System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving speech or text data from a user; means for analyzing a context of the received data using natural language processing techniques; means for estimating an intent of a response based on the analyzed context; means for comparing context analysis results and response estimation results to identify a lack of mutual understanding; means for visualizing the lack of mutual understanding and generating summary data; and means for transmitting the generated visualization results and summary data to a user terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Confirming mutual understanding is extremely important in learning, education, and communication, but the process is complicated, and it is often difficult to clearly identify what is not understood. Conventional systems tend to focus on the "understood" parts, which can leave learners and interlocutors feeling confused and confused about what they don't understand. The purpose of this invention is to solve this problem and clarify the lack of mutual understanding. [Means for solving the problem]

[0005] The present invention provides a system including: means for receiving utterances and text data from a user; means for analyzing the context of the received data using natural language processing technology; means for inferring the intention of the response based on the analyzed context; means for identifying a lack of mutual understanding by comparing the context analysis result with the response estimation result; means for visualizing the lack of mutual understanding and generating summary data; and means for transmitting the generated visualization result and summary data to a user terminal. This system clarifies the lack of mutual understanding, visualizes which parts the user specifically does not understand, and provides appropriate feedback, thereby improving the effectiveness of learning and communication.

[0006] "User" refers to a person or group that uses the system.

[0007] "Speech" refers to the expression or communication that a person makes using voice.

[0008] "Text data" refers to information expressed in written characters.

[0009] "Context" refers to information about the meaning and background of a particular utterance or text.

[0010] "Natural language processing technology" refers to technology that enables computers to understand and process human language.

[0011] "Response intention" refers to the content or purpose that the speaker wants to convey through their utterance.

[0012] "Lack of mutual understanding" refers to a situation in which the intention or meaning is not properly conveyed between the speaker and the listener in communication.

[0013] "Visualization" refers to the representation of information through visual means such as diagrams and graphs.

[0014] "Summary data" refers to information that summarizes long information in a concise manner.

[0015] "User terminal" refers to a device or equipment that is directly operated by a user. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention provides a system that analyzes user utterances and text data to identify and visualize lack of mutual understanding. The specific program processing of this system will be described below.

[0038] Server-side processing

[0039] 1. Data reception:

[0040] The server receives speech and text data from the user. For example, a student may ask a question such as "I don't know how to solve this equation" through speech or text. This data is sent to the server, which then receives it.

[0041] 2. Contextual analysis:

[0042] The server uses natural language processing technology to analyze the context of the received speech and text data. For example, it extracts information about the mathematical formula and how to solve it, and analyzes its meaning and background.

[0043] 3. Response analysis:

[0044] Similarly, the server uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "That can be solved using the basic integral formula," the server infers that the intent of this response means, "You need to understand the basic integral formula."

[0045] 4. Identifying the lack of mutual understanding:

[0046] By combining the results of context analysis and response analysis, the server identifies which part the user does not understand. In this case, it identifies that the student does not understand the "basic integral formula."

[0047] 5. Visualization and summary generation:

[0048] The system generates summary data to visualize and clearly display the identified areas of insufficient understanding, such as a message like "You lack understanding of the basic integral formula" along with an example of how to apply the formula.

[0049] 6. Data Transmission:

[0050] The generated visualization results and summary data are sent to the user's device, allowing the student to specifically identify their own lack of understanding and move on to the next learning step.

[0051] Terminal side processing

[0052] 1. Data reception:

[0053] The user device receives the visualization results and summary data sent from the server, such as a student's smartphone or PC.

[0054] 2. Data display:

[0055] The user terminal displays the received data to the user, for example, displaying a message such as "You lack understanding of the basic integral formula" along with specific step-by-step explanations and diagrams.

[0056] Specific examples

[0057] As a concrete example, consider the case where a student asks, "I don't know how to solve this equation" in a mathematics class. The student's speech data is sent to the server, which receives this data. Next, context analysis is used to analyze the meaning and background information of "how to solve the equation," and the teacher's response, "You can solve it by using the basic integral formula," is received. The server infers the intent of this response and determines that the student does not understand the "basic integral formula." Finally, a visualized summary message stating "You lack understanding of the basic integral formula" and an explanatory diagram are generated and sent to the user's device. The device receives this and displays it to the student, allowing them to specifically identify their lack of understanding and advance their learning.

[0058] This system allows users to clearly understand what they do not understand and receive appropriate feedback, thereby improving the effectiveness of learning and communication.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user inputs a question or utterance. For example, a student inputs the text "I don't know how to solve this equation." The input data is sent to the server.

[0062] Step 2:

[0063] The server captures and stores the speech and text data received from the user, and prepares the received data for the next analysis step.

[0064] Step 3:

[0065] The server uses natural language processing technology on the received speech data. Specifically, it analyzes the structure and grammatical elements of the text and extracts the context. This identifies the problem domain, i.e., "how to solve mathematical equations."

[0066] Step 4:

[0067] The server performs response analysis on the utterance content. When a teacher inputs a response such as "You can solve that by using the basic integral formula," the server infers the teacher's intention and analyzes the answer strategy "basic integral formula."

[0068] Step 5:

[0069] The server integrates the results of context analysis and response analysis to identify a lack of mutual understanding. Specifically, it identifies that the student does not understand the "basic integral formula" and expresses this in one word.

[0070] Step 6:

[0071] The server visualizes the gaps in mutual understanding and generates summary data, such as a diagram that includes an example of the application of the formula along with a message saying, "You lack understanding of the basic integral formula."

[0072] Step 7:

[0073] The server sends the generated visualization results and summary data to the user's terminal, allowing the user to receive specific feedback.

[0074] Step 8:

[0075] The terminal receives the visualization results and summary data sent from the server, and the received data is displayed appropriately for the user, allowing students to check its contents.

[0076] Step 9:

[0077] Users can view the visualization results and summary data on their devices, which helps students pinpoint areas they don't understand and clarify the next steps they should take.

[0078] By going through each step in this way, users can specifically identify their own lack of understanding and progress in their studies efficiently.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] Conventional communication support systems have had difficulty identifying and quickly visualizing any lack of mutual understanding between the user and teacher, and informing the user of this. This has led to problems such as reduced learning efficiency and communication effectiveness. In particular, in conversations involving complex concepts and technical terms, it has been necessary to identify which parts the user does not understand and provide appropriate feedback.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes means for receiving voice data and text data from a user, means for preprocessing the received data, means for analyzing the context of the preprocessed data using natural language processing technology, means for preprocessing received response data, means for estimating the intent of the preprocessed response data, means for comparing the context analysis result with the response intention estimation result to identify a lack of mutual understanding, means for visualizing the lack of mutual understanding and generating summary data, and means for transmitting the generated visualization result and summary data to a user terminal. This makes it possible to quickly identify a lack of mutual understanding between a user and a teacher and provide appropriate visual feedback.

[0084] "User" refers to an individual who uses the system to communicate and learn.

[0085] "Voice data" refers to data that has been saved in digital form and contains the content of a user's speech.

[0086] "Text data" refers to character information entered by the user.

[0087] "Means for receiving" refers to the function by which the server obtains data sent by the user.

[0088] "Preprocessing" refers to the process of converting received data into a format that is easy to analyze.

[0089] "Natural language processing technology" refers to the technology that uses computers to understand and analyze human language.

[0090] "Context" refers to the context or background information of an utterance or sentence.

[0091] "Means of analysis" refers to the technology used to extract and understand information from received data.

[0092] "Response data" refers to information returned by a teacher or the like in response to a user's question.

[0093] "Means for inferring intention" refers to the function of analyzing and inferring what a speaker or writer intends.

[0094] "Mutual lack of understanding" refers to a situation where there is a discrepancy in understanding of information between the user and the respondent.

[0095] "Visualization" refers to the representation of data or information in visual form, such as a chart or graph.

[0096] "Summary data" refers to data that summarizes detailed information concisely.

[0097] "Transmitting means" refers to a function for sending data generated by the server to the user terminal.

[0098] "User terminal" refers to a device such as a computer or smartphone used by a user.

[0099] The present invention provides a system that analyzes user utterances and text data to identify and visualize lack of mutual understanding. A specific embodiment of this system will be described below.

[0100] Server side

[0101] 1. Data reception:

[0102] The server receives voice and text data from the user. For voice data, it uses voice recognition software (e.g., a voice recognition API) to convert the voice into text. For text data, it receives it as is.

[0103] 2. Speech-text preprocessing:

[0104] The server preprocesses the text data converted from speech or received directly, including removing unnecessary spaces and special characters.

[0105] 3. Contextual analysis:

[0106] Natural language processing technology (e.g., natural language processing API) is used on the preprocessed text data to extract context and keywords. For example, information related to "mathematical formulas" and "solution methods" is analyzed.

[0107] 4. Teacher response received:

[0108] Response data from the teacher to the user's question is received. For example, if the teacher answers "You can solve that by using the basic integral formula," this text data is received.

[0109] 5. Response analysis:

[0110] Response data is also analyzed using natural language processing technology. For example, the keyword "basic integral formula" is extracted and its intent is analyzed.

[0111] 6. Identifying the lack of mutual understanding:

[0112] The results of context analysis are compared with the response intent estimation results to identify which part the user does not understand. In this case, it is identified that the student does not understand the "basic integral formula."

[0113] 7. Visualization and summary generation:

[0114] To visualize the identified gaps in understanding, we generate graphs and charts using a visualization library (e.g., visualization library). We also create a summary message that reads, "You lack understanding of the basic integral formula," and illustrate an example of the application of that formula.

[0115] 8. Data Transmission:

[0116] The generated visualization results and summary data are sent to the user's terminal via an HTTP response, allowing the user to access the data.

[0117] Terminal side

[0118] 1. Data reception:

[0119] The user terminal receives the visualization results and summary data sent from the server, and converts them into the required format for display.

[0120] 2. Data display:

[0121] The user terminal displays the received data to the user. For example, using a web browser, HTML and JavaScript may be used to display step-by-step explanations and diagrams on the screen along with the message "You lack understanding of the basic integral formula."

[0122] Specific examples

[0123] Consider the case where a student asks "I don't know how to solve this equation" in a math class. The student's speech data is sent to the server, which receives this data. Next, a speech recognition API is used to convert the speech data into text data, and a natural language processing API is used to analyze the meaning and background information of "how to solve the equation" through context analysis. The teacher's response, "You can solve it by using the basic integral formula," is sent to the server, which receives this response and analyzes the intent of the response.

[0124] The server identifies that the student does not understand the "basic integral formula" and uses a visualization library to generate a summary message stating "You lack understanding of the basic integral formula" along with an explanatory diagram. Once the data is received and sent to the user's device, it is displayed in the browser using HTML and JavaScript. The student can then identify specific areas of understanding that are lacking and move forward with their studies.

[0125] Prompt Sentence Examples

[0126] "A student asks, 'I don't know how to solve this mathematical equation.' Analyze this speech data and, based on the teacher's response, 'You can solve it using the basic integral formula,' identify that the student does not understand the 'basic integral formula,' and explain the process for visualizing and displaying this information."

[0127] Although the embodiment of the invention has been described above, the invention is not limited to this, and various modifications are possible without departing from the spirit of the invention.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1: Receiving data

[0130] The server receives voice and text data from the user. For example, when a student says, "I don't know how to solve this equation," the voice data is sent to the server. To receive the voice data, an HTTP request is used. The input is the voice data and text data, and the output is the received data.

[0131] Step 2: Speech-text preprocessing

[0132] The server converts the received voice data into text using voice recognition software (e.g., voice recognition API). It also cleans the received text data. Specifically, it removes unnecessary spaces and special characters. The input is voice data and text data, and the output is preprocessed text data.

[0133] Step 3: Context Analysis

[0134] The server performs context analysis on the preprocessed text data using natural language processing technology (e.g., natural language processing API). For example, it extracts keywords and contextual information related to "formulas" and "solution methods." This analysis provides important information and background information. The input is the preprocessed text data, and the output is the analyzed contextual information.

[0135] Step 4: Receiving the teacher's response

[0136] The server receives the teacher's response data to the user's question. If the teacher replies, "That can be solved using the basic integral formula," the server receives the text data. The input is the teacher's text data, and the output is the received response data.

[0137] Step 5: Response analysis

[0138] The server also uses natural language processing technology to analyze the received response data. Specifically, it extracts the keyword "basic integral formula" and infers its intent. The input is the preprocessed response data, and the output is the intent of the analyzed response.

[0139] Step 6: Identify the gap in mutual understanding

[0140] The server compares the results of context analysis with the response intent estimation result to identify which part the user does not understand. For example, it identifies that a student does not understand the "basic integral formula." The input is the analyzed context information and response intent, and the output is the identified lack of understanding.

[0141] Step 7: Generate visualizations and summaries

[0142] The server generates graphs and figures using a visualization library (e.g., visualization library) to visualize the identified gaps in understanding. It also displays a summary message saying "You lack understanding of the basic integral formula" and illustrates an example of how to apply that formula. The input is the identified gaps in understanding, and the output is the generated visualization results and summary data.

[0143] Step 8: Send data

[0144] The server sends the generated visualization results and summary data to the user terminal. Specifically, it sends the data via an HTTP response. The input is the visualization results and summary data, and the output is the data sent to the user terminal.

[0145] Step 9: Receiving Data

[0146] The user terminal receives the visualization results and summary data sent from the server, receives the HTTP response, and imports the data. The input is the data sent from the server, and the output is the received data.

[0147] Step 10: Data Display

[0148] The user terminal displays the received data to the user. Specifically, it uses HTML and JavaScript to display step-by-step explanations and diagrams on the screen along with the message "You lack understanding of the basic integral formula." The input is the received data, and the output is the information displayed to the user.

[0149] (Application example 1)

[0150] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0151] Conventional educational support systems are not sufficient to simply identify areas where the user lacks understanding, and lack specific feedback and explanations, which reduces the effectiveness of the user's learning. Furthermore, there is a lack of a means to effectively display visualized feedback on devices such as smartphones, which limits the actual learning support provided.

[0152] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0153] In this invention, the server includes a means for providing educational feedback specific to the user's lack of understanding, a means for displaying visualized feedback on the user's smartphone, a means for generating and displaying specific explanations and step-by-step procedures for the user's lack of understanding using a generative AI model, and a means for presenting additional information to fill in the lack of understanding using prompt sentences. This allows the user to receive information that fills in the lack of understanding in a specific and visual way in real time, significantly improving learning effectiveness.

[0154] "User" refers to a general user who uses the system to input speech or text data.

[0155] "Utterance" refers to words or phrases spoken by a user.

[0156] "Text data" refers to sentences or information entered by a user in text format.

[0157] "Natural language processing technology" refers to technology that enables computers to understand and process human language.

[0158] "Context" refers to the context or background information associated with speech or text data.

[0159] "Response intent" refers to the content or purpose that a user intends to convey through a particular utterance or text.

[0160] "Mutual incomprehension" refers to a situation in which there is a discrepancy in the interpretation of meaning or intent between the user and the system or another interlocutor.

[0161] "Visualization" refers to the display of data or information in a visual format.

[0162] "Summary data" refers to data that succinctly summarizes analyzed information and feedback.

[0163] "User terminal" refers to a device such as a smartphone or PC used by a user.

[0164] "Instructional feedback" refers to specific, instructional information provided to users where they have difficulty understanding something.

[0165] A "smartphone" is a type of mobile phone that is a portable device that can connect to the Internet and use applications.

[0166] A "generative AI model" refers to an artificial intelligence model that has been trained in advance based on a large amount of data.

[0167] A "prompt sentence" refers to a leading and instructive sentence that provides the user with additional information.

[0168] A system for implementing this invention exchanges data between a user and a server, uses natural language processing technology to identify areas where the user lacks understanding, and provides visual feedback to a smartphone.

[0169] Hardware and Software

[0170] Hardware

[0171] Smartphone: A handheld device that allows users to input speech and text data and receive feedback.

[0172] Server: A central processing unit for data analysis and feedback generation.

[0173] software

[0174] SpeechRecognition library: Used to convert user speech into text data.

[0175] Transformers library: Leverages natural language processing techniques to analyze user input data and use generative AI models.

[0176] Matplotlib: Used to visualize parts that are not fully understood.

[0177] Data processing and calculation flow

[0178] 1. Speech Recognition: The speech that a user speaks into their smartphone is captured as audio and converted into text using the SpeechRecognition library. For example, say, "I don't understand the basic formula for integrals."

[0179] 2. NLP analysis: The text data is sent to the server and natural language processing is performed using the Transformers library, which analyzes the user's intent and context.

[0180] 3. Response intent estimation: The server uses the analyzed data to identify which parts the user did not understand.

[0181] 4. Visualization: After the weaknesses are identified, visual feedback is generated using Matplotlib.

[0182] 5. Sending feedback: The server sends the visual feedback and specific explanatory information to the smartphone.

[0183] Specific examples

[0184] For example, if a user asks, "I don't understand the basic integral formula," this data is sent from the smartphone to the server. The server receives this text and uses the Transformers library to identify a lack of understanding regarding the "basic integral formula." The program then visualizes that portion, for example, by using Matplotlib to represent an example of the application of the basic integral formula. The visualized feedback and specific explanatory information are then displayed on the smartphone.

[0185] Prompt Sentence Examples

[0186] The prompt is:

[0187] context_text =

[0188] The fundamental integral formula is a key concept in calculus and has the following formula:

[0189] ∫f'(x)dx = f(x) + C

[0190] If you don't understand this formula, check out the steps below:

[0191] 1. Review the basic concepts of differentiation.

[0192] 2. Deepen understanding through examples of application of basic integral formulas.

[0193] 3. Browse additional educational materials and online resources.

[0194] Based on this example, users can receive information in real time that complements specific areas of their understanding, significantly improving their learning effectiveness.

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] A smartphone inputs speech from the user as voice data. When the user speaks a question or uncertainty, the smartphone's microphone captures it. Next, speech recognition software (SpeechRecognition library) converts the voice data into text data. In this case, the input is voice data and the output is text data. For example, an utterance such as "I don't understand the basic formula for integrals" can be converted into text.

[0198] Step 2:

[0199] The smartphone sends text data to the server. The input here is the user's text data, and the output is the data to be sent to the server. This includes the operation of sending the text data to the server via the Internet.

[0200] Step 3:

[0201] The server analyzes the received text data. It uses natural language processing technology (Transformers library) to analyze the context of the text data. The input is the user's text data, and the output is the context analysis results. Specifically, the main text is the "basic integral formula," and related context information is extracted.

[0202] Step 4:

[0203] The server identifies the user's lack of understanding based on the analyzed context. Using a generative AI model, it infers the specific areas of lack of understanding from the user's utterances. The input is the result of the context analysis, and the output is the identified areas of lack of understanding. In this case, it is identified that the user lacks understanding of the "basic formula for integration."

[0204] Step 5:

[0205] The server visualizes the identified areas of incomprehension. It uses visualization libraries such as Matplotlib to display information in a format that is easy for users to understand. The input is the areas of incomprehension, and the output is visualized feedback. For example, it visualizes an example of the application of the basic integral formula.

[0206] Step 6:

[0207] The server compiles the visualized feedback and generates explanatory information using prompts. The input is the visualization data and explanatory information for the areas of incomprehension, and the output is feedback data including specific prompts. The prompts include specific explanations and step-by-step instructions.

[0208] Step 7:

[0209] The server sends the generated feedback data to the user's smartphone. The input is the feedback data, and the output is the data to be sent to the smartphone. These data are sent via the Internet.

[0210] Step 8:

[0211] The smartphone displays the received feedback data. Visualized feedback and specific explanatory information are presented to the user. The input is the feedback data, and the output is a visual display for the user. This includes the user checking the specific feedback on the smartphone screen regarding areas of incomplete understanding.

[0212] These steps allow users to concretely and visually grasp their own lack of understanding and receive feedback to improve their learning.

[0213] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0214] The present invention provides a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and combines it with an emotion engine that recognizes the user's emotions. Specific program processing of this system is described below.

[0215] Server-side processing

[0216] 1. Data reception:

[0217] The server receives speech and text data from the user. For example, a student may input text such as "I don't know how to solve this mathematical equation." The emotion engine also receives the user's emotional state at the same time. The input data is sent to the server, which then receives it.

[0218] 2. Contextual analysis:

[0219] The server uses natural language processing technology to analyze the context of the received speech and text data. For example, it extracts information about the mathematical formula and how to solve it, and analyzes its meaning and background.

[0220] 3. Response analysis:

[0221] Similarly, the server uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "That can be solved using the basic integral formula," the server infers that the intent of this response means, "You need to understand the basic integral formula."

[0222] 4. Emotion analysis:

[0223] The emotion engine estimates the user's emotional state from the received data. For example, it analyzes whether the student is expressing emotions such as "confused" or "anxious." This emotional state is reflected in the analysis results.

[0224] 5. Identifying the lack of mutual understanding:

[0225] By integrating the results of context analysis, response analysis, and sentiment analysis, the server identifies which part the user does not understand. In this case, it identifies that the student does not understand the "basic integral formula," while also taking into account the student's emotional state.

[0226] 6. Visualization and summary generation:

[0227] The system generates summary data to visualize the identified areas of insufficient understanding and the user's emotional state, and displays them in an easy-to-understand manner. For example, it displays a message such as "You lack understanding of the basic integral formula," along with an example of how to apply the formula, providing feedback according to the user's emotional state.

[0228] 7. Data Transmission:

[0229] The generated visualization results and summary data are sent to the user's device, allowing the user to specifically identify their own lack of understanding and receive appropriate feedback according to their emotions.

[0230] Terminal side processing

[0231] 1. Data reception:

[0232] The user device receives the visualization results and summary data sent from the server, such as a student's smartphone or PC.

[0233] 2. Data display:

[0234] The user device displays the received data to the user. For example, it might display a message like "You lack understanding of the basic integral formula," along with specific step-by-step explanations and illustrations. It might also display encouraging messages and advice based on the user's emotional state.

[0235] Specific examples

[0236] As a specific example, consider a case in which a student asks, "I don't know how to solve this equation" in a math class, expressing confusion. The student's speech data and emotion data are sent to the server, which receives them and performs context analysis. The server then infers the teacher's intent from the teacher's response, "You can solve it by using the basic integral formula." The emotion engine recognizes the student's confusion and identifies the student's confusion along with their lack of understanding of the "basic integral formula." Based on this information, the system generates visualization data such as "You lack understanding of the basic integral formula" and an encouraging message such as "Even if you're confused, stay calm and keep trying," and sends this data to the user's device. The device displays this to the student, allowing them to clearly understand their lack of understanding and receive specific advice.

[0237] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] The user inputs a question or utterance. For example, a student may input text such as "I don't know how to solve this mathematical equation." The emotion engine recognizes emotions from the user's voice and text, and simultaneously detects the emotional state of "confused." This data is sent to the server.

[0241] Step 2:

[0242] The server captures and stores the received speech and text data from the user, as well as the detected emotion data, and prepares the received data for the next analysis step.

[0243] Step 3:

[0244] The server uses natural language processing technology to perform context analysis on the received speech and text data. For example, it extracts information about "mathematical formulas" and "solution methods" and analyzes their meaning and background. This analysis allows the server to identify the problem domain.

[0245] Step 4:

[0246] The server also uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "You can solve that by using the basic integral formula," the server infers that the intent of this response is the solution strategy of "using the basic integral formula."

[0247] Step 5:

[0248] The emotion engine analyzes emotions from user utterances and text data and provides the results to the server. For example, if the emotion "confusion" is detected, the emotion engine notifies the server of that information.

[0249] Step 6:

[0250] The server integrates the results of context analysis, response intent estimation, and emotion analysis from the emotion engine to identify which part the user does not understand and their emotional state at that time. For example, it can identify that a student does not understand the "basic integral formula" and is confused.

[0251] Step 7:

[0252] The server visualizes the gaps in mutual understanding and generates summary data according to the user's emotional state. Specifically, it generates a message such as "You lack understanding of the basic integral formula" and an encouraging message such as "If you're confused, go back to the basics."

[0253] Step 8:

[0254] The server sends the generated visualization results and summary data to the user terminal, allowing the user to receive specific feedback.

[0255] Step 9:

[0256] The terminal receives the visualization results and summary data sent from the server, and displays the received data appropriately to the user, for example, displaying a message such as "You lack understanding of the basic integral formula" along with detailed explanations, illustrations, and encouraging messages.

[0257] Step 10:

[0258] Users can view the visualization results and summary data on their devices, which allows students to specifically identify areas they do not understand, receive appropriate explanations and emotional advice, and move on to the next step in their learning.

[0259] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[0260] Example 2

[0261] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0262] Conventional systems have limitations in identifying lack of mutual understanding simply by analyzing the user's questions and responses. Furthermore, they provide feedback without taking the user's emotional state into consideration, making effective communication difficult. As a result, it is difficult to identify which part the user does not understand, and appropriate responses may not be possible.

[0263] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0264] In this invention, the server includes means for receiving utterances, text data, and emotional states from a user, means for analyzing the context of the received data using natural language processing technology, means for estimating the intention of a response based on the analyzed context, means for estimating the emotional state of the user using emotion analysis technology, means for identifying a lack of mutual understanding by integrating the results of the context analysis, the response intention estimation result, and the emotion analysis result, means for visualizing the lack of mutual understanding and generating summary data, and means for transmitting the generated visualization result and summary data to a user terminal. This makes it possible to specifically identify the user's lack of understanding and provide appropriate feedback accordingly.

[0265] "Means for receiving user utterances, text data, and emotional state" refers to a device or method that collects voice data, text data, and additional data input by the user for determining the user's emotions, and transmits them to a server.

[0266] "Means for analyzing the context of received data using natural language processing technology" refers to devices or methods that apply natural language analysis algorithms to analyze collected voice data or text data in order to understand its context and meaning.

[0267] "Means for inferring the intent of a response based on analyzed context" refers to a device or method for identifying the intent of a user's statement or question based on context-analyzed data and generating an appropriate response.

[0268] "Means for estimating a user's emotional state using emotion analysis technology" refers to technology or methods for analyzing voice data, facial expression data, etc. collected from a user to determine the emotions the user is feeling.

[0269] The "means for identifying a lack of mutual understanding by integrating the results of context analysis, response intention estimation, and sentiment analysis" is a method for integrating the results of the aforementioned data analysis to identify areas of lack of understanding between the user and the system or between other users.

[0270] The "means for visualizing the lack of mutual understanding and generating summary data" is a method for visually displaying the lack of understanding and generating summary data in a format that can be intuitively understood by the user.

[0271] The "means for transmitting the generated visualization results and summary data to the user terminal" refers to a communication method or protocol for transmitting the visualization results and summary data to the terminal used by the user.

[0272] The present invention provides a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and combines it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0273] Server-side processing

[0274] The server first receives speech and text data from the user. When the user types text into the device, such as "I don't know how to solve this mathematical equation," this data is sent to the server. At the same time, the emotion engine analyzes the user's voice and facial expression data, and also sends their emotional state to the server. The server receives this data and proceeds to the next stage of analysis.

[0275] The server uses natural language processing technology to analyze the context of the received data. To do this, it uses natural language processing libraries such as Google Cloud Natural Language API and SpaCy. For example, it extracts keywords such as "mathematical formula" and "how to solve" and understands the context based on them. Next, it infers the intent of the response based on the analyzed context. If the teacher answers, "That can be solved using the basic integral formula," it infers the intent of the response as "You need to understand the basic integral formula."

[0276] Furthermore, an emotion engine is used to estimate the user's emotional state. Using emotion analysis tools such as IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, it is determined whether the user is feeling "confused" or "anxious." The results of this emotion analysis are reflected in the analysis results.

[0277] The server integrates the results of context analysis, response intent estimation, and sentiment analysis to identify gaps in mutual understanding. For example, it can identify that a student does not understand the "basic integral formula" and also detect feelings of confusion.

[0278] The server then visualizes the identified gaps in understanding and the user's emotional state, generating summary data in a format that the user can intuitively understand. For example, the server might display a message such as "You lack understanding of a basic integral formula," along with step-by-step examples of how to apply the formula. It also provides encouraging messages and links to additional resources for users who are confused. The visualization and summary data are then sent to the user's device.

[0279] Terminal side processing

[0280] The user's device receives the visualization results and summary data sent from the server. For example, this could be a student's smartphone or PC. The received data is then displayed to the student. For example, a message such as "Your understanding of the basic integral formula is lacking" may be displayed along with specific explanations and illustrations. Encouraging messages and advice based on the user's emotional state may also be displayed. By viewing this, the user can specifically identify areas of lack of understanding and solutions, and move on to the next learning step.

[0281] Specific examples

[0282] As a specific example, consider a case in which a student asks, "I don't know how to solve this equation" in a math class, expressing confusion. The student's speech data and emotion data are sent to the server, which receives them and performs context analysis. The server then infers the teacher's intent from the teacher's response, "You can solve it by using the basic integral formula." The emotion engine recognizes the student's confusion and identifies the student's confusion along with their lack of understanding of the "basic integral formula." Based on this information, the system generates visualization data such as "You lack understanding of the basic integral formula" and an encouraging message such as "Even if you're confused, stay calm and keep trying," and sends this data to the user's device. The device displays this to the student, allowing them to clearly understand their lack of understanding and receive specific advice.

[0283] Prompt Sentence Examples

[0284] "When a student asks, 'I don't know how to solve this equation,' analyze the teacher's response and the student's feelings to identify the student's lack of understanding and generate feedback."

[0285] "Based on what students say and how they feel, identify areas of lack of understanding and generate feedback that visualizes those areas."

[0286] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[0287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0288] Step 1:

[0289] Receives user utterances, text data, and emotional states

[0290] The server first receives speech and text data sent from the user's device. For example, a student may type and send the text "I don't know how to solve this mathematical equation." At the same time that this text data is sent to the server, the emotion engine analyzes the user's voice and facial expression data, and their emotional state is also sent to the server. The specific input data is the speech, text data, and emotional state, and this data is stored on the server as output.

[0291] Step 2:

[0292] Context Analysis

[0293] The server performs context analysis on the received speech and text data using natural language processing technology (for example, Google Cloud Natural Language API or SpaCy). In this step, the meaning of words and phrases in the speech and text data is analyzed to understand the context. For example, keywords such as "mathematical formula" and "how to solve" are extracted and their relevance and meaning are analyzed. The input data is text data, and the output data is the analyzed context information. This process includes grammatical analysis and dependency analysis.

[0294] Step 3:

[0295] Infer response intent

[0296] The server also uses natural language processing technology to infer the intent of responses from teachers and other users. For example, if a teacher replies, "That can be solved using the basic integral formula," the server infers the intent from this response: "You need to understand the basic integral formula." The input data is the response text from the teacher, and the output data is the inferred intent. Specific operations include sending the response data to the analysis module and obtaining the results.

[0297] Step 4:

[0298] Estimating the user's emotional state

[0299] The server uses an emotion engine to estimate the user's emotional state. This process uses tools such as IBM Watson Tone Analyzer and Microsoft Azure Text Analytics. For example, emotions such as "confused" or "anxious" are analyzed from the user's voice and facial expression data. The input data is the user's voice and facial expression data, and the output data is the analyzed emotional state. Specific operations include sending data to the emotion analysis tool, receiving a response, and obtaining the analysis results.

[0300] Step 5:

[0301] Identifying a lack of mutual understanding

[0302] The server integrates the results of the context analysis, response intent estimation, and emotional state analysis to identify the parts of the sentence that the user does not understand. In this case, the analysis results indicate that the student does not understand the basic integral formula, and the accompanying emotional state of being confused is also taken into account. The input data are all of the above analysis results, and the output data are the identified gaps in mutual understanding. Specific operations include integrating each analysis result and applying an algorithm to identify the gaps.

[0303] Step 6:

[0304] Generate visualizations and summary data

[0305] The server generates summary data to visualize the identified gaps in understanding and the user's emotional state, and displays them in an easy-to-understand manner. For example, it might display a message saying, "You lack understanding of the basic integral formula," along with a step-by-step example of how to apply the formula. It might also provide encouraging messages and links to additional resources for confused users. The input data are the identified gaps in understanding and the user's emotional state, and the output data is the visualized summary data.

[0306] Step 7:

[0307] Data transmission

[0308] The server sends the generated visualization results and summary data to the user's terminal. To ensure data consistency and accuracy, encrypted communication is used, for example, using the SSL / TLS protocol. The input data are the generated visualization results and summary data, and the output data is the data sent to the user's terminal.

[0309] Step 8:

[0310] Data Display

[0311] The user terminal receives the visualization results and summary data sent from the server and displays them to the user. For example, it may display a message such as "You lack understanding of the basic integral formula," along with specific step-by-step explanations and illustrations. It may also display encouraging messages and advice based on the user's emotional state. The input data are the visualization results and summary data sent from the server, and the output data is the information displayed on the terminal. Specific operations include invoking a screen display module after receiving the data and displaying the information in an appropriate format.

[0312] (Application example 2)

[0313] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0314] Conventional systems were able to analyze user utterances and text data to identify lack of mutual understanding, but lacked a means to provide feedback based on the user's emotional state. As a result, they were unable to provide appropriate feedback that was in line with the user's emotions, limiting the effectiveness of learning and communication. The present invention aims to provide a system that provides feedback that takes the user's emotional state into account, thereby achieving more effective promotion of understanding and support.

[0315] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0316] In this invention, the server includes means for receiving utterances and text data from a user, means for analyzing the context of the received data using natural language processing technology, means for estimating the intention of the response based on the analyzed context, means for comparing the context analysis result with the response estimation result to identify a lack of mutual understanding, means for visualizing the lack of mutual understanding and generating summary data, means for transmitting the generated visualization result and summary data to a user terminal, means for recognizing and analyzing the user's emotional state, and means for generating feedback based on the emotional state. This makes it possible to provide appropriate feedback tailored to the user's emotional state, promote user understanding, and improve learning effectiveness and the quality of communication.

[0317] "User speech and text data" refers to information provided by the user through voice or text.

[0318] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[0319] "Context" refers to the context, including the background, situation, and related information of a particular utterance or text.

[0320] "Response intent" refers to the purpose or intent of a response to a received utterance or text.

[0321] "Lack of mutual understanding" refers to a situation in which both parties in a dialogue do not fully understand the intentions or content of the other.

[0322] "Visualization" refers to the display of information in the form of graphs, charts, images, etc.

[0323] "Summary data" refers to data that briefly summarizes key information.

[0324] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) used by a user to receive or send information.

[0325] "Emotional state" refers to the emotions a user is feeling at a particular moment.

[0326] "Feedback" refers to advice, comments, and responses provided to the user by the system.

[0327] This invention is an educational support system that combines a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and an emotion engine that recognizes user emotions. This system executes the following processes through various software programs. The system mainly operates in cooperation with the server and user terminals.

[0328] 1. Server-side processing

[0329] The server includes the following main programs and functions:

[0330] Data reception: A method for receiving speech or text data from a user. For example, the server receives data sent from a user device such as a smartphone or PC.

[0331] Contextual analysis: Analyzing the context of received data using natural language processing techniques (e.g., common natural language processing APIs). For example, extracting and analyzing information related to "math problem solving."

[0332] Response analysis: A method of analyzing response data from educational content providers using natural language processing technology to infer their intent.

[0333] Sentiment analysis: A method of recognizing and analyzing emotions from user speech and text data using an emotion recognition engine (e.g., a general emotion analysis API).

[0334] Identifying gaps in mutual understanding: A means of integrating the results of context analysis, response analysis, and sentiment analysis to identify areas where there is a gap in mutual understanding.

[0335] Visualization and summary generation: A means to visualize the identified gaps in understanding and the user's emotional state and generate summary data. For example, generating a diagram that accompanies the message "I don't understand the basic integral formula."

[0336] Data transmission: A means to transmit the generated visualization results and summary data to the user terminal.

[0337] 2. Terminal processing

[0338] The user terminal includes the following processing functions:

[0339] Data reception: A means to receive visualization results and summary data sent from the server.

[0340] Data display: A method for displaying received data to the user. For example, displaying a message such as "You lack understanding of the basic integral formula" and providing explanations using concrete examples and diagrams.

[0341] Specific examples

[0342] When a user utters or inputs text such as "I don't understand the background of this historical event," the server receives this and performs context analysis. It then obtains the response data from the educational content provider, "The economic background of this event is important," and infers the user's intent. The emotion recognition engine recognizes the user's confused emotion and integrates the context analysis results, response data, and emotion data to determine that the user does not understand the "economic background." As a result, "You lack understanding of the economic background" is visualized and sent to the user's device along with a message such as "If you have difficulty, try thinking about it step by step."

[0343] Prompt Sentence Examples

[0344] input:

[0345] plaintext

[0346] User says: "I don't understand the context of this historical event."

[0347] User Emotion: Confused

[0348] Generate feedback based on gaps in understanding and emotions.

[0349] This system is expected to improve learning effectiveness by allowing users to accurately identify areas of lack of understanding during learning and receive appropriate feedback tailored to their emotions.

[0350] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0351] Step 1:

[0352] Data reception

[0353] The user inputs speech or text data from a device such as a smartphone or PC. The input data is sent to the server via the network. If the data is voice, the server converts it into text using a speech recognition engine (e.g., a general speech recognition API).

[0354] Input: User utterances and text data

[0355] Output: Text data

[0356] Step 2:

[0357] Contextual Analysis

[0358] The server uses natural language processing technology (e.g., a general natural language processing API) to analyze the context of the received text data. Specifically, it extracts important keywords and phrases from the text and identifies the problems or questions the user is having.

[0359] Input: Text data

[0360] Output: Context analysis results (list of keywords and phrases)

[0361] Step 3:

[0362] Response Analysis

[0363] The system uses natural language processing technology to analyze the response data of educational content providers (e.g., instructors and teachers) and infer their intent. For example, from the instructor's response, "The economic background of this incident is important," the system focuses on the "economic background" and clarifies the instructor's intent.

[0364] Input: Instructor response data

[0365] Output: Response intent predictions

[0366] Step 4:

[0367] Emotion analysis

[0368] The server uses an emotion recognition engine (e.g., a general emotion analysis API) to recognize emotions from the user's text data and speech data. For example, it extracts emotions such as "confused" or "anxious."

[0369] Input: User text or speech data

[0370] Output: User's emotional state

[0371] Step 5:

[0372] Identifying gaps in mutual understanding

[0373] The server integrates the results of context analysis, response analysis, and sentiment analysis to identify which parts the user does not understand, thereby clarifying specific areas of incomprehension, such as the user's lack of understanding of the economic background.

[0374] Input: Context analysis results, response intent estimation results, emotional state

[0375] Output: Identification of areas of incomprehension

[0376] Step 6:

[0377] Visualization and summary generation

[0378] The system generates summary data to visualize the identified areas of incomprehension and the user's emotional state and display them in an easy-to-understand format. For example, it generates a summary message such as "You lack understanding of the economic background," along with an illustration explaining the background, and adds feedback such as "Even if you are confused, please remain calm and proceed."

[0379] Input: Identification of incomplete understanding, user's emotional state

[0380] Output: Summary data and visualization results

[0381] Step 7:

[0382] Data transmission

[0383] The server then sends the generated visualization results and summary data to the user's device, where the user can display the received data, specifically identifying areas of incomplete understanding, and receive appropriate feedback.

[0384] Input: Summary data and visualization results

[0385] Output: Data sent to the user's terminal

[0386] Examples:

[0387] The user speaks or inputs text saying, "I don't understand the background to this historical event." The server receives this and converts it into text if it is voice data. It then uses natural language processing technology to perform context analysis, and similarly analyzes the instructor's response data to determine the response intent. Next, an emotion recognition engine recognizes the user's emotional state and determines that the user is "confused." This data is integrated to determine that the user does not understand the "economic background." The server generates summary data saying, "You lack understanding of the economic background," and sends it to the user's device along with illustrations and feedback.

[0388] Example prompt sentence:

[0389] input:

[0390] plaintext

[0391] User says: "I don't understand the context of this historical event."

[0392] User Emotion: Confused

[0393] Generate feedback based on gaps in understanding and emotions.

[0394] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0395] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0396] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0397] [Second embodiment]

[0398] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0399] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0400] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0401] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0402] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0403] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0404] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0405] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0406] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0407] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0408] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0409] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0410] The present invention provides a system that analyzes user utterances and text data to identify and visualize lack of mutual understanding. The specific program processing of this system will be described below.

[0411] Server-side processing

[0412] 1. Data reception:

[0413] The server receives speech and text data from the user. For example, a student may ask a question such as "I don't know how to solve this equation" through speech or text. This data is sent to the server, which then receives it.

[0414] 2. Contextual analysis:

[0415] The server uses natural language processing technology to analyze the context of the received speech and text data. For example, it extracts information about the mathematical formula and how to solve it, and analyzes its meaning and background.

[0416] 3. Response analysis:

[0417] Similarly, the server uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "That can be solved using the basic integral formula," the server infers that the intent of this response means, "You need to understand the basic integral formula."

[0418] 4. Identifying the lack of mutual understanding:

[0419] By combining the results of context analysis and response analysis, the server identifies which part the user does not understand. In this case, it identifies that the student does not understand the "basic integral formula."

[0420] 5. Visualization and summary generation:

[0421] The system generates summary data to visualize and clearly display the identified areas of insufficient understanding, such as a message like "You lack understanding of the basic integral formula" along with an example of how to apply the formula.

[0422] 6. Data Transmission:

[0423] The generated visualization results and summary data are sent to the user's device, allowing the student to specifically identify their own lack of understanding and move on to the next learning step.

[0424] Terminal side processing

[0425] 1. Data reception:

[0426] The user device receives the visualization results and summary data sent from the server, such as a student's smartphone or PC.

[0427] 2. Data display:

[0428] The user terminal displays the received data to the user, for example, displaying a message such as "You lack understanding of the basic integral formula" along with specific step-by-step explanations and diagrams.

[0429] Specific examples

[0430] As a concrete example, consider the case where a student asks, "I don't know how to solve this equation" in a mathematics class. The student's speech data is sent to the server, which receives this data. Next, context analysis is used to analyze the meaning and background information of "how to solve the equation," and the teacher's response, "You can solve it by using the basic integral formula," is received. The server infers the intent of this response and determines that the student does not understand the "basic integral formula." Finally, a visualized summary message stating "You lack understanding of the basic integral formula" and an explanatory diagram are generated and sent to the user's device. The device receives this and displays it to the student, allowing them to specifically identify their lack of understanding and advance their learning.

[0431] This system allows users to clearly understand what they do not understand and receive appropriate feedback, thereby improving the effectiveness of learning and communication.

[0432] The processing flow will be explained below.

[0433] Step 1:

[0434] The user inputs a question or utterance. For example, a student inputs the text "I don't know how to solve this equation." The input data is sent to the server.

[0435] Step 2:

[0436] The server captures and stores the speech and text data received from the user, and prepares the received data for the next analysis step.

[0437] Step 3:

[0438] The server uses natural language processing technology on the received speech data. Specifically, it analyzes the structure and grammatical elements of the text and extracts the context. This identifies the problem domain, i.e., "how to solve mathematical equations."

[0439] Step 4:

[0440] The server performs response analysis on the utterance content. When a teacher inputs a response such as "You can solve that by using the basic integral formula," the server infers the teacher's intention and analyzes the answer strategy "basic integral formula."

[0441] Step 5:

[0442] The server integrates the results of context analysis and response analysis to identify a lack of mutual understanding. Specifically, it identifies that the student does not understand the "basic integral formula" and expresses this in one word.

[0443] Step 6:

[0444] The server visualizes the gaps in mutual understanding and generates summary data, such as a diagram that includes an example of the application of the formula along with a message saying, "You lack understanding of the basic integral formula."

[0445] Step 7:

[0446] The server sends the generated visualization results and summary data to the user's terminal, allowing the user to receive specific feedback.

[0447] Step 8:

[0448] The terminal receives the visualization results and summary data sent from the server, and the received data is displayed appropriately for the user, allowing students to check its contents.

[0449] Step 9:

[0450] Users can view the visualization results and summary data on their devices, which helps students pinpoint areas they don't understand and clarify the next steps they should take.

[0451] By going through each step in this way, users can specifically identify their own lack of understanding and progress in their studies efficiently.

[0452] Example 1

[0453] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0454] Conventional communication support systems have had difficulty identifying and quickly visualizing any lack of mutual understanding between the user and teacher, and informing the user of this. This has led to problems such as reduced learning efficiency and communication effectiveness. In particular, in conversations involving complex concepts and technical terms, it has been necessary to identify which parts the user does not understand and provide appropriate feedback.

[0455] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0456] In this invention, the server includes means for receiving voice data and text data from a user, means for preprocessing the received data, means for analyzing the context of the preprocessed data using natural language processing technology, means for preprocessing received response data, means for estimating the intent of the preprocessed response data, means for comparing the context analysis result with the response intention estimation result to identify a lack of mutual understanding, means for visualizing the lack of mutual understanding and generating summary data, and means for transmitting the generated visualization result and summary data to a user terminal. This makes it possible to quickly identify a lack of mutual understanding between a user and a teacher and provide appropriate visual feedback.

[0457] "User" refers to an individual who uses the system to communicate and learn.

[0458] "Voice data" refers to data that has been saved in digital form and contains the content of a user's speech.

[0459] "Text data" refers to character information entered by the user.

[0460] "Means for receiving" refers to the function by which the server obtains data sent by the user.

[0461] "Preprocessing" refers to the process of converting received data into a format that is easy to analyze.

[0462] "Natural language processing technology" refers to the technology that uses computers to understand and analyze human language.

[0463] "Context" refers to the context or background information of an utterance or sentence.

[0464] "Means of analysis" refers to the technology used to extract and understand information from received data.

[0465] "Response data" refers to information returned by a teacher or the like in response to a user's question.

[0466] "Means for inferring intention" refers to the function of analyzing and inferring what a speaker or writer intends.

[0467] "Mutual lack of understanding" refers to a situation where there is a discrepancy in understanding of information between the user and the respondent.

[0468] "Visualization" refers to the representation of data or information in visual form, such as a chart or graph.

[0469] "Summary data" refers to data that summarizes detailed information concisely.

[0470] "Transmitting means" refers to a function for sending data generated by the server to the user terminal.

[0471] "User terminal" refers to a device such as a computer or smartphone used by a user.

[0472] The present invention provides a system that analyzes user utterances and text data to identify and visualize lack of mutual understanding. A specific embodiment of this system will be described below.

[0473] Server side

[0474] 1. Data reception:

[0475] The server receives voice and text data from the user. For voice data, it uses voice recognition software (e.g., a voice recognition API) to convert the voice into text. For text data, it receives it as is.

[0476] 2. Speech-text preprocessing:

[0477] The server preprocesses the text data converted from speech or received directly, including removing unnecessary spaces and special characters.

[0478] 3. Contextual analysis:

[0479] Natural language processing technology (e.g., natural language processing API) is used on the preprocessed text data to extract context and keywords. For example, information related to "mathematical formulas" and "solution methods" is analyzed.

[0480] 4. Teacher response received:

[0481] Response data from the teacher to the user's question is received. For example, if the teacher answers "You can solve that by using the basic integral formula," this text data is received.

[0482] 5. Response analysis:

[0483] Response data is also analyzed using natural language processing technology. For example, the keyword "basic integral formula" is extracted and its intent is analyzed.

[0484] 6. Identifying the lack of mutual understanding:

[0485] The results of context analysis are compared with the response intent estimation results to identify which part the user does not understand. In this case, it is identified that the student does not understand the "basic integral formula."

[0486] 7. Visualization and summary generation:

[0487] To visualize the identified gaps in understanding, we generate graphs and charts using a visualization library (e.g., visualization library). We also create a summary message that reads, "You lack understanding of the basic integral formula," and illustrate an example of the application of that formula.

[0488] 8. Data Transmission:

[0489] The generated visualization results and summary data are sent to the user's terminal via an HTTP response, allowing the user to access the data.

[0490] Terminal side

[0491] 1. Data reception:

[0492] The user terminal receives the visualization results and summary data sent from the server, and converts them into the required format for display.

[0493] 2. Data display:

[0494] The user terminal displays the received data to the user. For example, using a web browser, HTML and JavaScript may be used to display step-by-step explanations and diagrams on the screen along with the message "You lack understanding of the basic integral formula."

[0495] Specific examples

[0496] Consider the case where a student asks "I don't know how to solve this equation" in a math class. The student's speech data is sent to the server, which receives this data. Next, a speech recognition API is used to convert the speech data into text data, and a natural language processing API is used to analyze the meaning and background information of "how to solve the equation" through context analysis. The teacher's response, "You can solve it by using the basic integral formula," is sent to the server, which receives this response and analyzes the intent of the response.

[0497] The server identifies that the student does not understand the "basic integral formula" and uses a visualization library to generate a summary message stating "You lack understanding of the basic integral formula" along with an explanatory diagram. Once the data is received and sent to the user's device, it is displayed in the browser using HTML and JavaScript. The student can then identify specific areas of understanding that are lacking and move forward with their studies.

[0498] Prompt Sentence Examples

[0499] "A student asks, 'I don't know how to solve this mathematical equation.' Analyze this speech data and, based on the teacher's response, 'You can solve it using the basic integral formula,' identify that the student does not understand the 'basic integral formula,' and explain the process for visualizing and displaying this information."

[0500] Although the embodiment of the invention has been described above, the invention is not limited to this, and various modifications are possible without departing from the spirit of the invention.

[0501] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0502] Step 1: Receiving data

[0503] The server receives voice and text data from the user. For example, when a student says, "I don't know how to solve this equation," the voice data is sent to the server. To receive the voice data, an HTTP request is used. The input is the voice data and text data, and the output is the received data.

[0504] Step 2: Speech-text preprocessing

[0505] The server converts the received voice data into text using voice recognition software (e.g., voice recognition API). It also cleans the received text data. Specifically, it removes unnecessary spaces and special characters. The input is voice data and text data, and the output is preprocessed text data.

[0506] Step 3: Context Analysis

[0507] The server performs context analysis on the preprocessed text data using natural language processing technology (e.g., natural language processing API). For example, it extracts keywords and contextual information related to "formulas" and "solution methods." This analysis provides important information and background information. The input is the preprocessed text data, and the output is the analyzed contextual information.

[0508] Step 4: Receiving the teacher's response

[0509] The server receives the teacher's response data to the user's question. If the teacher replies, "That can be solved using the basic integral formula," the server receives the text data. The input is the teacher's text data, and the output is the received response data.

[0510] Step 5: Response analysis

[0511] The server also uses natural language processing technology to analyze the received response data. Specifically, it extracts the keyword "basic integral formula" and infers its intent. The input is the preprocessed response data, and the output is the intent of the analyzed response.

[0512] Step 6: Identify the gap in mutual understanding

[0513] The server compares the results of context analysis with the response intent estimation result to identify which part the user does not understand. For example, it identifies that a student does not understand the "basic integral formula." The input is the analyzed context information and response intent, and the output is the identified lack of understanding.

[0514] Step 7: Generate visualizations and summaries

[0515] The server generates graphs and figures using a visualization library (e.g., visualization library) to visualize the identified gaps in understanding. It also displays a summary message saying "You lack understanding of the basic integral formula" and illustrates an example of how to apply that formula. The input is the identified gaps in understanding, and the output is the generated visualization results and summary data.

[0516] Step 8: Send data

[0517] The server sends the generated visualization results and summary data to the user terminal. Specifically, it sends the data via an HTTP response. The input is the visualization results and summary data, and the output is the data sent to the user terminal.

[0518] Step 9: Receiving Data

[0519] The user terminal receives the visualization results and summary data sent from the server, receives the HTTP response, and imports the data. The input is the data sent from the server, and the output is the received data.

[0520] Step 10: Data Display

[0521] The user terminal displays the received data to the user. Specifically, it uses HTML and JavaScript to display step-by-step explanations and diagrams on the screen along with the message "You lack understanding of the basic integral formula." The input is the received data, and the output is the information displayed to the user.

[0522] (Application example 1)

[0523] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0524] Conventional educational support systems are not sufficient to simply identify areas where the user lacks understanding, and lack specific feedback and explanations, which reduces the effectiveness of the user's learning. Furthermore, there is a lack of a means to effectively display visualized feedback on devices such as smartphones, which limits the actual learning support provided.

[0525] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0526] In this invention, the server includes a means for providing educational feedback specific to the user's lack of understanding, a means for displaying visualized feedback on the user's smartphone, a means for generating and displaying specific explanations and step-by-step procedures for the user's lack of understanding using a generative AI model, and a means for presenting additional information to fill in the lack of understanding using prompt sentences. This allows the user to receive information that fills in the lack of understanding in a specific and visual way in real time, significantly improving learning effectiveness.

[0527] "User" refers to a general user who uses the system to input speech or text data.

[0528] "Utterance" refers to words or phrases spoken by a user.

[0529] "Text data" refers to sentences or information entered by a user in text format.

[0530] "Natural language processing technology" refers to technology that enables computers to understand and process human language.

[0531] "Context" refers to the context or background information associated with speech or text data.

[0532] "Response intent" refers to the content or purpose that a user intends to convey through a particular utterance or text.

[0533] "Mutual incomprehension" refers to a situation in which there is a discrepancy in the interpretation of meaning or intent between the user and the system or another interlocutor.

[0534] "Visualization" refers to the display of data or information in a visual format.

[0535] "Summary data" refers to data that succinctly summarizes analyzed information and feedback.

[0536] "User terminal" refers to a device such as a smartphone or PC used by a user.

[0537] "Instructional feedback" refers to specific, instructional information provided to users where they have difficulty understanding something.

[0538] A "smartphone" is a type of mobile phone that is a portable device that can connect to the Internet and use applications.

[0539] A "generative AI model" refers to an artificial intelligence model that has been trained in advance based on a large amount of data.

[0540] A "prompt sentence" refers to a leading and instructive sentence that provides the user with additional information.

[0541] A system for implementing this invention exchanges data between a user and a server, uses natural language processing technology to identify areas where the user lacks understanding, and provides visual feedback to a smartphone.

[0542] Hardware and Software

[0543] Hardware

[0544] Smartphone: A handheld device that allows users to input speech and text data and receive feedback.

[0545] Server: A central processing unit for data analysis and feedback generation.

[0546] software

[0547] SpeechRecognition library: Used to convert user speech into text data.

[0548] Transformers library: Leverages natural language processing techniques to analyze user input data and use generative AI models.

[0549] Matplotlib: Used to visualize parts that are not fully understood.

[0550] Data processing and calculation flow

[0551] 1. Speech Recognition: The speech that a user speaks into their smartphone is captured as audio and converted into text using the SpeechRecognition library. For example, say, "I don't understand the basic formula for integrals."

[0552] 2. NLP analysis: The text data is sent to the server and natural language processing is performed using the Transformers library, which analyzes the user's intent and context.

[0553] 3. Response intent estimation: The server uses the analyzed data to identify which parts the user did not understand.

[0554] 4. Visualization: After the weaknesses are identified, visual feedback is generated using Matplotlib.

[0555] 5. Sending feedback: The server sends the visual feedback and specific explanatory information to the smartphone.

[0556] Specific examples

[0557] For example, if a user asks, "I don't understand the basic integral formula," this data is sent from the smartphone to the server. The server receives this text and uses the Transformers library to identify a lack of understanding regarding the "basic integral formula." The program then visualizes that portion, for example, by using Matplotlib to represent an example of the application of the basic integral formula. The visualized feedback and specific explanatory information are then displayed on the smartphone.

[0558] Prompt Sentence Examples

[0559] The prompt is:

[0560] context_text =

[0561] The fundamental integral formula is a key concept in calculus and has the following formula:

[0562] ∫f'(x)dx = f(x) + C

[0563] If you don't understand this formula, check out the steps below:

[0564] 1. Review the basic concepts of differentiation.

[0565] 2. Deepen understanding through examples of application of basic integral formulas.

[0566] 3. Browse additional educational materials and online resources.

[0567] Based on this example, users can receive information in real time that complements specific areas of their understanding, significantly improving their learning effectiveness.

[0568] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0569] Step 1:

[0570] A smartphone inputs speech from the user as voice data. When the user speaks a question or uncertainty, the smartphone's microphone captures it. Next, speech recognition software (SpeechRecognition library) converts the voice data into text data. In this case, the input is voice data and the output is text data. For example, an utterance such as "I don't understand the basic formula for integrals" can be converted into text.

[0571] Step 2:

[0572] The smartphone sends text data to the server. The input here is the user's text data, and the output is the data to be sent to the server. This includes the operation of sending the text data to the server via the Internet.

[0573] Step 3:

[0574] The server analyzes the received text data. It uses natural language processing technology (Transformers library) to analyze the context of the text data. The input is the user's text data, and the output is the context analysis results. Specifically, the main text is the "basic integral formula," and related context information is extracted.

[0575] Step 4:

[0576] The server identifies the user's lack of understanding based on the analyzed context. Using a generative AI model, it infers the specific areas of lack of understanding from the user's utterances. The input is the result of the context analysis, and the output is the identified areas of lack of understanding. In this case, it is identified that the user lacks understanding of the "basic formula for integration."

[0577] Step 5:

[0578] The server visualizes the identified areas of incomprehension. It uses visualization libraries such as Matplotlib to display information in a format that is easy for users to understand. The input is the areas of incomprehension, and the output is visualized feedback. For example, it visualizes an example of the application of the basic integral formula.

[0579] Step 6:

[0580] The server compiles the visualized feedback and generates explanatory information using prompts. The input is the visualization data and explanatory information for the areas of incomprehension, and the output is feedback data including specific prompts. The prompts include specific explanations and step-by-step instructions.

[0581] Step 7:

[0582] The server sends the generated feedback data to the user's smartphone. The input is the feedback data, and the output is the data to be sent to the smartphone. These data are sent via the Internet.

[0583] Step 8:

[0584] The smartphone displays the received feedback data. Visualized feedback and specific explanatory information are presented to the user. The input is the feedback data, and the output is a visual display for the user. This includes the user checking the specific feedback on the smartphone screen regarding areas of incomplete understanding.

[0585] These steps allow users to concretely and visually grasp their own lack of understanding and receive feedback to improve their learning.

[0586] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0587] The present invention provides a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and combines it with an emotion engine that recognizes the user's emotions. Specific program processing of this system is described below.

[0588] Server-side processing

[0589] 1. Data reception:

[0590] The server receives speech and text data from the user. For example, a student may input text such as "I don't know how to solve this mathematical equation." The emotion engine also receives the user's emotional state at the same time. The input data is sent to the server, which then receives it.

[0591] 2. Contextual analysis:

[0592] The server uses natural language processing technology to analyze the context of the received speech and text data. For example, it extracts information about the mathematical formula and how to solve it, and analyzes its meaning and background.

[0593] 3. Response analysis:

[0594] Similarly, the server uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "That can be solved using the basic integral formula," the server infers that the intent of this response means, "You need to understand the basic integral formula."

[0595] 4. Emotion analysis:

[0596] The emotion engine estimates the user's emotional state from the received data. For example, it analyzes whether the student is expressing emotions such as "confused" or "anxious." This emotional state is reflected in the analysis results.

[0597] 5. Identifying the lack of mutual understanding:

[0598] By integrating the results of context analysis, response analysis, and sentiment analysis, the server identifies which part the user does not understand. In this case, it identifies that the student does not understand the "basic integral formula," while also taking into account the student's emotional state.

[0599] 6. Visualization and summary generation:

[0600] The system generates summary data to visualize the identified areas of insufficient understanding and the user's emotional state, and displays them in an easy-to-understand manner. For example, it displays a message such as "You lack understanding of the basic integral formula," along with an example of how to apply the formula, providing feedback according to the user's emotional state.

[0601] 7. Data Transmission:

[0602] The generated visualization results and summary data are sent to the user's device, allowing the user to specifically identify their own lack of understanding and receive appropriate feedback according to their emotions.

[0603] Terminal side processing

[0604] 1. Data reception:

[0605] The user device receives the visualization results and summary data sent from the server, such as a student's smartphone or PC.

[0606] 2. Data display:

[0607] The user device displays the received data to the user. For example, it might display a message like "You lack understanding of the basic integral formula," along with specific step-by-step explanations and illustrations. It might also display encouraging messages and advice based on the user's emotional state.

[0608] Specific examples

[0609] As a specific example, consider a case in which a student asks, "I don't know how to solve this equation" in a math class, expressing confusion. The student's speech data and emotion data are sent to the server, which receives them and performs context analysis. The server then infers the teacher's intent from the teacher's response, "You can solve it by using the basic integral formula." The emotion engine recognizes the student's confusion and identifies the student's confusion along with their lack of understanding of the "basic integral formula." Based on this information, the system generates visualization data such as "You lack understanding of the basic integral formula" and an encouraging message such as "Even if you're confused, stay calm and keep trying," and sends this data to the user's device. The device displays this to the student, allowing them to clearly understand their lack of understanding and receive specific advice.

[0610] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[0611] The processing flow will be explained below.

[0612] Step 1:

[0613] The user inputs a question or utterance. For example, a student may input text such as "I don't know how to solve this mathematical equation." The emotion engine recognizes emotions from the user's voice and text, and simultaneously detects the emotional state of "confused." This data is sent to the server.

[0614] Step 2:

[0615] The server captures and stores the received speech and text data from the user, as well as the detected emotion data, and prepares the received data for the next analysis step.

[0616] Step 3:

[0617] The server uses natural language processing technology to perform context analysis on the received speech and text data. For example, it extracts information about "mathematical formulas" and "solution methods" and analyzes their meaning and background. This analysis allows the server to identify the problem domain.

[0618] Step 4:

[0619] The server also uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "You can solve that by using the basic integral formula," the server infers that the intent of this response is the solution strategy of "using the basic integral formula."

[0620] Step 5:

[0621] The emotion engine analyzes emotions from user utterances and text data and provides the results to the server. For example, if the emotion "confusion" is detected, the emotion engine notifies the server of that information.

[0622] Step 6:

[0623] The server integrates the results of context analysis, response intent estimation, and emotion analysis from the emotion engine to identify which part the user does not understand and their emotional state at that time. For example, it can identify that a student does not understand the "basic integral formula" and is confused.

[0624] Step 7:

[0625] The server visualizes the gaps in mutual understanding and generates summary data according to the user's emotional state. Specifically, it generates a message such as "You lack understanding of the basic integral formula" and an encouraging message such as "If you're confused, go back to the basics."

[0626] Step 8:

[0627] The server sends the generated visualization results and summary data to the user terminal, allowing the user to receive specific feedback.

[0628] Step 9:

[0629] The terminal receives the visualization results and summary data sent from the server, and displays the received data appropriately to the user, for example, displaying a message such as "You lack understanding of the basic integral formula" along with detailed explanations, illustrations, and encouraging messages.

[0630] Step 10:

[0631] Users can view the visualization results and summary data on their devices, which allows students to specifically identify areas they do not understand, receive appropriate explanations and emotional advice, and move on to the next step in their learning.

[0632] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[0633] Example 2

[0634] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0635] Conventional systems have limitations in identifying lack of mutual understanding simply by analyzing the user's questions and responses. Furthermore, they provide feedback without taking the user's emotional state into consideration, making effective communication difficult. As a result, it is difficult to identify which part the user does not understand, and appropriate responses may not be possible.

[0636] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0637] In this invention, the server includes means for receiving utterances, text data, and emotional states from a user, means for analyzing the context of the received data using natural language processing technology, means for estimating the intention of a response based on the analyzed context, means for estimating the emotional state of the user using emotion analysis technology, means for identifying a lack of mutual understanding by integrating the results of the context analysis, the response intention estimation result, and the emotion analysis result, means for visualizing the lack of mutual understanding and generating summary data, and means for transmitting the generated visualization result and summary data to a user terminal. This makes it possible to specifically identify the user's lack of understanding and provide appropriate feedback accordingly.

[0638] "Means for receiving user utterances, text data, and emotional state" refers to a device or method that collects voice data, text data, and additional data input by the user for determining the user's emotions, and transmits them to a server.

[0639] "Means for analyzing the context of received data using natural language processing technology" refers to devices or methods that apply natural language analysis algorithms to analyze collected voice data or text data in order to understand its context and meaning.

[0640] "Means for inferring the intent of a response based on analyzed context" refers to a device or method for identifying the intent of a user's statement or question based on context-analyzed data and generating an appropriate response.

[0641] "Means for estimating a user's emotional state using emotion analysis technology" refers to technology or methods for analyzing voice data, facial expression data, etc. collected from a user to determine the emotions the user is feeling.

[0642] The "means for identifying a lack of mutual understanding by integrating the results of context analysis, response intention estimation, and sentiment analysis" is a method for integrating the results of the aforementioned data analysis to identify areas of lack of understanding between the user and the system or between other users.

[0643] The "means for visualizing the lack of mutual understanding and generating summary data" is a method for visually displaying the lack of understanding and generating summary data in a format that can be intuitively understood by the user.

[0644] The "means for transmitting the generated visualization results and summary data to the user terminal" refers to a communication method or protocol for transmitting the visualization results and summary data to the terminal used by the user.

[0645] The present invention provides a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and combines it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0646] Server-side processing

[0647] The server first receives speech and text data from the user. When the user types text into the device, such as "I don't know how to solve this mathematical equation," this data is sent to the server. At the same time, the emotion engine analyzes the user's voice and facial expression data, and also sends their emotional state to the server. The server receives this data and proceeds to the next stage of analysis.

[0648] The server uses natural language processing technology to analyze the context of the received data. To do this, it uses natural language processing libraries such as Google Cloud Natural Language API and SpaCy. For example, it extracts keywords such as "mathematical formula" and "how to solve" and understands the context based on them. Next, it infers the intent of the response based on the analyzed context. If the teacher answers, "That can be solved using the basic integral formula," it infers the intent of the response as "You need to understand the basic integral formula."

[0649] Furthermore, an emotion engine is used to estimate the user's emotional state. Using emotion analysis tools such as IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, it is determined whether the user is feeling "confused" or "anxious." The results of this emotion analysis are reflected in the analysis results.

[0650] The server integrates the results of context analysis, response intent estimation, and sentiment analysis to identify gaps in mutual understanding. For example, it can identify that a student does not understand the "basic integral formula" and also detect feelings of confusion.

[0651] The server then visualizes the identified gaps in understanding and the user's emotional state, generating summary data in a format that the user can intuitively understand. For example, the server might display a message such as "You lack understanding of a basic integral formula," along with step-by-step examples of how to apply the formula. It also provides encouraging messages and links to additional resources for users who are confused. The visualization and summary data are then sent to the user's device.

[0652] Terminal side processing

[0653] The user's device receives the visualization results and summary data sent from the server. For example, this could be a student's smartphone or PC. The received data is then displayed to the student. For example, a message such as "Your understanding of the basic integral formula is lacking" may be displayed along with specific explanations and illustrations. Encouraging messages and advice based on the user's emotional state may also be displayed. By viewing this, the user can specifically identify areas of lack of understanding and solutions, and move on to the next learning step.

[0654] Specific examples

[0655] As a specific example, consider a case in which a student asks, "I don't know how to solve this equation" in a math class, expressing confusion. The student's speech data and emotion data are sent to the server, which receives them and performs context analysis. The server then infers the teacher's intent from the teacher's response, "You can solve it by using the basic integral formula." The emotion engine recognizes the student's confusion and identifies the student's confusion along with their lack of understanding of the "basic integral formula." Based on this information, the system generates visualization data such as "You lack understanding of the basic integral formula" and an encouraging message such as "Even if you're confused, stay calm and keep trying," and sends this data to the user's device. The device displays this to the student, allowing them to clearly understand their lack of understanding and receive specific advice.

[0656] Prompt Sentence Examples

[0657] "When a student asks, 'I don't know how to solve this equation,' analyze the teacher's response and the student's feelings to identify the student's lack of understanding and generate feedback."

[0658] "Based on what students say and how they feel, identify areas of lack of understanding and generate feedback that visualizes those areas."

[0659] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[0660] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0661] Step 1:

[0662] Receives user utterances, text data, and emotional states

[0663] The server first receives speech and text data sent from the user's device. For example, a student may type and send the text "I don't know how to solve this mathematical equation." At the same time that this text data is sent to the server, the emotion engine analyzes the user's voice and facial expression data, and their emotional state is also sent to the server. The specific input data is the speech, text data, and emotional state, and this data is stored on the server as output.

[0664] Step 2:

[0665] Context Analysis

[0666] The server performs context analysis on the received speech and text data using natural language processing technology (for example, Google Cloud Natural Language API or SpaCy). In this step, the meaning of words and phrases in the speech and text data is analyzed to understand the context. For example, keywords such as "mathematical formula" and "how to solve" are extracted and their relevance and meaning are analyzed. The input data is text data, and the output data is the analyzed context information. This process includes grammatical analysis and dependency analysis.

[0667] Step 3:

[0668] Infer response intent

[0669] The server also uses natural language processing technology to infer the intent of responses from teachers and other users. For example, if a teacher replies, "That can be solved using the basic integral formula," the server infers the intent from this response: "You need to understand the basic integral formula." The input data is the response text from the teacher, and the output data is the inferred intent. Specific operations include sending the response data to the analysis module and obtaining the results.

[0670] Step 4:

[0671] Estimating the user's emotional state

[0672] The server uses an emotion engine to estimate the user's emotional state. This process uses tools such as IBM Watson Tone Analyzer and Microsoft Azure Text Analytics. For example, emotions such as "confused" or "anxious" are analyzed from the user's voice and facial expression data. The input data is the user's voice and facial expression data, and the output data is the analyzed emotional state. Specific operations include sending data to the emotion analysis tool, receiving a response, and obtaining the analysis results.

[0673] Step 5:

[0674] Identifying a lack of mutual understanding

[0675] The server integrates the results of the context analysis, response intent estimation, and emotional state analysis to identify the parts of the sentence that the user does not understand. In this case, the analysis results indicate that the student does not understand the basic integral formula, and the accompanying emotional state of being confused is also taken into account. The input data are all of the above analysis results, and the output data are the identified gaps in mutual understanding. Specific operations include integrating each analysis result and applying an algorithm to identify the gaps.

[0676] Step 6:

[0677] Generate visualizations and summary data

[0678] The server generates summary data to visualize the identified gaps in understanding and the user's emotional state, and displays them in an easy-to-understand manner. For example, it might display a message saying, "You lack understanding of the basic integral formula," along with a step-by-step example of how to apply the formula. It might also provide encouraging messages and links to additional resources for confused users. The input data are the identified gaps in understanding and the user's emotional state, and the output data is the visualized summary data.

[0679] Step 7:

[0680] Data transmission

[0681] The server sends the generated visualization results and summary data to the user's terminal. To ensure data consistency and accuracy, encrypted communication is used, for example, using the SSL / TLS protocol. The input data are the generated visualization results and summary data, and the output data is the data sent to the user's terminal.

[0682] Step 8:

[0683] Data Display

[0684] The user terminal receives the visualization results and summary data sent from the server and displays them to the user. For example, it may display a message such as "You lack understanding of the basic integral formula," along with specific step-by-step explanations and illustrations. It may also display encouraging messages and advice based on the user's emotional state. The input data are the visualization results and summary data sent from the server, and the output data is the information displayed on the terminal. Specific operations include invoking a screen display module after receiving the data and displaying the information in an appropriate format.

[0685] (Application example 2)

[0686] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0687] Conventional systems were able to analyze user utterances and text data to identify lack of mutual understanding, but lacked a means to provide feedback based on the user's emotional state. As a result, they were unable to provide appropriate feedback that was in line with the user's emotions, limiting the effectiveness of learning and communication. The present invention aims to provide a system that provides feedback that takes the user's emotional state into account, thereby achieving more effective promotion of understanding and support.

[0688] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0689] In this invention, the server includes means for receiving utterances and text data from a user, means for analyzing the context of the received data using natural language processing technology, means for estimating the intention of the response based on the analyzed context, means for comparing the context analysis result with the response estimation result to identify a lack of mutual understanding, means for visualizing the lack of mutual understanding and generating summary data, means for transmitting the generated visualization result and summary data to a user terminal, means for recognizing and analyzing the user's emotional state, and means for generating feedback based on the emotional state. This makes it possible to provide appropriate feedback tailored to the user's emotional state, promote user understanding, and improve learning effectiveness and the quality of communication.

[0690] "User speech and text data" refers to information provided by the user through voice or text.

[0691] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[0692] "Context" refers to the context, including the background, situation, and related information of a particular utterance or text.

[0693] "Response intent" refers to the purpose or intent of a response to a received utterance or text.

[0694] "Lack of mutual understanding" refers to a situation in which both parties in a dialogue do not fully understand the intentions or content of the other.

[0695] "Visualization" refers to the display of information in the form of graphs, charts, images, etc.

[0696] "Summary data" refers to data that briefly summarizes key information.

[0697] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) used by a user to receive or send information.

[0698] "Emotional state" refers to the emotions a user is feeling at a particular moment.

[0699] "Feedback" refers to advice, comments, and responses provided to the user by the system.

[0700] This invention is an educational support system that combines a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and an emotion engine that recognizes user emotions. This system executes the following processes through various software programs. The system mainly operates in cooperation with the server and user terminals.

[0701] 1. Server-side processing

[0702] The server includes the following main programs and functions:

[0703] Data reception: A method for receiving speech or text data from a user. For example, the server receives data sent from a user device such as a smartphone or PC.

[0704] Contextual analysis: Analyzing the context of received data using natural language processing techniques (e.g., common natural language processing APIs). For example, extracting and analyzing information related to "math problem solving."

[0705] Response analysis: A method of analyzing response data from educational content providers using natural language processing technology to infer their intent.

[0706] Sentiment analysis: A method of recognizing and analyzing emotions from user speech and text data using an emotion recognition engine (e.g., a general emotion analysis API).

[0707] Identifying gaps in mutual understanding: A means of integrating the results of context analysis, response analysis, and sentiment analysis to identify areas where there is a gap in mutual understanding.

[0708] Visualization and summary generation: A means to visualize the identified gaps in understanding and the user's emotional state and generate summary data. For example, generating a diagram that accompanies the message "I don't understand the basic integral formula."

[0709] Data transmission: A means to transmit the generated visualization results and summary data to the user terminal.

[0710] 2. Terminal processing

[0711] The user terminal includes the following processing functions:

[0712] Data reception: A means to receive visualization results and summary data sent from the server.

[0713] Data display: A method for displaying received data to the user. For example, displaying a message such as "You lack understanding of the basic integral formula" and providing explanations using concrete examples and diagrams.

[0714] Specific examples

[0715] When a user utters or inputs text such as "I don't understand the background of this historical event," the server receives this and performs context analysis. It then obtains the response data from the educational content provider, "The economic background of this event is important," and infers the user's intent. The emotion recognition engine recognizes the user's confused emotion and integrates the context analysis results, response data, and emotion data to determine that the user does not understand the "economic background." As a result, "You lack understanding of the economic background" is visualized and sent to the user's device along with a message such as "If you have difficulty, try thinking about it step by step."

[0716] Prompt Sentence Examples

[0717] input:

[0718] plaintext

[0719] User says: "I don't understand the context of this historical event."

[0720] User Emotion: Confused

[0721] Generate feedback based on gaps in understanding and emotions.

[0722] This system is expected to improve learning effectiveness by allowing users to accurately identify areas of lack of understanding during learning and receive appropriate feedback tailored to their emotions.

[0723] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0724] Step 1:

[0725] Data reception

[0726] The user inputs speech or text data from a device such as a smartphone or PC. The input data is sent to the server via the network. If the data is voice, the server converts it into text using a speech recognition engine (e.g., a general speech recognition API).

[0727] Input: User utterances and text data

[0728] Output: Text data

[0729] Step 2:

[0730] Contextual Analysis

[0731] The server uses natural language processing technology (e.g., a general natural language processing API) to analyze the context of the received text data. Specifically, it extracts important keywords and phrases from the text and identifies the problems or questions the user is having.

[0732] Input: Text data

[0733] Output: Context analysis results (list of keywords and phrases)

[0734] Step 3:

[0735] Response Analysis

[0736] The system uses natural language processing technology to analyze the response data of educational content providers (e.g., instructors and teachers) and infer their intent. For example, from the instructor's response, "The economic background of this incident is important," the system focuses on the "economic background" and clarifies the instructor's intent.

[0737] Input: Instructor response data

[0738] Output: Response intent predictions

[0739] Step 4:

[0740] Emotion analysis

[0741] The server uses an emotion recognition engine (e.g., a general emotion analysis API) to recognize emotions from the user's text data and speech data. For example, it extracts emotions such as "confused" or "anxious."

[0742] Input: User text or speech data

[0743] Output: User's emotional state

[0744] Step 5:

[0745] Identifying gaps in mutual understanding

[0746] The server integrates the results of context analysis, response analysis, and sentiment analysis to identify which parts the user does not understand, thereby clarifying specific areas of incomprehension, such as the user's lack of understanding of the economic background.

[0747] Input: Context analysis results, response intent estimation results, emotional state

[0748] Output: Identification of areas of incomprehension

[0749] Step 6:

[0750] Visualization and summary generation

[0751] The system generates summary data to visualize the identified areas of incomprehension and the user's emotional state and display them in an easy-to-understand format. For example, it generates a summary message such as "You lack understanding of the economic background," along with an illustration explaining the background, and adds feedback such as "Even if you are confused, please remain calm and proceed."

[0752] Input: Identification of incomplete understanding, user's emotional state

[0753] Output: Summary data and visualization results

[0754] Step 7:

[0755] Data transmission

[0756] The server then sends the generated visualization results and summary data to the user's device, where the user can display the received data, specifically identifying areas of incomplete understanding, and receive appropriate feedback.

[0757] Input: Summary data and visualization results

[0758] Output: Data sent to the user's terminal

[0759] Examples:

[0760] The user speaks or inputs text saying, "I don't understand the background to this historical event." The server receives this and converts it into text if it is voice data. It then uses natural language processing technology to perform context analysis, and similarly analyzes the instructor's response data to determine the response intent. Next, an emotion recognition engine recognizes the user's emotional state and determines that the user is "confused." This data is integrated to determine that the user does not understand the "economic background." The server generates summary data saying, "You lack understanding of the economic background," and sends it to the user's device along with illustrations and feedback.

[0761] Example prompt sentence:

[0762] input:

[0763] plaintext

[0764] User says: "I don't understand the context of this historical event."

[0765] User Emotion: Confused

[0766] Generate feedback based on gaps in understanding and emotions.

[0767] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0768] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0769] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0770] [Third embodiment]

[0771] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0772] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0773] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0774] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0775] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0776] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0777] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0778] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0779] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0780] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0781] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0782] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0783] The present invention provides a system that analyzes user utterances and text data to identify and visualize lack of mutual understanding. The specific program processing of this system will be described below.

[0784] Server-side processing

[0785] 1. Data reception:

[0786] The server receives speech and text data from the user. For example, a student may ask a question such as "I don't know how to solve this equation" through speech or text. This data is sent to the server, which then receives it.

[0787] 2. Contextual analysis:

[0788] The server uses natural language processing technology to analyze the context of the received speech and text data. For example, it extracts information about the mathematical formula and how to solve it, and analyzes its meaning and background.

[0789] 3. Response analysis:

[0790] Similarly, the server uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "That can be solved using the basic integral formula," the server infers that the intent of this response means, "You need to understand the basic integral formula."

[0791] 4. Identifying the lack of mutual understanding:

[0792] By combining the results of context analysis and response analysis, the server identifies which part the user does not understand. In this case, it identifies that the student does not understand the "basic integral formula."

[0793] 5. Visualization and summary generation:

[0794] The system generates summary data to visualize and clearly display the identified areas of insufficient understanding, such as a message like "You lack understanding of the basic integral formula" along with an example of how to apply the formula.

[0795] 6. Data Transmission:

[0796] The generated visualization results and summary data are sent to the user's device, allowing the student to specifically identify their own lack of understanding and move on to the next learning step.

[0797] Terminal side processing

[0798] 1. Data reception:

[0799] The user device receives the visualization results and summary data sent from the server, such as a student's smartphone or PC.

[0800] 2. Data display:

[0801] The user terminal displays the received data to the user, for example, displaying a message such as "You lack understanding of the basic integral formula" along with specific step-by-step explanations and diagrams.

[0802] Specific examples

[0803] As a concrete example, consider the case where a student asks, "I don't know how to solve this equation" in a mathematics class. The student's speech data is sent to the server, which receives this data. Next, context analysis is used to analyze the meaning and background information of "how to solve the equation," and the teacher's response, "You can solve it by using the basic integral formula," is received. The server infers the intent of this response and determines that the student does not understand the "basic integral formula." Finally, a visualized summary message stating "You lack understanding of the basic integral formula" and an explanatory diagram are generated and sent to the user's device. The device receives this and displays it to the student, allowing them to specifically identify their lack of understanding and advance their learning.

[0804] This system allows users to clearly understand what they do not understand and receive appropriate feedback, thereby improving the effectiveness of learning and communication.

[0805] The processing flow will be explained below.

[0806] Step 1:

[0807] The user inputs a question or utterance. For example, a student inputs the text "I don't know how to solve this equation." The input data is sent to the server.

[0808] Step 2:

[0809] The server captures and stores the speech and text data received from the user, and prepares the received data for the next analysis step.

[0810] Step 3:

[0811] The server uses natural language processing technology on the received speech data. Specifically, it analyzes the structure and grammatical elements of the text and extracts the context. This identifies the problem domain, i.e., "how to solve mathematical equations."

[0812] Step 4:

[0813] The server performs response analysis on the utterance content. When a teacher inputs a response such as "You can solve that by using the basic integral formula," the server infers the teacher's intention and analyzes the answer strategy "basic integral formula."

[0814] Step 5:

[0815] The server integrates the results of context analysis and response analysis to identify a lack of mutual understanding. Specifically, it identifies that the student does not understand the "basic integral formula" and expresses this in one word.

[0816] Step 6:

[0817] The server visualizes the gaps in mutual understanding and generates summary data, such as a diagram that includes an example of the application of the formula along with a message saying, "You lack understanding of the basic integral formula."

[0818] Step 7:

[0819] The server sends the generated visualization results and summary data to the user's terminal, allowing the user to receive specific feedback.

[0820] Step 8:

[0821] The terminal receives the visualization results and summary data sent from the server, and the received data is displayed appropriately for the user, allowing students to check its contents.

[0822] Step 9:

[0823] Users can view the visualization results and summary data on their devices, which helps students pinpoint areas they don't understand and clarify the next steps they should take.

[0824] By going through each step in this way, users can specifically identify their own lack of understanding and progress in their studies efficiently.

[0825] Example 1

[0826] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0827] Conventional communication support systems have had difficulty identifying and quickly visualizing any lack of mutual understanding between the user and teacher, and informing the user of this. This has led to problems such as reduced learning efficiency and communication effectiveness. In particular, in conversations involving complex concepts and technical terms, it has been necessary to identify which parts the user does not understand and provide appropriate feedback.

[0828] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0829] In this invention, the server includes means for receiving voice data and text data from a user, means for preprocessing the received data, means for analyzing the context of the preprocessed data using natural language processing technology, means for preprocessing received response data, means for estimating the intent of the preprocessed response data, means for comparing the context analysis result with the response intention estimation result to identify a lack of mutual understanding, means for visualizing the lack of mutual understanding and generating summary data, and means for transmitting the generated visualization result and summary data to a user terminal. This makes it possible to quickly identify a lack of mutual understanding between a user and a teacher and provide appropriate visual feedback.

[0830] "User" refers to an individual who uses the system to communicate and learn.

[0831] "Voice data" refers to data that has been saved in digital form and contains the content of a user's speech.

[0832] "Text data" refers to character information entered by the user.

[0833] "Means for receiving" refers to the function by which the server obtains data sent by the user.

[0834] "Preprocessing" refers to the process of converting received data into a format that is easy to analyze.

[0835] "Natural language processing technology" refers to the technology that uses computers to understand and analyze human language.

[0836] "Context" refers to the context or background information of an utterance or sentence.

[0837] "Means of analysis" refers to the technology used to extract and understand information from received data.

[0838] "Response data" refers to information returned by a teacher or the like in response to a user's question.

[0839] "Means for inferring intention" refers to the function of analyzing and inferring what a speaker or writer intends.

[0840] "Mutual lack of understanding" refers to a situation where there is a discrepancy in understanding of information between the user and the respondent.

[0841] "Visualization" refers to the representation of data or information in visual form, such as a chart or graph.

[0842] "Summary data" refers to data that summarizes detailed information concisely.

[0843] "Transmitting means" refers to a function for sending data generated by the server to the user terminal.

[0844] "User terminal" refers to a device such as a computer or smartphone used by a user.

[0845] The present invention provides a system that analyzes user utterances and text data to identify and visualize lack of mutual understanding. A specific embodiment of this system will be described below.

[0846] Server side

[0847] 1. Data reception:

[0848] The server receives voice and text data from the user. For voice data, it uses voice recognition software (e.g., a voice recognition API) to convert the voice into text. For text data, it receives it as is.

[0849] 2. Speech-text preprocessing:

[0850] The server preprocesses the text data converted from speech or received directly, including removing unnecessary spaces and special characters.

[0851] 3. Contextual analysis:

[0852] Natural language processing technology (e.g., natural language processing API) is used on the preprocessed text data to extract context and keywords. For example, information related to "mathematical formulas" and "solution methods" is analyzed.

[0853] 4. Teacher response received:

[0854] Response data from the teacher to the user's question is received. For example, if the teacher answers "You can solve that by using the basic integral formula," this text data is received.

[0855] 5. Response analysis:

[0856] Response data is also analyzed using natural language processing technology. For example, the keyword "basic integral formula" is extracted and its intent is analyzed.

[0857] 6. Identifying the lack of mutual understanding:

[0858] The results of context analysis are compared with the response intent estimation results to identify which part the user does not understand. In this case, it is identified that the student does not understand the "basic integral formula."

[0859] 7. Visualization and summary generation:

[0860] To visualize the identified gaps in understanding, we generate graphs and charts using a visualization library (e.g., visualization library). We also create a summary message that reads, "You lack understanding of the basic integral formula," and illustrate an example of the application of that formula.

[0861] 8. Data Transmission:

[0862] The generated visualization results and summary data are sent to the user's terminal via an HTTP response, allowing the user to access the data.

[0863] Terminal side

[0864] 1. Data reception:

[0865] The user terminal receives the visualization results and summary data sent from the server, and converts them into the required format for display.

[0866] 2. Data display:

[0867] The user terminal displays the received data to the user. For example, using a web browser, HTML and JavaScript may be used to display step-by-step explanations and diagrams on the screen along with the message "You lack understanding of the basic integral formula."

[0868] Specific examples

[0869] Consider the case where a student asks "I don't know how to solve this equation" in a math class. The student's speech data is sent to the server, which receives this data. Next, a speech recognition API is used to convert the speech data into text data, and a natural language processing API is used to analyze the meaning and background information of "how to solve the equation" through context analysis. The teacher's response, "You can solve it by using the basic integral formula," is sent to the server, which receives this response and analyzes the intent of the response.

[0870] The server identifies that the student does not understand the "basic integral formula" and uses a visualization library to generate a summary message stating "You lack understanding of the basic integral formula" along with an explanatory diagram. Once the data is received and sent to the user's device, it is displayed in the browser using HTML and JavaScript. The student can then identify specific areas of understanding that are lacking and move forward with their studies.

[0871] Prompt Sentence Examples

[0872] "A student asks, 'I don't know how to solve this mathematical equation.' Analyze this speech data and, based on the teacher's response, 'You can solve it using the basic integral formula,' identify that the student does not understand the 'basic integral formula,' and explain the process for visualizing and displaying this information."

[0873] Although the embodiment of the invention has been described above, the invention is not limited to this, and various modifications are possible without departing from the spirit of the invention.

[0874] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0875] Step 1: Receiving data

[0876] The server receives voice and text data from the user. For example, when a student says, "I don't know how to solve this equation," the voice data is sent to the server. To receive the voice data, an HTTP request is used. The input is the voice data and text data, and the output is the received data.

[0877] Step 2: Speech-text preprocessing

[0878] The server converts the received voice data into text using voice recognition software (e.g., voice recognition API). It also cleans the received text data. Specifically, it removes unnecessary spaces and special characters. The input is voice data and text data, and the output is preprocessed text data.

[0879] Step 3: Context Analysis

[0880] The server performs context analysis on the preprocessed text data using natural language processing technology (e.g., natural language processing API). For example, it extracts keywords and contextual information related to "formulas" and "solution methods." This analysis provides important information and background information. The input is the preprocessed text data, and the output is the analyzed contextual information.

[0881] Step 4: Receiving the teacher's response

[0882] The server receives the teacher's response data to the user's question. If the teacher replies, "That can be solved using the basic integral formula," the server receives the text data. The input is the teacher's text data, and the output is the received response data.

[0883] Step 5: Response analysis

[0884] The server also uses natural language processing technology to analyze the received response data. Specifically, it extracts the keyword "basic integral formula" and infers its intent. The input is the preprocessed response data, and the output is the intent of the analyzed response.

[0885] Step 6: Identify the gap in mutual understanding

[0886] The server compares the results of context analysis with the response intent estimation result to identify which part the user does not understand. For example, it identifies that a student does not understand the "basic integral formula." The input is the analyzed context information and response intent, and the output is the identified lack of understanding.

[0887] Step 7: Generate visualizations and summaries

[0888] The server generates graphs and figures using a visualization library (e.g., visualization library) to visualize the identified gaps in understanding. It also displays a summary message saying "You lack understanding of the basic integral formula" and illustrates an example of how to apply that formula. The input is the identified gaps in understanding, and the output is the generated visualization results and summary data.

[0889] Step 8: Send data

[0890] The server sends the generated visualization results and summary data to the user terminal. Specifically, it sends the data via an HTTP response. The input is the visualization results and summary data, and the output is the data sent to the user terminal.

[0891] Step 9: Receiving Data

[0892] The user terminal receives the visualization results and summary data sent from the server, receives the HTTP response, and imports the data. The input is the data sent from the server, and the output is the received data.

[0893] Step 10: Data Display

[0894] The user terminal displays the received data to the user. Specifically, it uses HTML and JavaScript to display step-by-step explanations and diagrams on the screen along with the message "You lack understanding of the basic integral formula." The input is the received data, and the output is the information displayed to the user.

[0895] (Application example 1)

[0896] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0897] Conventional educational support systems are not sufficient to simply identify areas where the user lacks understanding, and lack specific feedback and explanations, which reduces the effectiveness of the user's learning. Furthermore, there is a lack of a means to effectively display visualized feedback on devices such as smartphones, which limits the actual learning support provided.

[0898] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0899] In this invention, the server includes a means for providing educational feedback specific to the user's lack of understanding, a means for displaying visualized feedback on the user's smartphone, a means for generating and displaying specific explanations and step-by-step procedures for the user's lack of understanding using a generative AI model, and a means for presenting additional information to fill in the lack of understanding using prompt sentences. This allows the user to receive information that fills in the lack of understanding in a specific and visual way in real time, significantly improving learning effectiveness.

[0900] "User" refers to a general user who uses the system to input speech or text data.

[0901] "Utterance" refers to words or phrases spoken by a user.

[0902] "Text data" refers to sentences or information entered by a user in text format.

[0903] "Natural language processing technology" refers to technology that enables computers to understand and process human language.

[0904] "Context" refers to the context or background information associated with speech or text data.

[0905] "Response intent" refers to the content or purpose that a user intends to convey through a particular utterance or text.

[0906] "Mutual incomprehension" refers to a situation in which there is a discrepancy in the interpretation of meaning or intent between the user and the system or another interlocutor.

[0907] "Visualization" refers to the display of data or information in a visual format.

[0908] "Summary data" refers to data that succinctly summarizes analyzed information and feedback.

[0909] "User terminal" refers to a device such as a smartphone or PC used by a user.

[0910] "Instructional feedback" refers to specific, instructional information provided to users where they have difficulty understanding something.

[0911] A "smartphone" is a type of mobile phone that is a portable device that can connect to the Internet and use applications.

[0912] A "generative AI model" refers to an artificial intelligence model that has been trained in advance based on a large amount of data.

[0913] A "prompt sentence" refers to a leading and instructive sentence that provides the user with additional information.

[0914] A system for implementing this invention exchanges data between a user and a server, uses natural language processing technology to identify areas where the user lacks understanding, and provides visual feedback to a smartphone.

[0915] Hardware and Software

[0916] Hardware

[0917] Smartphone: A handheld device that allows users to input speech and text data and receive feedback.

[0918] Server: A central processing unit for data analysis and feedback generation.

[0919] software

[0920] SpeechRecognition library: Used to convert user speech into text data.

[0921] Transformers library: Leverages natural language processing techniques to analyze user input data and use generative AI models.

[0922] Matplotlib: Used to visualize parts that are not fully understood.

[0923] Data processing and calculation flow

[0924] 1. Speech Recognition: The speech that a user speaks into their smartphone is captured as audio and converted into text using the SpeechRecognition library. For example, say, "I don't understand the basic formula for integrals."

[0925] 2. NLP analysis: The text data is sent to the server and natural language processing is performed using the Transformers library, which analyzes the user's intent and context.

[0926] 3. Response intent estimation: The server uses the analyzed data to identify which parts the user did not understand.

[0927] 4. Visualization: After the weaknesses are identified, visual feedback is generated using Matplotlib.

[0928] 5. Sending feedback: The server sends the visual feedback and specific explanatory information to the smartphone.

[0929] Specific examples

[0930] For example, if a user asks, "I don't understand the basic integral formula," this data is sent from the smartphone to the server. The server receives this text and uses the Transformers library to identify a lack of understanding regarding the "basic integral formula." The program then visualizes that portion, for example, by using Matplotlib to represent an example of the application of the basic integral formula. The visualized feedback and specific explanatory information are then displayed on the smartphone.

[0931] Prompt Sentence Examples

[0932] The prompt is:

[0933] context_text =

[0934] The fundamental integral formula is a key concept in calculus and has the following formula:

[0935] ∫f'(x)dx = f(x) + C

[0936] If you don't understand this formula, check out the steps below:

[0937] 1. Review the basic concepts of differentiation.

[0938] 2. Deepen understanding through examples of application of basic integral formulas.

[0939] 3. Browse additional educational materials and online resources.

[0940] Based on this example, users can receive information in real time that complements specific areas of their understanding, significantly improving their learning effectiveness.

[0941] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0942] Step 1:

[0943] A smartphone inputs speech from the user as voice data. When the user speaks a question or uncertainty, the smartphone's microphone captures it. Next, speech recognition software (SpeechRecognition library) converts the voice data into text data. In this case, the input is voice data and the output is text data. For example, an utterance such as "I don't understand the basic formula for integrals" can be converted into text.

[0944] Step 2:

[0945] The smartphone sends text data to the server. The input here is the user's text data, and the output is the data to be sent to the server. This includes the operation of sending the text data to the server via the Internet.

[0946] Step 3:

[0947] The server analyzes the received text data. It uses natural language processing technology (Transformers library) to analyze the context of the text data. The input is the user's text data, and the output is the context analysis results. Specifically, the main text is the "basic integral formula," and related context information is extracted.

[0948] Step 4:

[0949] The server identifies the user's lack of understanding based on the analyzed context. Using a generative AI model, it infers the specific areas of lack of understanding from the user's utterances. The input is the result of the context analysis, and the output is the identified areas of lack of understanding. In this case, it is identified that the user lacks understanding of the "basic formula for integration."

[0950] Step 5:

[0951] The server visualizes the identified areas of incomprehension. It uses visualization libraries such as Matplotlib to display information in a format that is easy for users to understand. The input is the areas of incomprehension, and the output is visualized feedback. For example, it visualizes an example of the application of the basic integral formula.

[0952] Step 6:

[0953] The server compiles the visualized feedback and generates explanatory information using prompts. The input is the visualization data and explanatory information for the areas of incomprehension, and the output is feedback data including specific prompts. The prompts include specific explanations and step-by-step instructions.

[0954] Step 7:

[0955] The server sends the generated feedback data to the user's smartphone. The input is the feedback data, and the output is the data to be sent to the smartphone. These data are sent via the Internet.

[0956] Step 8:

[0957] The smartphone displays the received feedback data. Visualized feedback and specific explanatory information are presented to the user. The input is the feedback data, and the output is a visual display for the user. This includes the user checking the specific feedback on the smartphone screen regarding areas of incomplete understanding.

[0958] These steps allow users to concretely and visually grasp their own lack of understanding and receive feedback to improve their learning.

[0959] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0960] The present invention provides a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and combines it with an emotion engine that recognizes the user's emotions. Specific program processing of this system is described below.

[0961] Server-side processing

[0962] 1. Data reception:

[0963] The server receives speech and text data from the user. For example, a student may input text such as "I don't know how to solve this mathematical equation." The emotion engine also receives the user's emotional state at the same time. The input data is sent to the server, which then receives it.

[0964] 2. Contextual analysis:

[0965] The server uses natural language processing technology to analyze the context of the received speech and text data. For example, it extracts information about the mathematical formula and how to solve it, and analyzes its meaning and background.

[0966] 3. Response analysis:

[0967] Similarly, the server uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "That can be solved using the basic integral formula," the server infers that the intent of this response means, "You need to understand the basic integral formula."

[0968] 4. Emotion analysis:

[0969] The emotion engine estimates the user's emotional state from the received data. For example, it analyzes whether the student is expressing emotions such as "confused" or "anxious." This emotional state is reflected in the analysis results.

[0970] 5. Identifying the lack of mutual understanding:

[0971] By integrating the results of context analysis, response analysis, and sentiment analysis, the server identifies which part the user does not understand. In this case, it identifies that the student does not understand the "basic integral formula," while also taking into account the student's emotional state.

[0972] 6. Visualization and summary generation:

[0973] The system generates summary data to visualize the identified areas of insufficient understanding and the user's emotional state, and displays them in an easy-to-understand manner. For example, it displays a message such as "You lack understanding of the basic integral formula," along with an example of how to apply the formula, providing feedback according to the user's emotional state.

[0974] 7. Data Transmission:

[0975] The generated visualization results and summary data are sent to the user's device, allowing the user to specifically identify their own lack of understanding and receive appropriate feedback according to their emotions.

[0976] Terminal side processing

[0977] 1. Data reception:

[0978] The user device receives the visualization results and summary data sent from the server, such as a student's smartphone or PC.

[0979] 2. Data display:

[0980] The user device displays the received data to the user. For example, it might display a message like "You lack understanding of the basic integral formula," along with specific step-by-step explanations and illustrations. It might also display encouraging messages and advice based on the user's emotional state.

[0981] Specific examples

[0982] As a specific example, consider a case in which a student asks, "I don't know how to solve this equation" in a math class, expressing confusion. The student's speech data and emotion data are sent to the server, which receives them and performs context analysis. The server then infers the teacher's intent from the teacher's response, "You can solve it by using the basic integral formula." The emotion engine recognizes the student's confusion and identifies the student's confusion along with their lack of understanding of the "basic integral formula." Based on this information, the system generates visualization data such as "You lack understanding of the basic integral formula" and an encouraging message such as "Even if you're confused, stay calm and keep trying," and sends this data to the user's device. The device displays this to the student, allowing them to clearly understand their lack of understanding and receive specific advice.

[0983] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[0984] The processing flow will be explained below.

[0985] Step 1:

[0986] The user inputs a question or utterance. For example, a student may input text such as "I don't know how to solve this mathematical equation." The emotion engine recognizes emotions from the user's voice and text, and simultaneously detects the emotional state of "confused." This data is sent to the server.

[0987] Step 2:

[0988] The server captures and stores the received speech and text data from the user, as well as the detected emotion data, and prepares the received data for the next analysis step.

[0989] Step 3:

[0990] The server uses natural language processing technology to perform context analysis on the received speech and text data. For example, it extracts information about "mathematical formulas" and "solution methods" and analyzes their meaning and background. This analysis allows the server to identify the problem domain.

[0991] Step 4:

[0992] The server also uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "You can solve that by using the basic integral formula," the server infers that the intent of this response is the solution strategy of "using the basic integral formula."

[0993] Step 5:

[0994] The emotion engine analyzes emotions from user utterances and text data and provides the results to the server. For example, if the emotion "confusion" is detected, the emotion engine notifies the server of that information.

[0995] Step 6:

[0996] The server integrates the results of context analysis, response intent estimation, and emotion analysis from the emotion engine to identify which part the user does not understand and their emotional state at that time. For example, it can identify that a student does not understand the "basic integral formula" and is confused.

[0997] Step 7:

[0998] The server visualizes the gaps in mutual understanding and generates summary data according to the user's emotional state. Specifically, it generates a message such as "You lack understanding of the basic integral formula" and an encouraging message such as "If you're confused, go back to the basics."

[0999] Step 8:

[1000] The server sends the generated visualization results and summary data to the user terminal, allowing the user to receive specific feedback.

[1001] Step 9:

[1002] The terminal receives the visualization results and summary data sent from the server, and displays the received data appropriately to the user, for example, displaying a message such as "You lack understanding of the basic integral formula" along with detailed explanations, illustrations, and encouraging messages.

[1003] Step 10:

[1004] Users can view the visualization results and summary data on their devices, which allows students to specifically identify areas they do not understand, receive appropriate explanations and emotional advice, and move on to the next step in their learning.

[1005] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[1006] Example 2

[1007] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1008] Conventional systems have limitations in identifying lack of mutual understanding simply by analyzing the user's questions and responses. Furthermore, they provide feedback without taking the user's emotional state into consideration, making effective communication difficult. As a result, it is difficult to identify which part the user does not understand, and appropriate responses may not be possible.

[1009] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1010] In this invention, the server includes means for receiving utterances, text data, and emotional states from a user, means for analyzing the context of the received data using natural language processing technology, means for estimating the intention of a response based on the analyzed context, means for estimating the emotional state of the user using emotion analysis technology, means for identifying a lack of mutual understanding by integrating the results of the context analysis, the response intention estimation result, and the emotion analysis result, means for visualizing the lack of mutual understanding and generating summary data, and means for transmitting the generated visualization result and summary data to a user terminal. This makes it possible to specifically identify the user's lack of understanding and provide appropriate feedback accordingly.

[1011] "Means for receiving user utterances, text data, and emotional state" refers to a device or method that collects voice data, text data, and additional data input by the user for determining the user's emotions, and transmits them to a server.

[1012] "Means for analyzing the context of received data using natural language processing technology" refers to devices or methods that apply natural language analysis algorithms to analyze collected voice data or text data in order to understand its context and meaning.

[1013] "Means for inferring the intent of a response based on analyzed context" refers to a device or method for identifying the intent of a user's statement or question based on context-analyzed data and generating an appropriate response.

[1014] "Means for estimating a user's emotional state using emotion analysis technology" refers to technology or methods for analyzing voice data, facial expression data, etc. collected from a user to determine the emotions the user is feeling.

[1015] The "means for identifying a lack of mutual understanding by integrating the results of context analysis, response intention estimation, and sentiment analysis" is a method for integrating the results of the aforementioned data analysis to identify areas of lack of understanding between the user and the system or between other users.

[1016] The "means for visualizing the lack of mutual understanding and generating summary data" is a method for visually displaying the lack of understanding and generating summary data in a format that can be intuitively understood by the user.

[1017] The "means for transmitting the generated visualization results and summary data to the user terminal" refers to a communication method or protocol for transmitting the visualization results and summary data to the terminal used by the user.

[1018] The present invention provides a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and combines it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1019] Server-side processing

[1020] The server first receives speech and text data from the user. When the user types text into the device, such as "I don't know how to solve this mathematical equation," this data is sent to the server. At the same time, the emotion engine analyzes the user's voice and facial expression data, and also sends their emotional state to the server. The server receives this data and proceeds to the next stage of analysis.

[1021] The server uses natural language processing technology to analyze the context of the received data. To do this, it uses natural language processing libraries such as Google Cloud Natural Language API and SpaCy. For example, it extracts keywords such as "mathematical formula" and "how to solve" and understands the context based on them. Next, it infers the intent of the response based on the analyzed context. If the teacher answers, "That can be solved using the basic integral formula," it infers the intent of the response as "You need to understand the basic integral formula."

[1022] Furthermore, an emotion engine is used to estimate the user's emotional state. Using emotion analysis tools such as IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, it is determined whether the user is feeling "confused" or "anxious." The results of this emotion analysis are reflected in the analysis results.

[1023] The server integrates the results of context analysis, response intent estimation, and sentiment analysis to identify gaps in mutual understanding. For example, it can identify that a student does not understand the "basic integral formula" and also detect feelings of confusion.

[1024] The server then visualizes the identified gaps in understanding and the user's emotional state, generating summary data in a format that the user can intuitively understand. For example, the server might display a message such as "You lack understanding of a basic integral formula," along with step-by-step examples of how to apply the formula. It also provides encouraging messages and links to additional resources for users who are confused. The visualization and summary data are then sent to the user's device.

[1025] Terminal side processing

[1026] The user's device receives the visualization results and summary data sent from the server. For example, this could be a student's smartphone or PC. The received data is then displayed to the student. For example, a message such as "Your understanding of the basic integral formula is lacking" may be displayed along with specific explanations and illustrations. Encouraging messages and advice based on the user's emotional state may also be displayed. By viewing this, the user can specifically identify areas of lack of understanding and solutions, and move on to the next learning step.

[1027] Specific examples

[1028] As a specific example, consider a case in which a student asks, "I don't know how to solve this equation" in a math class, expressing confusion. The student's speech data and emotion data are sent to the server, which receives them and performs context analysis. The server then infers the teacher's intent from the teacher's response, "You can solve it by using the basic integral formula." The emotion engine recognizes the student's confusion and identifies the student's confusion along with their lack of understanding of the "basic integral formula." Based on this information, the system generates visualization data such as "You lack understanding of the basic integral formula" and an encouraging message such as "Even if you're confused, stay calm and keep trying," and sends this data to the user's device. The device displays this to the student, allowing them to clearly understand their lack of understanding and receive specific advice.

[1029] Prompt Sentence Examples

[1030] "When a student asks, 'I don't know how to solve this equation,' analyze the teacher's response and the student's feelings to identify the student's lack of understanding and generate feedback."

[1031] "Based on what students say and how they feel, identify areas of lack of understanding and generate feedback that visualizes those areas."

[1032] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[1033] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1034] Step 1:

[1035] Receives user utterances, text data, and emotional states

[1036] The server first receives speech and text data sent from the user's device. For example, a student may type and send the text "I don't know how to solve this mathematical equation." At the same time that this text data is sent to the server, the emotion engine analyzes the user's voice and facial expression data, and their emotional state is also sent to the server. The specific input data is the speech, text data, and emotional state, and this data is stored on the server as output.

[1037] Step 2:

[1038] Context Analysis

[1039] The server performs context analysis on the received speech and text data using natural language processing technology (for example, Google Cloud Natural Language API or SpaCy). In this step, the meaning of words and phrases in the speech and text data is analyzed to understand the context. For example, keywords such as "mathematical formula" and "how to solve" are extracted and their relevance and meaning are analyzed. The input data is text data, and the output data is the analyzed context information. This process includes grammatical analysis and dependency analysis.

[1040] Step 3:

[1041] Infer response intent

[1042] The server also uses natural language processing technology to infer the intent of responses from teachers and other users. For example, if a teacher replies, "That can be solved using the basic integral formula," the server infers the intent from this response: "You need to understand the basic integral formula." The input data is the response text from the teacher, and the output data is the inferred intent. Specific operations include sending the response data to the analysis module and obtaining the results.

[1043] Step 4:

[1044] Estimating the user's emotional state

[1045] The server uses an emotion engine to estimate the user's emotional state. This process uses tools such as IBM Watson Tone Analyzer and Microsoft Azure Text Analytics. For example, emotions such as "confused" or "anxious" are analyzed from the user's voice and facial expression data. The input data is the user's voice and facial expression data, and the output data is the analyzed emotional state. Specific operations include sending data to the emotion analysis tool, receiving a response, and obtaining the analysis results.

[1046] Step 5:

[1047] Identifying a lack of mutual understanding

[1048] The server integrates the results of the context analysis, response intent estimation, and emotional state analysis to identify the parts of the sentence that the user does not understand. In this case, the analysis results indicate that the student does not understand the basic integral formula, and the accompanying emotional state of being confused is also taken into account. The input data are all of the above analysis results, and the output data are the identified gaps in mutual understanding. Specific operations include integrating each analysis result and applying an algorithm to identify the gaps.

[1049] Step 6:

[1050] Generate visualizations and summary data

[1051] The server generates summary data to visualize the identified gaps in understanding and the user's emotional state, and displays them in an easy-to-understand manner. For example, it might display a message saying, "You lack understanding of the basic integral formula," along with a step-by-step example of how to apply the formula. It might also provide encouraging messages and links to additional resources for confused users. The input data are the identified gaps in understanding and the user's emotional state, and the output data is the visualized summary data.

[1052] Step 7:

[1053] Data transmission

[1054] The server sends the generated visualization results and summary data to the user's terminal. To ensure data consistency and accuracy, encrypted communication is used, for example, using the SSL / TLS protocol. The input data are the generated visualization results and summary data, and the output data is the data sent to the user's terminal.

[1055] Step 8:

[1056] Data Display

[1057] The user terminal receives the visualization results and summary data sent from the server and displays them to the user. For example, it may display a message such as "You lack understanding of the basic integral formula," along with specific step-by-step explanations and illustrations. It may also display encouraging messages and advice based on the user's emotional state. The input data are the visualization results and summary data sent from the server, and the output data is the information displayed on the terminal. Specific operations include invoking a screen display module after receiving the data and displaying the information in an appropriate format.

[1058] (Application example 2)

[1059] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1060] Conventional systems were able to analyze user utterances and text data to identify lack of mutual understanding, but lacked a means to provide feedback based on the user's emotional state. As a result, they were unable to provide appropriate feedback that was in line with the user's emotions, limiting the effectiveness of learning and communication. The present invention aims to provide a system that provides feedback that takes the user's emotional state into account, thereby achieving more effective promotion of understanding and support.

[1061] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1062] In this invention, the server includes means for receiving utterances and text data from a user, means for analyzing the context of the received data using natural language processing technology, means for estimating the intention of the response based on the analyzed context, means for comparing the context analysis result with the response estimation result to identify a lack of mutual understanding, means for visualizing the lack of mutual understanding and generating summary data, means for transmitting the generated visualization result and summary data to a user terminal, means for recognizing and analyzing the user's emotional state, and means for generating feedback based on the emotional state. This makes it possible to provide appropriate feedback tailored to the user's emotional state, promote user understanding, and improve learning effectiveness and the quality of communication.

[1063] "User speech and text data" refers to information provided by the user through voice or text.

[1064] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[1065] "Context" refers to the context, including the background, situation, and related information of a particular utterance or text.

[1066] "Response intent" refers to the purpose or intent of a response to a received utterance or text.

[1067] "Lack of mutual understanding" refers to a situation in which both parties in a dialogue do not fully understand the intentions or content of the other.

[1068] "Visualization" refers to the display of information in the form of graphs, charts, images, etc.

[1069] "Summary data" refers to data that briefly summarizes key information.

[1070] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) used by a user to receive or send information.

[1071] "Emotional state" refers to the emotions a user is feeling at a particular moment.

[1072] "Feedback" refers to advice, comments, and responses provided to the user by the system.

[1073] This invention is an educational support system that combines a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and an emotion engine that recognizes user emotions. This system executes the following processes through various software programs. The system mainly operates in cooperation with the server and user terminals.

[1074] 1. Server-side processing

[1075] The server includes the following main programs and functions:

[1076] Data reception: A method for receiving speech or text data from a user. For example, the server receives data sent from a user device such as a smartphone or PC.

[1077] Contextual analysis: Analyzing the context of received data using natural language processing techniques (e.g., common natural language processing APIs). For example, extracting and analyzing information related to "math problem solving."

[1078] Response analysis: A method of analyzing response data from educational content providers using natural language processing technology to infer their intent.

[1079] Sentiment analysis: A method of recognizing and analyzing emotions from user speech and text data using an emotion recognition engine (e.g., a general emotion analysis API).

[1080] Identifying gaps in mutual understanding: A means of integrating the results of context analysis, response analysis, and sentiment analysis to identify areas where there is a gap in mutual understanding.

[1081] Visualization and summary generation: A means to visualize the identified gaps in understanding and the user's emotional state and generate summary data. For example, generating a diagram that accompanies the message "I don't understand the basic integral formula."

[1082] Data transmission: A means to transmit the generated visualization results and summary data to the user terminal.

[1083] 2. Terminal processing

[1084] The user terminal includes the following processing functions:

[1085] Data reception: A means to receive visualization results and summary data sent from the server.

[1086] Data display: A method for displaying received data to the user. For example, displaying a message such as "You lack understanding of the basic integral formula" and providing explanations using concrete examples and diagrams.

[1087] Specific examples

[1088] When a user utters or inputs text such as "I don't understand the background of this historical event," the server receives this and performs context analysis. It then obtains the response data from the educational content provider, "The economic background of this event is important," and infers the user's intent. The emotion recognition engine recognizes the user's confused emotion and integrates the context analysis results, response data, and emotion data to determine that the user does not understand the "economic background." As a result, "You lack understanding of the economic background" is visualized and sent to the user's device along with a message such as "If you have difficulty, try thinking about it step by step."

[1089] Prompt Sentence Examples

[1090] input:

[1091] plaintext

[1092] User says: "I don't understand the context of this historical event."

[1093] User Emotion: Confused

[1094] Generate feedback based on gaps in understanding and emotions.

[1095] This system is expected to improve learning effectiveness by allowing users to accurately identify areas of lack of understanding during learning and receive appropriate feedback tailored to their emotions.

[1096] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1097] Step 1:

[1098] Data reception

[1099] The user inputs speech or text data from a device such as a smartphone or PC. The input data is sent to the server via the network. If the data is voice, the server converts it into text using a speech recognition engine (e.g., a general speech recognition API).

[1100] Input: User utterances and text data

[1101] Output: Text data

[1102] Step 2:

[1103] Contextual Analysis

[1104] The server uses natural language processing technology (e.g., a general natural language processing API) to analyze the context of the received text data. Specifically, it extracts important keywords and phrases from the text and identifies the problems or questions the user is having.

[1105] Input: Text data

[1106] Output: Context analysis results (list of keywords and phrases)

[1107] Step 3:

[1108] Response Analysis

[1109] The system uses natural language processing technology to analyze the response data of educational content providers (e.g., instructors and teachers) and infer their intent. For example, from the instructor's response, "The economic background of this incident is important," the system focuses on the "economic background" and clarifies the instructor's intent.

[1110] Input: Instructor response data

[1111] Output: Response intent predictions

[1112] Step 4:

[1113] Emotion analysis

[1114] The server uses an emotion recognition engine (e.g., a general emotion analysis API) to recognize emotions from the user's text data and speech data. For example, it extracts emotions such as "confused" or "anxious."

[1115] Input: User text or speech data

[1116] Output: User's emotional state

[1117] Step 5:

[1118] Identifying gaps in mutual understanding

[1119] The server integrates the results of context analysis, response analysis, and sentiment analysis to identify which parts the user does not understand, thereby clarifying specific areas of incomprehension, such as the user's lack of understanding of the economic background.

[1120] Input: Context analysis results, response intent estimation results, emotional state

[1121] Output: Identification of areas of incomprehension

[1122] Step 6:

[1123] Visualization and summary generation

[1124] The system generates summary data to visualize the identified areas of incomprehension and the user's emotional state and display them in an easy-to-understand format. For example, it generates a summary message such as "You lack understanding of the economic background," along with an illustration explaining the background, and adds feedback such as "Even if you are confused, please remain calm and proceed."

[1125] Input: Identification of incomplete understanding, user's emotional state

[1126] Output: Summary data and visualization results

[1127] Step 7:

[1128] Data transmission

[1129] The server then sends the generated visualization results and summary data to the user's device, where the user can display the received data, specifically identifying areas of incomplete understanding, and receive appropriate feedback.

[1130] Input: Summary data and visualization results

[1131] Output: Data sent to the user's terminal

[1132] Examples:

[1133] The user speaks or inputs text saying, "I don't understand the background to this historical event." The server receives this and converts it into text if it is voice data. It then uses natural language processing technology to perform context analysis, and similarly analyzes the instructor's response data to determine the response intent. Next, an emotion recognition engine recognizes the user's emotional state and determines that the user is "confused." This data is integrated to determine that the user does not understand the "economic background." The server generates summary data saying, "You lack understanding of the economic background," and sends it to the user's device along with illustrations and feedback.

[1134] Example prompt sentence:

[1135] input:

[1136] plaintext

[1137] User says: "I don't understand the context of this historical event."

[1138] User Emotion: Confused

[1139] Generate feedback based on gaps in understanding and emotions.

[1140] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1141] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1142] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1143] [Fourth embodiment]

[1144] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1145] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1146] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1147] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1148] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1149] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1150] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1151] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1152] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1153] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1155] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1156] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1157] The present invention provides a system that analyzes user utterances and text data to identify and visualize lack of mutual understanding. The specific program processing of this system will be described below.

[1158] Server-side processing

[1159] 1. Data reception:

[1160] The server receives speech and text data from the user. For example, a student may ask a question such as "I don't know how to solve this equation" through speech or text. This data is sent to the server, which then receives it.

[1161] 2. Contextual analysis:

[1162] The server uses natural language processing technology to analyze the context of the received speech and text data. For example, it extracts information about the mathematical formula and how to solve it, and analyzes its meaning and background.

[1163] 3. Response analysis:

[1164] Similarly, the server uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "That can be solved using the basic integral formula," the server infers that the intent of this response means, "You need to understand the basic integral formula."

[1165] 4. Identifying the lack of mutual understanding:

[1166] By combining the results of context analysis and response analysis, the server identifies which part the user does not understand. In this case, it identifies that the student does not understand the "basic integral formula."

[1167] 5. Visualization and summary generation:

[1168] The system generates summary data to visualize and clearly display the identified areas of insufficient understanding, such as a message like "You lack understanding of the basic integral formula" along with an example of how to apply the formula.

[1169] 6. Data Transmission:

[1170] The generated visualization results and summary data are sent to the user's device, allowing the student to specifically identify their own lack of understanding and move on to the next learning step.

[1171] Terminal side processing

[1172] 1. Data reception:

[1173] The user device receives the visualization results and summary data sent from the server, such as a student's smartphone or PC.

[1174] 2. Data display:

[1175] The user terminal displays the received data to the user, for example, displaying a message such as "You lack understanding of the basic integral formula" along with specific step-by-step explanations and diagrams.

[1176] Specific examples

[1177] As a concrete example, consider the case where a student asks, "I don't know how to solve this equation" in a mathematics class. The student's speech data is sent to the server, which receives this data. Next, context analysis is used to analyze the meaning and background information of "how to solve the equation," and the teacher's response, "You can solve it by using the basic integral formula," is received. The server infers the intent of this response and determines that the student does not understand the "basic integral formula." Finally, a visualized summary message stating "You lack understanding of the basic integral formula" and an explanatory diagram are generated and sent to the user's device. The device receives this and displays it to the student, allowing them to specifically identify their lack of understanding and advance their learning.

[1178] This system allows users to clearly understand what they do not understand and receive appropriate feedback, thereby improving the effectiveness of learning and communication.

[1179] The processing flow will be explained below.

[1180] Step 1:

[1181] The user inputs a question or utterance. For example, a student inputs the text "I don't know how to solve this equation." The input data is sent to the server.

[1182] Step 2:

[1183] The server captures and stores the speech and text data received from the user, and prepares the received data for the next analysis step.

[1184] Step 3:

[1185] The server uses natural language processing technology on the received speech data. Specifically, it analyzes the structure and grammatical elements of the text and extracts the context. This identifies the problem domain, i.e., "how to solve mathematical equations."

[1186] Step 4:

[1187] The server performs response analysis on the utterance content. When a teacher inputs a response such as "You can solve that by using the basic integral formula," the server infers the teacher's intention and analyzes the answer strategy "basic integral formula."

[1188] Step 5:

[1189] The server integrates the results of context analysis and response analysis to identify a lack of mutual understanding. Specifically, it identifies that the student does not understand the "basic integral formula" and expresses this in one word.

[1190] Step 6:

[1191] The server visualizes the gaps in mutual understanding and generates summary data, such as a diagram that includes an example of the application of the formula along with a message saying, "You lack understanding of the basic integral formula."

[1192] Step 7:

[1193] The server sends the generated visualization results and summary data to the user's terminal, allowing the user to receive specific feedback.

[1194] Step 8:

[1195] The terminal receives the visualization results and summary data sent from the server, and the received data is displayed appropriately for the user, allowing students to check its contents.

[1196] Step 9:

[1197] Users can view the visualization results and summary data on their devices, which helps students pinpoint areas they don't understand and clarify the next steps they should take.

[1198] By going through each step in this way, users can specifically identify their own lack of understanding and progress in their studies efficiently.

[1199] Example 1

[1200] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1201] Conventional communication support systems have had difficulty identifying and quickly visualizing any lack of mutual understanding between the user and teacher, and informing the user of this. This has led to problems such as reduced learning efficiency and communication effectiveness. In particular, in conversations involving complex concepts and technical terms, it has been necessary to identify which parts the user does not understand and provide appropriate feedback.

[1202] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1203] In this invention, the server includes means for receiving voice data and text data from a user, means for preprocessing the received data, means for analyzing the context of the preprocessed data using natural language processing technology, means for preprocessing received response data, means for estimating the intent of the preprocessed response data, means for comparing the context analysis result with the response intention estimation result to identify a lack of mutual understanding, means for visualizing the lack of mutual understanding and generating summary data, and means for transmitting the generated visualization result and summary data to a user terminal. This makes it possible to quickly identify a lack of mutual understanding between a user and a teacher and provide appropriate visual feedback.

[1204] "User" refers to an individual who uses the system to communicate and learn.

[1205] "Voice data" refers to data that has been saved in digital form and contains the content of a user's speech.

[1206] "Text data" refers to character information entered by the user.

[1207] "Means for receiving" refers to the function by which the server obtains data sent by the user.

[1208] "Preprocessing" refers to the process of converting received data into a format that is easy to analyze.

[1209] "Natural language processing technology" refers to the technology that uses computers to understand and analyze human language.

[1210] "Context" refers to the context or background information of an utterance or sentence.

[1211] "Means of analysis" refers to the technology used to extract and understand information from received data.

[1212] "Response data" refers to information returned by a teacher or the like in response to a user's question.

[1213] "Means for inferring intention" refers to the function of analyzing and inferring what a speaker or writer intends.

[1214] "Mutual lack of understanding" refers to a situation where there is a discrepancy in understanding of information between the user and the respondent.

[1215] "Visualization" refers to the representation of data or information in visual form, such as a chart or graph.

[1216] "Summary data" refers to data that summarizes detailed information concisely.

[1217] "Transmitting means" refers to a function for sending data generated by the server to the user terminal.

[1218] "User terminal" refers to a device such as a computer or smartphone used by a user.

[1219] The present invention provides a system that analyzes user utterances and text data to identify and visualize lack of mutual understanding. A specific embodiment of this system will be described below.

[1220] Server side

[1221] 1. Data reception:

[1222] The server receives voice and text data from the user. For voice data, it uses voice recognition software (e.g., a voice recognition API) to convert the voice into text. For text data, it receives it as is.

[1223] 2. Speech-text preprocessing:

[1224] The server preprocesses the text data converted from speech or received directly, including removing unnecessary spaces and special characters.

[1225] 3. Contextual analysis:

[1226] Natural language processing technology (e.g., natural language processing API) is used on the preprocessed text data to extract context and keywords. For example, information related to "mathematical formulas" and "solution methods" is analyzed.

[1227] 4. Teacher response received:

[1228] Response data from the teacher to the user's question is received. For example, if the teacher answers "You can solve that by using the basic integral formula," this text data is received.

[1229] 5. Response analysis:

[1230] Response data is also analyzed using natural language processing technology. For example, the keyword "basic integral formula" is extracted and its intent is analyzed.

[1231] 6. Identifying the lack of mutual understanding:

[1232] The results of context analysis are compared with the response intent estimation results to identify which part the user does not understand. In this case, it is identified that the student does not understand the "basic integral formula."

[1233] 7. Visualization and summary generation:

[1234] To visualize the identified gaps in understanding, we generate graphs and charts using a visualization library (e.g., visualization library). We also create a summary message that reads, "You lack understanding of the basic integral formula," and illustrate an example of the application of that formula.

[1235] 8. Data Transmission:

[1236] The generated visualization results and summary data are sent to the user's terminal via an HTTP response, allowing the user to access the data.

[1237] Terminal side

[1238] 1. Data reception:

[1239] The user terminal receives the visualization results and summary data sent from the server, and converts them into the required format for display.

[1240] 2. Data display:

[1241] The user terminal displays the received data to the user. For example, using a web browser, HTML and JavaScript may be used to display step-by-step explanations and diagrams on the screen along with the message "You lack understanding of the basic integral formula."

[1242] Specific examples

[1243] Consider the case where a student asks "I don't know how to solve this equation" in a math class. The student's speech data is sent to the server, which receives this data. Next, a speech recognition API is used to convert the speech data into text data, and a natural language processing API is used to analyze the meaning and background information of "how to solve the equation" through context analysis. The teacher's response, "You can solve it by using the basic integral formula," is sent to the server, which receives this response and analyzes the intent of the response.

[1244] The server identifies that the student does not understand the "basic integral formula" and uses a visualization library to generate a summary message stating "You lack understanding of the basic integral formula" along with an explanatory diagram. Once the data is received and sent to the user's device, it is displayed in the browser using HTML and JavaScript. The student can then identify specific areas of understanding that are lacking and move forward with their studies.

[1245] Prompt Sentence Examples

[1246] "A student asks, 'I don't know how to solve this mathematical equation.' Analyze this speech data and, based on the teacher's response, 'You can solve it using the basic integral formula,' identify that the student does not understand the 'basic integral formula,' and explain the process for visualizing and displaying this information."

[1247] Although the embodiment of the invention has been described above, the invention is not limited to this, and various modifications are possible without departing from the spirit of the invention.

[1248] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1249] Step 1: Receiving data

[1250] The server receives voice and text data from the user. For example, when a student says, "I don't know how to solve this equation," the voice data is sent to the server. To receive the voice data, an HTTP request is used. The input is the voice data and text data, and the output is the received data.

[1251] Step 2: Speech-text preprocessing

[1252] The server converts the received voice data into text using voice recognition software (e.g., voice recognition API). It also cleans the received text data. Specifically, it removes unnecessary spaces and special characters. The input is voice data and text data, and the output is preprocessed text data.

[1253] Step 3: Context Analysis

[1254] The server performs context analysis on the preprocessed text data using natural language processing technology (e.g., natural language processing API). For example, it extracts keywords and contextual information related to "formulas" and "solution methods." This analysis provides important information and background information. The input is the preprocessed text data, and the output is the analyzed contextual information.

[1255] Step 4: Receiving the teacher's response

[1256] The server receives the teacher's response data to the user's question. If the teacher replies, "That can be solved using the basic integral formula," the server receives the text data. The input is the teacher's text data, and the output is the received response data.

[1257] Step 5: Response analysis

[1258] The server also uses natural language processing technology to analyze the received response data. Specifically, it extracts the keyword "basic integral formula" and infers its intent. The input is the preprocessed response data, and the output is the intent of the analyzed response.

[1259] Step 6: Identify the gap in mutual understanding

[1260] The server compares the results of context analysis with the response intent estimation result to identify which part the user does not understand. For example, it identifies that a student does not understand the "basic integral formula." The input is the analyzed context information and response intent, and the output is the identified lack of understanding.

[1261] Step 7: Generate visualizations and summaries

[1262] The server generates graphs and figures using a visualization library (e.g., visualization library) to visualize the identified gaps in understanding. It also displays a summary message saying "You lack understanding of the basic integral formula" and illustrates an example of how to apply that formula. The input is the identified gaps in understanding, and the output is the generated visualization results and summary data.

[1263] Step 8: Send data

[1264] The server sends the generated visualization results and summary data to the user terminal. Specifically, it sends the data via an HTTP response. The input is the visualization results and summary data, and the output is the data sent to the user terminal.

[1265] Step 9: Receiving Data

[1266] The user terminal receives the visualization results and summary data sent from the server, receives the HTTP response, and imports the data. The input is the data sent from the server, and the output is the received data.

[1267] Step 10: Data Display

[1268] The user terminal displays the received data to the user. Specifically, it uses HTML and JavaScript to display step-by-step explanations and diagrams on the screen along with the message "You lack understanding of the basic integral formula." The input is the received data, and the output is the information displayed to the user.

[1269] (Application example 1)

[1270] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1271] Conventional educational support systems are not sufficient to simply identify areas where the user lacks understanding, and lack specific feedback and explanations, which reduces the effectiveness of the user's learning. Furthermore, there is a lack of a means to effectively display visualized feedback on devices such as smartphones, which limits the actual learning support provided.

[1272] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1273] In this invention, the server includes a means for providing educational feedback specific to the user's lack of understanding, a means for displaying visualized feedback on the user's smartphone, a means for generating and displaying specific explanations and step-by-step procedures for the user's lack of understanding using a generative AI model, and a means for presenting additional information to fill in the lack of understanding using prompt sentences. This allows the user to receive information that fills in the lack of understanding in a specific and visual way in real time, significantly improving learning effectiveness.

[1274] "User" refers to a general user who uses the system to input speech or text data.

[1275] "Utterance" refers to words or phrases spoken by a user.

[1276] "Text data" refers to sentences or information entered by a user in text format.

[1277] "Natural language processing technology" refers to technology that enables computers to understand and process human language.

[1278] "Context" refers to the context or background information associated with speech or text data.

[1279] "Response intent" refers to the content or purpose that a user intends to convey through a particular utterance or text.

[1280] "Mutual incomprehension" refers to a situation in which there is a discrepancy in the interpretation of meaning or intent between the user and the system or another interlocutor.

[1281] "Visualization" refers to the display of data or information in a visual format.

[1282] "Summary data" refers to data that succinctly summarizes analyzed information and feedback.

[1283] "User terminal" refers to a device such as a smartphone or PC used by a user.

[1284] "Instructional feedback" refers to specific, instructional information provided to users where they have difficulty understanding something.

[1285] A "smartphone" is a type of mobile phone that is a portable device that can connect to the Internet and use applications.

[1286] A "generative AI model" refers to an artificial intelligence model that has been trained in advance based on a large amount of data.

[1287] A "prompt sentence" refers to a leading and instructive sentence that provides the user with additional information.

[1288] A system for implementing this invention exchanges data between a user and a server, uses natural language processing technology to identify areas where the user lacks understanding, and provides visual feedback to a smartphone.

[1289] Hardware and Software

[1290] Hardware

[1291] Smartphone: A handheld device that allows users to input speech and text data and receive feedback.

[1292] Server: A central processing unit for data analysis and feedback generation.

[1293] software

[1294] SpeechRecognition library: Used to convert user speech into text data.

[1295] Transformers library: Leverages natural language processing techniques to analyze user input data and use generative AI models.

[1296] Matplotlib: Used to visualize parts that are not fully understood.

[1297] Data processing and calculation flow

[1298] 1. Speech Recognition: The speech that a user speaks into their smartphone is captured as audio and converted into text using the SpeechRecognition library. For example, say, "I don't understand the basic formula for integrals."

[1299] 2. NLP analysis: The text data is sent to the server and natural language processing is performed using the Transformers library, which analyzes the user's intent and context.

[1300] 3. Response intent estimation: The server uses the analyzed data to identify which parts the user did not understand.

[1301] 4. Visualization: After the weaknesses are identified, visual feedback is generated using Matplotlib.

[1302] 5. Sending feedback: The server sends the visual feedback and specific explanatory information to the smartphone.

[1303] Specific examples

[1304] For example, if a user asks, "I don't understand the basic integral formula," this data is sent from the smartphone to the server. The server receives this text and uses the Transformers library to identify a lack of understanding regarding the "basic integral formula." The program then visualizes that portion, for example, by using Matplotlib to represent an example of the application of the basic integral formula. The visualized feedback and specific explanatory information are then displayed on the smartphone.

[1305] Prompt Sentence Examples

[1306] The prompt is:

[1307] context_text =

[1308] The fundamental integral formula is a key concept in calculus and has the following formula:

[1309] ∫f'(x)dx = f(x) + C

[1310] If you don't understand this formula, check out the steps below:

[1311] 1. Review the basic concepts of differentiation.

[1312] 2. Deepen understanding through examples of application of basic integral formulas.

[1313] 3. Browse additional educational materials and online resources.

[1314] Based on this example, users can receive information in real time that complements specific areas of their understanding, significantly improving their learning effectiveness.

[1315] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1316] Step 1:

[1317] A smartphone inputs speech from the user as voice data. When the user speaks a question or uncertainty, the smartphone's microphone captures it. Next, speech recognition software (SpeechRecognition library) converts the voice data into text data. In this case, the input is voice data and the output is text data. For example, an utterance such as "I don't understand the basic formula for integrals" can be converted into text.

[1318] Step 2:

[1319] The smartphone sends text data to the server. The input here is the user's text data, and the output is the data to be sent to the server. This includes the operation of sending the text data to the server via the Internet.

[1320] Step 3:

[1321] The server analyzes the received text data. It uses natural language processing technology (Transformers library) to analyze the context of the text data. The input is the user's text data, and the output is the context analysis results. Specifically, the main text is the "basic integral formula," and related context information is extracted.

[1322] Step 4:

[1323] The server identifies the user's lack of understanding based on the analyzed context. Using a generative AI model, it infers the specific areas of lack of understanding from the user's utterances. The input is the result of the context analysis, and the output is the identified areas of lack of understanding. In this case, it is identified that the user lacks understanding of the "basic formula for integration."

[1324] Step 5:

[1325] The server visualizes the identified areas of incomprehension. It uses visualization libraries such as Matplotlib to display information in a format that is easy for users to understand. The input is the areas of incomprehension, and the output is visualized feedback. For example, it visualizes an example of the application of the basic integral formula.

[1326] Step 6:

[1327] The server compiles the visualized feedback and generates explanatory information using prompts. The input is the visualization data and explanatory information for the areas of incomprehension, and the output is feedback data including specific prompts. The prompts include specific explanations and step-by-step instructions.

[1328] Step 7:

[1329] The server sends the generated feedback data to the user's smartphone. The input is the feedback data, and the output is the data to be sent to the smartphone. These data are sent via the Internet.

[1330] Step 8:

[1331] The smartphone displays the received feedback data. Visualized feedback and specific explanatory information are presented to the user. The input is the feedback data, and the output is a visual display for the user. This includes the user checking the specific feedback on the smartphone screen regarding areas of incomplete understanding.

[1332] These steps allow users to concretely and visually grasp their own lack of understanding and receive feedback to improve their learning.

[1333] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1334] The present invention provides a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and combines it with an emotion engine that recognizes the user's emotions. Specific program processing of this system is described below.

[1335] Server-side processing

[1336] 1. Data reception:

[1337] The server receives speech and text data from the user. For example, a student may input text such as "I don't know how to solve this mathematical equation." The emotion engine also receives the user's emotional state at the same time. The input data is sent to the server, which then receives it.

[1338] 2. Contextual analysis:

[1339] The server uses natural language processing technology to analyze the context of the received speech and text data. For example, it extracts information about the mathematical formula and how to solve it, and analyzes its meaning and background.

[1340] 3. Response analysis:

[1341] Similarly, the server uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "That can be solved using the basic integral formula," the server infers that the intent of this response means, "You need to understand the basic integral formula."

[1342] 4. Emotion analysis:

[1343] The emotion engine estimates the user's emotional state from the received data. For example, it analyzes whether the student is expressing emotions such as "confused" or "anxious." This emotional state is reflected in the analysis results.

[1344] 5. Identifying the lack of mutual understanding:

[1345] By integrating the results of context analysis, response analysis, and sentiment analysis, the server identifies which part the user does not understand. In this case, it identifies that the student does not understand the "basic integral formula," while also taking into account the student's emotional state.

[1346] 6. Visualization and summary generation:

[1347] The system generates summary data to visualize the identified areas of insufficient understanding and the user's emotional state, and displays them in an easy-to-understand manner. For example, it displays a message such as "You lack understanding of the basic integral formula," along with an example of how to apply the formula, providing feedback according to the user's emotional state.

[1348] 7. Data Transmission:

[1349] The generated visualization results and summary data are sent to the user's device, allowing the user to specifically identify their own lack of understanding and receive appropriate feedback according to their emotions.

[1350] Terminal side processing

[1351] 1. Data reception:

[1352] The user device receives the visualization results and summary data sent from the server, such as a student's smartphone or PC.

[1353] 2. Data display:

[1354] The user device displays the received data to the user. For example, it might display a message like "You lack understanding of the basic integral formula," along with specific step-by-step explanations and illustrations. It might also display encouraging messages and advice based on the user's emotional state.

[1355] Specific examples

[1356] As a specific example, consider a case in which a student asks, "I don't know how to solve this equation" in a math class, expressing confusion. The student's speech data and emotion data are sent to the server, which receives them and performs context analysis. The server then infers the teacher's intent from the teacher's response, "You can solve it by using the basic integral formula." The emotion engine recognizes the student's confusion and identifies the student's confusion along with their lack of understanding of the "basic integral formula." Based on this information, the system generates visualization data such as "You lack understanding of the basic integral formula" and an encouraging message such as "Even if you're confused, stay calm and keep trying," and sends this data to the user's device. The device displays this to the student, allowing them to clearly understand their lack of understanding and receive specific advice.

[1357] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[1358] The processing flow will be explained below.

[1359] Step 1:

[1360] The user inputs a question or utterance. For example, a student may input text such as "I don't know how to solve this mathematical equation." The emotion engine recognizes emotions from the user's voice and text, and simultaneously detects the emotional state of "confused." This data is sent to the server.

[1361] Step 2:

[1362] The server captures and stores the received speech and text data from the user, as well as the detected emotion data, and prepares the received data for the next analysis step.

[1363] Step 3:

[1364] The server uses natural language processing technology to perform context analysis on the received speech and text data. For example, it extracts information about "mathematical formulas" and "solution methods" and analyzes their meaning and background. This analysis allows the server to identify the problem domain.

[1365] Step 4:

[1366] The server also uses natural language processing technology to infer the intent of the teacher's response data. For example, if the teacher responds, "You can solve that by using the basic integral formula," the server infers that the intent of this response is the solution strategy of "using the basic integral formula."

[1367] Step 5:

[1368] The emotion engine analyzes emotions from user utterances and text data and provides the results to the server. For example, if the emotion "confusion" is detected, the emotion engine notifies the server of that information.

[1369] Step 6:

[1370] The server integrates the results of context analysis, response intent estimation, and emotion analysis from the emotion engine to identify which part the user does not understand and their emotional state at that time. For example, it can identify that a student does not understand the "basic integral formula" and is confused.

[1371] Step 7:

[1372] The server visualizes the gaps in mutual understanding and generates summary data according to the user's emotional state. Specifically, it generates a message such as "You lack understanding of the basic integral formula" and an encouraging message such as "If you're confused, go back to the basics."

[1373] Step 8:

[1374] The server sends the generated visualization results and summary data to the user terminal, allowing the user to receive specific feedback.

[1375] Step 9:

[1376] The terminal receives the visualization results and summary data sent from the server, and displays the received data appropriately to the user, for example, displaying a message such as "You lack understanding of the basic integral formula" along with detailed explanations, illustrations, and encouraging messages.

[1377] Step 10:

[1378] Users can view the visualization results and summary data on their devices, which allows students to specifically identify areas they do not understand, receive appropriate explanations and emotional advice, and move on to the next step in their learning.

[1379] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[1380] Example 2

[1381] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1382] Conventional systems have limitations in identifying lack of mutual understanding simply by analyzing the user's questions and responses. Furthermore, they provide feedback without taking the user's emotional state into consideration, making effective communication difficult. As a result, it is difficult to identify which part the user does not understand, and appropriate responses may not be possible.

[1383] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1384] In this invention, the server includes means for receiving utterances, text data, and emotional states from a user, means for analyzing the context of the received data using natural language processing technology, means for estimating the intention of a response based on the analyzed context, means for estimating the emotional state of the user using emotion analysis technology, means for identifying a lack of mutual understanding by integrating the results of the context analysis, the response intention estimation result, and the emotion analysis result, means for visualizing the lack of mutual understanding and generating summary data, and means for transmitting the generated visualization result and summary data to a user terminal. This makes it possible to specifically identify the user's lack of understanding and provide appropriate feedback accordingly.

[1385] "Means for receiving user utterances, text data, and emotional state" refers to a device or method that collects voice data, text data, and additional data input by the user for determining the user's emotions, and transmits them to a server.

[1386] "Means for analyzing the context of received data using natural language processing technology" refers to devices or methods that apply natural language analysis algorithms to analyze collected voice data or text data in order to understand its context and meaning.

[1387] "Means for inferring the intent of a response based on analyzed context" refers to a device or method for identifying the intent of a user's statement or question based on context-analyzed data and generating an appropriate response.

[1388] "Means for estimating a user's emotional state using emotion analysis technology" refers to technology or methods for analyzing voice data, facial expression data, etc. collected from a user to determine the emotions the user is feeling.

[1389] The "means for identifying a lack of mutual understanding by integrating the results of context analysis, response intention estimation, and sentiment analysis" is a method for integrating the results of the aforementioned data analysis to identify areas of lack of understanding between the user and the system or between other users.

[1390] The "means for visualizing the lack of mutual understanding and generating summary data" is a method for visually displaying the lack of understanding and generating summary data in a format that can be intuitively understood by the user.

[1391] The "means for transmitting the generated visualization results and summary data to the user terminal" refers to a communication method or protocol for transmitting the visualization results and summary data to the terminal used by the user.

[1392] The present invention provides a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and combines it with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1393] Server-side processing

[1394] The server first receives speech and text data from the user. When the user types text into the device, such as "I don't know how to solve this mathematical equation," this data is sent to the server. At the same time, the emotion engine analyzes the user's voice and facial expression data, and also sends their emotional state to the server. The server receives this data and proceeds to the next stage of analysis.

[1395] The server uses natural language processing technology to analyze the context of the received data. To do this, it uses natural language processing libraries such as Google Cloud Natural Language API and SpaCy. For example, it extracts keywords such as "mathematical formula" and "how to solve" and understands the context based on them. Next, it infers the intent of the response based on the analyzed context. If the teacher answers, "That can be solved using the basic integral formula," it infers the intent of the response as "You need to understand the basic integral formula."

[1396] Furthermore, an emotion engine is used to estimate the user's emotional state. Using emotion analysis tools such as IBM Watson Tone Analyzer and Microsoft Azure Text Analytics, it is determined whether the user is feeling "confused" or "anxious." The results of this emotion analysis are reflected in the analysis results.

[1397] The server integrates the results of context analysis, response intent estimation, and sentiment analysis to identify gaps in mutual understanding. For example, it can identify that a student does not understand the "basic integral formula" and also detect feelings of confusion.

[1398] The server then visualizes the identified gaps in understanding and the user's emotional state, generating summary data in a format that the user can intuitively understand. For example, the server might display a message such as "You lack understanding of a basic integral formula," along with step-by-step examples of how to apply the formula. It also provides encouraging messages and links to additional resources for users who are confused. The visualization and summary data are then sent to the user's device.

[1399] Terminal side processing

[1400] The user's device receives the visualization results and summary data sent from the server. For example, this could be a student's smartphone or PC. The received data is then displayed to the student. For example, a message such as "Your understanding of the basic integral formula is lacking" may be displayed along with specific explanations and illustrations. Encouraging messages and advice based on the user's emotional state may also be displayed. By viewing this, the user can specifically identify areas of lack of understanding and solutions, and move on to the next learning step.

[1401] Specific examples

[1402] As a specific example, consider a case in which a student asks, "I don't know how to solve this equation" in a math class, expressing confusion. The student's speech data and emotion data are sent to the server, which receives them and performs context analysis. The server then infers the teacher's intent from the teacher's response, "You can solve it by using the basic integral formula." The emotion engine recognizes the student's confusion and identifies the student's confusion along with their lack of understanding of the "basic integral formula." Based on this information, the system generates visualization data such as "You lack understanding of the basic integral formula" and an encouraging message such as "Even if you're confused, stay calm and keep trying," and sends this data to the user's device. The device displays this to the student, allowing them to clearly understand their lack of understanding and receive specific advice.

[1403] Prompt Sentence Examples

[1404] "When a student asks, 'I don't know how to solve this equation,' analyze the teacher's response and the student's feelings to identify the student's lack of understanding and generate feedback."

[1405] "Based on what students say and how they feel, identify areas of lack of understanding and generate feedback that visualizes those areas."

[1406] This system allows users to specifically identify their own lack of understanding and receive appropriate feedback based on their emotions, further improving the effectiveness of learning and communication.

[1407] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1408] Step 1:

[1409] Receives user utterances, text data, and emotional states

[1410] The server first receives speech and text data sent from the user's device. For example, a student may type and send the text "I don't know how to solve this mathematical equation." At the same time that this text data is sent to the server, the emotion engine analyzes the user's voice and facial expression data, and their emotional state is also sent to the server. The specific input data is the speech, text data, and emotional state, and this data is stored on the server as output.

[1411] Step 2:

[1412] Context Analysis

[1413] The server performs context analysis on the received speech and text data using natural language processing technology (for example, Google Cloud Natural Language API or SpaCy). In this step, the meaning of words and phrases in the speech and text data is analyzed to understand the context. For example, keywords such as "mathematical formula" and "how to solve" are extracted and their relevance and meaning are analyzed. The input data is text data, and the output data is the analyzed context information. This process includes grammatical analysis and dependency analysis.

[1414] Step 3:

[1415] Infer response intent

[1416] The server also uses natural language processing technology to infer the intent of responses from teachers and other users. For example, if a teacher replies, "That can be solved using the basic integral formula," the server infers the intent from this response: "You need to understand the basic integral formula." The input data is the response text from the teacher, and the output data is the inferred intent. Specific operations include sending the response data to the analysis module and obtaining the results.

[1417] Step 4:

[1418] Estimating the user's emotional state

[1419] The server uses an emotion engine to estimate the user's emotional state. This process uses tools such as IBM Watson Tone Analyzer and Microsoft Azure Text Analytics. For example, emotions such as "confused" or "anxious" are analyzed from the user's voice and facial expression data. The input data is the user's voice and facial expression data, and the output data is the analyzed emotional state. Specific operations include sending data to the emotion analysis tool, receiving a response, and obtaining the analysis results.

[1420] Step 5:

[1421] Identifying a lack of mutual understanding

[1422] The server integrates the results of the context analysis, response intent estimation, and emotional state analysis to identify the parts of the sentence that the user does not understand. In this case, the analysis results indicate that the student does not understand the basic integral formula, and the accompanying emotional state of being confused is also taken into account. The input data are all of the above analysis results, and the output data are the identified gaps in mutual understanding. Specific operations include integrating each analysis result and applying an algorithm to identify the gaps.

[1423] Step 6:

[1424] Generate visualizations and summary data

[1425] The server generates summary data to visualize the identified gaps in understanding and the user's emotional state, and displays them in an easy-to-understand manner. For example, it might display a message saying, "You lack understanding of the basic integral formula," along with a step-by-step example of how to apply the formula. It might also provide encouraging messages and links to additional resources for confused users. The input data are the identified gaps in understanding and the user's emotional state, and the output data is the visualized summary data.

[1426] Step 7:

[1427] Data transmission

[1428] The server sends the generated visualization results and summary data to the user's terminal. To ensure data consistency and accuracy, encrypted communication is used, for example, using the SSL / TLS protocol. The input data are the generated visualization results and summary data, and the output data is the data sent to the user's terminal.

[1429] Step 8:

[1430] Data Display

[1431] The user terminal receives the visualization results and summary data sent from the server and displays them to the user. For example, it may display a message such as "You lack understanding of the basic integral formula," along with specific step-by-step explanations and illustrations. It may also display encouraging messages and advice based on the user's emotional state. The input data are the visualization results and summary data sent from the server, and the output data is the information displayed on the terminal. Specific operations include invoking a screen display module after receiving the data and displaying the information in an appropriate format.

[1432] (Application example 2)

[1433] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1434] Conventional systems were able to analyze user utterances and text data to identify lack of mutual understanding, but lacked a means to provide feedback based on the user's emotional state. As a result, they were unable to provide appropriate feedback that was in line with the user's emotions, limiting the effectiveness of learning and communication. The present invention aims to provide a system that provides feedback that takes the user's emotional state into account, thereby achieving more effective promotion of understanding and support.

[1435] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1436] In this invention, the server includes means for receiving utterances and text data from a user, means for analyzing the context of the received data using natural language processing technology, means for estimating the intention of the response based on the analyzed context, means for comparing the context analysis result with the response estimation result to identify a lack of mutual understanding, means for visualizing the lack of mutual understanding and generating summary data, means for transmitting the generated visualization result and summary data to a user terminal, means for recognizing and analyzing the user's emotional state, and means for generating feedback based on the emotional state. This makes it possible to provide appropriate feedback tailored to the user's emotional state, promote user understanding, and improve learning effectiveness and the quality of communication.

[1437] "User speech and text data" refers to information provided by the user through voice or text.

[1438] "Natural language processing technology" refers to technology that enables computers to understand and analyze human language.

[1439] "Context" refers to the context, including the background, situation, and related information of a particular utterance or text.

[1440] "Response intent" refers to the purpose or intent of a response to a received utterance or text.

[1441] "Lack of mutual understanding" refers to a situation in which both parties in a dialogue do not fully understand the intentions or content of the other.

[1442] "Visualization" refers to the display of information in the form of graphs, charts, images, etc.

[1443] "Summary data" refers to data that briefly summarizes key information.

[1444] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) used by a user to receive or send information.

[1445] "Emotional state" refers to the emotions a user is feeling at a particular moment.

[1446] "Feedback" refers to advice, comments, and responses provided to the user by the system.

[1447] This invention is an educational support system that combines a system that analyzes user utterances and text data, identifies and visualizes lack of mutual understanding, and an emotion engine that recognizes user emotions. This system executes the following processes through various software programs. The system mainly operates in cooperation with the server and user terminals.

[1448] 1. Server-side processing

[1449] The server includes the following main programs and functions:

[1450] Data reception: A method for receiving speech or text data from a user. For example, the server receives data sent from a user device such as a smartphone or PC.

[1451] Contextual analysis: Analyzing the context of received data using natural language processing techniques (e.g., common natural language processing APIs). For example, extracting and analyzing information related to "math problem solving."

[1452] Response analysis: A method of analyzing response data from educational content providers using natural language processing technology to infer their intent.

[1453] Sentiment analysis: A method of recognizing and analyzing emotions from user speech and text data using an emotion recognition engine (e.g., a general emotion analysis API).

[1454] Identifying gaps in mutual understanding: A means of integrating the results of context analysis, response analysis, and sentiment analysis to identify areas where there is a gap in mutual understanding.

[1455] Visualization and summary generation: A means to visualize the identified gaps in understanding and the user's emotional state and generate summary data. For example, generating a diagram that accompanies the message "I don't understand the basic integral formula."

[1456] Data transmission: A means to transmit the generated visualization results and summary data to the user terminal.

[1457] 2. Terminal processing

[1458] The user terminal includes the following processing functions:

[1459] Data reception: A means to receive visualization results and summary data sent from the server.

[1460] Data display: A method for displaying received data to the user. For example, displaying a message such as "You lack understanding of the basic integral formula" and providing explanations using concrete examples and diagrams.

[1461] Specific examples

[1462] When a user utters or inputs text such as "I don't understand the background of this historical event," the server receives this and performs context analysis. It then obtains the response data from the educational content provider, "The economic background of this event is important," and infers the user's intent. The emotion recognition engine recognizes the user's confused emotion and integrates the context analysis results, response data, and emotion data to determine that the user does not understand the "economic background." As a result, "You lack understanding of the economic background" is visualized and sent to the user's device along with a message such as "If you have difficulty, try thinking about it step by step."

[1463] Prompt Sentence Examples

[1464] input:

[1465] plaintext

[1466] User says: "I don't understand the context of this historical event."

[1467] User Emotion: Confused

[1468] Generate feedback based on gaps in understanding and emotions.

[1469] This system is expected to improve learning effectiveness by allowing users to accurately identify areas of lack of understanding during learning and receive appropriate feedback tailored to their emotions.

[1470] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1471] Step 1:

[1472] Data reception

[1473] The user inputs speech or text data from a device such as a smartphone or PC. The input data is sent to the server via the network. If the data is voice, the server converts it into text using a speech recognition engine (e.g., a general speech recognition API).

[1474] Input: User utterances and text data

[1475] Output: Text data

[1476] Step 2:

[1477] Contextual Analysis

[1478] The server uses natural language processing technology (e.g., a general natural language processing API) to analyze the context of the received text data. Specifically, it extracts important keywords and phrases from the text and identifies the problems or questions the user is having.

[1479] Input: Text data

[1480] Output: Context analysis results (list of keywords and phrases)

[1481] Step 3:

[1482] Response Analysis

[1483] The system uses natural language processing technology to analyze the response data of educational content providers (e.g., instructors and teachers) and infer their intent. For example, from the instructor's response, "The economic background of this incident is important," the system focuses on the "economic background" and clarifies the instructor's intent.

[1484] Input: Instructor response data

[1485] Output: Response intent predictions

[1486] Step 4:

[1487] Emotion analysis

[1488] The server uses an emotion recognition engine (e.g., a general emotion analysis API) to recognize emotions from the user's text data and speech data. For example, it extracts emotions such as "confused" or "anxious."

[1489] Input: User text or speech data

[1490] Output: User's emotional state

[1491] Step 5:

[1492] Identifying gaps in mutual understanding

[1493] The server integrates the results of context analysis, response analysis, and sentiment analysis to identify which parts the user does not understand, thereby clarifying specific areas of incomprehension, such as the user's lack of understanding of the economic background.

[1494] Input: Context analysis results, response intent estimation results, emotional state

[1495] Output: Identification of areas of incomprehension

[1496] Step 6:

[1497] Visualization and summary generation

[1498] The system generates summary data to visualize the identified areas of incomprehension and the user's emotional state and display them in an easy-to-understand format. For example, it generates a summary message such as "You lack understanding of the economic background," along with an illustration explaining the background, and adds feedback such as "Even if you are confused, please remain calm and proceed."

[1499] Input: Identification of incomplete understanding, user's emotional state

[1500] Output: Summary data and visualization results

[1501] Step 7:

[1502] Data transmission

[1503] The server then sends the generated visualization results and summary data to the user's device, where the user can display the received data, specifically identifying areas of incomplete understanding, and receive appropriate feedback.

[1504] Input: Summary data and visualization results

[1505] Output: Data sent to the user's terminal

[1506] Examples:

[1507] The user speaks or inputs text saying, "I don't understand the background to this historical event." The server receives this and converts it into text if it is voice data. It then uses natural language processing technology to perform context analysis, and similarly analyzes the instructor's response data to determine the response intent. Next, an emotion recognition engine recognizes the user's emotional state and determines that the user is "confused." This data is integrated to determine that the user does not understand the "economic background." The server generates summary data saying, "You lack understanding of the economic background," and sends it to the user's device along with illustrations and feedback.

[1508] Example prompt sentence:

[1509] input:

[1510] plaintext

[1511] User says: "I don't understand the context of this historical event."

[1512] User Emotion: Confused

[1513] Generate feedback based on gaps in understanding and emotions.

[1514] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1515] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1516] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1517] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1518] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1519] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1520] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1521] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1522] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1523] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1524] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1525] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1526] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1527] 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.

[1528] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1529] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1530] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1531] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1532] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1533] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1534] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1535] The following is further disclosed regarding the above embodiment.

[1536] (Claim 1)

[1537] means for receiving speech or text data from a user;

[1538] means for analyzing the context of the received data using natural language processing techniques;

[1539] a means for inferring the intent of the response based on the analyzed context;

[1540] A means of comparing the results of context analysis with response estimation to identify gaps in mutual understanding;

[1541] a means of visualizing the lack of mutual understanding and generating summary data;

[1542] means for transmitting the generated visualization results and summary data to a user terminal;

[1543] A system including:

[1544] (Claim 2)

[1545] 10. The system of claim 1, wherein the context analysis means extracts and analyzes contextual and background information.

[1546] (Claim 3)

[1547] 2. The system according to claim 1, wherein the response intention estimation means estimates the speaker's intention using natural language processing technology.

[1548] "Example 1"

[1549] (Claim 1)

[1550] means for receiving voice data and text data from a user;

[1551] means for preprocessing the received data;

[1552] means for analyzing the context of the preprocessed data using natural language processing techniques;

[1553] means for pre-processing received response data;

[1554] means for estimating intent of the preprocessed response data;

[1555] a means for comparing the results of context analysis with the results of response intent estimation to identify lack of mutual understanding;

[1556] a means of visualizing the lack of mutual understanding and generating summary data;

[1557] means for transmitting the generated visualization results and summary data to a user terminal;

[1558] A system including:

[1559] (Claim 2)

[1560] 10. The system of claim 1, wherein the context analysis means extracts and analyzes contextual and background information.

[1561] (Claim 3)

[1562] 2. The system according to claim 1, wherein the response intention estimation means estimates the speaker's intention using natural language processing technology.

[1563] "Application Example 1"

[1564] (Claim 1)

[1565] means for receiving speech or text data from a user;

[1566] means for analyzing the context of the received data using natural language processing techniques;

[1567] a means for inferring the intent of the response based on the analyzed context;

[1568] A means of comparing the results of context analysis with response estimation to identify gaps in mutual understanding;

[1569] a means of visualizing the lack of mutual understanding and generating summary data;

[1570] means for transmitting the generated visualization results and summary data to a user terminal;

[1571] a means for providing educational feedback specific to the user's understanding gaps; and

[1572] a means for displaying the visual feedback on the user's smartphone;

[1573] A system including:

[1574] (Claim 2)

[1575] 10. The system of claim 1, wherein the context analysis means extracts and analyzes contextual and background information.

[1576] (Claim 3)

[1577] 2. The system according to claim 1, wherein the response intention estimation means estimates the speaker's intention using natural language processing technology.

[1578] (Claim 4)

[1579] The system of claim 1, wherein the visualized feedback uses a generative AI model to generate and display specific explanations and step-by-step instructions for areas where the user's understanding is lacking.

[1580] (Claim 5)

[1581] The system according to claim 1, wherein the feedback display means presents additional information to the user's smartphone using a prompt sentence to complement any incomplete understanding.

[1582] "Example 2: Combining Emotion Engines"

[1583] (Claim 1)

[1584] means for receiving speech, text data and emotional state from a user;

[1585] means for analyzing the context of the received data using natural language processing techniques;

[1586] a means for inferring the intent of the response based on the analyzed context;

[1587] means for estimating a user's emotional state using emotion analysis technology;

[1588] a means for identifying a lack of mutual understanding by integrating the results of the context analysis, the response intention estimation, and the sentiment analysis;

[1589] a means of visualizing the lack of mutual understanding and generating summary data;

[1590] means for transmitting the generated visualization results and summary data to a user terminal;

[1591] A system including:

[1592] (Claim 2)

[1593] 2. The system according to claim 1, wherein the context analysis means extracts and analyzes contextual information and background information from the text data.

[1594] (Claim 3)

[1595] 2. The system according to claim 1, wherein the response intention estimation means estimates the speaker's intention using natural language processing technology.

[1596] "Application example 2 when combining emotion engines"

[1597] (Claim 1)

[1598] means for receiving speech or text data from a user;

[1599] means for analyzing the context of the received data using natural language processing techniques;

[1600] a means for inferring the intent of the response based on the analyzed context;

[1601] A means of comparing the results of context analysis with response estimation to identify gaps in mutual understanding;

[1602] a means of visualizing the lack of mutual understanding and generating summary data;

[1603] means for transmitting the generated visualization results and summary data to a user terminal;

[1604] means for recognizing and analyzing the emotional state of a user;

[1605] means for generating feedback based on the emotional state;

[1606] A system including:

[1607] (Claim 2)

[1608] 10. The system of claim 1, wherein the context analysis means extracts and analyzes contextual and background information.

[1609] (Claim 3)

[1610] 2. The system according to claim 1, wherein the response intention estimation means estimates the speaker's intention using natural language processing technology.

[1611] (Claim 4)

[1612] 2. The system according to claim 1, wherein the emotional state recognition means extracts and analyzes emotions from user utterances or text data.

[1613] (Claim 5)

[1614] 10. The system of claim 1, wherein the emotion-based feedback generating means generates a feedback message according to the user's emotional state. [Explanation of symbols]

[1615] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving speech or text data from a user; means for analyzing the context of the received data using natural language processing techniques; a means for inferring the intent of the response based on the analyzed context; A means of comparing the results of context analysis with response estimation to identify gaps in mutual understanding; a means of visualizing the lack of mutual understanding and generating summary data; means for transmitting the generated visualization results and summary data to a user terminal; A system including:

2. 10. The system of claim 1, wherein the context analysis means extracts and analyzes contextual and background information.

3. 2. The system according to claim 1, wherein the response intention estimation means estimates the speaker's intention using natural language processing technology.

Images