system

Abstract

We provide the system. [Solution] A means for acquiring user dialogue and storing that dialogue data in a storage device, A means for analyzing stored dialogue data using natural language processing technology and generating scores for evaluating instructional effectiveness and trust relationships, A means of presenting suggestions for improving instruction based on the generated score, A means of accumulating past data and providing feedback on areas for improvement in instruction over the long term, 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 performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional one-on-one guidance, it is difficult to accommodate the different learning styles of individual students and to build a trust relationship with the instructor. As a result, there is variation in the guidance effect, and the problem is that the satisfaction and learning achievements of the students are not fully achieved. Furthermore, the instructor has a large burden of providing individual feedback and it is difficult to conduct guidance efficiently.

Means for Solving the Problems

[0005] This invention provides a system that acquires user dialogues and analyzes that data, thereby supporting improved instructional efficiency and the building of trust based on the content of the dialogues. Specifically, it analyzes the dialogue data using natural language processing technology and generates a score that evaluates instructional effectiveness and trust, thereby presenting optimized instructional improvement suggestions for the user. Furthermore, by accumulating past data and providing feedback on areas for continuous improvement, it enables effective instruction over the long term.

[0006] "Dialogue data" refers to information in audio or text format collected during communication between users.

[0007] "Natural language processing technology" refers to artificial intelligence technologies used by computers to understand, interpret, and generate human language.

[0008] The "Instructional Effectiveness Score" is an evaluation index that quantifies the learning outcomes of users and the effectiveness of instruction based on analyzed dialogue data.

[0009] The "trust score" is an evaluation index that quantifies the degree of psychological safety and emotional connection between students and instructors during their interactions.

[0010] A "teaching improvement suggestion" is a specific action plan that users can implement to improve their teaching methods, based on the generated score.

[0011] "Long-term feedback" refers to information used to provide users with ongoing areas for improvement and growth trends based on accumulated session data. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] 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 a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of 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 Example 2 when an emotion engine is combined. [[ID=3​​​​​​​​​​​​​​​​​In the following embodiments, the labeled 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.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] As an embodiment of this invention, a system is constructed in which a server, a terminal, and a user cooperate. The system is centered around the server, which interacts with the user through the terminal. It also has a mechanism to analyze the generated data and make suggestions to the user.

[0034] First, users (instructors and students) engage in dialogue, and the content is collected by the device as audio or text data. This data is sent to the server in real time. The server analyzes this data using natural language processing techniques to extract the dialogue's topic, emotions, and important keywords.

[0035] Next, the server calculates an effectiveness score and a trust score based on the analysis results. These scores serve as criteria for evaluation and are indicators of how effective the system is. For example, when a student says "I see, I understand" to indicate comprehension, the server adjusts the score as positive feedback.

[0036] Furthermore, the server generates specific suggestions for improving instruction based on the scores. These suggestions are notified to the instructor in real time via the terminal, allowing the instructor to immediately adjust their teaching methods accordingly. For example, an instruction might be given such as, "The student is confused, so please explain things more clearly."

[0037] The server accumulates dialogue data over the long term and provides regular feedback to determine user growth and areas for improvement in instruction. This feedback allows instructors to review the effectiveness of past lessons and apply that knowledge to future sessions.

[0038] These modules and functions enable this system to support the building of trust and effectively improve individual instruction through real-time dialogue analysis and feedback. The above is the basic form for carrying out the present invention.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] Users (instructors and students) initiate online or in-person instruction sessions. The device prepares to collect the session's dialogue in audio or text format and send it to the server.

[0042] Step 2:

[0043] The terminal transmits the collected conversation data to the server in real time. The server stores the received data and prepares it for the next analysis step.

[0044] Step 3:

[0045] The server analyzes the stored dialogue data using natural language processing techniques. Specifically, the server classifies the topics of the dialogues, performs sentiment analysis, and extracts relevant keywords and phrases.

[0046] Step 4:

[0047] The server calculates instruction effectiveness scores and trust scores based on the analysis results. Here, factors such as positive feedback and close communication are taken into account in the scoring.

[0048] Step 5:

[0049] The server generates specific instructional improvement suggestions based on the generated scores. These suggestions consist of actions that can be implemented immediately.

[0050] Step 6:

[0051] The terminal notifies the instructor of improvement suggestions received from the server. The instructor can then adjust their teaching methods on the spot, taking these suggestions into consideration.

[0052] Step 7:

[0053] The server accumulates all interaction data over the long term and analyzes the effectiveness of past instruction and the progress in building trust. This forms the basis for providing feedback for the next session.

[0054] Step 8:

[0055] The server periodically provides instructors with feedback on the analysis results via their terminals. This feedback includes evaluations of past instruction and insights for further improvement.

[0056] (Example 1)

[0057] 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."

[0058] In today's educational environment, it is essential to adapt teaching methods to each learner's level of understanding and interests. However, traditional classroom settings present challenges in real-time dialogue analysis and concrete improvements to teaching methods. Therefore, there is an urgent need to develop an effective feedback system that maximizes educational effectiveness and builds trust.

[0059] 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.

[0060] This invention includes a server that acquires dialogue between users and stores the digitized dialogue information in a storage medium; a server that analyzes the stored dialogue information using language processing technology and generates indicators for evaluating educational effectiveness and reliability coefficients; and a server that presents suggestions for educational improvement based on the generated indicators. This enables real-time dialogue analysis and concrete suggestions for improving instruction.

[0061] "Users" refers to the collective term for educators and learners who use the system to interact with each other.

[0062] "Dialogue information" refers to audio or text data that digitizes conversations between users.

[0063] "Storage medium" refers to a device or technology for storing digital information, and includes hard disks and cloud storage.

[0064] "Language processing technology" refers to techniques for analyzing natural language and understanding its meaning and structure.

[0065] "Educational effectiveness" is an indicator that shows the positive impact and results that educational activities have on learners.

[0066] The "trust coefficient" is a numerical indicator that shows the strength of the trust relationship formed between educators and learners.

[0067] An "indicator" is a numerical representation of the state or characteristics of the subject being evaluated, and serves as a standard for evaluation and judgment.

[0068] A "generative artificial intelligence model" refers to artificial intelligence technology that can automatically generate new information and suggestions based on input data.

[0069] "Educational improvement proposals" are pieces of information that suggest changes or adjustments to teaching methods in order to enhance learners' understanding and interest.

[0070] A description of embodiments for carrying out this invention will be given.

[0071] The system consists of a server, terminals, and users (instructors and students). Users initiate interactions through their terminals, which collect these interactions as audio or text data. The terminals then transmit the collected data to the server in real time.

[0072] The server plays the primary role of analyzing the received data. This analysis utilizes generative artificial intelligence models as a natural language processing technique. For example, language models from OpenAI® can be used. The server uses these models to extract the conversation's topic, sentiment, and key keywords. Based on this information, the server calculates scores indicating educational effectiveness and confidence levels.

[0073] Next, the server generates specific suggestions for improving teaching based on the calculated scores. These suggestions are communicated to instructors via their terminals, providing support for adjusting teaching methods in real time. For example, a suggestion might be, "Students are having difficulty understanding, so please make your explanations more specific."

[0074] The server also analyzes long-term data and regularly provides feedback to understand user growth and areas for improvement in instruction. This feedback serves as a foundation for instructors to reflect on past lessons and apply that knowledge to future lessons.

[0075] As a concrete example, the prompt input to the generating AI model would be, "Evaluate the student's understanding of the new concept and generate effective teaching improvement suggestions." Using this prompt, the server can analyze the student's understanding of the learning material and suggest appropriate teaching methods.

[0076] This system provides a more reliable educational environment and enables effective improvement of individual instruction through real-time dialogue analysis and feedback.

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

[0078] Step 1:

[0079] The user initiates a conversation through the terminal. The user inputs the conversation in voice or text format. The terminal converts this conversation into digital data using speech recognition or text processing and prepares it as conversation information. The input is the user's voice or text, and the output is digitized conversation information.

[0080] Step 2:

[0081] The terminal transmits prepared dialogue information to the server in real time. The terminal transports digital data to the server via network communication. The input is digitized dialogue information, and the output is the dialogue information that has reached the server.

[0082] Step 3:

[0083] The server analyzes the received dialogue information. Using a generative AI model, the server analyzes the dialogue information with natural language processing techniques to extract topics, emotions, and important keywords. The input is the dialogue information, and the output is the extracted analysis results. In this analysis, the AI ​​model understands the content of the dialogue and even judges the emotional tone.

[0084] Step 4:

[0085] The server calculates an educational effectiveness score and a trust relationship score based on the analysis results. The server compares the analysis results data with evaluation criteria and generates each score using a scoring algorithm. The input is the analysis results, and the output is the educational effectiveness score and the trust relationship score.

[0086] Step 5:

[0087] The server generates educational improvement suggestions based on the calculated score. The server evaluates the score and uses a generative AI model to create specific improvement suggestions. The inputs are the educational effectiveness score and the trust score, and the output is improvement suggestions. These suggestions include actions that the AI ​​model generates based on similar cases and existing knowledge bases.

[0088] Step 6:

[0089] The server sends generated educational improvement suggestions to instructors via terminals and notifies them. The server sends suggestions to terminals via network communication, and the terminals use their notification functions to inform instructors. The input is improvement suggestions, and the output is the notification received by the instructor. This communication is conducted in real time.

[0090] Step 7:

[0091] The server analyzes long-term accumulated dialogue data and provides regular feedback to the user. The server evaluates the information stored in the database along with past analysis results, extracts points for user growth and improvement in instruction, and creates a feedback report. The input is long-term accumulated data, and the output is a feedback report.

[0092] (Application Example 1)

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

[0094] In modern educational settings and home learning, accurately grasping the varying learning progress of each user and immediately implementing appropriate instructional improvements is difficult. Furthermore, there is a lack of concrete methods for improvement that enable effective instruction while building trust with users, thus creating a need to effectively support learners' growth.

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

[0096] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device; means for analyzing the stored dialogue data using natural language processing technology and generating a score for evaluating the effectiveness of instruction and trust relationship; means for presenting suggestions for improving instruction based on the generated score; means for accumulating past data and providing feedback on areas for improvement in instruction over the long term; and means for providing real-time feedback to the user via a terminal that collects the dialogue data and optimizing the user's learning progress. This enables learners to receive immediate feedback based on their individual needs and to make effective progress in their learning.

[0097] "Users" refers to individuals or groups who interact with the system and receive guidance through it.

[0098] "Dialogue data" refers to digital information that includes the content of voice and text communication between users.

[0099] A "memory device" refers to an electronic data recording medium used to store collected dialogue data.

[0100] "Natural language processing technology" is a general term for technologies used to process and analyze human language using computers.

[0101] The "instructional effectiveness score" refers to an index used to quantify and evaluate a user's learning progress and level of understanding.

[0102] A "trust score" refers to an index used to quantify and evaluate the level of trust in communication between users.

[0103] "Feedback" refers to specific suggestions for improvement and guidance methods that are generated based on the analysis results.

[0104] A "terminal" refers to an electronic device used by a user to interact with a system.

[0105] "Real-time" refers to the temporal nature of dialogue and feedback occurring immediately.

[0106] The system implementing this invention is realized through a series of processes centered on the acquisition, analysis, and feedback of dialogue data. Specifically, it is configured as follows:

[0107] First, the device collects the user's conversation and converts it into text data using speech recognition software (e.g., a speech recognition API). This text data is then quickly sent to a server and stored in its memory.

[0108] The server uses natural language processing technologies (such as spaCy and speech analysis libraries) to analyze the received dialogue data. This analysis process applies algorithms that generate instruction effectiveness scores and trust scores, quantifying the user's level of understanding and trust.

[0109] After generating a score, the server utilizes a generative AI model to generate personalized feedback and offers users individualized suggestions for improving their instruction. This feedback is immediately presented to the user via their device, enabling real-time learning improvement. For example, if the server suggests that "it would be good to include more specific examples," that suggestion is immediately displayed on the device.

[0110] Furthermore, the server uses dialogue data and generated feedback to analyze long-term trends and support the user's continuous growth. This makes it possible to review the effectiveness of past instruction and use that information to improve future instruction.

[0111] For example, if a child says, "I don't understand this part of the math problem," the server can analyze the dialogue data and generate feedback such as, "Let me explain this area in more detail."

[0112] An example of a prompt might be: "Analyze the following text to identify the sentiment and create appropriate feedback. Text: 'I still haven't solved this problem.'"

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The device captures the user interaction as audio data. Speech recognition software is used to convert this audio data into text. The input is audio data, and the output is text data. This conversion process transforms speech into written information.

[0116] Step 2:

[0117] The terminal sends the converted text data to the server in real time. This transmission process uses a stable communication protocol to ensure that the data reaches the server quickly while preventing data loss. The input is text data, and the output is the raw text data that arrives at the server.

[0118] Step 3:

[0119] The server analyzes received text data using natural language processing techniques. Specifically, it performs calculations to extract emotions, topics, and keywords from the text content. The input is raw text data, and the output is the analysis result including topics, emotions, and keywords. This analysis allows for an understanding of the meaning and emotional shifts in the dialogue.

[0120] Step 4:

[0121] The server generates an instructional effectiveness score and a trust relationship score based on the analysis results. These scores, quantified using an algorithm, serve as a basis for making specific improvements to instruction. The input is the analysis results, and the output is the instructional effectiveness score and the trust relationship score. This allows for the evaluation of the user's learning progress.

[0122] Step 5:

[0123] The server utilizes a generated AI model to produce specific feedback based on the score. This feedback includes suggestions for improving the user's learning process. The input is the score, and the output is the feedback content. This process allows learners to find the optimal solutions for improvement.

[0124] Step 6:

[0125] The server sends the generated feedback to the terminal and presents it to the user in real time. The terminal conveys this information to the user in either voice or text format. The input is the feedback content, and the output is the notification to the user. This step makes it possible to provide precise guidance at the moment of learning.

[0126] Step 7:

[0127] The server accumulates dialogue data and scores over the long term, providing feedback to the user on the effectiveness of past instruction. This helps improve future instructional strategies. The input is past dialogue data and scores, and the output is long-term feedback in continuous learning support. This process allows for the sustained improvement of learning effectiveness.

[0128] 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.

[0129] This invention is a system that supports the effectiveness of instruction and the building of trust by comprehensively analyzing the user's dialogue and emotions, and has the following configuration.

[0130] The system consists of a terminal that collects dialogue data, a server equipped with an emotion engine, and users who utilize it. First, the users, an instructor and a student, begin a dialogue session. The terminal collects the dialogue in either voice or text format and transmits the data to the server in real time.

[0131] The server first analyzes the received dialogue data using natural language processing techniques to extract topics and keywords. Furthermore, it uses an emotion engine to recognize the emotions contained in the dialogue in detail. This includes elements such as voice tone, language choice, and context.

[0132] For example, if a student expresses frustration by saying, "I really don't understand," the emotion engine recognizes this as an emotion of "anxiety" or "disappointment." This information is used in the subsequent score generation, where the server calculates evaluation scores for teaching effectiveness and trust. The result of emotion recognition contributes significantly to the score, with the positivity or negativity of the emotion adjusting the score.

[0133] The server then generates specific suggestions for improving instruction based on the generated score. These suggestions reflect the content of the conversation and the emotions perceived, providing advice tailored to the user's psychological state. For example, if a student indicates "anxiety," the suggestion might be to "provide more specific examples in the next session."

[0134] The server also stores all data over the long term and regularly evaluates and provides feedback on the user's emotional changes and the effectiveness of the instruction. This feedback reflects past emotional changes and the development of trust relationships, forming the basis for instructors to provide more effective instruction.

[0135] In this way, a system that incorporates an emotional engine can build deeper understanding and trust compared to conventional teaching methods, maximizing learning effectiveness. This approach is expected to significantly improve the quality of education and students' learning experience.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] Users (instructors and students) initiate online or in-person instruction sessions. The device collects data from the conversation during the session in real time through recording or text input.

[0139] Step 2:

[0140] The device sends the collected voice or text data to the server. The server prepares to store that data in its database.

[0141] Step 3:

[0142] The server analyzes the received dialogue data using natural language processing techniques. This analysis includes topic classification, extraction of key keywords, and initial preparation for sentiment analysis.

[0143] Step 4:

[0144] The server uses an emotion engine to recognize emotions from dialogue data. For audio data, it uses tone analysis, and for text data, it uses word choice and contextual analysis.

[0145] Step 5:

[0146] The server calculates an instruction effectiveness score and a trust score based on the analysis results. These scores include positive and negative emotions, quantitatively evaluating the quality and reliability of the instruction.

[0147] Step 6:

[0148] The server generates instructional improvement suggestions based on the calculated score. These suggestions include specific actions tailored to the user's current emotional state and are sent to the device.

[0149] Step 7:

[0150] The terminal displays real-time suggestions for improving instruction from the server to the instructor. The instructor uses these suggestions to adjust their teaching methods on the spot, providing more individualized instruction.

[0151] Step 8:

[0152] The server accumulates past dialogue data and sentiment analysis results over the long term, providing feedback on areas for improvement in instruction and progress in building trust. This enables continuous improvement of instruction.

[0153] (Example 2)

[0154] 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".

[0155] Traditional teaching methods made it difficult to efficiently grasp the emotional fluctuations and trust-building processes in user interactions, resulting in a lack of appropriate improvement suggestions to maximize teaching effectiveness. Furthermore, there was a problem in that methods for evaluating long-term teaching effectiveness and emotional changes, and providing feedback, were not sufficiently established.

[0156] 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.

[0157] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device, means for analyzing the stored dialogue data using natural language processing technology and generating evaluation indicators for evaluating the effectiveness of instruction and trust relationships, and means for generating and presenting suggestions for improving instruction based on the evaluation indicators. This enables detailed recognition of the user's emotions and instructional improvements that take into account the context of the conversation.

[0158] "Users" refers to individuals or groups of people who use the system, both as instructors and students.

[0159] "Dialogue" refers to the process of exchanging information between users via voice or text.

[0160] A "memory device" is hardware or software used to store dialogue data and analysis results.

[0161] "Natural language processing technology" is the technology that enables computers to understand, analyze, and process human language.

[0162] An "evaluation indicator" is a numerical value or standard calculated to numerically or qualitatively evaluate the effectiveness of instruction or the relationship of trust.

[0163] A "proposal" is a specific improvement plan or advice provided to the user based on evaluation indicators.

[0164] "Emotion recognition" is the process of identifying the psychological states contained in a user's dialogue.

[0165] "Feedback" refers to information that provides users with guidance and analysis results regarding changes in their emotions.

[0166] This invention is a system that comprehensively analyzes users' dialogue and emotions to support effective instruction and the building of trust. The system mainly consists of terminals, a server, and the users who utilize it.

[0167] Terminal role:

[0168] The device collects dialogue data using a voice input device or text input device when the instructor and student begin a dialogue session. The voice data is converted to a specific format, while the text data is sent directly to the server.

[0169] Server role:

[0170] The server stores the received dialogue data and analyzes it using natural language processing (NLP) techniques. Specifically, it uses NLP tools (e.g., SpaCy or NLTK) to extract topics and keywords from the text and understand their content. In addition, it uses an emotion engine to recognize the user's emotions. Emotion recognition takes into account voice tone and text context, and the analysis results are quantified as evaluation metrics.

[0171] The server uses a generative AI model based on the evaluation metrics to generate instructional improvement suggestions tailored to each individual case. For example, if a student expresses concern, saying, "I don't understand this part," the server will generate a suggestion such as, "We will add a more detailed explanation of this topic in the next lecture."

[0172] Furthermore, all data is accumulated over the long term, and the effectiveness of instruction and the evolution of emotions are regularly fed back. This allows instructors, as users, to develop more effective teaching strategies based on past data.

[0173] User roles:

[0174] This system allows users to accept instructional improvement suggestions provided during dialogue sessions and incorporate them into specific teaching strategies. These suggestions serve as guidelines for improving the quality of instruction and contribute to an enhanced learning experience.

[0175] Example of a prompt:

[0176] One possible input to the generative AI model would be, "Identify the emotions the student felt when asking the question, and suggest guidance that aligns with those emotions." This prompt is expected to enable the system to perform appropriate emotion analysis and suggest guidance.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The terminal initiates a dialogue session between the user (instructor) and student, and collects dialogue data using voice input devices and text input devices. The specific input is either voice data or text data. The terminal converts this data into an appropriate format and sends it to the server. The output is the converted dialogue data.

[0180] Step 2:

[0181] The server stores the received dialogue data in its memory. The input is the formatted dialogue data sent from the terminal. The server records this data and prepares it for the next analysis process. The output is the stored dialogue data.

[0182] Step 3:

[0183] The server uses natural language processing (NLP) techniques to analyze the stored dialogue data. The input is the dialogue data stored in memory. Specifically, NLP tools are used to process the data to extract topics and keywords from the text. The output is the extracted topics and keywords.

[0184] Step 4:

[0185] The server uses an emotion engine to perform emotion recognition from the analyzed data. The input consists of topics and keywords extracted in the previous stage. Specifically, it uses an emotion analysis algorithm to evaluate speech tone and text vocabulary selection, and performs data calculations to identify the user's emotion. The identified emotion is obtained as the output.

[0186] Step 5:

[0187] The server generates evaluation metrics to assess the effectiveness of instruction and trust based on recognized emotions and extracted information. The input consists of emotion data and topic / keyword information. A generative AI model is used to generate evaluation scores through complex data calculations. The output provides evaluation scores for instruction effectiveness and trustworthiness.

[0188] Step 6:

[0189] The server uses a generative AI model to create specific suggestions for improving instruction based on the evaluation score and presents them to the user. The input is the generated evaluation score, and the server generates appropriate advice for the user based on the prompt "Identify the emotions the student felt when asking the question and suggest instruction that aligns with those emotions." The generated instruction suggestions are provided as output.

[0190] Step 7:

[0191] The server accumulates dialogue data, emotion recognition results, and evaluation scores over the long term, and periodically analyzes this data. The input is all the data accumulated within the system. Based on this, the server generates feedback, providing the user with information on past guidance effectiveness and emotional changes. Feedback information is generated as output.

[0192] (Application Example 2)

[0193] 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".

[0194] Traditional education systems have faced challenges in providing sufficient feedback based on users' emotions and the content of their conversations, making it difficult to improve teaching effectiveness and build trust. Furthermore, there was the problem of not being able to provide appropriate suggestions for improving instruction tailored to individual users in real time.

[0195] 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.

[0196] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device; means for analyzing the stored dialogue data using natural language processing technology and generating a score for evaluating teaching effectiveness and trust relationships; and means for recognizing the speech, performing emotion analysis, and providing feedback appropriate to the recognized emotion based on that analysis. This makes it possible to accurately analyze the emotions of users in an educational setting and provide personalized teaching improvement suggestions in real time.

[0197] A "user" is an individual or group that uses the system and is the subject that receives guidance and feedback through dialogue.

[0198] "Dialogue data" refers to information collected as audio or text between users, and is used for sentiment analysis and instructional improvement.

[0199] A "storage device" is a hardware or software system for storing collected dialogue data, and is used as storage in the analysis and evaluation process.

[0200] "Natural language processing technology" is a general term for algorithms and methods used to analyze dialogue data and extract topics and keywords, and is a technology for language understanding.

[0201] "Instructional effectiveness" is an indicator used to evaluate the progress and level of understanding of users' learning, and is a standard for measuring the effectiveness of instruction.

[0202] "Trust" refers to the psychological bond and trust built between users, and is an important element for promoting instruction and learning.

[0203] A "score" is an evaluation criterion generated based on dialogue and emotions, and is an indicator that quantifies the effectiveness of instruction and the relationship of trust.

[0204] "Feedback" refers to information provided to users, including suggestions for improvement and advice, and is a response given to enhance the quality of learning and instruction.

[0205] "Emotional analysis" is a process that involves analyzing the content of a conversation in detail to identify the emotional state of the user, and it is an analytical technique that takes into account voice tone and context.

[0206] The system that realizes this invention acquires and analyzes user interactions to provide appropriate feedback. The system mainly consists of three elements: a server, a terminal, and a user.

[0207] The server uses speech recognition software to convert the dialogue data received from the terminal into text. Then, using natural language processing technology, it analyzes the text for topics and emotions related to the instruction and generates a score that evaluates trust and the effectiveness of the instruction. For example, if a user says "I really don't understand," the server classifies that statement as "anxiety" or "disappointment" and reflects it in the score. The server then uses this score to provide specific suggestions for improving the instruction, tailored to the dialogue and the emotions recognized. For example, it might suggest, "In the next session, we will provide more specific examples."

[0208] The device is equipped with a microphone and text input interface to collect user conversations and has the ability to transmit the collected data to a server in real time. Users participate in conversations via voice or text through the device and receive feedback on how the content and emotions of their conversations are being analyzed.

[0209] As a concrete example, if a user inputs "I'd like it to be a little easier to understand," the system processes the request using an emotion analysis engine and proposes an appropriate response, such as slowing down the explanation and re-explaining the content. An example of a prompt is also shown: "An example of a prompt from an AI model to analyze student dialogue and identify emotions: 'Please specify the anxiety or disappointment the student is feeling.'"

[0210] In this way, the cycle of interaction analysis and feedback provided by the server can improve the quality of learning and enhance the effectiveness of instruction.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The terminal captures the user's dialogue as either voice or text. The input is the user's voice or text data, which the terminal converts into a digital signal and sends to the server. This process ensures that the user's requests and statements are stored as data.

[0214] Step 2:

[0215] The server converts the received audio data into text using speech recognition software. The input is audio data sent from the terminal, and the output is text data. The server applies a speech recognition algorithm, analyzes phonemes, and generates a string of characters.

[0216] Step 3:

[0217] The server applies natural language processing techniques to the generated text data to extract keywords and topics. The input is text data generated by speech recognition, and the output is parsed topic information. This process involves syntactic analysis to identify important information.

[0218] Step 4:

[0219] The server uses an emotion analysis engine based on extracted topic information to identify the user's emotions. The input is topic information, and the output is emotion data. The server uses an emotion analysis algorithm to estimate emotions from the tone of speech and selected words.

[0220] Step 5:

[0221] The server generates a score that evaluates the effectiveness of instruction and trust based on identified sentiment data and topic information. The input is sentiment data and topic information, and the output is the score. This allows the server to quantitatively assess the user's state.

[0222] Step 6:

[0223] The server creates specific guidance improvement suggestions for the user based on the generated score and provides feedback via the terminal. The input is the score, and the output is the improvement suggestion. The server assembles the suggestions and presents appropriate responses based on the user's psychological state.

[0224] Step 7:

[0225] Users receive feedback through their devices and use it in subsequent dialogue sessions and learning activities. The input is the feedback content, and the output is the improvement of their learning. By reviewing the feedback and incorporating it into their learning plans, users can improve the quality of their learning.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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".

[0242] As an embodiment of this invention, a system is constructed in which a server, a terminal, and a user cooperate. The system is centered around the server, which interacts with the user through the terminal. It also has a mechanism to analyze the generated data and make suggestions to the user.

[0243] First, users (instructors and students) engage in dialogue, and the content is collected by the device as audio or text data. This data is sent to the server in real time. The server analyzes this data using natural language processing techniques to extract the dialogue's topic, emotions, and important keywords.

[0244] Next, the server calculates an effectiveness score and a trust score based on the analysis results. These scores serve as criteria for evaluation and are indicators of how effective the system is. For example, when a student says "I see, I understand" to indicate comprehension, the server adjusts the score as positive feedback.

[0245] Furthermore, the server generates specific suggestions for improving instruction based on the scores. These suggestions are notified to the instructor in real time via the terminal, allowing the instructor to immediately adjust their teaching methods accordingly. For example, an instruction might be given such as, "The student is confused, so please explain things more clearly."

[0246] The server accumulates dialogue data over the long term and provides regular feedback to determine user growth and areas for improvement in instruction. This feedback allows instructors to review the effectiveness of past lessons and apply that knowledge to future sessions.

[0247] These modules and functions enable this system to support the building of trust and effectively improve individual instruction through real-time dialogue analysis and feedback. The above is the basic form for carrying out the present invention.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] Users (instructors and students) initiate online or in-person instruction sessions. The device prepares to collect the session's dialogue in audio or text format and send it to the server.

[0251] Step 2:

[0252] The terminal transmits the collected conversation data to the server in real time. The server stores the received data and prepares it for the next analysis step.

[0253] Step 3:

[0254] The server analyzes the stored dialogue data using natural language processing techniques. Specifically, the server classifies the topics of the dialogues, performs sentiment analysis, and extracts relevant keywords and phrases.

[0255] Step 4:

[0256] The server calculates instruction effectiveness scores and trust scores based on the analysis results. Here, factors such as positive feedback and close communication are taken into account in the scoring.

[0257] Step 5:

[0258] The server generates specific instructional improvement suggestions based on the generated scores. These suggestions consist of actions that can be implemented immediately.

[0259] Step 6:

[0260] The terminal notifies the instructor of improvement suggestions received from the server. The instructor can then adjust their teaching methods on the spot, taking these suggestions into consideration.

[0261] Step 7:

[0262] The server accumulates all interaction data over the long term and analyzes the effectiveness of past instruction and the progress in building trust. This forms the basis for providing feedback for the next session.

[0263] Step 8:

[0264] The server periodically provides instructors with feedback on the analysis results via their terminals. This feedback includes evaluations of past instruction and insights for further improvement.

[0265] (Example 1)

[0266] 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."

[0267] In today's educational environment, it is essential to adapt teaching methods to each learner's level of understanding and interests. However, traditional classroom settings present challenges in real-time dialogue analysis and concrete improvements to teaching methods. Therefore, there is an urgent need to develop an effective feedback system that maximizes educational effectiveness and builds trust.

[0268] 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.

[0269] This invention includes a server that acquires dialogue between users and stores the digitized dialogue information in a storage medium; a server that analyzes the stored dialogue information using language processing technology and generates indicators for evaluating educational effectiveness and reliability coefficients; and a server that presents suggestions for educational improvement based on the generated indicators. This enables real-time dialogue analysis and concrete suggestions for improving instruction.

[0270] "Users" refers to the collective term for educators and learners who use the system to interact with each other.

[0271] "Dialogue information" refers to audio or text data that digitizes conversations between users.

[0272] "Storage medium" refers to a device or technology for storing digital information, and includes hard disks and cloud storage.

[0273] "Language processing technology" refers to techniques for analyzing natural language and understanding its meaning and structure.

[0274] "Educational effectiveness" is an indicator that shows the positive impact and results that educational activities have on learners.

[0275] The "trust coefficient" is a numerical indicator that shows the strength of the trust relationship formed between educators and learners.

[0276] An "indicator" is a numerical representation of the state or characteristics of the subject being evaluated, and serves as a standard for evaluation and judgment.

[0277] A "generative artificial intelligence model" refers to artificial intelligence technology that can automatically generate new information and suggestions based on input data.

[0278] "Educational improvement proposals" are pieces of information that suggest changes or adjustments to teaching methods in order to enhance learners' understanding and interest.

[0279] A description of embodiments for carrying out this invention will be given.

[0280] The system consists of a server, terminals, and users (instructors and students). Users initiate interactions through their terminals, which collect these interactions as audio or text data. The terminals then transmit the collected data to the server in real time.

[0281] The server plays the primary role of analyzing the received data. This analysis utilizes generative artificial intelligence models as a natural language processing technique. For example, OpenAI's language models can be used. The server uses these models to extract the conversation's topic, sentiment, and key keywords. Based on this information, the server calculates scores indicating educational effectiveness and confidence levels.

[0282] Next, the server generates specific suggestions for improving teaching based on the calculated scores. These suggestions are communicated to instructors via their terminals, providing support for adjusting teaching methods in real time. For example, a suggestion might be, "Students are having difficulty understanding, so please make your explanations more specific."

[0283] The server further analyzes long-term data and periodically provides feedback for understanding the growth of users and areas for improvement in guidance. This feedback serves as a basis for the instructor to review past guidance and apply it to future guidance.

[0284] As a specific example, the prompt text input into the generative AI model is "Please evaluate the students' understanding of new concepts and generate effective proposals for improving guidance." By using this prompt, the server can analyze the understanding of the learning content and propose appropriate guidance methods.

[0285] This system can provide a more reliable educational environment through real-time dialogue analysis and feedback, and effectively improve individual guidance.

[0286] The flow of the specific process in Example 1 will be described using FIG. 11.

[0287] Step 1:

[0288] The user starts the dialogue through the terminal. The user inputs the dialogue in voice or text format. The terminal converts this dialogue into digital data using speech recognition or text processing and prepares it as dialogue information. What is input is the user's voice or text, and what is output is digitized dialogue information.

[0289] Step 2:

[0290] The terminal transmits the prepared dialogue information to the server in real time. The terminal transports the digital data to the server via network communication. What is input is digitized dialogue information, and what is output is the dialogue information that reaches the server side.

[0291] Step 3:

[0292] The server analyzes the received dialogue information. Using a generative AI model, the server analyzes the dialogue information with natural language processing techniques to extract topics, emotions, and important keywords. The input is the dialogue information, and the output is the extracted analysis results. In this analysis, the AI ​​model understands the content of the dialogue and even judges the emotional tone.

[0293] Step 4:

[0294] The server calculates an educational effectiveness score and a trust relationship score based on the analysis results. The server compares the analysis results data with evaluation criteria and generates each score using a scoring algorithm. The input is the analysis results, and the output is the educational effectiveness score and the trust relationship score.

[0295] Step 5:

[0296] The server generates educational improvement suggestions based on the calculated score. The server evaluates the score and uses a generative AI model to create specific improvement suggestions. The inputs are the educational effectiveness score and the trust score, and the output is improvement suggestions. These suggestions include actions that the AI ​​model generates based on similar cases and existing knowledge bases.

[0297] Step 6:

[0298] The server sends generated educational improvement suggestions to instructors via terminals and notifies them. The server sends suggestions to terminals via network communication, and the terminals use their notification functions to inform instructors. The input is improvement suggestions, and the output is the notification received by the instructor. This communication is conducted in real time.

[0299] Step 7:

[0300] The server analyzes long-term accumulated dialogue data and provides regular feedback to the user. The server evaluates the information stored in the database along with past analysis results, extracts points for user growth and improvement in instruction, and creates a feedback report. The input is long-term accumulated data, and the output is a feedback report.

[0301] (Application Example 1)

[0302] 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."

[0303] In modern educational settings and home learning, accurately grasping the varying learning progress of each user and immediately implementing appropriate instructional improvements is difficult. Furthermore, there is a lack of concrete methods for improvement that enable effective instruction while building trust with users, thus creating a need to effectively support learners' growth.

[0304] 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.

[0305] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device; means for analyzing the stored dialogue data using natural language processing technology and generating a score for evaluating the effectiveness of instruction and trust relationship; means for presenting suggestions for improving instruction based on the generated score; means for accumulating past data and providing feedback on areas for improvement in instruction over the long term; and means for providing real-time feedback to the user via a terminal that collects the dialogue data and optimizing the user's learning progress. This enables learners to receive immediate feedback based on their individual needs and to make effective progress in their learning.

[0306] "Users" refers to individuals or groups who interact with the system and receive guidance through it.

[0307] "Dialogue data" refers to digital information that includes the content of communication between users through voice or text.

[0308] "Memory device" refers to an electronic data recording medium for storing the collected dialogue data.

[0309] "Natural language processing technology" is a general term for technologies used to process and analyze human language with a computer.

[0310] "Guidance effect score" refers to an indicator for numerically evaluating the learning progress and understanding level of users.

[0311] "Trust relationship score" refers to an indicator for numerically evaluating the degree of trust in communication between users.

[0312] "Feedback" refers to specific proposal information regarding improvement and guidance methods generated based on the analysis results.

[0313] "Terminal" refers to an electronic device used by users to interact with the system.

[0314] "Real-time" refers to the temporal property in which dialogue and feedback are carried out immediately.

[0315] The system for implementing this invention is realized through a series of processes centered around the acquisition, analysis, and feedback of dialogue data. Specifically, it is configured as follows.

[0316] First, the terminal collects the dialogue with the user and converts the dialogue into text data using speech recognition software (e.g., speech recognition API). This text data is quickly sent to the server and stored in the memory device.

[0317] The server uses natural language processing technologies (such as spaCy and speech analysis libraries) to analyze the received dialogue data. This analysis process applies algorithms that generate instruction effectiveness scores and trust scores, quantifying the user's level of understanding and trust.

[0318] After generating a score, the server utilizes a generative AI model to generate personalized feedback and offers users individualized suggestions for improving their instruction. This feedback is immediately presented to the user via their device, enabling real-time learning improvement. For example, if the server suggests that "it would be good to include more specific examples," that suggestion is immediately displayed on the device.

[0319] Furthermore, the server uses dialogue data and generated feedback to analyze long-term trends and support the user's continuous growth. This makes it possible to review the effectiveness of past instruction and use that information to improve future instruction.

[0320] For example, if a child says, "I don't understand this part of the math problem," the server can analyze the dialogue data and generate feedback such as, "Let me explain this area in more detail."

[0321] An example of a prompt might be: "Analyze the following text to identify the sentiment and create appropriate feedback. Text: 'I still haven't solved this problem.'"

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The device captures the user interaction as audio data. Speech recognition software is used to convert this audio data into text. The input is audio data, and the output is text data. This conversion process transforms speech into written information.

[0325] Step 2:

[0326] The terminal sends the converted text data to the server in real time. This transmission process uses a stable communication protocol to ensure that the data reaches the server quickly while preventing data loss. The input is text data, and the output is the raw text data that arrives at the server.

[0327] Step 3:

[0328] The server analyzes received text data using natural language processing techniques. Specifically, it performs calculations to extract emotions, topics, and keywords from the text content. The input is raw text data, and the output is the analysis result including topics, emotions, and keywords. This analysis allows for an understanding of the meaning and emotional shifts in the dialogue.

[0329] Step 4:

[0330] The server generates an instructional effectiveness score and a trust relationship score based on the analysis results. These scores, quantified using an algorithm, serve as a basis for making specific improvements to instruction. The input is the analysis results, and the output is the instructional effectiveness score and the trust relationship score. This allows for the evaluation of the user's learning progress.

[0331] Step 5:

[0332] The server utilizes a generated AI model to produce specific feedback based on the score. This feedback includes suggestions for improving the user's learning process. The input is the score, and the output is the feedback content. This process allows learners to find the optimal solutions for improvement.

[0333] Step 6:

[0334] The server sends the generated feedback to the terminal and presents it to the user in real time. The terminal conveys this information to the user in either voice or text format. The input is the feedback content, and the output is the notification to the user. This step makes it possible to provide precise guidance at the moment of learning.

[0335] Step 7:

[0336] The server accumulates dialogue data and scores over the long term, providing feedback to the user on the effectiveness of past instruction. This helps improve future instructional strategies. The input is past dialogue data and scores, and the output is long-term feedback in continuous learning support. This process allows for the sustained improvement of learning effectiveness.

[0337] 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.

[0338] This invention is a system that supports the effectiveness of instruction and the building of trust by comprehensively analyzing the user's dialogue and emotions, and has the following configuration.

[0339] The system consists of a terminal that collects dialogue data, a server equipped with an emotion engine, and users who utilize it. First, the users, an instructor and a student, begin a dialogue session. The terminal collects the dialogue in either voice or text format and transmits the data to the server in real time.

[0340] The server first analyzes the received dialogue data using natural language processing techniques to extract topics and keywords. Furthermore, it uses an emotion engine to recognize the emotions contained in the dialogue in detail. This includes elements such as voice tone, language choice, and context.

[0341] For example, if a student expresses frustration by saying, "I really don't understand," the emotion engine recognizes this as an emotion of "anxiety" or "disappointment." This information is used in the subsequent score generation, where the server calculates evaluation scores for teaching effectiveness and trust. The result of emotion recognition contributes significantly to the score, with the positivity or negativity of the emotion adjusting the score.

[0342] The server then generates specific suggestions for improving instruction based on the generated score. These suggestions reflect the content of the conversation and the emotions perceived, providing advice tailored to the user's psychological state. For example, if a student indicates "anxiety," the suggestion might be to "provide more specific examples in the next session."

[0343] The server also stores all data over the long term and regularly evaluates and provides feedback on the user's emotional changes and the effectiveness of the instruction. This feedback reflects past emotional changes and the development of trust relationships, forming the basis for instructors to provide more effective instruction.

[0344] In this way, a system that incorporates an emotional engine can build deeper understanding and trust compared to conventional teaching methods, maximizing learning effectiveness. This approach is expected to significantly improve the quality of education and students' learning experience.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] Users (instructors and students) initiate online or in-person instruction sessions. The device collects data from the conversation during the session in real time through recording or text input.

[0348] Step 2:

[0349] The device sends the collected voice or text data to the server. The server prepares to store that data in its database.

[0350] Step 3:

[0351] The server analyzes the received dialogue data using natural language processing techniques. This analysis includes topic classification, extraction of key keywords, and initial preparation for sentiment analysis.

[0352] Step 4:

[0353] The server uses an emotion engine to recognize emotions from dialogue data. For audio data, it uses tone analysis, and for text data, it uses word choice and contextual analysis.

[0354] Step 5:

[0355] The server calculates an instruction effectiveness score and a trust score based on the analysis results. These scores include positive and negative emotions, quantitatively evaluating the quality and reliability of the instruction.

[0356] Step 6:

[0357] The server generates instructional improvement suggestions based on the calculated score. These suggestions include specific actions tailored to the user's current emotional state and are sent to the device.

[0358] Step 7:

[0359] The terminal displays real-time suggestions for improving instruction from the server to the instructor. The instructor uses these suggestions to adjust their teaching methods on the spot, providing more individualized instruction.

[0360] Step 8:

[0361] The server accumulates past dialogue data and sentiment analysis results over the long term, providing feedback on areas for improvement in instruction and progress in building trust. This enables continuous improvement of instruction.

[0362] (Example 2)

[0363] 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".

[0364] Traditional teaching methods made it difficult to efficiently grasp the emotional fluctuations and trust-building processes in user interactions, resulting in a lack of appropriate improvement suggestions to maximize teaching effectiveness. Furthermore, there was a problem in that methods for evaluating long-term teaching effectiveness and emotional changes, and providing feedback, were not sufficiently established.

[0365] 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.

[0366] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device, means for analyzing the stored dialogue data using natural language processing technology and generating evaluation indicators for evaluating the effectiveness of instruction and trust relationships, and means for generating and presenting suggestions for improving instruction based on the evaluation indicators. This enables detailed recognition of the user's emotions and instructional improvements that take into account the context of the conversation.

[0367] "Users" refers to individuals or groups of people who use the system, both as instructors and students.

[0368] "Dialogue" refers to the process of exchanging information between users via voice or text.

[0369] A "memory device" is hardware or software used to store dialogue data and analysis results.

[0370] "Natural language processing technology" is the technology that enables computers to understand, analyze, and process human language.

[0371] An "evaluation indicator" is a numerical value or standard calculated to numerically or qualitatively evaluate the effectiveness of instruction or the relationship of trust.

[0372] A "proposal" is a specific improvement plan or advice provided to the user based on evaluation indicators.

[0373] "Emotion recognition" is the process of identifying the psychological states contained in a user's dialogue.

[0374] "Feedback" refers to information that provides users with guidance and analysis results regarding changes in their emotions.

[0375] This invention is a system that comprehensively analyzes users' dialogue and emotions to support effective instruction and the building of trust. The system mainly consists of terminals, a server, and the users who utilize it.

[0376] Terminal role:

[0377] The device collects dialogue data using a voice input device or text input device when the instructor and student begin a dialogue session. The voice data is converted to a specific format, while the text data is sent directly to the server.

[0378] Server role:

[0379] The server stores the received dialogue data and analyzes it using natural language processing (NLP) techniques. Specifically, it uses NLP tools (e.g., SpaCy or NLTK) to extract topics and keywords from the text and understand their content. In addition, it uses an emotion engine to recognize the user's emotions. Emotion recognition takes into account voice tone and text context, and the analysis results are quantified as evaluation metrics.

[0380] The server uses a generative AI model based on the evaluation metrics to generate instructional improvement suggestions tailored to each individual case. For example, if a student expresses concern, saying, "I don't understand this part," the server will generate a suggestion such as, "We will add a more detailed explanation of this topic in the next lecture."

[0381] Furthermore, all data is accumulated over the long term, and the effectiveness of instruction and the evolution of emotions are regularly fed back. This allows instructors, as users, to develop more effective teaching strategies based on past data.

[0382] User roles:

[0383] This system allows users to accept instructional improvement suggestions provided during dialogue sessions and incorporate them into specific teaching strategies. These suggestions serve as guidelines for improving the quality of instruction and contribute to an enhanced learning experience.

[0384] Example of a prompt:

[0385] One possible input to the generative AI model would be, "Identify the emotions the student felt when asking the question, and suggest guidance that aligns with those emotions." This prompt is expected to enable the system to perform appropriate emotion analysis and suggest guidance.

[0386] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0387] Step 1:

[0388] The terminal initiates a dialogue session between the user (instructor) and student, and collects dialogue data using voice input devices and text input devices. The specific input is either voice data or text data. The terminal converts this data into an appropriate format and sends it to the server. The output is the converted dialogue data.

[0389] Step 2:

[0390] The server stores the received dialogue data in its memory. The input is the formatted dialogue data sent from the terminal. The server records this data and prepares it for the next analysis process. The output is the stored dialogue data.

[0391] Step 3:

[0392] The server uses natural language processing (NLP) techniques to analyze the stored dialogue data. The input is the dialogue data stored in memory. Specifically, NLP tools are used to process the data to extract topics and keywords from the text. The output is the extracted topics and keywords.

[0393] Step 4:

[0394] The server uses an emotion engine to perform emotion recognition from the analyzed data. The input consists of topics and keywords extracted in the previous stage. Specifically, it uses an emotion analysis algorithm to evaluate speech tone and text vocabulary selection, and performs data calculations to identify the user's emotion. The identified emotion is obtained as the output.

[0395] Step 5:

[0396] The server generates evaluation metrics to assess the effectiveness of instruction and trust based on recognized emotions and extracted information. The input consists of emotion data and topic / keyword information. A generative AI model is used to generate evaluation scores through complex data calculations. The output provides evaluation scores for instruction effectiveness and trustworthiness.

[0397] Step 6:

[0398] The server uses a generative AI model to create specific suggestions for improving instruction based on the evaluation score and presents them to the user. The input is the generated evaluation score, and the server generates appropriate advice for the user based on the prompt "Identify the emotions the student felt when asking the question and suggest instruction that aligns with those emotions." The generated instruction suggestions are provided as output.

[0399] Step 7:

[0400] The server accumulates dialogue data, emotion recognition results, and evaluation scores over the long term, and periodically analyzes this data. The input is all the data accumulated within the system. Based on this, the server generates feedback, providing the user with information on past guidance effectiveness and emotional changes. Feedback information is generated as output.

[0401] (Application Example 2)

[0402] 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."

[0403] Traditional education systems have faced challenges in providing sufficient feedback based on users' emotions and the content of their conversations, making it difficult to improve teaching effectiveness and build trust. Furthermore, there was the problem of not being able to provide appropriate suggestions for improving instruction tailored to individual users in real time.

[0404] 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.

[0405] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device; means for analyzing the stored dialogue data using natural language processing technology and generating a score for evaluating teaching effectiveness and trust relationships; and means for recognizing the speech, performing emotion analysis, and providing feedback appropriate to the recognized emotion based on that analysis. This makes it possible to accurately analyze the emotions of users in an educational setting and provide personalized teaching improvement suggestions in real time.

[0406] A "user" is an individual or group that uses the system and is the subject that receives guidance and feedback through dialogue.

[0407] "Dialogue data" refers to information collected as audio or text between users, and is used for sentiment analysis and instructional improvement.

[0408] A "storage device" is a hardware or software system for storing collected dialogue data, and is used as storage in the analysis and evaluation process.

[0409] "Natural language processing technology" is a general term for algorithms and methods used to analyze dialogue data and extract topics and keywords, and is a technology for language understanding.

[0410] "Instructional effectiveness" is an indicator used to evaluate the progress and level of understanding of users' learning, and is a standard for measuring the effectiveness of instruction.

[0411] "Trust" refers to the psychological bond and trust built between users, and is an important element for promoting instruction and learning.

[0412] A "score" is an evaluation criterion generated based on dialogue and emotions, and is an indicator that quantifies the effectiveness of instruction and the relationship of trust.

[0413] "Feedback" refers to information provided to users, including suggestions for improvement and advice, and is a response given to enhance the quality of learning and instruction.

[0414] "Emotional analysis" is a process that involves analyzing the content of a conversation in detail to identify the emotional state of the user, and it is an analytical technique that takes into account voice tone and context.

[0415] The system that realizes this invention acquires and analyzes user interactions to provide appropriate feedback. The system mainly consists of three elements: a server, a terminal, and a user.

[0416] The server uses speech recognition software to convert the dialogue data received from the terminal into text. Then, using natural language processing technology, it analyzes the text for topics and emotions related to the instruction and generates a score that evaluates trust and the effectiveness of the instruction. For example, if a user says "I really don't understand," the server classifies that statement as "anxiety" or "disappointment" and reflects it in the score. The server then uses this score to provide specific suggestions for improving the instruction, tailored to the dialogue and the emotions recognized. For example, it might suggest, "In the next session, we will provide more specific examples."

[0417] The device is equipped with a microphone and text input interface to collect user conversations and has the ability to transmit the collected data to a server in real time. Users participate in conversations via voice or text through the device and receive feedback on how the content and emotions of their conversations are being analyzed.

[0418] As a concrete example, if a user inputs "I'd like it to be a little easier to understand," the system processes the request using an emotion analysis engine and proposes an appropriate response, such as slowing down the explanation and re-explaining the content. An example of a prompt is also shown: "An example of a prompt from an AI model to analyze student dialogue and identify emotions: 'Please specify the anxiety or disappointment the student is feeling.'"

[0419] In this way, the cycle of interaction analysis and feedback provided by the server can improve the quality of learning and enhance the effectiveness of instruction.

[0420] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0421] Step 1:

[0422] The terminal captures the user's dialogue as either voice or text. The input is the user's voice or text data, which the terminal converts into a digital signal and sends to the server. This process ensures that the user's requests and statements are stored as data.

[0423] Step 2:

[0424] The server converts the received audio data into text using speech recognition software. The input is audio data sent from the terminal, and the output is text data. The server applies a speech recognition algorithm, analyzes phonemes, and generates a string of characters.

[0425] Step 3:

[0426] The server applies natural language processing techniques to the generated text data to extract keywords and topics. The input is text data generated by speech recognition, and the output is parsed topic information. This process involves syntactic analysis to identify important information.

[0427] Step 4:

[0428] The server uses an emotion analysis engine based on extracted topic information to identify the user's emotions. The input is topic information, and the output is emotion data. The server uses an emotion analysis algorithm to estimate emotions from the tone of speech and selected words.

[0429] Step 5:

[0430] The server generates a score that evaluates the effectiveness of instruction and trust based on identified sentiment data and topic information. The input is sentiment data and topic information, and the output is the score. This allows the server to quantitatively assess the user's state.

[0431] Step 6:

[0432] The server creates specific guidance improvement suggestions for the user based on the generated score and provides feedback via the terminal. The input is the score, and the output is the improvement suggestion. The server assembles the suggestions and presents appropriate responses based on the user's psychological state.

[0433] Step 7:

[0434] Users receive feedback through their devices and use it in subsequent dialogue sessions and learning activities. The input is the feedback content, and the output is the improvement of their learning. By reviewing the feedback and incorporating it into their learning plans, users can improve the quality of their learning.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Third Embodiment]

[0439] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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".

[0451] As an embodiment of this invention, a system is constructed in which a server, a terminal, and a user cooperate. The system is centered around the server, which interacts with the user through the terminal. It also has a mechanism to analyze the generated data and make suggestions to the user.

[0452] First, users (instructors and students) engage in dialogue, and the content is collected by the device as audio or text data. This data is sent to the server in real time. The server analyzes this data using natural language processing techniques to extract the dialogue's topic, emotions, and important keywords.

[0453] Next, the server calculates an effectiveness score and a trust score based on the analysis results. These scores serve as criteria for evaluation and are indicators of how effective the system is. For example, when a student says "I see, I understand" to indicate comprehension, the server adjusts the score as positive feedback.

[0454] Furthermore, the server generates specific suggestions for improving instruction based on the scores. These suggestions are notified to the instructor in real time via the terminal, allowing the instructor to immediately adjust their teaching methods accordingly. For example, an instruction might be given such as, "The student is confused, so please explain things more clearly."

[0455] The server accumulates dialogue data over the long term and provides regular feedback to determine user growth and areas for improvement in instruction. This feedback allows instructors to review the effectiveness of past lessons and apply that knowledge to future sessions.

[0456] These modules and functions enable this system to support the building of trust and effectively improve individual instruction through real-time dialogue analysis and feedback. The above is the basic form for carrying out the present invention.

[0457] The following describes the processing flow.

[0458] Step 1:

[0459] Users (instructors and students) initiate online or in-person instruction sessions. The device prepares to collect the session's dialogue in audio or text format and send it to the server.

[0460] Step 2:

[0461] The terminal transmits the collected conversation data to the server in real time. The server stores the received data and prepares it for the next analysis step.

[0462] Step 3:

[0463] The server analyzes the stored dialogue data using natural language processing techniques. Specifically, the server classifies the topics of the dialogues, performs sentiment analysis, and extracts relevant keywords and phrases.

[0464] Step 4:

[0465] The server calculates instruction effectiveness scores and trust scores based on the analysis results. Here, factors such as positive feedback and close communication are taken into account in the scoring.

[0466] Step 5:

[0467] The server generates specific instructional improvement suggestions based on the generated scores. These suggestions consist of actions that can be implemented immediately.

[0468] Step 6:

[0469] The terminal notifies the instructor of improvement suggestions received from the server. The instructor can then adjust their teaching methods on the spot, taking these suggestions into consideration.

[0470] Step 7:

[0471] The server accumulates all interaction data over the long term and analyzes the effectiveness of past instruction and the progress in building trust. This forms the basis for providing feedback for the next session.

[0472] Step 8:

[0473] The server periodically provides instructors with feedback on the analysis results via their terminals. This feedback includes evaluations of past instruction and insights for further improvement.

[0474] (Example 1)

[0475] 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."

[0476] In today's educational environment, it is essential to adapt teaching methods to each learner's level of understanding and interests. However, traditional classroom settings present challenges in real-time dialogue analysis and concrete improvements to teaching methods. Therefore, there is an urgent need to develop an effective feedback system that maximizes educational effectiveness and builds trust.

[0477] 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.

[0478] This invention includes a server that acquires dialogue between users and stores the digitized dialogue information in a storage medium; a server that analyzes the stored dialogue information using language processing technology and generates indicators for evaluating educational effectiveness and reliability coefficients; and a server that presents suggestions for educational improvement based on the generated indicators. This enables real-time dialogue analysis and concrete suggestions for improving instruction.

[0479] "Users" refers to the collective term for educators and learners who use the system to interact with each other.

[0480] "Dialogue information" refers to audio or text data that digitizes conversations between users.

[0481] "Storage medium" refers to a device or technology for storing digital information, and includes hard disks and cloud storage.

[0482] "Language processing technology" refers to techniques for analyzing natural language and understanding its meaning and structure.

[0483] "Educational effectiveness" is an indicator that shows the positive impact and results that educational activities have on learners.

[0484] The "trust coefficient" is a numerical indicator that shows the strength of the trust relationship formed between educators and learners.

[0485] An "indicator" is a numerical representation of the state or characteristics of the subject being evaluated, and serves as a standard for evaluation and judgment.

[0486] A "generative artificial intelligence model" refers to artificial intelligence technology that can automatically generate new information and suggestions based on input data.

[0487] "Educational improvement proposals" are pieces of information that suggest changes or adjustments to teaching methods in order to enhance learners' understanding and interest.

[0488] A description of embodiments for carrying out this invention will be given.

[0489] The system consists of a server, terminals, and users (instructors and students). Users initiate interactions through their terminals, which collect these interactions as audio or text data. The terminals then transmit the collected data to the server in real time.

[0490] The server plays the primary role of analyzing the received data. This analysis utilizes generative artificial intelligence models as a natural language processing technique. For example, OpenAI's language models can be used. The server uses these models to extract the conversation's topic, sentiment, and key keywords. Based on this information, the server calculates scores indicating educational effectiveness and confidence levels.

[0491] Next, the server generates specific suggestions for improving teaching based on the calculated scores. These suggestions are communicated to instructors via their terminals, providing support for adjusting teaching methods in real time. For example, a suggestion might be, "Students are having difficulty understanding, so please make your explanations more specific."

[0492] The server also analyzes long-term data and regularly provides feedback to understand user growth and areas for improvement in instruction. This feedback serves as a foundation for instructors to reflect on past lessons and apply that knowledge to future lessons.

[0493] As a concrete example, the prompt input to the generating AI model would be, "Evaluate the student's understanding of the new concept and generate effective teaching improvement suggestions." Using this prompt, the server can analyze the student's understanding of the learning material and suggest appropriate teaching methods.

[0494] This system provides a more reliable educational environment and enables effective improvement of individual instruction through real-time dialogue analysis and feedback.

[0495] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0496] Step 1:

[0497] The user initiates a conversation through the terminal. The user inputs the conversation in voice or text format. The terminal converts this conversation into digital data using speech recognition or text processing and prepares it as conversation information. The input is the user's voice or text, and the output is digitized conversation information.

[0498] Step 2:

[0499] The terminal transmits prepared dialogue information to the server in real time. The terminal transports digital data to the server via network communication. The input is digitized dialogue information, and the output is the dialogue information that has reached the server.

[0500] Step 3:

[0501] The server analyzes the received dialogue information. Using a generative AI model, the server analyzes the dialogue information with natural language processing techniques to extract topics, emotions, and important keywords. The input is the dialogue information, and the output is the extracted analysis results. In this analysis, the AI ​​model understands the content of the dialogue and even judges the emotional tone.

[0502] Step 4:

[0503] The server calculates an educational effectiveness score and a trust relationship score based on the analysis results. The server compares the analysis results data with evaluation criteria and generates each score using a scoring algorithm. The input is the analysis results, and the output is the educational effectiveness score and the trust relationship score.

[0504] Step 5:

[0505] The server generates educational improvement suggestions based on the calculated score. The server evaluates the score and uses a generative AI model to create specific improvement suggestions. The inputs are the educational effectiveness score and the trust score, and the output is improvement suggestions. These suggestions include actions that the AI ​​model generates based on similar cases and existing knowledge bases.

[0506] Step 6:

[0507] The server sends generated educational improvement suggestions to instructors via terminals and notifies them. The server sends suggestions to terminals via network communication, and the terminals use their notification functions to inform instructors. The input is improvement suggestions, and the output is the notification received by the instructor. This communication is conducted in real time.

[0508] Step 7:

[0509] The server analyzes long-term accumulated dialogue data and provides regular feedback to the user. The server evaluates the information stored in the database along with past analysis results, extracts points for user growth and improvement in instruction, and creates a feedback report. The input is long-term accumulated data, and the output is a feedback report.

[0510] (Application Example 1)

[0511] 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."

[0512] In modern educational settings and home learning, accurately grasping the varying learning progress of each user and immediately implementing appropriate instructional improvements is difficult. Furthermore, there is a lack of concrete methods for improvement that enable effective instruction while building trust with users, thus creating a need to effectively support learners' growth.

[0513] 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.

[0514] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device; means for analyzing the stored dialogue data using natural language processing technology and generating a score for evaluating the effectiveness of instruction and trust relationship; means for presenting suggestions for improving instruction based on the generated score; means for accumulating past data and providing feedback on areas for improvement in instruction over the long term; and means for providing real-time feedback to the user via a terminal that collects the dialogue data and optimizing the user's learning progress. This enables learners to receive immediate feedback based on their individual needs and to make effective progress in their learning.

[0515] "Users" refers to individuals or groups who interact with the system and receive guidance through it.

[0516] "Dialogue data" refers to digital information that includes the content of voice and text communication between users.

[0517] A "memory device" refers to an electronic data recording medium used to store collected dialogue data.

[0518] "Natural language processing technology" is a general term for technologies used to process and analyze human language using computers.

[0519] The "instructional effectiveness score" refers to an index used to quantify and evaluate a user's learning progress and level of understanding.

[0520] A "trust score" refers to an index used to quantify and evaluate the level of trust in communication between users.

[0521] "Feedback" refers to specific suggestions for improvement and guidance methods that are generated based on the analysis results.

[0522] A "terminal" refers to an electronic device used by a user to interact with a system.

[0523] "Real-time" refers to the temporal nature of dialogue and feedback occurring immediately.

[0524] The system implementing this invention is realized through a series of processes centered on the acquisition, analysis, and feedback of dialogue data. Specifically, it is configured as follows:

[0525] First, the device collects the user's conversation and converts it into text data using speech recognition software (e.g., a speech recognition API). This text data is then quickly sent to a server and stored in its memory.

[0526] The server uses natural language processing technologies (such as spaCy and speech analysis libraries) to analyze the received dialogue data. This analysis process applies algorithms that generate instruction effectiveness scores and trust scores, quantifying the user's level of understanding and trust.

[0527] After generating a score, the server utilizes a generative AI model to generate personalized feedback and offers users individualized suggestions for improving their instruction. This feedback is immediately presented to the user via their device, enabling real-time learning improvement. For example, if the server suggests that "it would be good to include more specific examples," that suggestion is immediately displayed on the device.

[0528] Furthermore, the server uses dialogue data and generated feedback to analyze long-term trends and support the user's continuous growth. This makes it possible to review the effectiveness of past instruction and use that information to improve future instruction.

[0529] For example, if a child says, "I don't understand this part of the math problem," the server can analyze the dialogue data and generate feedback such as, "Let me explain this area in more detail."

[0530] An example of a prompt might be: "Analyze the following text to identify the sentiment and create appropriate feedback. Text: 'I still haven't solved this problem.'"

[0531] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0532] Step 1:

[0533] The device captures the user interaction as audio data. Speech recognition software is used to convert this audio data into text. The input is audio data, and the output is text data. This conversion process transforms speech into written information.

[0534] Step 2:

[0535] The terminal sends the converted text data to the server in real time. This transmission process uses a stable communication protocol to ensure that the data reaches the server quickly while preventing data loss. The input is text data, and the output is the raw text data that arrives at the server.

[0536] Step 3:

[0537] The server analyzes received text data using natural language processing techniques. Specifically, it performs calculations to extract emotions, topics, and keywords from the text content. The input is raw text data, and the output is the analysis result including topics, emotions, and keywords. This analysis allows for an understanding of the meaning and emotional shifts in the dialogue.

[0538] Step 4:

[0539] The server generates an instructional effectiveness score and a trust relationship score based on the analysis results. These scores, quantified using an algorithm, serve as a basis for making specific improvements to instruction. The input is the analysis results, and the output is the instructional effectiveness score and the trust relationship score. This allows for the evaluation of the user's learning progress.

[0540] Step 5:

[0541] The server utilizes a generated AI model to produce specific feedback based on the score. This feedback includes suggestions for improving the user's learning process. The input is the score, and the output is the feedback content. This process allows learners to find the optimal solutions for improvement.

[0542] Step 6:

[0543] The server sends the generated feedback to the terminal and presents it to the user in real time. The terminal conveys this information to the user in either voice or text format. The input is the feedback content, and the output is the notification to the user. This step makes it possible to provide precise guidance at the moment of learning.

[0544] Step 7:

[0545] The server accumulates dialogue data and scores over the long term, providing feedback to the user on the effectiveness of past instruction. This helps improve future instructional strategies. The input is past dialogue data and scores, and the output is long-term feedback in continuous learning support. This process allows for the sustained improvement of learning effectiveness.

[0546] 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.

[0547] This invention is a system that supports the effectiveness of instruction and the building of trust by comprehensively analyzing the user's dialogue and emotions, and has the following configuration.

[0548] The system consists of a terminal that collects dialogue data, a server equipped with an emotion engine, and users who utilize it. First, the users, an instructor and a student, begin a dialogue session. The terminal collects the dialogue in either voice or text format and transmits the data to the server in real time.

[0549] The server first analyzes the received dialogue data using natural language processing techniques to extract topics and keywords. Furthermore, it uses an emotion engine to recognize the emotions contained in the dialogue in detail. This includes elements such as voice tone, language choice, and context.

[0550] For example, if a student expresses frustration by saying, "I really don't understand," the emotion engine recognizes this as an emotion of "anxiety" or "disappointment." This information is used in the subsequent score generation, where the server calculates evaluation scores for teaching effectiveness and trust. The result of emotion recognition contributes significantly to the score, with the positivity or negativity of the emotion adjusting the score.

[0551] The server then generates specific suggestions for improving instruction based on the generated score. These suggestions reflect the content of the conversation and the emotions perceived, providing advice tailored to the user's psychological state. For example, if a student indicates "anxiety," the suggestion might be to "provide more specific examples in the next session."

[0552] The server also stores all data over the long term and regularly evaluates and provides feedback on the user's emotional changes and the effectiveness of the instruction. This feedback reflects past emotional changes and the development of trust relationships, forming the basis for instructors to provide more effective instruction.

[0553] In this way, a system that incorporates an emotional engine can build deeper understanding and trust compared to conventional teaching methods, maximizing learning effectiveness. This approach is expected to significantly improve the quality of education and students' learning experience.

[0554] The following describes the processing flow.

[0555] Step 1:

[0556] Users (instructors and students) initiate online or in-person instruction sessions. The device collects data from the conversation during the session in real time through recording or text input.

[0557] Step 2:

[0558] The device sends the collected voice or text data to the server. The server prepares to store that data in its database.

[0559] Step 3:

[0560] The server analyzes the received dialogue data using natural language processing techniques. This analysis includes topic classification, extraction of key keywords, and initial preparation for sentiment analysis.

[0561] Step 4:

[0562] The server uses an emotion engine to recognize emotions from dialogue data. For audio data, it uses tone analysis, and for text data, it uses word choice and contextual analysis.

[0563] Step 5:

[0564] The server calculates an instruction effectiveness score and a trust score based on the analysis results. These scores include positive and negative emotions, quantitatively evaluating the quality and reliability of the instruction.

[0565] Step 6:

[0566] The server generates instructional improvement suggestions based on the calculated score. These suggestions include specific actions tailored to the user's current emotional state and are sent to the device.

[0567] Step 7:

[0568] The terminal displays real-time suggestions for improving instruction from the server to the instructor. The instructor uses these suggestions to adjust their teaching methods on the spot, providing more individualized instruction.

[0569] Step 8:

[0570] The server accumulates past dialogue data and sentiment analysis results over the long term, providing feedback on areas for improvement in instruction and progress in building trust. This enables continuous improvement of instruction.

[0571] (Example 2)

[0572] 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."

[0573] Traditional teaching methods made it difficult to efficiently grasp the emotional fluctuations and trust-building processes in user interactions, resulting in a lack of appropriate improvement suggestions to maximize teaching effectiveness. Furthermore, there was a problem in that methods for evaluating long-term teaching effectiveness and emotional changes, and providing feedback, were not sufficiently established.

[0574] 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.

[0575] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device, means for analyzing the stored dialogue data using natural language processing technology and generating evaluation indicators for evaluating the effectiveness of instruction and trust relationships, and means for generating and presenting suggestions for improving instruction based on the evaluation indicators. This enables detailed recognition of the user's emotions and instructional improvements that take into account the context of the conversation.

[0576] "Users" refers to individuals or groups of people who use the system, both as instructors and students.

[0577] "Dialogue" refers to the process of exchanging information between users via voice or text.

[0578] A "memory device" is hardware or software used to store dialogue data and analysis results.

[0579] "Natural language processing technology" is the technology that enables computers to understand, analyze, and process human language.

[0580] An "evaluation indicator" is a numerical value or standard calculated to numerically or qualitatively evaluate the effectiveness of instruction or the relationship of trust.

[0581] A "proposal" is a specific improvement plan or advice provided to the user based on evaluation indicators.

[0582] "Emotion recognition" is the process of identifying the psychological states contained in a user's dialogue.

[0583] "Feedback" refers to information that provides users with guidance and analysis results regarding changes in their emotions.

[0584] This invention is a system that comprehensively analyzes users' dialogue and emotions to support effective instruction and the building of trust. The system mainly consists of terminals, a server, and the users who utilize it.

[0585] Terminal role:

[0586] The device collects dialogue data using a voice input device or text input device when the instructor and student begin a dialogue session. The voice data is converted to a specific format, while the text data is sent directly to the server.

[0587] Server role:

[0588] The server stores the received dialogue data and analyzes it using natural language processing (NLP) techniques. Specifically, it uses NLP tools (e.g., SpaCy or NLTK) to extract topics and keywords from the text and understand their content. In addition, it uses an emotion engine to recognize the user's emotions. Emotion recognition takes into account voice tone and text context, and the analysis results are quantified as evaluation metrics.

[0589] The server uses a generative AI model based on the evaluation metrics to generate instructional improvement suggestions tailored to each individual case. For example, if a student expresses concern, saying, "I don't understand this part," the server will generate a suggestion such as, "We will add a more detailed explanation of this topic in the next lecture."

[0590] Furthermore, all data is accumulated over the long term, and the effectiveness of instruction and the evolution of emotions are regularly fed back. This allows instructors, as users, to develop more effective teaching strategies based on past data.

[0591] User roles:

[0592] This system allows users to accept instructional improvement suggestions provided during dialogue sessions and incorporate them into specific teaching strategies. These suggestions serve as guidelines for improving the quality of instruction and contribute to an enhanced learning experience.

[0593] Example of a prompt:

[0594] One possible input to the generative AI model would be, "Identify the emotions the student felt when asking the question, and suggest guidance that aligns with those emotions." This prompt is expected to enable the system to perform appropriate emotion analysis and suggest guidance.

[0595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0596] Step 1:

[0597] The terminal initiates a dialogue session between the user (instructor) and student, and collects dialogue data using voice input devices and text input devices. The specific input is either voice data or text data. The terminal converts this data into an appropriate format and sends it to the server. The output is the converted dialogue data.

[0598] Step 2:

[0599] The server stores the received dialogue data in its memory. The input is the formatted dialogue data sent from the terminal. The server records this data and prepares it for the next analysis process. The output is the stored dialogue data.

[0600] Step 3:

[0601] The server uses natural language processing (NLP) techniques to analyze the stored dialogue data. The input is the dialogue data stored in memory. Specifically, NLP tools are used to process the data to extract topics and keywords from the text. The output is the extracted topics and keywords.

[0602] Step 4:

[0603] The server uses an emotion engine to perform emotion recognition from the analyzed data. The input consists of topics and keywords extracted in the previous stage. Specifically, it uses an emotion analysis algorithm to evaluate speech tone and text vocabulary selection, and performs data calculations to identify the user's emotion. The identified emotion is obtained as the output.

[0604] Step 5:

[0605] The server generates evaluation metrics to assess the effectiveness of instruction and trust based on recognized emotions and extracted information. The input consists of emotion data and topic / keyword information. A generative AI model is used to generate evaluation scores through complex data calculations. The output provides evaluation scores for instruction effectiveness and trustworthiness.

[0606] Step 6:

[0607] The server uses a generative AI model to create specific suggestions for improving instruction based on the evaluation score and presents them to the user. The input is the generated evaluation score, and the server generates appropriate advice for the user based on the prompt "Identify the emotions the student felt when asking the question and suggest instruction that aligns with those emotions." The generated instruction suggestions are provided as output.

[0608] Step 7:

[0609] The server accumulates dialogue data, emotion recognition results, and evaluation scores over the long term, and periodically analyzes this data. The input is all the data accumulated within the system. Based on this, the server generates feedback, providing the user with information on past guidance effectiveness and emotional changes. Feedback information is generated as output.

[0610] (Application Example 2)

[0611] 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."

[0612] Traditional education systems have faced challenges in providing sufficient feedback based on users' emotions and the content of their conversations, making it difficult to improve teaching effectiveness and build trust. Furthermore, there was the problem of not being able to provide appropriate suggestions for improving instruction tailored to individual users in real time.

[0613] 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.

[0614] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device; means for analyzing the stored dialogue data using natural language processing technology and generating a score for evaluating teaching effectiveness and trust relationships; and means for recognizing the speech, performing emotion analysis, and providing feedback appropriate to the recognized emotion based on that analysis. This makes it possible to accurately analyze the emotions of users in an educational setting and provide personalized teaching improvement suggestions in real time.

[0615] A "user" is an individual or group that uses the system and is the subject that receives guidance and feedback through dialogue.

[0616] "Dialogue data" refers to information collected as audio or text between users, and is used for sentiment analysis and instructional improvement.

[0617] A "storage device" is a hardware or software system for storing collected dialogue data, and is used as storage in the analysis and evaluation process.

[0618] "Natural language processing technology" is a general term for algorithms and methods used to analyze dialogue data and extract topics and keywords, and is a technology for language understanding.

[0619] "Instructional effectiveness" is an indicator used to evaluate the progress and level of understanding of users' learning, and is a standard for measuring the effectiveness of instruction.

[0620] "Trust" refers to the psychological bond and trust built between users, and is an important element for promoting instruction and learning.

[0621] A "score" is an evaluation criterion generated based on dialogue and emotions, and is an indicator that quantifies the effectiveness of instruction and the relationship of trust.

[0622] "Feedback" refers to information provided to users, including suggestions for improvement and advice, and is a response given to enhance the quality of learning and instruction.

[0623] "Emotional analysis" is a process that involves analyzing the content of a conversation in detail to identify the emotional state of the user, and it is an analytical technique that takes into account voice tone and context.

[0624] The system that realizes this invention acquires and analyzes user interactions to provide appropriate feedback. The system mainly consists of three elements: a server, a terminal, and a user.

[0625] The server uses speech recognition software to convert the dialogue data received from the terminal into text. Then, using natural language processing technology, it analyzes the text for topics and emotions related to the instruction and generates a score that evaluates trust and the effectiveness of the instruction. For example, if a user says "I really don't understand," the server classifies that statement as "anxiety" or "disappointment" and reflects it in the score. The server then uses this score to provide specific suggestions for improving the instruction, tailored to the dialogue and the emotions recognized. For example, it might suggest, "In the next session, we will provide more specific examples."

[0626] The device is equipped with a microphone and text input interface to collect user conversations and has the ability to transmit the collected data to a server in real time. Users participate in conversations via voice or text through the device and receive feedback on how the content and emotions of their conversations are being analyzed.

[0627] As a concrete example, if a user inputs "I'd like it to be a little easier to understand," the system processes the request using an emotion analysis engine and proposes an appropriate response, such as slowing down the explanation and re-explaining the content. An example of a prompt is also shown: "An example of a prompt from an AI model to analyze student dialogue and identify emotions: 'Please specify the anxiety or disappointment the student is feeling.'"

[0628] In this way, the cycle of interaction analysis and feedback provided by the server can improve the quality of learning and enhance the effectiveness of instruction.

[0629] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0630] Step 1:

[0631] The terminal captures the user's dialogue as either voice or text. The input is the user's voice or text data, which the terminal converts into a digital signal and sends to the server. This process ensures that the user's requests and statements are stored as data.

[0632] Step 2:

[0633] The server converts the received audio data into text using speech recognition software. The input is audio data sent from the terminal, and the output is text data. The server applies a speech recognition algorithm, analyzes phonemes, and generates a string of characters.

[0634] Step 3:

[0635] The server applies natural language processing techniques to the generated text data to extract keywords and topics. The input is text data generated by speech recognition, and the output is parsed topic information. This process involves syntactic analysis to identify important information.

[0636] Step 4:

[0637] The server uses an emotion analysis engine based on extracted topic information to identify the user's emotions. The input is topic information, and the output is emotion data. The server uses an emotion analysis algorithm to estimate emotions from the tone of speech and selected words.

[0638] Step 5:

[0639] The server generates a score that evaluates the effectiveness of instruction and trust based on identified sentiment data and topic information. The input is sentiment data and topic information, and the output is the score. This allows the server to quantitatively assess the user's state.

[0640] Step 6:

[0641] The server creates specific guidance improvement suggestions for the user based on the generated score and provides feedback via the terminal. The input is the score, and the output is the improvement suggestion. The server assembles the suggestions and presents appropriate responses based on the user's psychological state.

[0642] Step 7:

[0643] Users receive feedback through their devices and use it in subsequent dialogue sessions and learning activities. The input is the feedback content, and the output is the improvement of their learning. By reviewing the feedback and incorporating it into their learning plans, users can improve the quality of their learning.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] [Fourth Embodiment]

[0648] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0649] 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.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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).

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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".

[0661] As an embodiment of this invention, a system is constructed in which a server, a terminal, and a user cooperate. The system is centered around the server, which interacts with the user through the terminal. It also has a mechanism to analyze the generated data and make suggestions to the user.

[0662] First, users (instructors and students) engage in dialogue, and the content is collected by the device as audio or text data. This data is sent to the server in real time. The server analyzes this data using natural language processing techniques to extract the dialogue's topic, emotions, and important keywords.

[0663] Next, the server calculates an effectiveness score and a trust score based on the analysis results. These scores serve as criteria for evaluation and are indicators of how effective the system is. For example, when a student says "I see, I understand" to indicate comprehension, the server adjusts the score as positive feedback.

[0664] Furthermore, the server generates specific suggestions for improving instruction based on the scores. These suggestions are notified to the instructor in real time via the terminal, allowing the instructor to immediately adjust their teaching methods accordingly. For example, an instruction might be given such as, "The student is confused, so please explain things more clearly."

[0665] The server accumulates dialogue data over the long term and provides regular feedback to determine user growth and areas for improvement in instruction. This feedback allows instructors to review the effectiveness of past lessons and apply that knowledge to future sessions.

[0666] These modules and functions enable this system to support the building of trust and effectively improve individual instruction through real-time dialogue analysis and feedback. The above is the basic form for carrying out the present invention.

[0667] The following describes the processing flow.

[0668] Step 1:

[0669] Users (instructors and students) initiate online or in-person instruction sessions. The device prepares to collect the session's dialogue in audio or text format and send it to the server.

[0670] Step 2:

[0671] The terminal transmits the collected conversation data to the server in real time. The server stores the received data and prepares it for the next analysis step.

[0672] Step 3:

[0673] The server analyzes the stored dialogue data using natural language processing techniques. Specifically, the server classifies the topics of the dialogues, performs sentiment analysis, and extracts relevant keywords and phrases.

[0674] Step 4:

[0675] The server calculates instruction effectiveness scores and trust scores based on the analysis results. Here, factors such as positive feedback and close communication are taken into account in the scoring.

[0676] Step 5:

[0677] The server generates specific instructional improvement suggestions based on the generated scores. These suggestions consist of actions that can be implemented immediately.

[0678] Step 6:

[0679] The terminal notifies the instructor of improvement suggestions received from the server. The instructor can then adjust their teaching methods on the spot, taking these suggestions into consideration.

[0680] Step 7:

[0681] The server accumulates all interaction data over the long term and analyzes the effectiveness of past instruction and the progress in building trust. This forms the basis for providing feedback for the next session.

[0682] Step 8:

[0683] The server periodically provides instructors with feedback on the analysis results via their terminals. This feedback includes evaluations of past instruction and insights for further improvement.

[0684] (Example 1)

[0685] 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".

[0686] In today's educational environment, it is essential to adapt teaching methods to each learner's level of understanding and interests. However, traditional classroom settings present challenges in real-time dialogue analysis and concrete improvements to teaching methods. Therefore, there is an urgent need to develop an effective feedback system that maximizes educational effectiveness and builds trust.

[0687] 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.

[0688] This invention includes a server that acquires dialogue between users and stores the digitized dialogue information in a storage medium; a server that analyzes the stored dialogue information using language processing technology and generates indicators for evaluating educational effectiveness and reliability coefficients; and a server that presents suggestions for educational improvement based on the generated indicators. This enables real-time dialogue analysis and concrete suggestions for improving instruction.

[0689] "Users" refers to the collective term for educators and learners who use the system to interact with each other.

[0690] "Dialogue information" refers to audio or text data that digitizes conversations between users.

[0691] "Storage medium" refers to a device or technology for storing digital information, and includes hard disks and cloud storage.

[0692] "Language processing technology" refers to techniques for analyzing natural language and understanding its meaning and structure.

[0693] "Educational effectiveness" is an indicator that shows the positive impact and results that educational activities have on learners.

[0694] The "trust coefficient" is a numerical indicator that shows the strength of the trust relationship formed between educators and learners.

[0695] An "indicator" is a numerical representation of the state or characteristics of the subject being evaluated, and serves as a standard for evaluation and judgment.

[0696] A "generative artificial intelligence model" refers to artificial intelligence technology that can automatically generate new information and suggestions based on input data.

[0697] "Educational improvement proposals" are pieces of information that suggest changes or adjustments to teaching methods in order to enhance learners' understanding and interest.

[0698] A description of embodiments for carrying out this invention will be given.

[0699] The system consists of a server, terminals, and users (instructors and students). Users initiate interactions through their terminals, which collect these interactions as audio or text data. The terminals then transmit the collected data to the server in real time.

[0700] The server plays the primary role of analyzing the received data. This analysis utilizes generative artificial intelligence models as a natural language processing technique. For example, OpenAI's language models can be used. The server uses these models to extract the conversation's topic, sentiment, and key keywords. Based on this information, the server calculates scores indicating educational effectiveness and confidence levels.

[0701] Next, the server generates specific suggestions for improving teaching based on the calculated scores. These suggestions are communicated to instructors via their terminals, providing support for adjusting teaching methods in real time. For example, a suggestion might be, "Students are having difficulty understanding, so please make your explanations more specific."

[0702] The server also analyzes long-term data and regularly provides feedback to understand user growth and areas for improvement in instruction. This feedback serves as a foundation for instructors to reflect on past lessons and apply that knowledge to future lessons.

[0703] As a concrete example, the prompt input to the generating AI model would be, "Evaluate the student's understanding of the new concept and generate effective teaching improvement suggestions." Using this prompt, the server can analyze the student's understanding of the learning material and suggest appropriate teaching methods.

[0704] This system provides a more reliable educational environment and enables effective improvement of individual instruction through real-time dialogue analysis and feedback.

[0705] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0706] Step 1:

[0707] The user initiates a conversation through the terminal. The user inputs the conversation in voice or text format. The terminal converts this conversation into digital data using speech recognition or text processing and prepares it as conversation information. The input is the user's voice or text, and the output is digitized conversation information.

[0708] Step 2:

[0709] The terminal transmits prepared dialogue information to the server in real time. The terminal transports digital data to the server via network communication. The input is digitized dialogue information, and the output is the dialogue information that has reached the server.

[0710] Step 3:

[0711] The server analyzes the received dialogue information. Using a generative AI model, the server analyzes the dialogue information with natural language processing techniques to extract topics, emotions, and important keywords. The input is the dialogue information, and the output is the extracted analysis results. In this analysis, the AI ​​model understands the content of the dialogue and even judges the emotional tone.

[0712] Step 4:

[0713] The server calculates an educational effectiveness score and a trust relationship score based on the analysis results. The server compares the analysis results data with evaluation criteria and generates each score using a scoring algorithm. The input is the analysis results, and the output is the educational effectiveness score and the trust relationship score.

[0714] Step 5:

[0715] The server generates educational improvement suggestions based on the calculated score. The server evaluates the score and uses a generative AI model to create specific improvement suggestions. The inputs are the educational effectiveness score and the trust score, and the output is improvement suggestions. These suggestions include actions that the AI ​​model generates based on similar cases and existing knowledge bases.

[0716] Step 6:

[0717] The server sends generated educational improvement suggestions to instructors via terminals and notifies them. The server sends suggestions to terminals via network communication, and the terminals use their notification functions to inform instructors. The input is improvement suggestions, and the output is the notification received by the instructor. This communication is conducted in real time.

[0718] Step 7:

[0719] The server analyzes long-term accumulated dialogue data and provides regular feedback to the user. The server evaluates the information stored in the database along with past analysis results, extracts points for user growth and improvement in instruction, and creates a feedback report. The input is long-term accumulated data, and the output is a feedback report.

[0720] (Application Example 1)

[0721] 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".

[0722] In modern educational settings and home learning, accurately grasping the varying learning progress of each user and immediately implementing appropriate instructional improvements is difficult. Furthermore, there is a lack of concrete methods for improvement that enable effective instruction while building trust with users, thus creating a need to effectively support learners' growth.

[0723] 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.

[0724] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device; means for analyzing the stored dialogue data using natural language processing technology and generating a score for evaluating the effectiveness of instruction and trust relationship; means for presenting suggestions for improving instruction based on the generated score; means for accumulating past data and providing feedback on areas for improvement in instruction over the long term; and means for providing real-time feedback to the user via a terminal that collects the dialogue data and optimizing the user's learning progress. This enables learners to receive immediate feedback based on their individual needs and to make effective progress in their learning.

[0725] "Users" refers to individuals or groups who interact with the system and receive guidance through it.

[0726] "Dialogue data" refers to digital information that includes the content of voice and text communication between users.

[0727] A "memory device" refers to an electronic data recording medium used to store collected dialogue data.

[0728] "Natural language processing technology" is a general term for technologies used to process and analyze human language using computers.

[0729] The "instructional effectiveness score" refers to an index used to quantify and evaluate a user's learning progress and level of understanding.

[0730] A "trust score" refers to an index used to quantify and evaluate the level of trust in communication between users.

[0731] "Feedback" refers to specific suggestions for improvement and guidance methods that are generated based on the analysis results.

[0732] A "terminal" refers to an electronic device used by a user to interact with a system.

[0733] "Real-time" refers to the temporal nature of dialogue and feedback occurring immediately.

[0734] The system implementing this invention is realized through a series of processes centered on the acquisition, analysis, and feedback of dialogue data. Specifically, it is configured as follows:

[0735] First, the device collects the user's conversation and converts it into text data using speech recognition software (e.g., a speech recognition API). This text data is then quickly sent to a server and stored in its memory.

[0736] The server uses natural language processing technologies (such as spaCy and speech analysis libraries) to analyze the received dialogue data. This analysis process applies algorithms that generate instruction effectiveness scores and trust scores, quantifying the user's level of understanding and trust.

[0737] After generating a score, the server utilizes a generative AI model to generate personalized feedback and offers users individualized suggestions for improving their instruction. This feedback is immediately presented to the user via their device, enabling real-time learning improvement. For example, if the server suggests that "it would be good to include more specific examples," that suggestion is immediately displayed on the device.

[0738] Furthermore, the server uses dialogue data and generated feedback to analyze long-term trends and support the user's continuous growth. This makes it possible to review the effectiveness of past instruction and use that information to improve future instruction.

[0739] For example, if a child says, "I don't understand this part of the math problem," the server can analyze the dialogue data and generate feedback such as, "Let me explain this area in more detail."

[0740] An example of a prompt might be: "Analyze the following text to identify the sentiment and create appropriate feedback. Text: 'I still haven't solved this problem.'"

[0741] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0742] Step 1:

[0743] The device captures the user interaction as audio data. Speech recognition software is used to convert this audio data into text. The input is audio data, and the output is text data. This conversion process transforms speech into written information.

[0744] Step 2:

[0745] The terminal sends the converted text data to the server in real time. This transmission process uses a stable communication protocol to ensure that the data reaches the server quickly while preventing data loss. The input is text data, and the output is the raw text data that arrives at the server.

[0746] Step 3:

[0747] The server analyzes received text data using natural language processing techniques. Specifically, it performs calculations to extract emotions, topics, and keywords from the text content. The input is raw text data, and the output is the analysis result including topics, emotions, and keywords. This analysis allows for an understanding of the meaning and emotional shifts in the dialogue.

[0748] Step 4:

[0749] The server generates an instructional effectiveness score and a trust relationship score based on the analysis results. These scores, quantified using an algorithm, serve as a basis for making specific improvements to instruction. The input is the analysis results, and the output is the instructional effectiveness score and the trust relationship score. This allows for the evaluation of the user's learning progress.

[0750] Step 5:

[0751] The server utilizes a generated AI model to produce specific feedback based on the score. This feedback includes suggestions for improving the user's learning process. The input is the score, and the output is the feedback content. This process allows learners to find the optimal solutions for improvement.

[0752] Step 6:

[0753] The server sends the generated feedback to the terminal and presents it to the user in real time. The terminal conveys this information to the user in either voice or text format. The input is the feedback content, and the output is the notification to the user. This step makes it possible to provide precise guidance at the moment of learning.

[0754] Step 7:

[0755] The server accumulates dialogue data and scores over the long term, providing feedback to the user on the effectiveness of past instruction. This helps improve future instructional strategies. The input is past dialogue data and scores, and the output is long-term feedback in continuous learning support. This process allows for the sustained improvement of learning effectiveness.

[0756] 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.

[0757] This invention is a system that supports the effectiveness of instruction and the building of trust by comprehensively analyzing the user's dialogue and emotions, and has the following configuration.

[0758] The system consists of a terminal that collects dialogue data, a server equipped with an emotion engine, and users who utilize it. First, the users, an instructor and a student, begin a dialogue session. The terminal collects the dialogue in either voice or text format and transmits the data to the server in real time.

[0759] The server first analyzes the received dialogue data using natural language processing techniques to extract topics and keywords. Furthermore, it uses an emotion engine to recognize the emotions contained in the dialogue in detail. This includes elements such as voice tone, language choice, and context.

[0760] For example, if a student expresses frustration by saying, "I really don't understand," the emotion engine recognizes this as an emotion of "anxiety" or "disappointment." This information is used in the subsequent score generation, where the server calculates evaluation scores for teaching effectiveness and trust. The result of emotion recognition contributes significantly to the score, with the positivity or negativity of the emotion adjusting the score.

[0761] The server then generates specific suggestions for improving instruction based on the generated score. These suggestions reflect the content of the conversation and the emotions perceived, providing advice tailored to the user's psychological state. For example, if a student indicates "anxiety," the suggestion might be to "provide more specific examples in the next session."

[0762] The server also stores all data over the long term and regularly evaluates and provides feedback on the user's emotional changes and the effectiveness of the instruction. This feedback reflects past emotional changes and the development of trust relationships, forming the basis for instructors to provide more effective instruction.

[0763] In this way, a system that incorporates an emotional engine can build deeper understanding and trust compared to conventional teaching methods, maximizing learning effectiveness. This approach is expected to significantly improve the quality of education and students' learning experience.

[0764] The following describes the processing flow.

[0765] Step 1:

[0766] Users (instructors and students) initiate online or in-person instruction sessions. The device collects data from the conversation during the session in real time through recording or text input.

[0767] Step 2:

[0768] The device sends the collected voice or text data to the server. The server prepares to store that data in its database.

[0769] Step 3:

[0770] The server analyzes the received dialogue data using natural language processing techniques. This analysis includes topic classification, extraction of key keywords, and initial preparation for sentiment analysis.

[0771] Step 4:

[0772] The server uses an emotion engine to recognize emotions from dialogue data. For audio data, it uses tone analysis, and for text data, it uses word choice and contextual analysis.

[0773] Step 5:

[0774] The server calculates an instruction effectiveness score and a trust score based on the analysis results. These scores include positive and negative emotions, quantitatively evaluating the quality and reliability of the instruction.

[0775] Step 6:

[0776] The server generates instructional improvement suggestions based on the calculated score. These suggestions include specific actions tailored to the user's current emotional state and are sent to the device.

[0777] Step 7:

[0778] The terminal displays real-time suggestions for improving instruction from the server to the instructor. The instructor uses these suggestions to adjust their teaching methods on the spot, providing more individualized instruction.

[0779] Step 8:

[0780] The server accumulates past dialogue data and sentiment analysis results over the long term, providing feedback on areas for improvement in instruction and progress in building trust. This enables continuous improvement of instruction.

[0781] (Example 2)

[0782] 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".

[0783] Traditional teaching methods made it difficult to efficiently grasp the emotional fluctuations and trust-building processes in user interactions, resulting in a lack of appropriate improvement suggestions to maximize teaching effectiveness. Furthermore, there was a problem in that methods for evaluating long-term teaching effectiveness and emotional changes, and providing feedback, were not sufficiently established.

[0784] 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.

[0785] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device, means for analyzing the stored dialogue data using natural language processing technology and generating evaluation indicators for evaluating the effectiveness of instruction and trust relationships, and means for generating and presenting suggestions for improving instruction based on the evaluation indicators. This enables detailed recognition of the user's emotions and instructional improvements that take into account the context of the conversation.

[0786] "Users" refers to individuals or groups of people who use the system, both as instructors and students.

[0787] "Dialogue" refers to the process of exchanging information between users via voice or text.

[0788] A "memory device" is hardware or software used to store dialogue data and analysis results.

[0789] "Natural language processing technology" is the technology that enables computers to understand, analyze, and process human language.

[0790] An "evaluation indicator" is a numerical value or standard calculated to numerically or qualitatively evaluate the effectiveness of instruction or the relationship of trust.

[0791] A "proposal" is a specific improvement plan or advice provided to the user based on evaluation indicators.

[0792] "Emotion recognition" is the process of identifying the psychological states contained in a user's dialogue.

[0793] "Feedback" refers to information that provides users with guidance and analysis results regarding changes in their emotions.

[0794] This invention is a system that comprehensively analyzes users' dialogue and emotions to support effective instruction and the building of trust. The system mainly consists of terminals, a server, and the users who utilize it.

[0795] Terminal role:

[0796] The device collects dialogue data using a voice input device or text input device when the instructor and student begin a dialogue session. The voice data is converted to a specific format, while the text data is sent directly to the server.

[0797] Server role:

[0798] The server stores the received dialogue data and analyzes it using natural language processing (NLP) techniques. Specifically, it uses NLP tools (e.g., SpaCy or NLTK) to extract topics and keywords from the text and understand their content. In addition, it uses an emotion engine to recognize the user's emotions. Emotion recognition takes into account voice tone and text context, and the analysis results are quantified as evaluation metrics.

[0799] The server uses a generative AI model based on the evaluation metrics to generate instructional improvement suggestions tailored to each individual case. For example, if a student expresses concern, saying, "I don't understand this part," the server will generate a suggestion such as, "We will add a more detailed explanation of this topic in the next lecture."

[0800] Furthermore, all data is accumulated over the long term, and the effectiveness of instruction and the evolution of emotions are regularly fed back. This allows instructors, as users, to develop more effective teaching strategies based on past data.

[0801] User roles:

[0802] This system allows users to accept instructional improvement suggestions provided during dialogue sessions and incorporate them into specific teaching strategies. These suggestions serve as guidelines for improving the quality of instruction and contribute to an enhanced learning experience.

[0803] Example of a prompt:

[0804] One possible input to the generative AI model would be, "Identify the emotions the student felt when asking the question, and suggest guidance that aligns with those emotions." This prompt is expected to enable the system to perform appropriate emotion analysis and suggest guidance.

[0805] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0806] Step 1:

[0807] The terminal initiates a dialogue session between the user (instructor) and student, and collects dialogue data using voice input devices and text input devices. The specific input is either voice data or text data. The terminal converts this data into an appropriate format and sends it to the server. The output is the converted dialogue data.

[0808] Step 2:

[0809] The server stores the received dialogue data in its memory. The input is the formatted dialogue data sent from the terminal. The server records this data and prepares it for the next analysis process. The output is the stored dialogue data.

[0810] Step 3:

[0811] The server uses natural language processing (NLP) techniques to analyze the stored dialogue data. The input is the dialogue data stored in memory. Specifically, NLP tools are used to process the data to extract topics and keywords from the text. The output is the extracted topics and keywords.

[0812] Step 4:

[0813] The server uses an emotion engine to perform emotion recognition from the analyzed data. The input consists of topics and keywords extracted in the previous stage. Specifically, it uses an emotion analysis algorithm to evaluate speech tone and text vocabulary selection, and performs data calculations to identify the user's emotion. The identified emotion is obtained as the output.

[0814] Step 5:

[0815] The server generates evaluation metrics to assess the effectiveness of instruction and trust based on recognized emotions and extracted information. The input consists of emotion data and topic / keyword information. A generative AI model is used to generate evaluation scores through complex data calculations. The output provides evaluation scores for instruction effectiveness and trustworthiness.

[0816] Step 6:

[0817] The server uses a generative AI model to create specific suggestions for improving instruction based on the evaluation score and presents them to the user. The input is the generated evaluation score, and the server generates appropriate advice for the user based on the prompt "Identify the emotions the student felt when asking the question and suggest instruction that aligns with those emotions." The generated instruction suggestions are provided as output.

[0818] Step 7:

[0819] The server accumulates dialogue data, emotion recognition results, and evaluation scores over the long term, and periodically analyzes this data. The input is all the data accumulated within the system. Based on this, the server generates feedback, providing the user with information on past guidance effectiveness and emotional changes. Feedback information is generated as output.

[0820] (Application Example 2)

[0821] 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".

[0822] Traditional education systems have faced challenges in providing sufficient feedback based on users' emotions and the content of their conversations, making it difficult to improve teaching effectiveness and build trust. Furthermore, there was the problem of not being able to provide appropriate suggestions for improving instruction tailored to individual users in real time.

[0823] 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.

[0824] In this invention, the server includes means for acquiring user dialogue and storing the dialogue data in a storage device; means for analyzing the stored dialogue data using natural language processing technology and generating a score for evaluating teaching effectiveness and trust relationships; and means for recognizing the speech, performing emotion analysis, and providing feedback appropriate to the recognized emotion based on that analysis. This makes it possible to accurately analyze the emotions of users in an educational setting and provide personalized teaching improvement suggestions in real time.

[0825] A "user" is an individual or group that uses the system and is the subject that receives guidance and feedback through dialogue.

[0826] "Dialogue data" refers to information collected as audio or text between users, and is used for sentiment analysis and instructional improvement.

[0827] A "storage device" is a hardware or software system for storing collected dialogue data, and is used as storage in the analysis and evaluation process.

[0828] "Natural language processing technology" is a general term for algorithms and methods used to analyze dialogue data and extract topics and keywords, and is a technology for language understanding.

[0829] "Instructional effectiveness" is an indicator used to evaluate the progress and level of understanding of users' learning, and is a standard for measuring the effectiveness of instruction.

[0830] "Trust" refers to the psychological bond and trust built between users, and is an important element for promoting instruction and learning.

[0831] A "score" is an evaluation criterion generated based on dialogue and emotions, and is an indicator that quantifies the effectiveness of instruction and the relationship of trust.

[0832] "Feedback" refers to information provided to users, including suggestions for improvement and advice, and is a response given to enhance the quality of learning and instruction.

[0833] "Emotional analysis" is a process that involves analyzing the content of a conversation in detail to identify the emotional state of the user, and it is an analytical technique that takes into account voice tone and context.

[0834] The system that realizes this invention acquires and analyzes user interactions to provide appropriate feedback. The system mainly consists of three elements: a server, a terminal, and a user.

[0835] The server uses speech recognition software to convert the dialogue data received from the terminal into text. Then, using natural language processing technology, it analyzes the text for topics and emotions related to the instruction and generates a score that evaluates trust and the effectiveness of the instruction. For example, if a user says "I really don't understand," the server classifies that statement as "anxiety" or "disappointment" and reflects it in the score. The server then uses this score to provide specific suggestions for improving the instruction, tailored to the dialogue and the emotions recognized. For example, it might suggest, "In the next session, we will provide more specific examples."

[0836] The device is equipped with a microphone and text input interface to collect user conversations and has the ability to transmit the collected data to a server in real time. Users participate in conversations via voice or text through the device and receive feedback on how the content and emotions of their conversations are being analyzed.

[0837] As a concrete example, if a user inputs "I'd like it to be a little easier to understand," the system processes the request using an emotion analysis engine and proposes an appropriate response, such as slowing down the explanation and re-explaining the content. An example of a prompt is also shown: "An example of a prompt from an AI model to analyze student dialogue and identify emotions: 'Please specify the anxiety or disappointment the student is feeling.'"

[0838] In this way, the cycle of interaction analysis and feedback provided by the server can improve the quality of learning and enhance the effectiveness of instruction.

[0839] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0840] Step 1:

[0841] The terminal captures the user's dialogue as either voice or text. The input is the user's voice or text data, which the terminal converts into a digital signal and sends to the server. This process ensures that the user's requests and statements are stored as data.

[0842] Step 2:

[0843] The server converts the received audio data into text using speech recognition software. The input is audio data sent from the terminal, and the output is text data. The server applies a speech recognition algorithm, analyzes phonemes, and generates a string of characters.

[0844] Step 3:

[0845] The server applies natural language processing techniques to the generated text data to extract keywords and topics. The input is text data generated by speech recognition, and the output is parsed topic information. This process involves syntactic analysis to identify important information.

[0846] Step 4:

[0847] The server uses an emotion analysis engine based on extracted topic information to identify the user's emotions. The input is topic information, and the output is emotion data. The server uses an emotion analysis algorithm to estimate emotions from the tone of speech and selected words.

[0848] Step 5:

[0849] The server generates a score that evaluates the effectiveness of instruction and trust based on identified sentiment data and topic information. The input is sentiment data and topic information, and the output is the score. This allows the server to quantitatively assess the user's state.

[0850] Step 6:

[0851] The server creates specific guidance improvement suggestions for the user based on the generated score and provides feedback via the terminal. The input is the score, and the output is the improvement suggestion. The server assembles the suggestions and presents appropriate responses based on the user's psychological state.

[0852] Step 7:

[0853] Users receive feedback through their devices and use it in subsequent dialogue sessions and learning activities. The input is the feedback content, and the output is the improvement of their learning. By reviewing the feedback and incorporating it into their learning plans, users can improve the quality of their learning.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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."

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] The following is further disclosed regarding the embodiments described above.

[0876] (Claim 1)

[0877] A means for acquiring user dialogue and storing that dialogue data in a storage device,

[0878] A means for analyzing stored dialogue data using natural language processing technology and generating scores for evaluating instructional effectiveness and trust relationships,

[0879] A means of presenting suggestions for improving instruction based on the generated score,

[0880] A means of accumulating past data and providing feedback on areas for improvement in instruction over the long term,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, which analyzes the content of conversations between users in real time and immediately presents suggestions for improving instruction.

[0884] (Claim 3)

[0885] The system according to claim 1, which provides definitions and calculation methods for various scores related to trust and effectiveness of guidance.

[0886] "Example 1"

[0887] (Claim 1)

[0888] A means for acquiring dialogue between users and storing the digitized dialogue information in a storage medium,

[0889] A means for analyzing stored dialogue information using language processing technology and generating indicators for evaluating educational effectiveness and confidence coefficients,

[0890] A means of presenting proposals for educational improvement based on the generated indicators,

[0891] A means of accumulating past information and providing feedback on areas for improvement in education over the long term,

[0892] In the analysis and index generation, a means of using a generative artificial intelligence model,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, which analyzes user interactions in real time and immediately presents suggestions for educational improvement.

[0896] (Claim 3)

[0897] The system according to claim 1, which provides definitions and calculation methods for various indicators related to the confidence coefficient and educational effectiveness.

[0898] "Application Example 1"

[0899] (Claim 1)

[0900] A means for acquiring user dialogue and storing that dialogue data in a storage device,

[0901] A means for analyzing stored dialogue data using natural language processing technology and generating scores for evaluating instructional effectiveness and trust relationships,

[0902] A means of presenting suggestions for improving instruction based on the generated score,

[0903] A means of accumulating past data and providing feedback on areas for improvement in instruction over the long term,

[0904] A means for providing real-time feedback to the user via a terminal that collects the aforementioned dialogue data, and for optimizing the user's learning progress,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, which analyzes the content of conversations between users in real time, immediately presents suggestions for improving instruction, and promotes user growth.

[0908] (Claim 3)

[0909] The system according to claim 1, which provides definitions and calculation methods for various scores related to trust and effectiveness of guidance, and generates and presents specific feedback to the user based on these.

[0910] "Example 2 of combining an emotion engine"

[0911] (Claim 1)

[0912] A means for acquiring user dialogue and storing that dialogue data in a storage device,

[0913] A means for analyzing stored dialogue data using natural language processing technology and generating evaluation indicators for evaluating instructional effectiveness and trust relationships,

[0914] A means of generating and presenting suggestions for improving instruction based on evaluation indicators,

[0915] A means of accumulating past data and regularly providing feedback on emotional changes and the effectiveness of guidance,

[0916] A means to recognize the user's emotions in detail and perform emotion analysis that takes into account the context of the conversation,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, which analyzes the content of conversations between users in real time and immediately provides suggestions for improving instruction.

[0920] (Claim 3)

[0921] The system according to claim 1, which provides definitions and calculation methods for various evaluation indicators related to trust and the effectiveness of guidance, and enables the generated proposals to provide guidance that is appropriate to the psychological state of the user.

[0922] "Application example 2 when combining with an emotional engine"

[0923] (Claim 1)

[0924] A means for acquiring user dialogue and storing that dialogue data in a storage device,

[0925] A means for analyzing stored dialogue data using natural language processing technology and generating scores for evaluating instructional effectiveness and trust relationships,

[0926] A means of presenting suggestions for improving instruction based on the generated score,

[0927] A means of accumulating past data and providing feedback on areas for improvement in instruction over the long term,

[0928] A means for recognizing spoken audio, performing emotion analysis, and providing feedback appropriate to the recognized emotion based on that analysis,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, which analyzes the content of conversations between users in real time and immediately presents suggestions for improving instruction.

[0932] (Claim 3)

[0933] The system according to claim 1, which provides definitions and calculation methods for various scores related to trust and effectiveness of guidance. [Explanation of Symbols]

[0934] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring user dialogue and storing that dialogue data in a storage device, A means for analyzing stored dialogue data using natural language processing technology and generating scores for evaluating instructional effectiveness and trust relationships, A means of presenting suggestions for improving instruction based on the generated score, A means of accumulating past data and providing feedback on areas for improvement in instruction over the long term, A system that includes this.

2. The system according to claim 1, which analyzes the content of conversations between users in real time and immediately presents suggestions for improving instruction.

3. The system according to claim 1, which provides definitions and calculation methods for various scores related to trust and effectiveness of guidance.

Images