back to the terminal. The input is to generate prompt sentences based on the user's interests using a generative AI model. The output is a communication topic suitable for the user.

[0233] Step 6:

[0234] The terminal presents the user with group information and topics received from the server. Input is the information generated in step 5, and output is information provided through screen displays and audio notifications. Specifically, information is efficiently conveyed through a user-friendly interface.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] [Second Embodiment]

[0239] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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).

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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".

[0251] This invention is a system designed to facilitate learner communication and enable effective collaborative learning. At the core of the system is an AI agent that collects and analyzes data from multiple learners, providing optimal group formation and smooth communication. This agent operates on a server and provides services to learners in real time as needed.

[0252] Data collection and analysis

[0253] Server: Retrieves learning history and interest data accumulated through learners' accounts. This data is stored in cloud storage and managed securely.

[0254] Device: Learners can input data through an intuitive UI for setting interests and goals. The input data is sent to the server and automatically added to the learner's profile.

[0255] Group Formation

[0256] Server: Using an AI algorithm, the server automatically creates optimal group formations based on each learner's data. Here, it considers learners' interests and the results of previous group activities to create well-balanced groups.

[0257] Communication support

[0258] Devices: Each learner's device displays discussion topics designed to facilitate effective communication within the group. These topics are generated based on daily news and the learners' interests.

[0259] User: Learners can engage in discussions and deepen their interactions based on the provided themes. The AI ​​provides additional questions and relevant information in real time to further stimulate the conversation.

[0260] Support for problem solving

[0261] Server: Searches for relevant textbooks and reference materials in response to assignments entered by learners. The AI ​​understands the context and presents the most relevant information.

[0262] Device: Links to helpful hints and resources for assignments are displayed, allowing learners to use them to progress autonomously in their studies.

[0263] Trouble detection and response

[0264] Server: Monitors chat content using natural language processing technology and immediately notifies educators if there are signs of trouble such as bullying or conflict.

[0265] Device: For minor issues, the system automatically provides guides to help learners resolve the problem themselves.

[0266] This system allows learners to engage in group activities through smooth communication and deepen their understanding of the assigned tasks. In addition, it reduces the burden on educators of monitoring student relationships and activities, enabling them to carry out their teaching duties more efficiently.

[0267] The following describes the processing flow.

[0268] Step 1:

[0269] The server collects learner basic information, learning history, and interest data from a cloud database and updates the data to the latest state. It also adds data for new learners if available.

[0270] Step 2:

[0271] The device displays a question form to the learner regarding their interests and learning goals, and sends the entered data to the server. This keeps the learner's profile up-to-date.

[0272] Step 3:

[0273] The server then uses the collected data to begin analysis with an AI algorithm. It evaluates each learner's learning style and interests, and extracts the information necessary for group formation.

[0274] Step 4:

[0275] The server organizes learners into optimal groups based on the analysis results. Here, it determines combinations that maximize the balance and learning effectiveness of each learner.

[0276] Step 5:

[0277] The terminal notifies the learner of the member list of the new group and the topic for group discussion. As a result, the learner can confirm their group and get ready to engage in activities.

[0278] Step 6:

[0279] The learner, who is the user, starts the activity of having discussions and exchanging ideas within the group based on the provided topic. Communication among learners is activated.

[0280] Step 7:

[0281] The server monitors the content and flow of the discussion, and generates and provides additional questions and support information to ensure smooth communication.

[0282] Step 8:

[0283] The server searches for relevant information from the database or external resources for the input task, and selects hints and reference materials useful for solving it.

[0284] Step 9:

[0285] The terminal displays the selected hints and materials to the learner and provides support for the learner to independently work on problem-solving.

[0286] Step 10:

[0287] The server analyzes the chat content using natural language processing technology, detects phrases related to signs of trouble or bullying. If a problem is detected, it notifies the educator without delay.

[0288] Step 11:

[0289] For minor troubles, the terminal presents individual self-solving guides to the learner and provides support for proactively solving the problem.

[0290] Through these steps, the PeerConnect system supports smooth communication among learners, promotes improved collaborative learning outcomes, and prevents problems from occurring.

[0291] (Example 1)

[0292] 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."

[0293] This invention aims to solve the problems of conventional collaborative learning systems, such as insufficient communication among learners and difficulty in forming groups appropriate to the learning progress. It also aims to support educators in quickly detecting problems among learners and responding appropriately.

[0294] 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.

[0295] In this invention, the server includes means for collecting and analyzing learner information, means for organizing the learners into optimal groups based on the analysis, and means for providing topics to promote interaction among the groups. This enables smooth communication among learners, realizes an optimal collaborative learning environment, and allows for early response in the event of trouble.

[0296] A "learner" refers to an individual who participates in an educational program and seeks to acquire knowledge.

[0297] "Means for collecting and analyzing information" refers to a system that collects data obtained from learners and analyzes it using analytical algorithms.

[0298] "Methods for forming optimal groups" refers to algorithms that automatically form groups based on learners' characteristics and interests.

[0299] "Means of providing topics to promote interaction" refers to a mechanism that presents relevant themes and discussion topics to stimulate communication among learners.

[0300] "Means for detecting signs of problems" refers to technologies that monitor the content of communication between learners and detect the occurrence of troubles or conflicts at an early stage.

[0301] "Educational personnel" refers to teachers and educational staff who are responsible for guiding and supporting learners.

[0302] "Means of displaying guidance" refers to interfaces and methods for presenting information and procedures that are helpful when learners attempt to solve problems on their own.

[0303] This invention is a system for facilitating collaborative learning among learners, and it functions through the combination of server, terminal, and user elements. An embodiment of this system is shown below.

[0304] The server uses a cloud platform to collect and manage learner information. Specifically, it uses a general-purpose cloud storage service to securely store learner account information and learning history. For information analysis, it uses machine learning frameworks such as TensorFlow or PyTorch to perform data calculations to classify learners' interests and characteristics based on the data obtained.

[0305] The device provides an interface with the learner, using front-end frameworks such as React and Angular to provide an intuitive and user-friendly environment. This allows learners to easily set their goals and interests on the device, and this information is sent to the server in real time, contributing to profile updates.

[0306] Based on the above information, the server uses an AI algorithm to organize learners into an optimal group. As an example of the algorithm, a method such as K-Nearest Neighbors (KNN) is used to analyze the similarity of attributes between learners and form a balanced group.

[0307] Also, on the terminal, a discussion theme generated using the generative AI model is displayed, and learners can communicate along that theme. For example, a prompt sentence such as "What do you think are the necessary efforts to reduce the impact of global warming?" can be cited as an example.

[0308] In the communication between users, that is, learners, a system is built where the server monitors the conversation content using natural language processing technology and notifies educational staff if there are signs of trouble. Also, for minor problems, guidance to promote self-resolution is displayed on the terminal to support enhancing the learners' autonomous problem-solving ability.

[0309] In this way, the present invention provides an integrated system for realizing smooth communication and collaborative learning among learners, enabling effective utilization in the educational field.

[0310] The flow of specific processing in Example 1 will be described using FIG. 11.

[0311] Step 1:

[0312] The server receives the account information, learning history, and data on interests sent from the learners' terminals and stores them in cloud storage. Based on this input, the server encrypts the data and manages it securely. The output is the learner information stored in an encrypted format.

[0313] Step 2:

[0314] The server analyzes the stored data. This analysis uses a machine learning framework to perform data calculations that identify the learner's interests and characteristics. Specifically, a model using TensorFlow performs data clustering. The input is the learner's historical data, and the output is a profile based on interests and characteristics.

[0315] Step 3:

[0316] The server uses an AI algorithm based on the analysis to form the optimal learning groups. Here, the K-Nearest Neighbors (KNN) algorithm is used to compare the attributes of the learners and determine the most suitable group for each of them. The input is profile information, and the output is the group formation result.

[0317] Step 4:

[0318] The terminal receives group information sent from the server and notifies the user. It then displays discussion themes generated by a generative AI model. Specifically, it uses natural language processing to construct highly relevant themes and provides them as prompts. The input is group information, and the output is the displayed discussion themes.

[0319] Step 5:

[0320] Users engage in discussions with other learners based on themes provided via their devices. During this process, AI provides additional prompts to encourage further dialogue. The input is the discussion theme, and the output is the communication between users.

[0321] Step 6:

[0322] The server constantly monitors user communication and uses natural language processing to detect signs of trouble. If a problem is detected, a notification is sent to the educator. For minor issues, instructions are displayed on the device to encourage self-resolution. Input is communication data, and output is trouble detection and notification, or presentation of instructions.

[0323] (Application Example 1)

[0324] 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."

[0325] Traditional learning platforms struggle to effectively facilitate interaction and collaborative learning among learners. Furthermore, they lack the functionality to proactively detect and appropriately address communication imbalances and problems that may arise during group learning. Additionally, there is a current lack of support for learners to deepen discussions based on their own interests and to effectively advance their learning.

[0326] 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.

[0327] In this invention, the server includes means for collecting and analyzing information on multiple users, means for organizing the users into an optimal group based on the analysis, means for providing topics to facilitate interaction among the groups, means for searching for and providing advice and reference information on tasks, and means for generating questions to stimulate discussion based on the presented topics. This enables learners to achieve deep learning through smooth communication and to effectively conduct group activities. Furthermore, by detecting signs of problems early and taking appropriate action, a safe and secure learning environment can be provided.

[0328] "Users" refers to individuals or groups that use the system, and in this case, it means people who participate in learning activities.

[0329] "Information" refers to data that users provide to the system, including their interests, the activities they participate in, and their past learning history.

[0330] "Analysis" is the process of evaluating collected information and understanding the characteristics and needs of users.

[0331] A "group" is a collection of users with common interests or goals that are formed when a system optimally organizes its user groups.

[0332] "Interaction" refers to communication, information sharing, and exchange of opinions among users, and the system aims to facilitate these activities.

[0333] "Topics" refer to themes and topics provided by the system to stimulate dialogue among users.

[0334] "Advice" refers to specific suggestions or methods that the system provides to users to help them solve problems.

[0335] "Reference information" refers to relevant materials and information that the system collects and presents to support the user's learning activities.

[0336] "Generating questions" is the process by which a system automatically creates relevant questions to deepen the discussion among users.

[0337] "Signs of a problem" refers to potential troubles lurking in communication between users, and detecting these is part of the system's monitoring function.

[0338] The main components of the system implementing this invention are a server, a terminal, and an AI agent. The server is built using Flask in Python and uses Pandas or Scikit-learn for data collection and analysis. The AI ​​agent generates a natural language processing model using TensorFlow or PyTorch. In this system, the server collects information from multiple users and stores it in a database. This aggregates the interests and past learning history of each individual user.

[0339] The server analyzes the collected data and uses Scikit-learn to organize users into optimal groups. These groups consist of users with common interests and goals, promoting effective collaborative learning. Furthermore, the server provides topics to encourage interaction among the devices, facilitating the initiation of natural communication.

[0340] The device uses a generative AI model to generate questions to stimulate discussion based on the provided topic. This model understands the context and presents topics that are easy for the user to talk about and that are of interest to them. For example, using a prompt such as "Please provide appropriate questions and information to discuss global warming based on the latest news" enables the generation of appropriate questions.

[0341] The terminal further searches for and provides advice and reference information related to tasks. By utilizing the provided reference information, users can develop problem-solving skills and proceed with learning autonomously. In addition, by monitoring communication between users and detecting signs of problems, a safe and secure learning environment can be provided. This system enables users to achieve deep learning through smooth communication and to conduct group activities effectively.

[0342] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0343] Step 1:

[0344] The server collects information from the user's device. It receives data such as the user's interests, goals, and past learning history as input, and stores it in a cloud database. At this stage, data transformation and cleansing are performed, and the data is stored in a standardized format.

[0345] Step 2:

[0346] The server analyzes the aggregated data. The input is the user data collected in Step 1, and a clustering algorithm is performed using Pandas and Scikit-learn. This identifies patterns in the user data and outputs the optimal grouping based on similarity.

[0347] Step 3:

[0348] The server selects topics to facilitate interaction among the generated group and sends them to the terminal. Input consists of current events and user profile information, and the AI ​​model uses this information to select relevant topics. The output is content presented to the user's terminal as part of that topic.

[0349] Step 4:

[0350] The terminal uses a generative AI model to generate questions to stimulate discussion based on the presented topic. The input is a topic sent from the server, and the output is the generated related questions presented to the user. The generative AI model utilizes natural language processing techniques to automatically create contextually appropriate questions.

[0351] Step 5:

[0352] The terminal accesses the server to search for helpful advice and reference information for the problem and provides it to the user. The input is the problem the user wants to solve, and the output is related materials and information links displayed on the terminal. The server processes the search query in response and selects the most relevant information.

[0353] Step 6:

[0354] The server monitors communication between users and detects signs of problems. Its input is real-time chat logs, and it uses a natural language processing model to detect issues. When a problem is detected, it notifies the instructor and prompts intervention if necessary.

[0355] 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.

[0356] This invention is a technology that facilitates smoother communication among learners by using a system that implements an emotion engine. This system is deployed on a server in the cloud and on the learner's terminal, and is designed to allow for real-time monitoring of learning progress and emotional state.

[0357] Data collection and emotion recognition

[0358] The server continuously collects and stores data such as learners' basic information, interests, and past learning history for analysis. In addition to this data, the emotion engine analyzes each learner's facial expressions, tone of voice, and input content to recognize their current emotional state in real time.

[0359] The device provides an interface for acquiring learner emotion data through voice and camera input. The acquired data is sent to a server and evaluated by an emotion engine.

[0360] Group formation and communication support

[0361] The server organizes optimal learning groups based on each learner's emotional state, interest data, and learning history. This process involves creating groups with balanced emotional states to facilitate smooth communication.

[0362] The device notifies learners of new group information and discussion topics tailored to their emotional state. For example, if the emotion engine detects that the learner is "happy," a positive topic such as "Let's share something funny that happened recently" will be provided.

[0363] Problem solving and emotional management

[0364] The learner, as the user, can work on assigned tasks and search for related information through their device. The server checks their emotional state and, if it determines they are experiencing stress, provides more easily understandable hints.

[0365] Trouble detection and emotional support

[0366] The server uses natural language processing technology to monitor messages between learners. If signs of trouble or negative emotions are detected, it immediately notifies the educator and prompts mediation as needed.

[0367] The device effectively supports self-reliance by displaying encouraging messages and positive feedback to alleviate negative emotions identified by the emotion engine in the learner.

[0368] This system allows learners to engage in collaborative learning in an environment that takes individual emotions into consideration, and enables educators to understand students' emotional states and group dynamics, thereby conducting educational activities more effectively.

[0369] The following describes the processing flow.

[0370] Step 1:

[0371] The server retrieves learner's basic information, learning history data, and interest profiles from a cloud database and prepares them for analysis.

[0372] Step 2:

[0373] The device uses a camera and microphone to capture the learner's facial expressions and voice, and transmits this data to a server in real time. This data is then analyzed by an emotion engine.

[0374] Step 3:

[0375] The server uses an emotion engine to analyze received facial and voice data and assess the learner's current emotional state. The results are reflected in each learner's profile.

[0376] Step 4:

[0377] The server applies an optimization algorithm to organize learning groups based on emotional states and other learning parameters. In this process, members are selected while considering emotional balance.

[0378] Step 5:

[0379] The device notifies the learner of the group they belong to and the associated communication topics. Topics are dynamically selected, taking into account the learner's emotional state.

[0380] Step 6:

[0381] The learner user initiates a discussion within the group based on a topic provided through their device. If the emotion engine detects positive emotions, the server may recommend additional positive events.

[0382] Step 7:

[0383] The server monitors the discussion content and uses natural language processing to detect signs of trouble or negative emotional expression. In cases where necessary, it sends notifications to educators.

[0384] Step 8:

[0385] The device uses an emotion engine to display suggestion messages and positive feedback to alleviate negative emotions and support learners.

[0386] Step 9:

[0387] When users work on assignments, they can access reference materials and hints sent from the server via their device, deepening their learning at their own pace. The emotion engine, if it detects stress, instructs the server to provide further hints.

[0388] These processing steps allow learners to enjoy an emotionally sensitive collaborative learning environment, and enable educators to grasp students' emotional developments in a timely manner.

[0389] (Example 2)

[0390] 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".

[0391] Traditional education systems have struggled to provide an effective collaborative learning environment that takes learners' emotional states into account. As a result, there have been problems such as poor communication among learners and limited learning effectiveness. Furthermore, there have been insufficient mechanisms for early detection of troubles and signs of problems and for appropriate intervention.

[0392] 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.

[0393] In this invention, the server includes means for acquiring and analyzing information on multiple learners, means for placing the learners into the most suitable group based on the analysis, and means for monitoring messages between learners and detecting signs of problems. This makes it possible to recognize the emotional state of learners in real time and provide support that is appropriate to their emotions.

[0394] "Educational participant" refers to an individual who participates in educational activities and engages in learning.

[0395] "Means of acquiring and analyzing information" refers to the process of collecting data on educational participants and processing and analyzing that data to understand the attributes and status of the participants.

[0396] "Methods for group placement" refers to the process of organizing educational participants into the most suitable groups based on the analysis results, thereby promoting collaborative learning.

[0397] "Means of monitoring messages and detecting early signs of problems" refers to a process of monitoring communication among trainees to detect potential troubles or problems early on.

[0398] "Means of recognizing emotional states" refers to a process that determines the emotions of trainees in real time by analyzing their facial expressions, voice, and input content.

[0399] "Means of providing support tailored to emotions" refers to the process of providing appropriate guidance and feedback to individual participants based on their recognized emotional state.

[0400] This invention is a system designed to recognize the emotions of learners in real time and optimize their learning. This system consists of a server and terminals and supports collaborative learning among learners.

[0401] The server collects and analyzes a wide range of information about the students, including their basic information, learning history, interests, and real-time input data. This analysis utilizes an emotion engine, which implements algorithms to analyze the students' facial expressions, voice, and input in real time. This emotion engine includes an emotion analysis algorithm written in Python, which classifies the students' emotions into states such as "happy," "sad," and "stressed."

[0402] The device uses a camera and microphone interface to capture the facial expressions and voices of the learners. This data is sent to a server for analysis by an emotion engine. The device also serves to notify learners of new group information and recommended discussion topics. For example, a learner judged to be enjoying themselves might be presented with a discussion topic such as "Let's share something funny."

[0403] The users, who are educational learners, can work on assignments provided by the server. The server monitors the learners' emotional state and provides easy-to-understand hints if it determines that they are experiencing stress. This entire process allows learners to learn efficiently in an emotionally responsive environment.

[0404] Specific examples of using the generative AI model include prompts such as, "Please suggest countermeasures for when the user is feeling stressed," and "Please suggest topics to facilitate a smooth group discussion." In this way, the system can provide support tailored to each participant in real time.

[0405] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0406] Step 1:

[0407] The device acquires information about the student using its camera and microphone. Input includes facial image data and audio data of the student. This data is collected and sent to a server. Specifically, the camera captures images every second, and the microphone records audio. This data is then processed by an emotion engine.

[0408] Step 2:

[0409] The server inputs received facial image and audio data into an emotion engine, which analyzes the emotional state in real time. The emotion engine uses a Python algorithm to perform the analysis and classify the participant's emotions into categories such as "happy," "sad," and "stressed." The output is the analyzed emotional state. Specifically, the server automatically registers the analysis results in a database.

[0410] Step 3:

[0411] The server sends prompt messages to the generative AI model based on the analysis results, and then organizes the optimal learning groups. The input includes the learners' emotional states and past learning history. The generative AI model analyzes the prompts and generates the optimal group configuration as output. Specifically, the server updates the group information based on the generated results.

[0412] Step 4:

[0413] The device notifies participants of newly formed group information and presents discussion topics tailored to their emotional state. Input includes group composition and topic information received from the server. Output consists of notifications and topics displayed on the user interface. Specifically, the device generates a push notification and displays the topic as a pop-up on the screen.

[0414] Step 5:

[0415] Users can work on tasks presented through their devices. While solving problems, they use their devices to search for necessary information. Input includes the task content and hints from the server. Output consists of guidelines and supplementary information to help complete the task without difficulty. Specifically, the server searches for and provides additional materials based on the task selected by the user.

[0416] Step 6:

[0417] The server monitors messages between students and uses natural language processing to detect negative emotions and signs of trouble. The input is chat data, which the monitoring system analyzes. The output is an alert notification to the education support staff. Specifically, keyword-based triggers are built, and notifications are sent immediately when a problem is detected.

[0418] (Application Example 2)

[0419] 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."

[0420] In today's learning environment, learners may experience difficulties communicating effectively due to changes in their emotional state. Furthermore, learning programs lacking appropriate task presentation and teaching methods can lead to decreased learner motivation and poor results. Because educators often struggle to understand the emotional states of individual learners and group dynamics, there is a need for support in conducting more effective educational activities.

[0421] 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.

[0422] In this invention, the server includes means for collecting and analyzing user emotional data, means for organizing users into optimal groups based on the analysis, and means for providing topics to facilitate communication among the groups. This enables the provision of an optimal learning environment tailored to the emotional state of learners, and allows educators to conduct effective educational activities while understanding the emotional state of individual learners.

[0423] "User" refers to a learner or individual in an educational environment who utilizes the system of the present invention.

[0424] "Emotional data" refers to information such as facial expressions, tone of voice, and input content that represent the user's emotional state.

[0425] "Means of analysis" refers to the technology that performs a process to interpret the user's emotional state and tendencies based on the emotional data collected.

[0426] "Methods for organizing into groups" refer to methods for organizing users into optimal groups based on analysis results, thereby promoting communication.

[0427] "Topics to facilitate communication" are topics that support active information exchange and opinion sharing among users within a group.

[0428] A "terminal" is a device that the user directly operates and is hardware used for collecting and providing emotional data.

[0429] A "server" is a computer system that serves as the core of the entire system, processing, analyzing, storing, and directing emotional data.

[0430] An "educator" is an individual who acts as a leader in a learning environment and conducts educational activities based on information provided by the system.

[0431] The system for realizing this invention is primarily composed of a server and terminals. In the embodiment of the invention, the server is located on the cloud and collects emotional data from multiple users, processing and analyzing it in real time. The server analyzes emotional data such as the user's facial expressions and voice tone, and uses advanced image processing libraries such as OpenCV and speech analysis technology to evaluate their emotional state.

[0432] The terminal is a device such as a smartphone or smart glasses, which, through direct user operation, collects emotional data via sensors such as cameras and microphones. The collected data is transmitted to a server via the terminal.

[0433] Specifically, the server analyzes the transmitted data and makes decisions to group users into the most suitable learning groups. Furthermore, to facilitate communication among users, it suggests topics based on their interests, and this information is fed back from the server to the terminals.

[0434] For example, by implementing this system in an educational institution, it is possible to analyze the emotional state of each learner. Based on these analysis results, learners with stable emotions can be grouped together, creating an environment where learning activities can proceed smoothly.

[0435] For example, by inputting a prompt such as "Design an AI algorithm that selects topics based on the learner's emotions" into a generating AI model, effective suggestions for learning topics can be achieved.

[0436] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0437] Step 1:

[0438] The device uses a camera and microphone to capture the user's facial expressions and voice tone, collecting emotional data. The input is real-time image and audio data, which is converted into numerical features using an external library (e.g., OpenCV). The output is numerical data of facial expressions and voice tone.

[0439] Step 2:

[0440] The terminal transmits digitized emotional data to the server. The input is the emotional data obtained in step 1, and the output is the data provided to the server in the cloud. Specifically, the Internet protocol is used for data transmission to ensure that the data is transferred securely.

[0441] Step 3:

[0442] The server analyzes the received emotional data to recognize the user's emotional state. The input is emotional data transmitted from the terminal, which is then analyzed using natural language processing techniques and machine learning algorithms. The output is an evaluation result indicating the user's emotional state.

[0443] Step 4:

[0444] The server organizes users into optimal learning groups based on their analyzed emotional states. The input is the evaluation result of the emotional state obtained in step 3, and the output is the group organization decision. Specifically, it uses a database to consider each user's attributes and places them in the most suitable group.

[0445] Step 5:

[0446] The server generates prompt sentences to suggest the most appropriate topics and feeds this information back to the terminal. The input is to generate prompt sentences based on the user's interests using a generative AI model. The output is a communication topic suitable for the user.

[0447] Step 6:

[0448] The terminal presents the user with group information and topics received from the server. Input is the information generated in step 5, and output is information provided through screen displays and audio notifications. Specifically, information is efficiently conveyed through a user-friendly interface.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] [Third Embodiment]

[0453] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0454] 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.

[0455] 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).

[0456] 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.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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.

[0464] 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".

[0465] This invention is a system designed to facilitate learner communication and enable effective collaborative learning. At the core of the system is an AI agent that collects and analyzes data from multiple learners, providing optimal group formation and smooth communication. This agent operates on a server and provides services to learners in real time as needed.

[0466] Data collection and analysis

[0467] Server: Retrieves learning history and interest data accumulated through learners' accounts. This data is stored in cloud storage and managed securely.

[0468] Device: Learners can input data through an intuitive UI for setting interests and goals. The input data is sent to the server and automatically added to the learner's profile.

[0469] Group Formation

[0470] Server: Using an AI algorithm, the server automatically creates optimal group formations based on each learner's data. Here, it considers learners' interests and the results of previous group activities to create well-balanced groups.

[0471] Communication support

[0472] Devices: Each learner's device displays discussion topics designed to facilitate effective communication within the group. These topics are generated based on daily news and the learners' interests.

[0473] User: Learners can engage in discussions and deepen their interactions based on the provided themes. The AI ​​provides additional questions and relevant information in real time to further stimulate the conversation.

[0474] Support for problem solving

[0475] Server: Searches for relevant textbooks and reference materials in response to assignments entered by learners. The AI ​​understands the context and presents the most relevant information.

[0476] Device: Links to helpful hints and resources for assignments are displayed, allowing learners to use them to progress autonomously in their studies.

[0477] Trouble detection and response

[0478] Server: Monitors chat content using natural language processing technology and immediately notifies educators if there are signs of trouble such as bullying or conflict.

[0479] Device: For minor issues, the system automatically provides guides to help learners resolve the problem themselves.

[0480] This system allows learners to engage in group activities through smooth communication and deepen their understanding of the assigned tasks. In addition, it reduces the burden on educators of monitoring student relationships and activities, enabling them to carry out their teaching duties more efficiently.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] The server collects learner basic information, learning history, and interest data from a cloud database and updates the data to the latest state. It also adds data for new learners if available.

[0484] Step 2:

[0485] The device displays a question form to the learner regarding their interests and learning goals, and sends the entered data to the server. This keeps the learner's profile up-to-date.

[0486] Step 3:

[0487] The server then uses the collected data to begin analysis with an AI algorithm. It evaluates each learner's learning style and interests, and extracts the information necessary for group formation.

[0488] Step 4:

[0489] The server organizes learners into optimal groups based on the analysis results. Here, it determines combinations that maximize the balance and learning effectiveness of each learner.

[0490] Step 5:

[0491] The device notifies learners of the new group's member list and the topic for group discussion. This allows learners to check their group and prepare to engage in the activity.

[0492] Step 6:

[0493] The learners, as users, begin activities to exchange ideas and engage in discussions within their groups based on the provided topic. This stimulates communication among learners.

[0494] Step 7:

[0495] The server monitors the content and flow of the discussion and generates and provides additional questions and support information to ensure smooth communication.

[0496] Step 8:

[0497] The server searches databases and external resources for relevant information regarding the submitted problem and selects hints and reference materials that can help solve it.

[0498] Step 9:

[0499] The device displays selected hints and materials to the learner, supporting them in independently working on problem-solving.

[0500] Step 10:

[0501] The server analyzes chat content using natural language processing technology to detect signs of trouble and terms related to bullying. If a problem is detected, it notifies the educator without delay.

[0502] Step 11:

[0503] For minor issues, the device will provide learners with individual self-help guides to support them in proactively resolving problems.

[0504] Through these steps, the PeerConnect system supports smooth communication among learners, promotes improved collaborative learning outcomes, and prevents problems from occurring.

[0505] (Example 1)

[0506] 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."

[0507] This invention aims to solve the problems of conventional collaborative learning systems, such as insufficient communication among learners and difficulty in forming groups appropriate to the learning progress. It also aims to support educators in quickly detecting problems among learners and responding appropriately.

[0508] 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.

[0509] In this invention, the server includes means for collecting and analyzing learner information, means for organizing the learners into optimal groups based on the analysis, and means for providing topics to promote interaction among the groups. This enables smooth communication among learners, realizes an optimal collaborative learning environment, and allows for early response in the event of trouble.

[0510] A "learner" refers to an individual who participates in an educational program and seeks to acquire knowledge.

[0511] "Means for collecting and analyzing information" refers to a system that collects data obtained from learners and analyzes it using analytical algorithms.

[0512] "Methods for forming optimal groups" refers to algorithms that automatically form groups based on learners' characteristics and interests.

[0513] "Means of providing topics to promote interaction" refers to a mechanism that presents relevant themes and discussion topics to stimulate communication among learners.

[0514] "Means for detecting signs of problems" refers to technologies that monitor the content of communication between learners and detect the occurrence of troubles or conflicts at an early stage.

[0515] "Educational personnel" refers to teachers and educational staff who are responsible for guiding and supporting learners.

[0516] "Means of displaying guidance" refers to interfaces and methods for presenting information and procedures that are helpful when learners attempt to solve problems on their own.

[0517] This invention is a system for facilitating collaborative learning among learners, and it functions through the combination of server, terminal, and user elements. An embodiment of this system is shown below.

[0518] The server uses a cloud platform to collect and manage learner information. Specifically, it uses a general-purpose cloud storage service to securely store learner account information and learning history. For information analysis, it uses machine learning frameworks such as TensorFlow or PyTorch to perform data calculations to classify learners' interests and characteristics based on the data obtained.

[0519] The device provides an interface with the learner, using front-end frameworks such as React and Angular to provide an intuitive and user-friendly environment. This allows learners to easily set their goals and interests on the device, and this information is sent to the server in real time, contributing to profile updates.

[0520] Based on the information above, the server uses an AI algorithm to organize learners into optimal groups. An example of such an algorithm is the K-Nearest Neighbors (KNN) method, which analyzes the similarity of learners' attributes to form balanced groups.

[0521] Furthermore, discussion topics generated using a generative AI model are displayed on the device, allowing learners to interact based on those topics. For example, a prompt such as, "What efforts do you think are necessary to reduce the impacts of global warming?" might be used.

[0522] In communication between users, i.e., learners, the system uses natural language processing technology to monitor conversation content and notifies educators if there are signs of trouble. Furthermore, for minor issues, the system displays guidance on the terminal to encourage self-resolution, supporting learners in developing their independent problem-solving abilities.

[0523] Thus, the present invention provides an integrated system for facilitating smooth communication and collaborative learning among learners, enabling its effective use in educational settings.

[0524] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0525] Step 1:

[0526] The server receives account information, learning history, and interest data sent from the learner's device and stores it in cloud storage. Based on this input, the server encrypts and securely manages the data. The output is learner information stored in encrypted format.

[0527] Step 2:

[0528] The server analyzes the stored data. This analysis uses a machine learning framework to perform data calculations that identify the learner's interests and characteristics. Specifically, a model using TensorFlow performs data clustering. The input is the learner's historical data, and the output is a profile based on interests and characteristics.

[0529] Step 3:

[0530] The server uses an AI algorithm based on the analysis to form the optimal learning groups. Here, the K-Nearest Neighbors (KNN) algorithm is used to compare the attributes of the learners and determine the most suitable group for each of them. The input is profile information, and the output is the group formation result.

[0531] Step 4:

[0532] The terminal receives group information sent from the server and notifies the user. It then displays discussion themes generated by a generative AI model. Specifically, it uses natural language processing to construct highly relevant themes and provides them as prompts. The input is group information, and the output is the displayed discussion themes.

[0533] Step 5:

[0534] Users engage in discussions with other learners based on themes provided via their devices. During this process, AI provides additional prompts to encourage further dialogue. The input is the discussion theme, and the output is the communication between users.

[0535] Step 6:

[0536] The server constantly monitors user communication and uses natural language processing to detect signs of trouble. If a problem is detected, a notification is sent to the educator. For minor issues, instructions are displayed on the device to encourage self-resolution. Input is communication data, and output is trouble detection and notification, or presentation of instructions.

[0537] (Application Example 1)

[0538] 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."

[0539] Traditional learning platforms struggle to effectively facilitate interaction and collaborative learning among learners. Furthermore, they lack the functionality to proactively detect and appropriately address communication imbalances and problems that may arise during group learning. Additionally, there is a current lack of support for learners to deepen discussions based on their own interests and to effectively advance their learning.

[0540] 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.

[0541] In this invention, the server includes means for collecting and analyzing information on multiple users, means for organizing the users into an optimal group based on the analysis, means for providing topics to facilitate interaction among the groups, means for searching for and providing advice and reference information on tasks, and means for generating questions to stimulate discussion based on the presented topics. This enables learners to achieve deep learning through smooth communication and to effectively conduct group activities. Furthermore, by detecting signs of problems early and taking appropriate action, a safe and secure learning environment can be provided.

[0542] "Users" refers to individuals or groups that use the system, and in this case, it means people who participate in learning activities.

[0543] "Information" refers to data that users provide to the system, including their interests, the activities they participate in, and their past learning history.

[0544] "Analysis" is the process of evaluating collected information and understanding the characteristics and needs of users.

[0545] A "group" is a collection of users with common interests or goals that are formed when a system optimally organizes its user groups.

[0546] "Interaction" refers to communication, information sharing, and exchange of opinions among users, and the system aims to facilitate these activities.

[0547] "Topics" refer to themes and topics provided by the system to stimulate dialogue among users.

[0548] "Advice" refers to specific suggestions or methods that the system provides to users to help them solve problems.

[0549] "Reference information" refers to relevant materials and information that the system collects and presents to support the user's learning activities.

[0550] "Generating questions" is the process by which a system automatically creates relevant questions to deepen the discussion among users.

[0551] "Signs of a problem" refers to potential troubles lurking in communication between users, and detecting these is part of the system's monitoring function.

[0552] The main components of the system implementing this invention are a server, a terminal, and an AI agent. The server is built using Flask in Python and uses Pandas or Scikit-learn for data collection and analysis. The AI ​​agent generates a natural language processing model using TensorFlow or PyTorch. In this system, the server collects information from multiple users and stores it in a database. This aggregates the interests and past learning history of each individual user.

[0553] The server analyzes the collected data and uses Scikit-learn to organize users into optimal groups. These groups consist of users with common interests and goals, promoting effective collaborative learning. Furthermore, the server provides topics to encourage interaction among the devices, facilitating the initiation of natural communication.

[0554] The device uses a generative AI model to generate questions to stimulate discussion based on the provided topic. This model understands the context and presents topics that are easy for the user to talk about and that are of interest to them. For example, using a prompt such as "Please provide appropriate questions and information to discuss global warming based on the latest news" enables the generation of appropriate questions.

[0555] The terminal further searches for and provides advice and reference information related to tasks. By utilizing the provided reference information, users can develop problem-solving skills and proceed with learning autonomously. In addition, by monitoring communication between users and detecting signs of problems, a safe and secure learning environment can be provided. This system enables users to achieve deep learning through smooth communication and to conduct group activities effectively.

[0556] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0557] Step 1:

[0558] The server collects information from the user's device. It receives data such as the user's interests, goals, and past learning history as input, and stores it in a cloud database. At this stage, data transformation and cleansing are performed, and the data is stored in a standardized format.

[0559] Step 2:

[0560] The server analyzes the aggregated data. The input is the user data collected in Step 1, and a clustering algorithm is performed using Pandas and Scikit-learn. This identifies patterns in the user data and outputs the optimal grouping based on similarity.

[0561] Step 3:

[0562] The server selects topics to facilitate interaction among the generated group and sends them to the terminal. Input consists of current events and user profile information, and the AI ​​model uses this information to select relevant topics. The output is content presented to the user's terminal as part of that topic.

[0563] Step 4:

[0564] The terminal uses a generative AI model to generate questions to stimulate discussion based on the presented topic. The input is a topic sent from the server, and the output is the generated related questions presented to the user. The generative AI model utilizes natural language processing techniques to automatically create contextually appropriate questions.

[0565] Step 5:

[0566] The terminal accesses the server to search for helpful advice and reference information for the problem and provides it to the user. The input is the problem the user wants to solve, and the output is related materials and information links displayed on the terminal. The server processes the search query in response and selects the most relevant information.

[0567] Step 6:

[0568] The server monitors communication between users and detects signs of problems. Its input is real-time chat logs, and it uses a natural language processing model to detect issues. When a problem is detected, it notifies the instructor and prompts intervention if necessary.

[0569] 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.

[0570] This invention is a technology that facilitates smoother communication among learners by using a system that implements an emotion engine. This system is deployed on a server in the cloud and on the learner's terminal, and is designed to allow for real-time monitoring of learning progress and emotional state.

[0571] Data collection and emotion recognition

[0572] The server continuously collects and stores data such as learners' basic information, interests, and past learning history for analysis. In addition to this data, the emotion engine analyzes each learner's facial expressions, tone of voice, and input content to recognize their current emotional state in real time.

[0573] The device provides an interface for acquiring learner emotion data through voice and camera input. The acquired data is sent to a server and evaluated by an emotion engine.

[0574] Group formation and communication support

[0575] The server organizes optimal learning groups based on each learner's emotional state, interest data, and learning history. This process involves creating groups with balanced emotional states to facilitate smooth communication.

[0576] The device notifies learners of new group information and discussion topics tailored to their emotional state. For example, if the emotion engine detects that the learner is "happy," a positive topic such as "Let's share something funny that happened recently" will be provided.

[0577] Problem solving and emotional management

[0578] The learner, as the user, can work on assigned tasks and search for related information through their device. The server checks their emotional state and, if it determines they are experiencing stress, provides more easily understandable hints.

[0579] Trouble detection and emotional support

[0580] The server uses natural language processing technology to monitor messages between learners. If signs of trouble or negative emotions are detected, it immediately notifies the educator and prompts mediation as needed.

[0581] The device effectively supports self-reliance by displaying encouraging messages and positive feedback to alleviate negative emotions identified by the emotion engine in the learner.

[0582] This system allows learners to engage in collaborative learning in an environment that takes individual emotions into consideration, and enables educators to understand students' emotional states and group dynamics, thereby conducting educational activities more effectively.

[0583] The following describes the processing flow.

[0584] Step 1:

[0585] The server retrieves learner's basic information, learning history data, and interest profiles from a cloud database and prepares them for analysis.

[0586] Step 2:

[0587] The device uses a camera and microphone to capture the learner's facial expressions and voice, and transmits this data to a server in real time. This data is then analyzed by an emotion engine.

[0588] Step 3:

[0589] The server uses an emotion engine to analyze received facial and voice data and assess the learner's current emotional state. The results are reflected in each learner's profile.

[0590] Step 4:

[0591] The server applies an optimization algorithm to organize learning groups based on emotional states and other learning parameters. In this process, members are selected while considering emotional balance.

[0592] Step 5:

[0593] The device notifies the learner of the group they belong to and the associated communication topics. Topics are dynamically selected, taking into account the learner's emotional state.

[0594] Step 6:

[0595] The learner user initiates a discussion within the group based on a topic provided through their device. If the emotion engine detects positive emotions, the server may recommend additional positive events.

[0596] Step 7:

[0597] The server monitors the discussion content and uses natural language processing to detect signs of trouble or negative emotional expression. In cases where necessary, it sends notifications to educators.

[0598] Step 8:

[0599] The device uses an emotion engine to display suggestion messages and positive feedback to alleviate negative emotions and support learners.

[0600] Step 9:

[0601] When users work on assignments, they can access reference materials and hints sent from the server via their device, deepening their learning at their own pace. The emotion engine, if it detects stress, instructs the server to provide further hints.

[0602] These processing steps allow learners to enjoy an emotionally sensitive collaborative learning environment, and enable educators to grasp students' emotional developments in a timely manner.

[0603] (Example 2)

[0604] 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."

[0605] Traditional education systems have struggled to provide an effective collaborative learning environment that takes learners' emotional states into account. As a result, there have been problems such as poor communication among learners and limited learning effectiveness. Furthermore, there have been insufficient mechanisms for early detection of troubles and signs of problems and for appropriate intervention.

[0606] 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.

[0607] In this invention, the server includes means for acquiring and analyzing information on multiple learners, means for placing the learners into the most suitable group based on the analysis, and means for monitoring messages between learners and detecting signs of problems. This makes it possible to recognize the emotional state of learners in real time and provide support that is appropriate to their emotions.

[0608] "Educational participant" refers to an individual who participates in educational activities and engages in learning.

[0609] "Means of acquiring and analyzing information" refers to the process of collecting data on educational participants and processing and analyzing that data to understand the attributes and status of the participants.

[0610] "Methods for group placement" refers to the process of organizing educational participants into the most suitable groups based on the analysis results, thereby promoting collaborative learning.

[0611] "Means of monitoring messages and detecting early signs of problems" refers to a process of monitoring communication among trainees to detect potential troubles or problems early on.

[0612] "Means of recognizing emotional states" refers to a process that determines the emotions of trainees in real time by analyzing their facial expressions, voice, and input content.

[0613] "Means of providing support tailored to emotions" refers to the process of providing appropriate guidance and feedback to individual participants based on their recognized emotional state.

[0614] This invention is a system designed to recognize the emotions of learners in real time and optimize their learning. This system consists of a server and terminals and supports collaborative learning among learners.

[0615] The server collects and analyzes a wide range of information about the students, including their basic information, learning history, interests, and real-time input data. This analysis utilizes an emotion engine, which implements algorithms to analyze the students' facial expressions, voice, and input in real time. This emotion engine includes an emotion analysis algorithm written in Python, which classifies the students' emotions into states such as "happy," "sad," and "stressed."

[0616] The device uses a camera and microphone interface to capture the facial expressions and voices of the learners. This data is sent to a server for analysis by an emotion engine. The device also serves to notify learners of new group information and recommended discussion topics. For example, a learner judged to be enjoying themselves might be presented with a discussion topic such as "Let's share something funny."

[0617] The users, who are educational learners, can work on assignments provided by the server. The server monitors the learners' emotional state and provides easy-to-understand hints if it determines that they are experiencing stress. This entire process allows learners to learn efficiently in an emotionally responsive environment.

[0618] Specific examples of using the generative AI model include prompts such as, "Please suggest countermeasures for when the user is feeling stressed," and "Please suggest topics to facilitate a smooth group discussion." In this way, the system can provide support tailored to each participant in real time.

[0619] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0620] Step 1:

[0621] The device acquires information about the student using its camera and microphone. Input includes facial image data and audio data of the student. This data is collected and sent to a server. Specifically, the camera captures images every second, and the microphone records audio. This data is then processed by an emotion engine.

[0622] Step 2:

[0623] The server inputs received facial image and audio data into an emotion engine, which analyzes the emotional state in real time. The emotion engine uses a Python algorithm to perform the analysis and classify the participant's emotions into categories such as "happy," "sad," and "stressed." The output is the analyzed emotional state. Specifically, the server automatically registers the analysis results in a database.

[0624] Step 3:

[0625] The server sends prompt messages to the generative AI model based on the analysis results, and then organizes the optimal learning groups. The input includes the learners' emotional states and past learning history. The generative AI model analyzes the prompts and generates the optimal group configuration as output. Specifically, the server updates the group information based on the generated results.

[0626] Step 4:

[0627] The device notifies participants of newly formed group information and presents discussion topics tailored to their emotional state. Input includes group composition and topic information received from the server. Output consists of notifications and topics displayed on the user interface. Specifically, the device generates a push notification and displays the topic as a pop-up on the screen.

[0628] Step 5:

[0629] Users can work on tasks presented through their devices. While solving problems, they use their devices to search for necessary information. Input includes the task content and hints from the server. Output consists of guidelines and supplementary information to help complete the task without difficulty. Specifically, the server searches for and provides additional materials based on the task selected by the user.

[0630] Step 6:

[0631] The server monitors messages between students and uses natural language processing to detect negative emotions and signs of trouble. The input is chat data, which the monitoring system analyzes. The output is an alert notification to the education support staff. Specifically, keyword-based triggers are built, and notifications are sent immediately when a problem is detected.

[0632] (Application Example 2)

[0633] 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."

[0634] In today's learning environment, learners may experience difficulties communicating effectively due to changes in their emotional state. Furthermore, learning programs lacking appropriate task presentation and teaching methods can lead to decreased learner motivation and poor results. Because educators often struggle to understand the emotional states of individual learners and group dynamics, there is a need for support in conducting more effective educational activities.

[0635] 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.

[0636] In this invention, the server includes means for collecting and analyzing user emotional data, means for organizing users into optimal groups based on the analysis, and means for providing topics to facilitate communication among the groups. This enables the provision of an optimal learning environment tailored to the emotional state of learners, and allows educators to conduct effective educational activities while understanding the emotional state of individual learners.

[0637] "User" refers to a learner or individual in an educational environment who utilizes the system of the present invention.

[0638] "Emotional data" refers to information such as facial expressions, tone of voice, and input content that represent the user's emotional state.

[0639] "Means of analysis" refers to the technology that performs a process to interpret the user's emotional state and tendencies based on the emotional data collected.

[0640] "Methods for organizing into groups" refer to methods for organizing users into optimal groups based on analysis results, thereby promoting communication.

[0641] "Topics to facilitate communication" are topics that support active information exchange and opinion sharing among users within a group.

[0642] A "terminal" is a device that the user directly operates and is hardware used for collecting and providing emotional data.

[0643] A "server" is a computer system that serves as the core of the entire system, processing, analyzing, storing, and directing emotional data.

[0644] An "educator" is an individual who acts as a leader in a learning environment and conducts educational activities based on information provided by the system.

[0645] The system for realizing this invention is primarily composed of a server and terminals. In the embodiment of the invention, the server is located on the cloud and collects emotional data from multiple users, processing and analyzing it in real time. The server analyzes emotional data such as the user's facial expressions and voice tone, and uses advanced image processing libraries such as OpenCV and speech analysis technology to evaluate their emotional state.

[0646] The terminal is a device such as a smartphone or smart glasses, which, through direct user operation, collects emotional data via sensors such as cameras and microphones. The collected data is transmitted to a server via the terminal.

[0647] Specifically, the server analyzes the transmitted data and makes decisions to group users into the most suitable learning groups. Furthermore, to facilitate communication among users, it suggests topics based on their interests, and this information is fed back from the server to the terminals.

[0648] For example, by implementing this system in an educational institution, it is possible to analyze the emotional state of each learner. Based on these analysis results, learners with stable emotions can be grouped together, creating an environment where learning activities can proceed smoothly.

[0649] For example, by inputting a prompt such as "Design an AI algorithm that selects topics based on the learner's emotions" into a generating AI model, effective suggestions for learning topics can be achieved.

[0650] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0651] Step 1:

[0652] The device uses a camera and microphone to capture the user's facial expressions and voice tone, collecting emotional data. The input is real-time image and audio data, which is converted into numerical features using an external library (e.g., OpenCV). The output is numerical data of facial expressions and voice tone.

[0653] Step 2:

[0654] The terminal transmits digitized emotional data to the server. The input is the emotional data obtained in step 1, and the output is the data provided to the server in the cloud. Specifically, the Internet protocol is used for data transmission to ensure that the data is transferred securely.

[0655] Step 3:

[0656] The server analyzes the received emotional data to recognize the user's emotional state. The input is emotional data transmitted from the terminal, which is then analyzed using natural language processing techniques and machine learning algorithms. The output is an evaluation result indicating the user's emotional state.

[0657] Step 4:

[0658] The server organizes users into optimal learning groups based on their analyzed emotional states. The input is the evaluation result of the emotional state obtained in step 3, and the output is the group organization decision. Specifically, it uses a database to consider each user's attributes and places them in the most suitable group.

[0659] Step 5:

[0660] The server generates prompt sentences to suggest the most appropriate topics and feeds this information back to the terminal. The input is to generate prompt sentences based on the user's interests using a generative AI model. The output is a communication topic suitable for the user.

[0661] Step 6:

[0662] The terminal presents the user with group information and topics received from the server. Input is the information generated in step 5, and output is information provided through screen displays and audio notifications. Specifically, information is efficiently conveyed through a user-friendly interface.

[0663] 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.

[0664] 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.

[0665] 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.

[0666] [Fourth Embodiment]

[0667] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0668] 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.

[0669] 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).

[0670] 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.

[0671] 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.

[0672] 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).

[0673] 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.

[0674] 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.

[0675] 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.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] 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".

[0680] This invention is a system designed to facilitate learner communication and enable effective collaborative learning. At the core of the system is an AI agent that collects and analyzes data from multiple learners, providing optimal group formation and smooth communication. This agent operates on a server and provides services to learners in real time as needed.

[0681] Data collection and analysis

[0682] Server: Retrieves learning history and interest data accumulated through learners' accounts. This data is stored in cloud storage and managed securely.

[0683] Device: Learners can input data through an intuitive UI for setting interests and goals. The input data is sent to the server and automatically added to the learner's profile.

[0684] Group Formation

[0685] Server: Using an AI algorithm, the server automatically creates optimal group formations based on each learner's data. Here, it considers learners' interests and the results of previous group activities to create well-balanced groups.

[0686] Communication support

[0687] Devices: Each learner's device displays discussion topics designed to facilitate effective communication within the group. These topics are generated based on daily news and the learners' interests.

[0688] User: Learners can engage in discussions and deepen their interactions based on the provided themes. The AI ​​provides additional questions and relevant information in real time to further stimulate the conversation.

[0689] Support for problem solving

[0690] Server: Searches for relevant textbooks and reference materials in response to assignments entered by learners. The AI ​​understands the context and presents the most relevant information.

[0691] Device: Links to helpful hints and resources for assignments are displayed, allowing learners to use them to progress autonomously in their studies.

[0692] Trouble detection and response

[0693] Server: Monitors chat content using natural language processing technology and immediately notifies educators if there are signs of trouble such as bullying or conflict.

[0694] Device: For minor issues, the system automatically provides guides to help learners resolve the problem themselves.

[0695] This system allows learners to engage in group activities through smooth communication and deepen their understanding of the assigned tasks. In addition, it reduces the burden on educators of monitoring student relationships and activities, enabling them to carry out their teaching duties more efficiently.

[0696] The following describes the processing flow.

[0697] Step 1:

[0698] The server collects learner basic information, learning history, and interest data from a cloud database and updates the data to the latest state. It also adds data for new learners if available.

[0699] Step 2:

[0700] The device displays a question form to the learner regarding their interests and learning goals, and sends the entered data to the server. This keeps the learner's profile up-to-date.

[0701] Step 3:

[0702] The server then uses the collected data to begin analysis with an AI algorithm. It evaluates each learner's learning style and interests, and extracts the information necessary for group formation.

[0703] Step 4:

[0704] The server organizes learners into optimal groups based on the analysis results. Here, it determines combinations that maximize the balance and learning effectiveness of each learner.

[0705] Step 5:

[0706] The device notifies learners of the new group's member list and the topic for group discussion. This allows learners to check their group and prepare to engage in the activity.

[0707] Step 6:

[0708] The learners, as users, begin activities to exchange ideas and engage in discussions within their groups based on the provided topic. This stimulates communication among learners.

[0709] Step 7:

[0710] The server monitors the content and flow of the discussion and generates and provides additional questions and support information to ensure smooth communication.

[0711] Step 8:

[0712] The server searches databases and external resources for relevant information regarding the submitted problem and selects hints and reference materials that can help solve it.

[0713] Step 9:

[0714] The device displays selected hints and materials to the learner, supporting them in independently working on problem-solving.

[0715] Step 10:

[0716] The server analyzes chat content using natural language processing technology to detect signs of trouble and terms related to bullying. If a problem is detected, it notifies the educator without delay.

[0717] Step 11:

[0718] For minor issues, the device will provide learners with individual self-help guides to support them in proactively resolving problems.

[0719] Through these steps, the PeerConnect system supports smooth communication among learners, promotes improved collaborative learning outcomes, and prevents problems from occurring.

[0720] (Example 1)

[0721] 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".

[0722] This invention aims to solve the problems of conventional collaborative learning systems, such as insufficient communication among learners and difficulty in forming groups appropriate to the learning progress. It also aims to support educators in quickly detecting problems among learners and responding appropriately.

[0723] 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.

[0724] In this invention, the server includes means for collecting and analyzing learner information, means for organizing the learners into optimal groups based on the analysis, and means for providing topics to promote interaction among the groups. This enables smooth communication among learners, realizes an optimal collaborative learning environment, and allows for early response in the event of trouble.

[0725] A "learner" refers to an individual who participates in an educational program and seeks to acquire knowledge.

[0726] "Means for collecting and analyzing information" refers to a system that collects data obtained from learners and analyzes it using analytical algorithms.

[0727] "Methods for forming optimal groups" refers to algorithms that automatically form groups based on learners' characteristics and interests.

[0728] "Means of providing topics to promote interaction" refers to a mechanism that presents relevant themes and discussion topics to stimulate communication among learners.

[0729] "Means for detecting signs of problems" refers to technologies that monitor the content of communication between learners and detect the occurrence of troubles or conflicts at an early stage.

[0730] "Educational personnel" refers to teachers and educational staff who are responsible for guiding and supporting learners.

[0731] "Means of displaying guidance" refers to interfaces and methods for presenting information and procedures that are helpful when learners attempt to solve problems on their own.

[0732] This invention is a system for facilitating collaborative learning among learners, and it functions through the combination of server, terminal, and user elements. An embodiment of this system is shown below.

[0733] The server uses a cloud platform to collect and manage learner information. Specifically, it uses a general-purpose cloud storage service to securely store learner account information and learning history. For information analysis, it uses machine learning frameworks such as TensorFlow or PyTorch to perform data calculations to classify learners' interests and characteristics based on the data obtained.

[0734] The device provides an interface with the learner, using front-end frameworks such as React and Angular to provide an intuitive and user-friendly environment. This allows learners to easily set their goals and interests on the device, and this information is sent to the server in real time, contributing to profile updates.

[0735] Based on the information above, the server uses an AI algorithm to organize learners into optimal groups. An example of such an algorithm is the K-Nearest Neighbors (KNN) method, which analyzes the similarity of learners' attributes to form balanced groups.

[0736] Furthermore, discussion topics generated using a generative AI model are displayed on the device, allowing learners to interact based on those topics. For example, a prompt such as, "What efforts do you think are necessary to reduce the impacts of global warming?" might be used.

[0737] In communication between users, i.e., learners, the system uses natural language processing technology to monitor conversation content and notifies educators if there are signs of trouble. Furthermore, for minor issues, the system displays guidance on the terminal to encourage self-resolution, supporting learners in developing their independent problem-solving abilities.

[0738] Thus, the present invention provides an integrated system for facilitating smooth communication and collaborative learning among learners, enabling its effective use in educational settings.

[0739] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0740] Step 1:

[0741] The server receives account information, learning history, and interest data sent from the learner's device and stores it in cloud storage. Based on this input, the server encrypts and securely manages the data. The output is learner information stored in encrypted format.

[0742] Step 2:

[0743] The server analyzes the stored data. This analysis uses a machine learning framework to perform data calculations that identify the learner's interests and characteristics. Specifically, a model using TensorFlow performs data clustering. The input is the learner's historical data, and the output is a profile based on interests and characteristics.

[0744] Step 3:

[0745] The server uses an AI algorithm based on the analysis to form the optimal learning groups. Here, the K-Nearest Neighbors (KNN) algorithm is used to compare the attributes of the learners and determine the most suitable group for each of them. The input is profile information, and the output is the group formation result.

[0746] Step 4:

[0747] The terminal receives group information sent from the server and notifies the user. It then displays discussion themes generated by a generative AI model. Specifically, it uses natural language processing to construct highly relevant themes and provides them as prompts. The input is group information, and the output is the displayed discussion themes.

[0748] Step 5:

[0749] Users engage in discussions with other learners based on themes provided via their devices. During this process, AI provides additional prompts to encourage further dialogue. The input is the discussion theme, and the output is the communication between users.

[0750] Step 6:

[0751] The server constantly monitors user communication and uses natural language processing to detect signs of trouble. If a problem is detected, a notification is sent to the educator. For minor issues, instructions are displayed on the device to encourage self-resolution. Input is communication data, and output is trouble detection and notification, or presentation of instructions.

[0752] (Application Example 1)

[0753] 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".

[0754] Traditional learning platforms struggle to effectively facilitate interaction and collaborative learning among learners. Furthermore, they lack the functionality to proactively detect and appropriately address communication imbalances and problems that may arise during group learning. Additionally, there is a current lack of support for learners to deepen discussions based on their own interests and to effectively advance their learning.

[0755] 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.

[0756] In this invention, the server includes means for collecting and analyzing information on multiple users, means for organizing the users into an optimal group based on the analysis, means for providing topics to facilitate interaction among the groups, means for searching for and providing advice and reference information on tasks, and means for generating questions to stimulate discussion based on the presented topics. This enables learners to achieve deep learning through smooth communication and to effectively conduct group activities. Furthermore, by detecting signs of problems early and taking appropriate action, a safe and secure learning environment can be provided.

[0757] "Users" refers to individuals or groups that use the system, and in this case, it means people who participate in learning activities.

[0758] "Information" refers to data that users provide to the system, including their interests, the activities they participate in, and their past learning history.

[0759] "Analysis" is the process of evaluating collected information and understanding the characteristics and needs of users.

[0760] A "group" is a collection of users with common interests or goals that are formed when a system optimally organizes its user groups.

[0761] "Interaction" refers to communication, information sharing, and exchange of opinions among users, and the system aims to facilitate these activities.

[0762] "Topics" refer to themes and topics provided by the system to stimulate dialogue among users.

[0763] "Advice" refers to specific suggestions or methods that the system provides to users to help them solve problems.

[0764] "Reference information" refers to relevant materials and information that the system collects and presents to support the user's learning activities.

[0765] "Generating questions" is the process by which a system automatically creates relevant questions to deepen the discussion among users.

[0766] "Signs of a problem" refers to potential troubles lurking in communication between users, and detecting these is part of the system's monitoring function.

[0767] The main components of the system implementing this invention are a server, a terminal, and an AI agent. The server is built using Flask in Python and uses Pandas or Scikit-learn for data collection and analysis. The AI ​​agent generates a natural language processing model using TensorFlow or PyTorch. In this system, the server collects information from multiple users and stores it in a database. This aggregates the interests and past learning history of each individual user.

[0768] The server analyzes the collected data and uses Scikit-learn to organize users into optimal groups. These groups consist of users with common interests and goals, promoting effective collaborative learning. Furthermore, the server provides topics to encourage interaction among the devices, facilitating the initiation of natural communication.

[0769] The device uses a generative AI model to generate questions to stimulate discussion based on the provided topic. This model understands the context and presents topics that are easy for the user to talk about and that are of interest to them. For example, using a prompt such as "Please provide appropriate questions and information to discuss global warming based on the latest news" enables the generation of appropriate questions.

[0770] The terminal further searches for and provides advice and reference information related to tasks. By utilizing the provided reference information, users can develop problem-solving skills and proceed with learning autonomously. In addition, by monitoring communication between users and detecting signs of problems, a safe and secure learning environment can be provided. This system enables users to achieve deep learning through smooth communication and to conduct group activities effectively.

[0771] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0772] Step 1:

[0773] The server collects information from the user's device. It receives data such as the user's interests, goals, and past learning history as input, and stores it in a cloud database. At this stage, data transformation and cleansing are performed, and the data is stored in a standardized format.

[0774] Step 2:

[0775] The server analyzes the aggregated data. The input is the user data collected in Step 1, and a clustering algorithm is performed using Pandas and Scikit-learn. This identifies patterns in the user data and outputs the optimal grouping based on similarity.

[0776] Step 3:

[0777] The server selects topics to facilitate interaction among the generated group and sends them to the terminal. Input consists of current events and user profile information, and the AI ​​model uses this information to select relevant topics. The output is content presented to the user's terminal as part of that topic.

[0778] Step 4:

[0779] The terminal uses a generative AI model to generate questions to stimulate discussion based on the presented topic. The input is a topic sent from the server, and the output is the generated related questions presented to the user. The generative AI model utilizes natural language processing techniques to automatically create contextually appropriate questions.

[0780] Step 5:

[0781] The terminal accesses the server to search for helpful advice and reference information for the problem and provides it to the user. The input is the problem the user wants to solve, and the output is related materials and information links displayed on the terminal. The server processes the search query in response and selects the most relevant information.

[0782] Step 6:

[0783] The server monitors communication between users and detects signs of problems. Its input is real-time chat logs, and it uses a natural language processing model to detect issues. When a problem is detected, it notifies the instructor and prompts intervention if necessary.

[0784] 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.

[0785] This invention is a technology that facilitates smoother communication among learners by using a system that implements an emotion engine. This system is deployed on a server in the cloud and on the learner's terminal, and is designed to allow for real-time monitoring of learning progress and emotional state.

[0786] Data collection and emotion recognition

[0787] The server continuously collects and stores data such as learners' basic information, interests, and past learning history for analysis. In addition to this data, the emotion engine analyzes each learner's facial expressions, tone of voice, and input content to recognize their current emotional state in real time.

[0788] The device provides an interface for acquiring learner emotion data through voice and camera input. The acquired data is sent to a server and evaluated by an emotion engine.

[0789] Group formation and communication support

[0790] The server organizes optimal learning groups based on each learner's emotional state, interest data, and learning history. This process involves creating groups with balanced emotional states to facilitate smooth communication.

[0791] The device notifies learners of new group information and discussion topics tailored to their emotional state. For example, if the emotion engine detects that the learner is "happy," a positive topic such as "Let's share something funny that happened recently" will be provided.

[0792] Problem solving and emotional management

[0793] The learner, as the user, can work on assigned tasks and search for related information through their device. The server checks their emotional state and, if it determines they are experiencing stress, provides more easily understandable hints.

[0794] Trouble detection and emotional support

[0795] The server uses natural language processing technology to monitor messages between learners. If signs of trouble or negative emotions are detected, it immediately notifies the educator and prompts mediation as needed.

[0796] The device effectively supports self-reliance by displaying encouraging messages and positive feedback to alleviate negative emotions identified by the emotion engine in the learner.

[0797] This system allows learners to engage in collaborative learning in an environment that takes individual emotions into consideration, and enables educators to understand students' emotional states and group dynamics, thereby conducting educational activities more effectively.

[0798] The following describes the processing flow.

[0799] Step 1:

[0800] The server retrieves learner's basic information, learning history data, and interest profiles from a cloud database and prepares them for analysis.

[0801] Step 2:

[0802] The device uses a camera and microphone to capture the learner's facial expressions and voice, and transmits this data to a server in real time. This data is then analyzed by an emotion engine.

[0803] Step 3:

[0804] The server uses an emotion engine to analyze received facial and voice data and assess the learner's current emotional state. The results are reflected in each learner's profile.

[0805] Step 4:

[0806] The server applies an optimization algorithm to organize learning groups based on emotional states and other learning parameters. In this process, members are selected while considering emotional balance.

[0807] Step 5:

[0808] The device notifies the learner of the group they belong to and the associated communication topics. Topics are dynamically selected, taking into account the learner's emotional state.

[0809] Step 6:

[0810] The learner user initiates a discussion within the group based on a topic provided through their device. If the emotion engine detects positive emotions, the server may recommend additional positive events.

[0811] Step 7:

[0812] The server monitors the discussion content and uses natural language processing to detect signs of trouble or negative emotional expression. In cases where necessary, it sends notifications to educators.

[0813] Step 8:

[0814] The device uses an emotion engine to display suggestion messages and positive feedback to alleviate negative emotions and support learners.

[0815] Step 9:

[0816] When users work on assignments, they can access reference materials and hints sent from the server via their device, deepening their learning at their own pace. The emotion engine, if it detects stress, instructs the server to provide further hints.

[0817] These processing steps allow learners to enjoy an emotionally sensitive collaborative learning environment, and enable educators to grasp students' emotional developments in a timely manner.

[0818] (Example 2)

[0819] 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".

[0820] Traditional education systems have struggled to provide an effective collaborative learning environment that takes learners' emotional states into account. As a result, there have been problems such as poor communication among learners and limited learning effectiveness. Furthermore, there have been insufficient mechanisms for early detection of troubles and signs of problems and for appropriate intervention.

[0821] 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.

[0822] In this invention, the server includes means for acquiring and analyzing information on multiple learners, means for placing the learners into the most suitable group based on the analysis, and means for monitoring messages between learners and detecting signs of problems. This makes it possible to recognize the emotional state of learners in real time and provide support that is appropriate to their emotions.

[0823] "Educational participant" refers to an individual who participates in educational activities and engages in learning.

[0824] "Means of acquiring and analyzing information" refers to the process of collecting data on educational participants and processing and analyzing that data to understand the attributes and status of the participants.

[0825] "Methods for group placement" refers to the process of organizing educational participants into the most suitable groups based on the analysis results, thereby promoting collaborative learning.

[0826] "Means of monitoring messages and detecting early signs of problems" refers to a process of monitoring communication among trainees to detect potential troubles or problems early on.

[0827] "Means of recognizing emotional states" refers to a process that determines the emotions of trainees in real time by analyzing their facial expressions, voice, and input content.

[0828] "Means of providing support tailored to emotions" refers to the process of providing appropriate guidance and feedback to individual participants based on their recognized emotional state.

[0829] This invention is a system designed to recognize the emotions of learners in real time and optimize their learning. This system consists of a server and terminals and supports collaborative learning among learners.

[0830] The server collects and analyzes a wide range of information about the students, including their basic information, learning history, interests, and real-time input data. This analysis utilizes an emotion engine, which implements algorithms to analyze the students' facial expressions, voice, and input in real time. This emotion engine includes an emotion analysis algorithm written in Python, which classifies the students' emotions into states such as "happy," "sad," and "stressed."

[0831] The device uses a camera and microphone interface to capture the facial expressions and voices of the learners. This data is sent to a server for analysis by an emotion engine. The device also serves to notify learners of new group information and recommended discussion topics. For example, a learner judged to be enjoying themselves might be presented with a discussion topic such as "Let's share something funny."

[0832] The users, who are educational learners, can work on assignments provided by the server. The server monitors the learners' emotional state and provides easy-to-understand hints if it determines that they are experiencing stress. This entire process allows learners to learn efficiently in an emotionally responsive environment.

[0833] Specific examples of using the generative AI model include prompts such as, "Please suggest countermeasures for when the user is feeling stressed," and "Please suggest topics to facilitate a smooth group discussion." In this way, the system can provide support tailored to each participant in real time.

[0834] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0835] Step 1:

[0836] The device acquires information about the student using its camera and microphone. Input includes facial image data and audio data of the student. This data is collected and sent to a server. Specifically, the camera captures images every second, and the microphone records audio. This data is then processed by an emotion engine.

[0837] Step 2:

[0838] The server inputs received facial image and audio data into an emotion engine, which analyzes the emotional state in real time. The emotion engine uses a Python algorithm to perform the analysis and classify the participant's emotions into categories such as "happy," "sad," and "stressed." The output is the analyzed emotional state. Specifically, the server automatically registers the analysis results in a database.

[0839] Step 3:

[0840] The server sends prompt messages to the generative AI model based on the analysis results, and then organizes the optimal learning groups. The input includes the learners' emotional states and past learning history. The generative AI model analyzes the prompts and generates the optimal group configuration as output. Specifically, the server updates the group information based on the generated results.

[0841] Step 4:

[0842] The device notifies participants of newly formed group information and presents discussion topics tailored to their emotional state. Input includes group composition and topic information received from the server. Output consists of notifications and topics displayed on the user interface. Specifically, the device generates a push notification and displays the topic as a pop-up on the screen.

[0843] Step 5:

[0844] Users can work on tasks presented through their devices. While solving problems, they use their devices to search for necessary information. Input includes the task content and hints from the server. Output consists of guidelines and supplementary information to help complete the task without difficulty. Specifically, the server searches for and provides additional materials based on the task selected by the user.

[0845] Step 6:

[0846] The server monitors messages between students and uses natural language processing to detect negative emotions and signs of trouble. The input is chat data, which the monitoring system analyzes. The output is an alert notification to the education support staff. Specifically, keyword-based triggers are built, and notifications are sent immediately when a problem is detected.

[0847] (Application Example 2)

[0848] 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".

[0849] In today's learning environment, learners may experience difficulties communicating effectively due to changes in their emotional state. Furthermore, learning programs lacking appropriate task presentation and teaching methods can lead to decreased learner motivation and poor results. Because educators often struggle to understand the emotional states of individual learners and group dynamics, there is a need for support in conducting more effective educational activities.

[0850] 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.

[0851] In this invention, the server includes means for collecting and analyzing user emotional data, means for organizing users into optimal groups based on the analysis, and means for providing topics to facilitate communication among the groups. This enables the provision of an optimal learning environment tailored to the emotional state of learners, and allows educators to conduct effective educational activities while understanding the emotional state of individual learners.

[0852] "User" refers to a learner or individual in an educational environment who utilizes the system of the present invention.

[0853] "Emotional data" refers to information such as facial expressions, tone of voice, and input content that represent the user's emotional state.

[0854] "Means of analysis" refers to the technology that performs a process to interpret the user's emotional state and tendencies based on the emotional data collected.

[0855] "Methods for organizing into groups" refer to methods for organizing users into optimal groups based on analysis results, thereby promoting communication.

[0856] "Topics to facilitate communication" are topics that support active information exchange and opinion sharing among users within a group.

[0857] A "terminal" is a device that the user directly operates and is hardware used for collecting and providing emotional data.

[0858] A "server" is a computer system that serves as the core of the entire system, processing, analyzing, storing, and directing emotional data.

[0859] An "educator" is an individual who acts as a leader in a learning environment and conducts educational activities based on information provided by the system.

[0860] The system for realizing this invention is primarily composed of a server and terminals. In the embodiment of the invention, the server is located on the cloud and collects emotional data from multiple users, processing and analyzing it in real time. The server analyzes emotional data such as the user's facial expressions and voice tone, and uses advanced image processing libraries such as OpenCV and speech analysis technology to evaluate their emotional state.

[0861] The terminal is a device such as a smartphone or smart glasses, which, through direct user operation, collects emotional data via sensors such as cameras and microphones. The collected data is transmitted to a server via the terminal.

[0862] Specifically, the server analyzes the transmitted data and makes decisions to group users into the most suitable learning groups. Furthermore, to facilitate communication among users, it suggests topics based on their interests, and this information is fed back from the server to the terminals.

[0863] For example, by implementing this system in an educational institution, it is possible to analyze the emotional state of each learner. Based on these analysis results, learners with stable emotions can be grouped together, creating an environment where learning activities can proceed smoothly.

[0864] For example, by inputting a prompt such as "Design an AI algorithm that selects topics based on the learner's emotions" into a generating AI model, effective suggestions for learning topics can be achieved.

[0865] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0866] Step 1:

[0867] The device uses a camera and microphone to capture the user's facial expressions and voice tone, collecting emotional data. The input is real-time image and audio data, which is converted into numerical features using an external library (e.g., OpenCV). The output is numerical data of facial expressions and voice tone.

[0868] Step 2:

[0869] The terminal transmits digitized emotional data to the server. The input is the emotional data obtained in step 1, and the output is the data provided to the server in the cloud. Specifically, the Internet protocol is used for data transmission to ensure that the data is transferred securely.

[0870] Step 3:

[0871] The server analyzes the received emotional data to recognize the user's emotional state. The input is emotional data transmitted from the terminal, which is then analyzed using natural language processing techniques and machine learning algorithms. The output is an evaluation result indicating the user's emotional state.

[0872] Step 4:

[0873] The server organizes users into optimal learning groups based on their analyzed emotional states. The input is the evaluation result of the emotional state obtained in step 3, and the output is the group organization decision. Specifically, it uses a database to consider each user's attributes and places them in the most suitable group.

[0874] Step 5:

[0875] The server generates prompt sentences to suggest the most appropriate topics and feeds this information back to the terminal. The input is to generate prompt sentences based on the user's interests using a generative AI model. The output is a communication topic suitable for the user.

[0876] Step 6:

[0877] The terminal presents the user with group information and topics received from the server. Input is the information generated in step 5, and output is information provided through screen displays and audio notifications. Specifically, information is efficiently conveyed through a user-friendly interface.

[0878] 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.

[0879] 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.

[0880] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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."

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0899] The following is further disclosed regarding the embodiments described above.

[0900] (Claim 1)

[0901] A means of collecting and analyzing data from multiple learners,

[0902] A means for organizing the learners into optimal groups based on the above analysis,

[0903] A means of providing topics to facilitate communication among the aforementioned group,

[0904] A means of searching for and providing hints and reference materials for the problem,

[0905] A means of monitoring messages between learners and detecting signs of trouble,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, further comprising means for notifying an educator when signs of the aforementioned trouble are detected.

[0909] (Claim 3)

[0910] The system according to claim 1, further comprising means for providing the learner with a guide to encourage self-reliance.

[0911] "Example 1"

[0912] (Claim 1)

[0913] A means of collecting and analyzing learner information,

[0914] A means for organizing the learners into an optimal group based on the aforementioned analysis,

[0915] A means of providing topics to promote interaction among the aforementioned group,

[0916] A means of searching for and presenting reference information regarding the problem,

[0917] A means of monitoring information among learners and detecting signs of problems,

[0918] A means of using a generative model to provide learning support based on the content of communications,

[0919] A system that includes this.

[0920] (Claim 2)

[0921] The system according to claim 1, further comprising means for notifying educators when signs of the aforementioned problem are detected.

[0922] (Claim 3)

[0923] The system according to claim 1, further comprising means for displaying instructions to encourage the learner to solve the problem on their own.

[0924] "Application Example 1"

[0925] (Claim 1)

[0926] A means of collecting and analyzing information from multiple users,

[0927] A means for organizing the users into an optimal group based on the above analysis,

[0928] A means of providing topics to promote interaction among the aforementioned group,

[0929] A means of searching for and providing advice and reference information regarding the issue,

[0930] A means of monitoring communication between users and detecting signs of problems,

[0931] A means of generating questions to stimulate discussion based on the presented topic,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, further comprising means for notifying a supervisor when signs of the aforementioned problem are detected.

[0935] (Claim 3)

[0936] The system according to claim 1, further comprising means for providing the user with guidelines to encourage self-resolution.

[0937] "Example 2 of combining an emotion engine"

[0938] (Claim 1)

[0939] A means of acquiring and analyzing information from multiple educational participants,

[0940] A means for assigning the trainees to the most suitable group based on the aforementioned analysis,

[0941] Means for providing the aforementioned group with topics to promote interaction,

[0942] Means for finding and providing guidelines and materials for addressing the issues,

[0943] A means of monitoring messages between educational participants and detecting early signs of problems,

[0944] A means of recognizing the emotional state of the aforementioned education participant and providing support based on those emotions,

[0945] A means for organizing the group using emotion analysis and considering diverse emotional states,

[0946] A system that includes this.

[0947] (Claim 2)

[0948] The system according to claim 1, further comprising means for notifying an educational support worker when a precursor to the aforementioned problem is detected.

[0949] (Claim 3)

[0950] The system according to claim 1, further comprising means for providing the aforementioned trainees with guidelines to encourage them to solve problems on their own.

[0951] "Application example 2 when combining with an emotional engine"

[0952] (Claim 1)

[0953] A means of collecting and analyzing emotional data from multiple users,

[0954] A means for organizing the users into an optimal group based on the above analysis,

[0955] Means for providing topics to facilitate communication with the aforementioned group,

[0956] A means of searching for and providing advice and reference information regarding the issue,

[0957] A means of monitoring messages between users and detecting signs of problems,

[0958] A means including a terminal and server for evaluating the user's emotional state and providing an optimal learning environment,

[0959] A system that includes this.

[0960] (Claim 2)

[0961] The system according to claim 1, further comprising means for notifying a supervisor when signs of the aforementioned problem are detected.

[0962] (Claim 3)

[0963] The system according to claim 1, further comprising means for providing the user with guidelines to encourage self-resolution. [Explanation of symbols]

[0964] 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 of collecting and analyzing data from multiple learners, A means for organizing the learners into optimal groups based on the above analysis, A means of providing topics to facilitate communication among the aforementioned group, A means of searching for and providing hints and reference materials for the problem, A means of monitoring messages between learners and detecting signs of trouble, A system that includes this.

2. The system according to claim 1, further comprising means for notifying an educator when signs of the aforementioned trouble are detected.

3. The system according to claim 1, further comprising means for providing the learner with a guide to encourage self-reliance.

Images