system

Abstract

Provide a system. The present invention includes: a means for receiving text data of the content of a presentation input by a user; means for analyzing the text data to generate feedback regarding the presentation; means for generating a question and answer based on the text data; means for providing said generated feedback and questions and answers to a user; A system including:

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] When practicing a presentation alone, self-judgment is required, resulting in a lack of objectivity in the evaluation. Furthermore, inviting others to practice is inefficient due to the need for scheduling and personnel costs. This creates challenges that make it difficult to conduct effective, high-quality rehearsals. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a means for receiving text data of a presentation content entered by a user, a means for analyzing the received text data to generate feedback about the presentation, a means for generating Q&A based on the text data, and a means for providing the generated feedback and Q&A to the user. Specifically, by generating feedback and Q&A using a large-scale language model, the system automatically provides objective and professional evaluation. Furthermore, by linking the user terminal with a server to send and receive information, quick and efficient rehearsals are possible.

[0006] "User" refers to a person who uses the system to input text data of the presentation content and receives the analysis results.

[0007] "Presentation content" refers to text data such as presentations and lectures that users input into the system.

[0008] "Text data" is character string data entered by the user to express the content of the presentation.

[0009] "Receiving" refers to the system obtaining text data entered by the user.

[0010] "Analysis" refers to the system processing the text data it receives and performing language processing to understand its content.

[0011] "Feedback" refers to information about evaluations of presentation content and areas for improvement that the system generates based on the analysis results.

[0012] "Question and Answer" refers to questions and answers related to the presentation content that the system generates based on text data.

[0013] "Providing" refers to presenting the generated feedback and questions and answers in a visible form to the user.

[0014] A "large-scale language model" refers to an advanced machine learning model that learns from massive amounts of data to understand and generate human language.

[0015] "Server" refers to a computer system that analyzes text data sent by a user, generates feedback and questions and answers, and sends them back to the terminal.

[0016] "Terminal" refers to the device where a user inputs presentation content and receives and displays feedback and questions sent from the server. [Brief explanation of the drawings]

[0017] [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 illustrating 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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention relates to a system that automatically generates and provides feedback and Q&A based on the text data of a presentation input by a user. This system helps users evaluate and improve their presentation content, and is an effective tool for achieving high-quality rehearsals.

[0039] Basic system configuration

[0040] The user inputs the content of the presentation into their device. The device sends this text data to the server. The server receives the input text data and analyzes it using a large-scale language model (LLM). After analyzing, the server generates feedback for the user and questions and answers related to the presentation content. The generated feedback and questions and answers are sent back to the device, which displays them to the user.

[0041] Program Overview

[0042] The program of this system consists of the following main modules:

[0043] 1. Data receiving module: Receives text data entered by the user.

[0044] 2. Data analysis module: Analyzes the received text data and generates feedback and questions and answers.

[0045] 3. Feedback generation module: Generates specific feedback based on the presentation content.

[0046] 4. Question and Answer Generation Module: Generates questions and answers related to the presentation content.

[0047] 5. Data transmission module: Sends the generated feedback and questions and answers to the user.

[0048] Processing Description

[0049] The user inputs the text data of the presentation content, for example, using a text editor or a dedicated input form.

[0050] The terminal sends the input text data to the server, which communicates via the network and passes the text data to the server.

[0051] The server analyzes the received text data. The server uses a large-scale language model to understand and analyze the content of the text data. This analysis process is carried out using natural language processing technology.

[0052] The server generates feedback based on the analysis results, including specific evaluations and suggestions for improvement regarding the content, structure, and behavior of the presentation.

[0053] The server generates a Q&A based on the text data, which includes anticipated questions related to the presentation and their answers.

[0054] The server sends the generated feedback and Q&A to the terminal, allowing the user to receive the evaluation results in real time.

[0055] The device displays feedback and Q&A to the user, who can use this information to improve their presentation and use it for their next rehearsal.

[0056] Specific examples

[0057] For example, if a user enters the following announcement:

[0058] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0059] The server receives this text and analyzes it using a large language model, which generates feedback and questions like this:

[0060] feedback:

[0061] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[0062] Q&A:

[0063] Question 1: Could you please explain the basic concepts of AI in more detail?

[0064] Question 2: Can you give some specific examples of ongoing research?

[0065] Question 3: How do you think future advances in AI technology will affect society?

[0066] Once users receive this feedback, they can take the improvements into account and revise their presentation. By preparing answers for questions, they can feel more confident when they give their presentation.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The user inputs the text data of the presentation. The user uses a dedicated input form or text editor to input the content of the presentation in text format into the terminal.

[0070] Step 2:

[0071] The terminal transmits the input text data to the server. When the user completes input and clicks the send button, the terminal transmits the text data to the server via the network.

[0072] Step 3:

[0073] The server receives the text data. The server successfully receives the data sent from the device and prepares it for analysis.

[0074] Step 4:

[0075] The server analyzes the text data. Using a large-scale language model, the server analyzes the received text data based on its content and deepens its understanding of the structure and expression of the presentation.

[0076] Step 5:

[0077] The server generates feedback based on the analysis results, including an evaluation of the presentation and suggestions for improvement, such as advice on the presentation structure, adding concrete examples, and visual representation methods.

[0078] Step 6:

[0079] The server generates questions and answers based on the text data. The server automatically generates anticipated questions and answers related to the presentation content. This generation process also uses a large-scale language model.

[0080] Step 7:

[0081] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[0082] Step 8:

[0083] The terminal displays the feedback and Q&A to the user. The terminal analyzes the data received from the server and displays it in a format that is easy for the user to view.

[0084] Step 9:

[0085] Users can revise and improve their presentations based on feedback and Q&A. Users can use the feedback they receive to improve their presentations and rehearse again.

[0086] Example 1

[0087] 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."

[0088] Previously, human feedback was required to evaluate and improve presentation content, which was problematic in that it was time-consuming and labor-intensive. Furthermore, while responding to anticipated questions is also important for a high-quality rehearsal, there was no automated system for doing so appropriately. This made it difficult for presenters to prepare efficiently and effectively.

[0089] 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.

[0090] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data using a generative AI model that uses a large-scale language model to generate feedback about the presentation, means for generating questions and answers based on the text data, and means for providing the generated feedback and questions and answers to the user, thereby enabling the user to automatically receive high-quality feedback and questions and answers.

[0091] A "user" is an individual or group that inputs text data of their own presentation content.

[0092] "Text data" is data in the form of text entered by the user as the content of the presentation.

[0093] A "generative AI model" is an algorithm that uses artificial intelligence techniques, including large-scale language models, to analyze text data and generate feedback and questions and answers.

[0094] "Feedback" refers to evaluation of the presentation content and specific instructions or suggestions for improvement.

[0095] "Questions and Answers" refers to anticipated questions related to the content of the presentation and their answers.

[0096] The "server" is a central computer system that receives text data sent by users and performs analysis and generation processing using generative AI models.

[0097] A "terminal" is a device on which a user inputs the content of their presentation, sends the data to the server, and receives and displays feedback and questions from the server.

[0098] "Data analysis" is the process of inputting text data into a generative AI model, understanding and analyzing its content, and generating feedback and questions and answers.

[0099] A "prompt" refers to an instruction or question that is input into a generative AI model, and the AI ​​analyzes and generates based on this.

[0100] The present invention relates to a system that allows users to input text data of their presentation content and automatically generates and provides feedback and Q&A based on that data. This system is an effective tool for helping users evaluate and improve their presentation content and achieving high-quality rehearsals. Specific embodiments of the system are described below.

[0101] Basic system configuration

[0102] Users input their presentation content into their own devices. For example, they can use a text editor or a web application input form. This input text data flows through the system in the following steps:

[0103] The terminal sends the input text data to the server, typically as an HTTP request over the Internet.

[0104] The server uses a large-scale language model (generative AI model) to analyze the received text data. This model uses natural language processing technology, such as OpenAI's GPT-3.

[0105] The server uses a generative AI model to analyze the content of the input text data and generate feedback, including the presentation content, structure, specific evaluations, and suggestions for improvement.

[0106] Furthermore, the server generates a question and answer session based on the text data, which includes anticipated questions related to the presentation content and their answers.

[0107] The generated feedback and questions are then sent back to the device, again via network communication.

[0108] Finally, the terminal displays the received feedback and questions and answers to the user, preferably in a visually easy-to-understand format through a user interface.

[0109] Specific examples

[0110] For example, if a user enters the following announcement:

[0111] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0112] When this input is sent from the device to the server, the server analyzes it using a large-scale language model. The prompt sentence is input to the generative AI model as follows:

[0113] Please analyze the following sentence: Today, I will be presenting the latest trends in AI technology...

[0114] The server uses this analysis to generate feedback such as:

[0115] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[0116] Additionally, the following questions and answers are generated:

[0117] Question 1: Could you please explain the basic concepts of AI in more detail?

[0118] Question 2: Can you give some specific examples of ongoing research?

[0119] Question 3: How do you think future advances in AI technology will affect society?

[0120] This feedback and Q&A is sent to the device and ultimately displayed to the user, who can use it to improve their presentation and prepare for their next rehearsal.

[0121] Thus, the present invention is a system that allows users to efficiently prepare presentations and receive high quality feedback and questions and answers.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] The user inputs the text data of the presentation using a text editor or an input form in a web application. The input data is saved as the original text of the presentation.

[0125] input:

[0126] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0127] output:

[0128] Input text data

[0129] Specific behavior:

[0130] The user types the content of the presentation into the input form.

[0131] Step 2:

[0132] The device sends the entered text data to the server. This operation is performed using network communication, specifically an HTTP POST request. The device creates a packet to send the text data to the server and sends it over the Internet.

[0133] input:

[0134] Text data entered by the user

[0135] output:

[0136] Text data sent to the server

[0137] Specific behavior:

[0138] The device generates and sends an HTTP request like this:

[0139] POST / analyze HTTP / 1.1

[0140] Host: example.com

[0141] Content-Type: application / json

[0142] Content-Length: 123

[0143] {

[0144] "text": "Today, I'll be presenting the latest developments in AI technology..."

[0145] }

[0146] Step 3:

[0147] The server analyzes the received text data. The server uses a generative AI model to generate prompts and analyze the data. In this process, the text data is input into the model to understand its content.

[0148] input:

[0149] Text data sent from the device

[0150] output:

[0151] Text data analysis results

[0152] Specific behavior:

[0153] The server inputs the following prompt into the generative AI model:

[0154] Please analyze the following sentence: Today, I will be presenting the latest trends in AI technology...

[0155] Step 4:

[0156] The server generates feedback based on the analysis results. This is the process of generating feedback statements that include specific evaluations and suggestions for improvement of the presentation content based on the analysis results obtained from the generative AI model.

[0157] input:

[0158] Text data analysis results

[0159] output:

[0160] Generated Feedback

[0161] Specific behavior:

[0162] The server generates feedback like this:

[0163] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[0164] Step 5:

[0165] The server generates a Q&A based on the text data. The Q&A consists of anticipated questions related to the presentation content and their answers, and is generated using a generative AI model.

[0166] input:

[0167] Text data analysis results

[0168] output:

[0169] Generated Q&A

[0170] Specific behavior:

[0171] The server generates a question and answer like this:

[0172] Question 1: Could you please explain the basic concepts of AI in more detail?

[0173] Question 2: Can you give some specific examples of ongoing research?

[0174] Question 3: How do you think future advances in AI technology will affect society?

[0175] Step 6:

[0176] The server sends the generated feedback and Q&A to the terminal. This operation also uses network communication and is sent as an HTTP response.

[0177] input:

[0178] Generated feedback and Q&A

[0179] output:

[0180] Feedback and Q&A sent to device

[0181] Specific behavior:

[0182] The server generates an HTTP response like this and sends it to the device:

[0183] HTTP / 1.1 200 OK

[0184] Content-Type: application / json

[0185] Content-Length: 345

[0186] {

[0187] "feedback": "The presentation is clearly structured and easy to understand...",

[0188] "qna": [

[0189] {"question": "Please explain the basic concepts of AI in more detail.", "answer": "..."},

[0190] {"question": "Please give some specific examples of ongoing research.", "answer": "..."}

[0191] ]

[0192] }

[0193] Step 7:

[0194] The device displays the received feedback and Q&A to the user in a visually easy-to-understand format using a user interface.

[0195] input:

[0196] Server-submitted feedback and questions

[0197] output:

[0198] Feedback and Q&A displayed to the user

[0199] Specific behavior:

[0200] The terminal generates an interface that displays the data as follows:

[0201] feedback:

[0202] "The presentation is clearly structured and easy to understand. However, adding more concrete examples would have helped to hold the audience's interest..."

[0203] Q&A:

[0204] Question 1: Could you please explain the basic concepts of AI in more detail?

[0205] Question 2: Can you give some specific examples of ongoing research?

[0206] (Application example 1)

[0207] 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."

[0208] In the past, it was not easy to effectively introduce new products and services in presentations at physical stores. It was especially difficult for inexperienced employees to deliver accurate presentations and respond promptly to questions and answers on the spot. Furthermore, the lack of preparation for immediate feedback and Q&A sessions led to inconsistent presentation quality.

[0209] 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.

[0210] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data and generating feedback regarding the presentation, means for generating questions and answers based on the text data, means for providing the generated feedback and questions and answers to the user, means for generating feedback to improve the effectiveness of the presentation, and means for receiving feedback in real time during the presentation, thereby enabling employees to improve the quality of their presentations, receive immediate feedback, and prepare for questions and answers.

[0211] A "user" is an individual or group that uses the system to input text data of the presentation content.

[0212] "Presentation content" refers to information and data presented as a presentation, and is primarily entered in text format.

[0213] "Text data" refers to character string data entered by the user, and includes specific sentences and explanations of the content of the presentation.

[0214] The "server" is a central processing unit that analyzes the received text data, generates feedback and questions and answers, and sends them to the terminal.

[0215] "Analysis" is the process of understanding the content of text data and evaluating and breaking down that content using natural language processing techniques.

[0216] "Feedback" includes evaluations and advice regarding the content, structure, and areas for improvement of the presentation, and is provided to the user.

[0217] "Questions and Answers" are anticipated questions and answers related to the presentation content, and are provided to help users prepare.

[0218] "Real-time" refers to the time period in which processing and feedback are immediate, and applies during a user's presentation.

[0219] "Presentation effectiveness" refers to the success of a user's presentation and its ability to gain the understanding and interest of the audience.

[0220] A "terminal" is a device through which a user inputs text data, sends it to the server, and displays and receives feedback and questions and answers.

[0221] A "large-scale language model" is a type of artificial intelligence trained from large amounts of text data, and is a model for analyzing and generating natural language.

[0222] The system for implementing this invention receives text data of presentation content entered by a user, analyzes it, and automatically generates feedback and Q&A. This system functions as a support tool for users to make their presentations more effective.

[0223] System Configuration

[0224] The system consists of the following main modules:

[0225] 1. Data receiving module: Receives the text data of the presentation entered by the user into the terminal.

[0226] 2. Data transmission module: The terminal transmits the received text data of the announcement to the server.

[0227] 3. Data analysis module: The server analyzes the received text data and generates feedback on the presentation and Q&A using natural language processing techniques and large-scale language models (e.g., OpenAI GPT-3).

[0228] 4. Feedback generation module: Based on the presentation content, specific feedback is generated to improve the quality of the presentation.

[0229] 5. Q&A generation module: Generates anticipated questions and answers based on the presentation content.

[0230] 6. Real-time feedback module: Provides real-time feedback during presentations.

[0231] 7. Data transmission module: The generated feedback and questions and answers are transmitted to the terminal and provided to the user.

[0232] Hardware and Software

[0233] Hardware: The system consists of a device used by the user (such as a smartphone or tablet) and a server that performs analysis and generation processing. The device has a user interface and data communication functions.

[0234] Software: The system includes modules for receiving, sending, and analyzing text data, generating feedback and Q&A, and providing real-time feedback. It is implemented in programming languages ​​such as Python and JavaScript. Large-scale language models such as OpenAI GPT-3 are used for analysis.

[0235] System Operation

[0236] 1. Text data input by the user: The user inputs the text data of the presentation using a dedicated application on their smartphone.

[0237] 2. Sending and receiving data: The entered text data is sent from the terminal to the server via the network.

[0238] 3. Data analysis and generation: The server analyzes the text data using a large-scale language model such as OpenAI GPT-3 and generates presentation feedback and Q&A.

[0239] 4. Providing feedback and Q&A: The generated feedback and Q&A are sent back to the terminal via the network and provided to the user, who can use this information to improve the presentation content.

[0240] 5. Providing real-time feedback: If real-time feedback is required during a presentation, the information is sent immediately from the server to the terminal and provided to the user.

[0241] Specific examples

[0242] For example, if a user enters the following presentation content:

[0243] "We'll introduce the new smartphone features. First, we'll talk about improved camera performance. Second, we'll talk about improved battery life. And finally, we'll talk about new software features."

[0244] Based on this text data, the server analyzes it and generates feedback and questions like the following:

[0245] feedback:

[0246] The presentation is well-structured, but it would be more effective if it included concrete use cases and a more detailed explanation of the new software features.

[0247] Q&A:

[0248] Question 1: What exactly are the improvements to camera performance?

[0249] Question 2: How much longer does the battery life increase?

[0250] Question 3: What benefits do the new software features provide?

[0251] This process allows users to receive real-time feedback and improve the quality of their presentations.

[0252] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0253] Step 1:

[0254] The user inputs the presentation content as text data using a dedicated application.

[0255] Input: The user enters the presentation content in text format.

[0256] Output: The text data is saved to the device.

[0257] Specific operation: The user launches a dedicated application on their smartphone and enters the presentation content into the input form.

[0258] Step 2:

[0259] The terminal transmits the input text data to the server.

[0260] Input: Text data entered by the user.

[0261] Output: The text data is sent over the network to the server.

[0262] Specific operation: The device sends the entered text data to the server via internet communication, where the data is encrypted for security reasons.

[0263] Step 3:

[0264] The server analyzes the received text data and generates feedback and questions and answers.

[0265] Input: Text data sent from the terminal.

[0266] Output: Feedback and Q&A are generated.

[0267] How it works: The server analyzes the text data using a large-scale language model (e.g., OpenAI GPT-3). This analysis uses natural language processing techniques. Based on the analysis results, it generates an evaluation of the presentation, feedback on areas for improvement, and related Q&A.

[0268] Step 4:

[0269] After generating the feedback and questions and answers, the server sends them to the terminal.

[0270] Input: Generated feedback and questions and answers.

[0271] Output: Feedback and Q&A are sent to the terminal.

[0272] Specific operation: The server sends the generated feedback and Q&A to the user's terminal via the network.

[0273] Step 5:

[0274] The terminal displays the received feedback and questions and answers to the user.

[0275] Input: Feedback and questions sent by the server.

[0276] Output: Feedback and questions are displayed visually to the user.

[0277] Specific operation: The device displays the received feedback and Q&A on the user interface of a dedicated application, allowing the user to view the feedback and prepare for potential questions and improve their presentation.

[0278] Step 6:

[0279] Provide real-time feedback during presentations.

[0280] Input: User presentation data collected in real time.

[0281] Output: Real-time feedback is provided to the user.

[0282] Specific operation: During a presentation, the device transmits the user's presentation content and progress to the server in real time, and the server immediately analyzes it using a large-scale language model. Based on the analysis results, feedback is generated in real time and sent to the device for display.

[0283] 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.

[0284] The present invention relates to a system that allows users to input text data of their presentations, automatically generates feedback and Q&A based on the data, and further adjusts the content by recognizing the user's emotions. This system is an effective tool for helping users evaluate and improve their presentations and providing feedback that takes into account the user's emotional state.

[0285] Basic system configuration

[0286] The user inputs their speech content into their device and then activates an emotion engine to recognize the user's emotional state. The device then sends this data to a server. The server receives the input text data and emotion data and analyzes the data using a large-scale language model (LLM). After analysis, the server generates feedback for the user and questions and answers related to the speech content. The generated feedback and questions and answers are also adjusted based on the user's emotional state. The generated feedback and questions and answers are then sent back to the device, which displays them to the user.

[0287] Program Overview

[0288] The program of this system consists of the following main modules:

[0289] 1. Data receiving module: Receives the text data and emotion data of the presentation entered by the user.

[0290] 2. Emotion Recognition Module: Analyzes user emotions in real time and collects the data.

[0291] 3. Data analysis module: Analyzes the received text data and sentiment data and generates feedback and questions and answers.

[0292] 4. Feedback generation module: Generates specific feedback based on the announcement and user sentiment.

[0293] 5. Question and Answer Generation Module: Generates relevant questions and answers based on the presentation content and sentiment data.

[0294] 6. Data transmission module: Sends the generated feedback and questions and answers to the user.

[0295] Processing Description

[0296] The user inputs the text data of the presentation. The user uses a dedicated input form or text editor to input the content of the presentation in text format into the terminal. In some cases, the user also wears a device for emotion recognition.

[0297] The device sends the entered text data and emotion data to the server. When the user completes the input and clicks the send button, the device sends this data to the server via the network.

[0298] The server receives the text data and emotion data. The server successfully receives the data sent from the device and prepares it for analysis.

[0299] The server analyzes the text data and emotion data. The server uses a large-scale language model to understand and analyze the content of the text data and emotion data. This analysis process is carried out using natural language processing technology and emotion recognition technology.

[0300] The server generates feedback based on the analysis results, including an evaluation of the presentation content and suggestions for improvement. By taking emotional data into account, the server generates content that takes into account the user's emotional state.

[0301] The server generates questions and answers based on text data and emotion data. The server automatically generates possible questions and answers related to the presentation content and emotion data. This generation process also uses large-scale language models and emotion recognition technology.

[0302] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[0303] The terminal displays the feedback and Q&A to the user. The terminal analyzes the data received from the server and displays it in a format that is easy for the user to view.

[0304] Specific examples

[0305] For example, if a user enters the following announcement:

[0306] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0307] Meanwhile, the emotion engine monitors the user's stress level and emotional state in real time, collecting data. The server receives and analyzes this text and emotion data. Based on the analysis, feedback and questions are generated, such as:

[0308] feedback:

[0309] The presentation's structure is clear and easy to understand. However, adding more specific examples would help capture the audience's interest. It would also be good to provide a more detailed explanation of future prospects. Furthermore, the emotional data suggests that you seem a little nervous, so we recommend taking a deep breath and relaxing.

[0310] Q&A:

[0311] Question 1: Could you please explain the basic concepts of AI in more detail?

[0312] Question 2: Can you give some specific examples of ongoing research?

[0313] Question 3: How do you think future advances in AI technology will affect society?

[0314] As soon as users receive this feedback, they can take the points for improvement into account and revise their presentation content. By preparing answers for questions, they can approach their actual presentation with greater confidence. Furthermore, based on emotional feedback, they can manage their own psychological state as they practice.

[0315] The processing flow will be explained below.

[0316] Step 1:

[0317] The user inputs the text data of the presentation. The user inputs the content of the presentation into the terminal using a dedicated input form or text editor. In addition, devices such as the camera and microphone are enabled for emotion recognition.

[0318] Step 2:

[0319] The terminal transmits the input text data and emotion data to the server. When the user clicks the "Send" button, the terminal transmits the text data and initial emotion data to the server via the network.

[0320] Step 3:

[0321] The server receives the text data and emotion data. The server successfully receives the data sent from the device and prepares for analysis.

[0322] Step 4:

[0323] The server analyzes the text data and uses a large-scale language model to analyze the content of the received text data and generate specific feedback about the presentation.

[0324] Step 5:

[0325] The server analyzes the emotional data. The server uses an emotion recognition engine to analyze the user's emotional state (tension, anxiety, joy, etc.). The analysis results include stress levels and emotional fluctuations.

[0326] Step 6:

[0327] The server generates feedback based on the analysis results. The server combines the results of the text data analysis and the emotional data analysis to create detailed feedback on the user's presentation. The feedback includes specific suggestions for improvement and instructions that take into account the user's emotional state.

[0328] Step 7:

[0329] The server generates questions and answers based on text data and emotional data. The server automatically generates anticipated questions and answers related to the presentation content, and these responses also take emotional data into consideration.

[0330] Step 8:

[0331] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[0332] Step 9:

[0333] The terminal displays the feedback and Q&A to the user. The terminal analyzes the feedback and Q&A received from the server and displays them in a format that is easy for the user to view.

[0334] Step 10:

[0335] Users can revise and improve their presentation content based on feedback and Q&A. Users can refer to the feedback they receive to improve their presentation content and manage their own psychological state based on emotional feedback.

[0336] Example 2

[0337] 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."

[0338] Conventional presentation support systems generate feedback and Q&A without considering the user's emotional state, making it difficult for users to make effective corrections or preparations when they are feeling nervous or stressed. Furthermore, the content of Q&A is simply generated based on the presentation content, which can lead to a lack of depth.

[0339] 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.

[0340] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data to generate feedback regarding the presentation, means for generating questions and answers based on the text data, means for adjusting the content of the feedback and questions and answers based on the emotional state of the user, and means for providing the generated feedback and questions and answers to the user, thereby making it possible to provide effective and specific feedback and questions and answers while taking the emotional state of the user into consideration.

[0341] A "user" is someone who uses the system to input presentation content and receive feedback and questions.

[0342] "Presentation content" is text data of a presentation or speech entered by the user.

[0343] "Text data" refers to the content of a presentation expressed as text information.

[0344] The term "means" refers to a specific device or module provided for performing a predetermined function.

[0345] "Analysis" is the process of understanding the content of input data and generating appropriate feedback and questions and answers.

[0346] "Feedback" is information that includes evaluation of the user's presentation and advice on how to improve it.

[0347] "Questions and Answers" is information that includes anticipated questions and answers based on the content of the presentation.

[0348] "Emotional state" refers to the user's psychological state and emotional response, including, for example, the degree of tension or stress.

[0349] A "large-scale language analysis model" is a large-scale machine learning model used for natural language processing, which learns language patterns and meanings from large amounts of text data.

[0350] An "information terminal" is an electronic device that users use to input presentation content and receive feedback and questions.

[0351] The "main control unit" is a central unit that analyzes the received data, generates feedback and questions and answers, and sends them to the information terminals.

[0352] This invention relates to a system that allows users to input text data of their presentations, automatically generates feedback and Q&A based on the data, and further adjusts the content by recognizing the user's emotions. This system is an effective tool for helping users evaluate and improve their presentations and providing feedback that takes into account the user's emotional state.

[0353] Basic system configuration

[0354] A user inputs a speech into his / her information terminal, and then activates a device for recognizing the user's emotional state. The terminal transmits this data to a main control device. The main control device receives the input text data and emotional data and analyzes the data using a large-scale language analysis model. After analysis, the main control device generates feedback for the user and questions and answers related to the speech. The generated feedback and questions and answers are also adjusted based on the user's emotional state. The generated feedback and questions and answers are then transmitted back to the terminal, which displays them to the user.

[0355] Examples of hardware and software:

[0356] Input device: The device that the user uses to input their presentation (e.g., personal computer, tablet, smartphone)

[0357] Emotion recognizers: devices that recognize the user's emotional state (e.g., heart rate monitors, wearable devices)

[0358] Master controller: A server or cloud service (e.g., a cloud computing platform) that analyzes input data and generates feedback and questions and answers.

[0359] Large language analysis models: AI models for analyzing natural language data (e.g., large-scale language models)

[0360] Communication network: A network (e.g., the Internet) for transmitting and receiving data between the terminal and the main control unit.

[0361] Specific operation explanation

[0362] The user inputs the contents of the presentation in text format into the terminal using a dedicated input form or a text editor (e.g., general word processing software). For emotion recognition, the user wears a device such as a heart rate monitor and connects it to the information terminal.

[0363] The terminal collects the input text data and emotion data and transmits them to the main control device via a network (e.g., the Internet).

[0364] The master controller uses large language analysis models to analyze the received text and emotion data. This process leverages natural language processing techniques (e.g., AI models) and emotion recognition techniques.

[0365] The master controller generates feedback based on the analysis, including a rating of the presentation and specific suggestions for improvement, and adjusts the feedback based on the user's emotional state.

[0366] The master controller generates relevant questions and answers based on the text data and the emotion data, which include possible questions related to the presentation and their answers.

[0367] The main control device sends the generated feedback and questions and answers back to the terminal again via the network.

[0368] The terminal displays the feedback and Q&A received from the main control device, allowing the user to revise their presentation based on the feedback and prepare answers for Q&A. Furthermore, the emotional feedback allows the user to manage their own psychological state as they practice.

[0369] Specific examples

[0370] For example, if a user enters the following announcement:

[0371] text

[0372] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0373] Meanwhile, the emotion engine monitors the user's stress level and heart rate in real time and collects data. The master controller receives and analyzes this text and emotion data. Based on the analysis results, feedback and Q&A are generated, such as:

[0374] feedback:

[0375] text

[0376] The presentation is clearly structured and easy to understand. However, adding more specific examples would help capture the audience's interest. It would also be good to provide more details about future prospects. Furthermore, the emotional data suggests that you seem a little nervous, so we recommend taking a deep breath and relaxing.

[0377] Q&A:

[0378] text

[0379] Question 1: Could you please explain the basic concepts of AI in more detail?

[0380] Question 2: Can you give some specific examples of ongoing research?

[0381] Question 3: How do you think future advances in AI technology will affect society?

[0382] Prompt Sentence Examples

[0383] Examples of prompts to input to a generative AI model might include:

[0384] text

[0385] The user entered the following announcement:

[0386] "Today, I will be presenting on the latest developments in AI technology. First, I will explain the basic concepts of AI, then talk about ongoing research and commercial applications. Finally, I will consider what the future holds."

[0387] Please generate feedback on this presentation, along with related questions and answers. Please also consider user sentiment data (high tension).

[0388] In this way, the system automatically analyzes the content of the user's presentation and provides feedback and Q&A, helping the user to give a more effective presentation.

[0389] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0390] Step 1:

[0391] The user inputs the text data of the presentation.

[0392] The user inputs the content of the presentation in text format into the terminal using a dedicated input form or a text editor (e.g., general word processing software). For emotion recognition, the user wears a device such as a heart rate monitor and connects it to the information terminal. The input data (the text of the presentation and emotion data) is sent to the terminal.

[0393] Step 2:

[0394] The terminal transmits the input text data and emotion data to the server.

[0395] The user completes the input and clicks the send button. At this point, the terminal uses the network (e.g., the Internet) to send the input data to the main control device. The input includes the text data of the announcement and the real-time emotion data obtained from the emotion device. The output is that these data are successfully sent to the server.

[0396] Step 3:

[0397] The server receives the data.

[0398] The server receives the text data and emotion data sent from the device, checks the consistency and completeness of the data, formats the input data (the text data of the announcement and the emotion data) for analysis, and outputs the formatted text data and emotion data.

[0399] Step 4:

[0400] The server analyzes the text data and the emotion data.

[0401] The server uses a large-scale language analysis model (e.g., large-scale language model) to analyze the content of text data and emotional data. It uses natural language processing technology (e.g., NLTK, SpaCy) and emotion recognition technology to break down and understand the input text sentence by sentence. The input for the analysis is organized text data and emotional data, and the output is a dataset of the analysis results.

[0402] Step 5:

[0403] The server generates feedback based on the analysis results.

[0404] Based on the analysis results, a large language analysis model is used to generate feedback on the user's post. The feedback includes an evaluation of the post and specific suggestions for improvement, and is adjusted based on the user's emotional state. The input is a dataset of the analysis results, and the output is text feedback for the user.

[0405] Step 6:

[0406] The server generates questions and answers based on the text data and the emotion data.

[0407] The server automatically generates possible questions and answers based on the presentation content and emotional data. The generation process uses large-scale language models and emotion recognition technology. The input is a dataset of analysis results, and the output is text data of the questions and answers.

[0408] Step 7:

[0409] The server transmits the generated feedback and questions and answers to the terminal.

[0410] The server returns the generated feedback and Q&A data to the terminal via the network. The input is the generated feedback and Q&A text data, and the output is that these data are successfully sent to the terminal.

[0411] Step 8:

[0412] The terminal displays feedback and questions to the user.

[0413] The terminal receives feedback and questions from the server and displays them in a format that is easy for the user to view. A web browser or a dedicated application is used here. The input is the text data of the feedback and questions received from the server, and the output is to display it for the user.

[0414] (Application example 2)

[0415] 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."

[0416] Conventional presentation feedback systems do not take the user's emotional state into account when generating feedback or Q&A, resulting in insufficient feedback when users practice presentations and inefficient improvement of presentation skills. Furthermore, because they are unable to recognize emotions in real time and adjust feedback based on the results, it is difficult to reduce the presenter's psychological burden. Similar problems occur when employees explain products, resulting in inconsistent quality of customer service.

[0417] 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.

[0418] In this invention, the server includes means for receiving text data and emotional data of the presentation content entered by the user, means for analyzing the text data and emotional data to generate feedback regarding the presentation, means for generating Q&A based on the text data and emotional data, means for providing the generated feedback and Q&A to the user, and means for adjusting the content of the feedback and Q&A based on the user's emotional state. This makes it possible to provide high-quality feedback and Q&A in real time that takes the user's emotional state into consideration, thereby improving the user's presentation skills and reducing psychological burden. It also improves the quality of customer service when employees are explaining products.

[0419] A "user" is a person who uses this system to input text data of the presentation content.

[0420] "Presentation content" refers to text data entered by the user, and refers to an explanation or report of information based on a specific theme.

[0421] "Text data" refers to character string information that a user inputs as content to be presented.

[0422] "Emotion data" refers to data that indicates the user's emotional state, and is psychological information that is acquired in real time.

[0423] "Feedback" refers to information entered by the user, including evaluations of the presentation content and suggestions for improvement.

[0424] "Questions and answers" refers to questions and corresponding answers generated based on the content of the presentation.

[0425] A "server" is a computer system that receives text data and emotion data sent by users, analyzes them, and generates feedback and questions and answers.

[0426] "Terminal" refers to a device through which a user inputs text data, transmits it to a server, and receives feedback and questions and answers from the server.

[0427] A "large-scale language model" refers to advanced algorithms and techniques that learn from large amounts of text data in natural language processing to generate and analyze text.

[0428] The "emotion engine" is a system that recognizes emotions from the user's facial expressions, tone of voice, etc., and generates that data.

[0429] This embodiment of the present invention handles the text data of the presentation content entered by the user and the user's emotional data in detail to generate feedback and Q&A for the user's presentation content, and also makes adjustments according to the user's emotional state. A specific implementation method of this system is described below.

[0430] Program Components

[0431] The system consists of the following main modules:

[0432] 1. Data receiving module:

[0433] Receive text data of the presentation content entered by the user, for example, using a dedicated input form or text editor.

[0434] 2. Emotion Recognition Module:

[0435] Emotion data is collected to analyze the user's emotions in real time. For this purpose, emotion recognition devices such as cameras and microphones are used. For example, software such as EmotionRecognizer is used.

[0436] 3. Data Analysis Module:

[0437] The received text data and emotion data are sent to a server for analysis. A large-scale language model (LLM) is used for the analysis. Possible applications include OpenAI's API.

[0438] 4. Feedback and Q&A generation module:

[0439] Feedback and Q&A are generated based on text and emotion data using a generative AI model, which is then sent from the server to the device.

[0440] 5. Data transmission module:

[0441] The generated feedback and Q&A data is sent to the user's device, for example, via an AWS (registered trademark) S3 bucket.

[0442] Hardware and software used

[0443] Smart glasses (e.g., Google® Glass®):

[0444] The user wears it to input text and collect emotion recognition data.

[0445] Cameras (e.g., in smart glasses):

[0446] It captures the user's facial expressions in real time and uses them to recognize emotions.

[0447] Server (e.g. AWS):

[0448] Receives, analyzes, and generates feedback on text and emotion data.

[0449] Generative AI models (e.g., OpenAI GPT):

[0450] Analyze text and sentiment data to generate feedback and Q&A.

[0451] Program processing

[0452] The server receives the text data of the presentation and the user's emotional data sent from the device. It then analyzes the received data and generates feedback and Q&A using a generative AI model. The generated feedback and Q&A are then sent back to the device and provided to the user. The content of the feedback and Q&A is also adjusted based on the emotional data.

[0453] Specific examples

[0454] For example, if a user enters the following announcement:

[0455] Today, I'll discuss the latest technology trends. First, I'll explain the basic concepts, then I'll talk about new research and applications. Finally, I'll discuss future prospects.

[0456] During this time, the emotion engine analyzes the user's emotional state and collects data. The server receives and analyzes this text and emotion data to generate feedback and Q&A, such as:

[0457] feedback:

[0458] The presentation structure is clear, but adding more concrete examples will help keep the audience engaged. Also, the emotional data suggests that you are a little nervous, so it would be good to incorporate some relaxation techniques.

[0459] Q&A:

[0460] Question 1: What are some specific application examples of the latest technology trends?

[0461] Question 2: What research do you expect to see in the future?

[0462] Question 3: Could you please elaborate on your future outlook?

[0463] Example prompt sentence:

[0464] User's emotional state: slightly nervous

[0465] Text data:

[0466] Today, I'll discuss the latest technology trends. First, I'll explain the basic concepts, then I'll talk about new research and applications. Finally, I'll discuss future prospects.

[0467] Please generate feedback and relevant questions and answers in the following format:

[0468] feedback:

[0469] Q&A:

[0470] This invention provides high-quality feedback and Q&A in real time while taking into account the user's emotional state, enabling more effective presentation practice and customer service. By using this system, users can improve their skills while reducing their psychological burden.

[0471] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0472] Step 1:

[0473] The user inputs the text data of the presentation.

[0474] Specifically, the user inputs the content of the presentation in text format using an input device attached to the smart glasses. The input text data is then saved in the terminal.

[0475] Step 2:

[0476] Recognize the user's emotional state in real time.

[0477] While the user is making a presentation, the device's built-in camera and emotion analysis software (e.g., EmotionRecognizer) are used to analyze the user's facial expressions and tone of voice. Emotion data is generated as a result of this analysis and stored on the device.

[0478] Step 3:

[0479] The terminal transmits the text data and the emotion data to the server.

[0480] The input text data and emotion data are sent from the device to the server via a network connection, allowing the server to prepare for analysis.

[0481] Step 4:

[0482] The server analyzes the received data.

[0483] The server uses the received text data and emotion data to perform analysis using a large-scale language model (e.g., OpenAI GPT). This analysis involves understanding the content of the text data and evaluating the emotion data, and generating optimal feedback and questions and answers for the user. The inputs for the analysis are text data and emotion data, and the outputs are feedback and questions and answers.

[0484] Step 5:

[0485] The server generates feedback and questions and answers.

[0486] Based on the analysis results of the large-scale language model, the server generates specific feedback and Q&A. Using the generative AI model, it evaluates the presentation content, suggests areas for improvement, and generates anticipated Q&A. The generated feedback and Q&A are stored on the server.

[0487] Step 6:

[0488] The server transmits the generated feedback and questions and answers to the terminal.

[0489] The feedback and questions are stored on the server and sent to the terminal via the network, allowing the user to check the results in real time.

[0490] Step 7:

[0491] The terminal displays feedback and questions and answers to the user.

[0492] The device receives feedback and Q&A from the server and displays it to the user. The feedback and Q&A are displayed in real time on the smart glasses display, allowing the user to review and revise their presentation.

[0493] This completes all processing steps, allowing the user to understand the evaluation of the presentation content and areas for improvement, and prepare for a question and answer session.

[0494] 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.

[0495] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0496] 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.

[0497] [Second embodiment]

[0498] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0499] 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.

[0500] 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).

[0501] 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.

[0502] 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.

[0503] 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).

[0504] 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.

[0505] 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.

[0506] 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.

[0507] 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.

[0508] 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.

[0509] 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."

[0510] The present invention relates to a system that automatically generates and provides feedback and Q&A based on the text data of a presentation input by a user. This system helps users evaluate and improve their presentation content, and is an effective tool for achieving high-quality rehearsals.

[0511] Basic system configuration

[0512] The user inputs the content of the presentation into their device. The device sends this text data to the server. The server receives the input text data and analyzes it using a large-scale language model (LLM). After analyzing, the server generates feedback for the user and questions and answers related to the presentation content. The generated feedback and questions and answers are sent back to the device, which displays them to the user.

[0513] Program Overview

[0514] The program of this system consists of the following main modules:

[0515] 1. Data receiving module: Receives text data entered by the user.

[0516] 2. Data analysis module: Analyzes the received text data and generates feedback and questions and answers.

[0517] 3. Feedback generation module: Generates specific feedback based on the presentation content.

[0518] 4. Question and Answer Generation Module: Generates questions and answers related to the presentation content.

[0519] 5. Data transmission module: Sends the generated feedback and questions and answers to the user.

[0520] Processing Description

[0521] The user inputs the text data of the presentation content, for example, using a text editor or a dedicated input form.

[0522] The terminal sends the input text data to the server, which communicates via the network and passes the text data to the server.

[0523] The server analyzes the received text data. The server uses a large-scale language model to understand and analyze the content of the text data. This analysis process is carried out using natural language processing technology.

[0524] The server generates feedback based on the analysis results, including specific evaluations and suggestions for improvement regarding the content, structure, and behavior of the presentation.

[0525] The server generates a Q&A based on the text data, which includes anticipated questions related to the presentation and their answers.

[0526] The server sends the generated feedback and Q&A to the terminal, allowing the user to receive the evaluation results in real time.

[0527] The device displays feedback and Q&A to the user, who can use this information to improve their presentation and use it for their next rehearsal.

[0528] Specific examples

[0529] For example, if a user enters the following announcement:

[0530] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0531] The server receives this text and analyzes it using a large language model, which generates feedback and questions like this:

[0532] feedback:

[0533] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[0534] Q&A:

[0535] Question 1: Could you please explain the basic concepts of AI in more detail?

[0536] Question 2: Can you give some specific examples of ongoing research?

[0537] Question 3: How do you think future advances in AI technology will affect society?

[0538] Once users receive this feedback, they can take the improvements into account and revise their presentation. By preparing answers for questions, they can feel more confident when they give their presentation.

[0539] The processing flow will be explained below.

[0540] Step 1:

[0541] The user inputs the text data of the presentation. The user uses a dedicated input form or text editor to input the content of the presentation in text format into the terminal.

[0542] Step 2:

[0543] The terminal transmits the input text data to the server. When the user completes input and clicks the send button, the terminal transmits the text data to the server via the network.

[0544] Step 3:

[0545] The server receives the text data. The server successfully receives the data sent from the device and prepares it for analysis.

[0546] Step 4:

[0547] The server analyzes the text data. Using a large-scale language model, the server analyzes the received text data based on its content and deepens its understanding of the structure and expression of the presentation.

[0548] Step 5:

[0549] The server generates feedback based on the analysis results, including an evaluation of the presentation and suggestions for improvement, such as advice on the presentation structure, adding concrete examples, and visual representation methods.

[0550] Step 6:

[0551] The server generates questions and answers based on the text data. The server automatically generates anticipated questions and answers related to the presentation content. This generation process also uses a large-scale language model.

[0552] Step 7:

[0553] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[0554] Step 8:

[0555] The terminal displays the feedback and Q&A to the user. The terminal analyzes the data received from the server and displays it in a format that is easy for the user to view.

[0556] Step 9:

[0557] Users can revise and improve their presentations based on feedback and Q&A. Users can use the feedback they receive to improve their presentations and rehearse again.

[0558] Example 1

[0559] 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."

[0560] Previously, human feedback was required to evaluate and improve presentation content, which was problematic in that it was time-consuming and labor-intensive. Furthermore, while responding to anticipated questions is also important for a high-quality rehearsal, there was no automated system for doing so appropriately. This made it difficult for presenters to prepare efficiently and effectively.

[0561] 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.

[0562] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data using a generative AI model that uses a large-scale language model to generate feedback about the presentation, means for generating questions and answers based on the text data, and means for providing the generated feedback and questions and answers to the user, thereby enabling the user to automatically receive high-quality feedback and questions and answers.

[0563] A "user" is an individual or group that inputs text data of their own presentation content.

[0564] "Text data" is data in the form of text entered by the user as the content of the presentation.

[0565] A "generative AI model" is an algorithm that uses artificial intelligence techniques, including large-scale language models, to analyze text data and generate feedback and questions and answers.

[0566] "Feedback" refers to evaluation of the presentation content and specific instructions or suggestions for improvement.

[0567] "Questions and Answers" refers to anticipated questions related to the content of the presentation and their answers.

[0568] The "server" is a central computer system that receives text data sent by users and performs analysis and generation processing using generative AI models.

[0569] A "terminal" is a device on which a user inputs the content of their presentation, sends the data to the server, and receives and displays feedback and questions from the server.

[0570] "Data analysis" is the process of inputting text data into a generative AI model, understanding and analyzing its content, and generating feedback and questions and answers.

[0571] A "prompt" refers to an instruction or question that is input into a generative AI model, and the AI ​​analyzes and generates based on this.

[0572] The present invention relates to a system that allows users to input text data of their presentation content and automatically generates and provides feedback and Q&A based on that data. This system is an effective tool for helping users evaluate and improve their presentation content and achieving high-quality rehearsals. Specific embodiments of the system are described below.

[0573] Basic system configuration

[0574] Users input their presentation content into their own devices. For example, they can use a text editor or a web application input form. This input text data flows through the system in the following steps:

[0575] The terminal sends the input text data to the server, typically as an HTTP request over the Internet.

[0576] The server uses a large-scale language model (generative AI model) to analyze the received text data, such as OpenAI's GPT-3, which utilizes natural language processing technology.

[0577] The server uses a generative AI model to analyze the content of the input text data and generate feedback, including the presentation content, structure, specific evaluations, and suggestions for improvement.

[0578] Furthermore, the server generates a question and answer session based on the text data, which includes anticipated questions related to the presentation content and their answers.

[0579] The generated feedback and questions are then sent back to the device, again via network communication.

[0580] Finally, the terminal displays the received feedback and questions and answers to the user, preferably in a visually easy-to-understand format through a user interface.

[0581] Specific examples

[0582] For example, if a user enters the following announcement:

[0583] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0584] When this input is sent from the device to the server, the server analyzes it using a large-scale language model. The prompt sentence is input to the generative AI model as follows:

[0585] Please analyze the following sentence: Today, I will be presenting the latest trends in AI technology...

[0586] The server uses this analysis to generate feedback such as:

[0587] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[0588] Additionally, the following questions and answers are generated:

[0589] Question 1: Could you please explain the basic concepts of AI in more detail?

[0590] Question 2: Can you give some specific examples of ongoing research?

[0591] Question 3: How do you think future advances in AI technology will affect society?

[0592] This feedback and Q&A is sent to the device and ultimately displayed to the user, who can use it to improve their presentation and prepare for their next rehearsal.

[0593] Thus, the present invention is a system that allows users to efficiently prepare presentations and receive high quality feedback and questions and answers.

[0594] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0595] Step 1:

[0596] The user inputs the text data of the presentation using a text editor or an input form in a web application. The input data is saved as the original text of the presentation.

[0597] input:

[0598] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0599] output:

[0600] Input text data

[0601] Specific behavior:

[0602] The user types the content of the presentation into the input form.

[0603] Step 2:

[0604] The device sends the entered text data to the server. This operation is performed using network communication, specifically an HTTP POST request. The device creates a packet to send the text data to the server and sends it over the Internet.

[0605] input:

[0606] Text data entered by the user

[0607] output:

[0608] Text data sent to the server

[0609] Specific behavior:

[0610] The device generates and sends an HTTP request like this:

[0611] POST / analyze HTTP / 1.1

[0612] Host: example.com

[0613] Content-Type: application / json

[0614] Content-Length: 123

[0615] {

[0616] "text": "Today, I'll be presenting the latest developments in AI technology..."

[0617] }

[0618] Step 3:

[0619] The server analyzes the received text data. The server uses a generative AI model to generate prompts and analyze the data. In this process, the text data is input into the model to understand its content.

[0620] input:

[0621] Text data sent from the device

[0622] output:

[0623] Text data analysis results

[0624] Specific behavior:

[0625] The server inputs the following prompt into the generative AI model:

[0626] Please analyze the following sentence: Today, I will be presenting the latest trends in AI technology...

[0627] Step 4:

[0628] The server generates feedback based on the analysis results. This is the process of generating feedback statements that include specific evaluations and suggestions for improvement of the presentation content based on the analysis results obtained from the generative AI model.

[0629] input:

[0630] Text data analysis results

[0631] output:

[0632] Generated Feedback

[0633] Specific behavior:

[0634] The server generates feedback like this:

[0635] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[0636] Step 5:

[0637] The server generates a Q&A based on the text data. The Q&A consists of anticipated questions related to the presentation content and their answers, and is generated using a generative AI model.

[0638] input:

[0639] Text data analysis results

[0640] output:

[0641] Generated Q&A

[0642] Specific behavior:

[0643] The server generates a question and answer like this:

[0644] Question 1: Could you please explain the basic concepts of AI in more detail?

[0645] Question 2: Can you give some specific examples of ongoing research?

[0646] Question 3: How do you think future advances in AI technology will affect society?

[0647] Step 6:

[0648] The server sends the generated feedback and Q&A to the terminal. This operation also uses network communication and is sent as an HTTP response.

[0649] input:

[0650] Generated feedback and Q&A

[0651] output:

[0652] Feedback and Q&A sent to device

[0653] Specific behavior:

[0654] The server generates an HTTP response like this and sends it to the device:

[0655] HTTP / 1.1 200 OK

[0656] Content-Type: application / json

[0657] Content-Length: 345

[0658] {

[0659] "feedback": "The presentation is clearly structured and easy to understand...",

[0660] "qna": [

[0661] {"question": "Please explain the basic concepts of AI in more detail.", "answer": "..."},

[0662] {"question": "Please give some specific examples of ongoing research.", "answer": "..."}

[0663] ]

[0664] }

[0665] Step 7:

[0666] The device displays the received feedback and Q&A to the user in a visually easy-to-understand format using a user interface.

[0667] input:

[0668] Server-submitted feedback and questions

[0669] output:

[0670] Feedback and Q&A displayed to the user

[0671] Specific behavior:

[0672] The terminal generates an interface that displays the data as follows:

[0673] feedback:

[0674] "The presentation is clearly structured and easy to understand. However, adding more concrete examples would have helped to hold the audience's interest..."

[0675] Q&A:

[0676] Question 1: Could you please explain the basic concepts of AI in more detail?

[0677] Question 2: Can you give some specific examples of ongoing research?

[0678] (Application example 1)

[0679] 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."

[0680] In the past, it was not easy to effectively introduce new products and services in presentations at physical stores. It was especially difficult for inexperienced employees to deliver accurate presentations and respond promptly to questions and answers on the spot. Furthermore, the lack of preparation for immediate feedback and Q&A sessions led to inconsistent presentation quality.

[0681] 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.

[0682] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data and generating feedback regarding the presentation, means for generating questions and answers based on the text data, means for providing the generated feedback and questions and answers to the user, means for generating feedback to improve the effectiveness of the presentation, and means for receiving feedback in real time during the presentation, thereby enabling employees to improve the quality of their presentations, receive immediate feedback, and prepare for questions and answers.

[0683] A "user" is an individual or group that uses the system to input text data of the presentation content.

[0684] "Presentation content" refers to information and data presented as a presentation, and is primarily entered in text format.

[0685] "Text data" refers to character string data entered by the user, and includes specific sentences and explanations of the content of the presentation.

[0686] The "server" is a central processing unit that analyzes the received text data, generates feedback and questions and answers, and sends them to the terminal.

[0687] "Analysis" is the process of understanding the content of text data and evaluating and breaking down that content using natural language processing techniques.

[0688] "Feedback" includes evaluations and advice regarding the content, structure, and areas for improvement of the presentation, and is provided to the user.

[0689] "Questions and Answers" are anticipated questions and answers related to the presentation content, and are provided to help users prepare.

[0690] "Real-time" refers to the time period in which processing and feedback are immediate, and applies during a user's presentation.

[0691] "Presentation effectiveness" refers to the success of a user's presentation and its ability to gain the understanding and interest of the audience.

[0692] A "terminal" is a device through which a user inputs text data, sends it to the server, and displays and receives feedback and questions and answers.

[0693] A "large-scale language model" is a type of artificial intelligence trained from large amounts of text data, and is a model for analyzing and generating natural language.

[0694] The system for implementing this invention receives text data of presentation content entered by a user, analyzes it, and automatically generates feedback and Q&A. This system functions as a support tool for users to make their presentations more effective.

[0695] System Configuration

[0696] The system consists of the following main modules:

[0697] 1. Data receiving module: Receives the text data of the presentation entered by the user into the terminal.

[0698] 2. Data transmission module: The terminal transmits the received text data of the announcement to the server.

[0699] 3. Data analysis module: The server analyzes the received text data and generates feedback on the presentation and Q&A using natural language processing techniques and large-scale language models (e.g., OpenAI GPT-3).

[0700] 4. Feedback generation module: Based on the presentation content, specific feedback is generated to improve the quality of the presentation.

[0701] 5. Q&A generation module: Generates anticipated questions and answers based on the presentation content.

[0702] 6. Real-time feedback module: Provides real-time feedback during presentations.

[0703] 7. Data transmission module: The generated feedback and questions and answers are transmitted to the terminal and provided to the user.

[0704] Hardware and Software

[0705] Hardware: The system consists of a device used by the user (such as a smartphone or tablet) and a server that performs analysis and generation processing. The device has a user interface and data communication functions.

[0706] Software: The system includes modules for receiving, sending, and analyzing text data, generating feedback and Q&A, and providing real-time feedback. These modules are implemented in programming languages ​​such as Python and JavaScript. Large-scale language models such as OpenAI GPT-3 are used for analysis.

[0707] System Operation

[0708] 1. Text data input by the user: The user inputs the text data of the presentation using a dedicated application on their smartphone.

[0709] 2. Sending and receiving data: The entered text data is sent from the terminal to the server via the network.

[0710] 3. Data analysis and generation: The server analyzes the text data using a large-scale language model such as OpenAI GPT-3 and generates presentation feedback and Q&A.

[0711] 4. Providing feedback and Q&A: The generated feedback and Q&A are sent back to the terminal via the network and provided to the user, who can use this information to improve the presentation content.

[0712] 5. Providing real-time feedback: If real-time feedback is required during a presentation, the information is sent immediately from the server to the terminal and provided to the user.

[0713] Specific examples

[0714] For example, if a user enters the following presentation content:

[0715] "We'll introduce the new smartphone features. First, we'll talk about improved camera performance. Second, we'll talk about improved battery life. And finally, we'll talk about new software features."

[0716] Based on this text data, the server analyzes it and generates feedback and questions like the following:

[0717] feedback:

[0718] The presentation is well-structured, but it would be more effective if it included concrete use cases and a more detailed explanation of the new software features.

[0719] Q&A:

[0720] Question 1: What exactly are the improvements to camera performance?

[0721] Question 2: How much longer does the battery life increase?

[0722] Question 3: What benefits do the new software features provide?

[0723] This process allows users to receive real-time feedback and improve the quality of their presentations.

[0724] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0725] Step 1:

[0726] The user inputs the presentation content as text data using a dedicated application.

[0727] Input: The user enters the presentation content in text format.

[0728] Output: The text data is saved to the device.

[0729] Specific operation: The user launches a dedicated application on their smartphone and enters the presentation content into the input form.

[0730] Step 2:

[0731] The terminal transmits the input text data to the server.

[0732] Input: Text data entered by the user.

[0733] Output: The text data is sent over the network to the server.

[0734] Specific operation: The device sends the entered text data to the server via internet communication, where the data is encrypted for security reasons.

[0735] Step 3:

[0736] The server analyzes the received text data and generates feedback and questions and answers.

[0737] Input: Text data sent from the terminal.

[0738] Output: Feedback and Q&A are generated.

[0739] How it works: The server analyzes the text data using a large-scale language model (e.g., OpenAI GPT-3). This analysis uses natural language processing techniques. Based on the analysis results, it generates an evaluation of the presentation, feedback on areas for improvement, and related Q&A.

[0740] Step 4:

[0741] After generating the feedback and questions and answers, the server sends them to the terminal.

[0742] Input: Generated feedback and questions and answers.

[0743] Output: Feedback and Q&A are sent to the terminal.

[0744] Specific operation: The server sends the generated feedback and Q&A to the user's terminal via the network.

[0745] Step 5:

[0746] The terminal displays the received feedback and questions and answers to the user.

[0747] Input: Feedback and questions sent by the server.

[0748] Output: Feedback and questions are displayed visually to the user.

[0749] Specific operation: The device displays the received feedback and Q&A on the user interface of a dedicated application, allowing the user to view the feedback and prepare for potential questions and improve their presentation.

[0750] Step 6:

[0751] Provide real-time feedback during presentations.

[0752] Input: User presentation data collected in real time.

[0753] Output: Real-time feedback is provided to the user.

[0754] Specific operation: During a presentation, the device transmits the user's presentation content and progress to the server in real time, and the server immediately analyzes it using a large-scale language model. Based on the analysis results, feedback is generated in real time and sent to the device for display.

[0755] 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.

[0756] The present invention relates to a system that allows users to input text data of their presentations, automatically generates feedback and Q&A based on the data, and further adjusts the content by recognizing the user's emotions. This system is an effective tool for helping users evaluate and improve their presentations and providing feedback that takes into account the user's emotional state.

[0757] Basic system configuration

[0758] The user inputs their speech content into their device and then activates an emotion engine to recognize the user's emotional state. The device then sends this data to a server. The server receives the input text data and emotion data and analyzes the data using a large-scale language model (LLM). After analysis, the server generates feedback for the user and questions and answers related to the speech content. The generated feedback and questions and answers are also adjusted based on the user's emotional state. The generated feedback and questions and answers are then sent back to the device, which displays them to the user.

[0759] Program Overview

[0760] The program of this system consists of the following main modules:

[0761] 1. Data receiving module: Receives the text data and emotion data of the presentation entered by the user.

[0762] 2. Emotion Recognition Module: Analyzes user emotions in real time and collects the data.

[0763] 3. Data analysis module: Analyzes the received text data and sentiment data and generates feedback and questions and answers.

[0764] 4. Feedback generation module: Generates specific feedback based on the announcement and user sentiment.

[0765] 5. Question and Answer Generation Module: Generates relevant questions and answers based on the presentation content and sentiment data.

[0766] 6. Data transmission module: Sends the generated feedback and questions and answers to the user.

[0767] Processing Description

[0768] The user inputs the text data of the presentation. The user uses a dedicated input form or text editor to input the content of the presentation in text format into the terminal. In some cases, the user also wears a device for emotion recognition.

[0769] The device sends the entered text data and emotion data to the server. When the user completes the input and clicks the send button, the device sends this data to the server via the network.

[0770] The server receives the text data and emotion data. The server successfully receives the data sent from the device and prepares it for analysis.

[0771] The server analyzes the text data and emotion data. The server uses a large-scale language model to understand and analyze the content of the text data and emotion data. This analysis process is carried out using natural language processing technology and emotion recognition technology.

[0772] The server generates feedback based on the analysis results, including an evaluation of the presentation content and suggestions for improvement. By taking emotional data into account, the server generates content that takes into account the user's emotional state.

[0773] The server generates questions and answers based on text data and emotion data. The server automatically generates possible questions and answers related to the presentation content and emotion data. This generation process also uses large-scale language models and emotion recognition technology.

[0774] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[0775] The terminal displays the feedback and Q&A to the user. The terminal analyzes the data received from the server and displays it in a format that is easy for the user to view.

[0776] Specific examples

[0777] For example, if a user enters the following announcement:

[0778] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0779] Meanwhile, the emotion engine monitors the user's stress level and emotional state in real time, collecting data. The server receives and analyzes this text and emotion data. Based on the analysis, feedback and questions are generated, such as:

[0780] feedback:

[0781] The presentation's structure is clear and easy to understand. However, adding more specific examples would help capture the audience's interest. It would also be good to provide a more detailed explanation of future prospects. Furthermore, the emotional data suggests that you seem a little nervous, so we recommend taking a deep breath and relaxing.

[0782] Q&A:

[0783] Question 1: Could you please explain the basic concepts of AI in more detail?

[0784] Question 2: Can you give some specific examples of ongoing research?

[0785] Question 3: How do you think future advances in AI technology will affect society?

[0786] As soon as users receive this feedback, they can take the points for improvement into account and revise their presentation content. By preparing answers for questions, they can approach their actual presentation with greater confidence. Furthermore, based on emotional feedback, they can manage their own psychological state as they practice.

[0787] The processing flow will be explained below.

[0788] Step 1:

[0789] The user inputs the text data of the presentation. The user inputs the content of the presentation into the terminal using a dedicated input form or text editor. In addition, devices such as the camera and microphone are enabled for emotion recognition.

[0790] Step 2:

[0791] The terminal transmits the input text data and emotion data to the server. When the user clicks the "Send" button, the terminal transmits the text data and initial emotion data to the server via the network.

[0792] Step 3:

[0793] The server receives the text data and emotion data. The server successfully receives the data sent from the device and prepares for analysis.

[0794] Step 4:

[0795] The server analyzes the text data and uses a large-scale language model to analyze the content of the received text data and generate specific feedback about the presentation.

[0796] Step 5:

[0797] The server analyzes the emotional data. The server uses an emotion recognition engine to analyze the user's emotional state (tension, anxiety, joy, etc.). The analysis results include stress levels and emotional fluctuations.

[0798] Step 6:

[0799] The server generates feedback based on the analysis results. The server combines the results of the text data analysis and the emotional data analysis to create detailed feedback on the user's presentation. The feedback includes specific suggestions for improvement and instructions that take into account the user's emotional state.

[0800] Step 7:

[0801] The server generates questions and answers based on text data and emotional data. The server automatically generates anticipated questions and answers related to the presentation content, and these responses also take emotional data into consideration.

[0802] Step 8:

[0803] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[0804] Step 9:

[0805] The terminal displays the feedback and Q&A to the user. The terminal analyzes the feedback and Q&A received from the server and displays them in a format that is easy for the user to view.

[0806] Step 10:

[0807] Users can revise and improve their presentation content based on feedback and Q&A. Users can refer to the feedback they receive to improve their presentation content and manage their own psychological state based on emotional feedback.

[0808] Example 2

[0809] 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."

[0810] Conventional presentation support systems generate feedback and Q&A without considering the user's emotional state, making it difficult for users to make effective corrections or preparations when they are feeling nervous or stressed. Furthermore, the content of Q&A is simply generated based on the presentation content, which can lead to a lack of depth.

[0811] 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.

[0812] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data to generate feedback regarding the presentation, means for generating questions and answers based on the text data, means for adjusting the content of the feedback and questions and answers based on the emotional state of the user, and means for providing the generated feedback and questions and answers to the user, thereby making it possible to provide effective and specific feedback and questions and answers while taking the emotional state of the user into consideration.

[0813] A "user" is someone who uses the system to input presentation content and receive feedback and questions.

[0814] "Presentation content" is text data of a presentation or speech entered by the user.

[0815] "Text data" refers to the content of a presentation expressed as text information.

[0816] The term "means" refers to a specific device or module provided for performing a predetermined function.

[0817] "Analysis" is the process of understanding the content of input data and generating appropriate feedback and questions and answers.

[0818] "Feedback" is information that includes evaluation of the user's presentation and advice on how to improve it.

[0819] "Questions and Answers" is information that includes anticipated questions and answers based on the content of the presentation.

[0820] "Emotional state" refers to the user's psychological state and emotional response, including, for example, the degree of tension or stress.

[0821] A "large-scale language analysis model" is a large-scale machine learning model used for natural language processing, which learns language patterns and meanings from large amounts of text data.

[0822] An "information terminal" is an electronic device that users use to input presentation content and receive feedback and questions.

[0823] The "main control unit" is a central unit that analyzes the received data, generates feedback and questions and answers, and sends them to the information terminals.

[0824] This invention relates to a system that allows users to input text data of their presentations, automatically generates feedback and Q&A based on the data, and further adjusts the content by recognizing the user's emotions. This system is an effective tool for helping users evaluate and improve their presentations and providing feedback that takes into account the user's emotional state.

[0825] Basic system configuration

[0826] A user inputs a speech into his / her information terminal, and then activates a device for recognizing the user's emotional state. The terminal transmits this data to a main control device. The main control device receives the input text data and emotional data and analyzes the data using a large-scale language analysis model. After analysis, the main control device generates feedback for the user and questions and answers related to the speech. The generated feedback and questions and answers are also adjusted based on the user's emotional state. The generated feedback and questions and answers are then transmitted back to the terminal, which displays them to the user.

[0827] Examples of hardware and software:

[0828] Input device: The device that the user uses to input their presentation (e.g., personal computer, tablet, smartphone)

[0829] Emotion recognizers: devices that recognize the user's emotional state (e.g., heart rate monitors, wearable devices)

[0830] Master controller: A server or cloud service (e.g., a cloud computing platform) that analyzes input data and generates feedback and questions and answers.

[0831] Large language analysis models: AI models for analyzing natural language data (e.g., large-scale language models)

[0832] Communication network: A network (e.g., the Internet) for transmitting and receiving data between the terminal and the main control unit.

[0833] Specific operation explanation

[0834] The user inputs the contents of the presentation in text format into the terminal using a dedicated input form or a text editor (e.g., general word processing software). For emotion recognition, the user wears a device such as a heart rate monitor and connects it to the information terminal.

[0835] The terminal collects the input text data and emotion data and transmits them to the main control device via a network (e.g., the Internet).

[0836] The master controller uses large language analysis models to analyze the received text and emotion data. This process leverages natural language processing techniques (e.g., AI models) and emotion recognition techniques.

[0837] The master controller generates feedback based on the analysis, including a rating of the presentation and specific suggestions for improvement, and adjusts the feedback based on the user's emotional state.

[0838] The master controller generates relevant questions and answers based on the text data and the emotion data, which include possible questions related to the presentation and their answers.

[0839] The main control device sends the generated feedback and questions and answers back to the terminal again via the network.

[0840] The terminal displays the feedback and Q&A received from the main control device, allowing the user to revise their presentation based on the feedback and prepare answers for Q&A. Furthermore, the emotional feedback allows the user to manage their own psychological state as they practice.

[0841] Specific examples

[0842] For example, if a user enters the following announcement:

[0843] text

[0844] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[0845] Meanwhile, the emotion engine monitors the user's stress level and heart rate in real time and collects data. The master controller receives and analyzes this text and emotion data. Based on the analysis results, feedback and Q&A are generated, such as:

[0846] feedback:

[0847] text

[0848] The presentation is clearly structured and easy to understand. However, adding more specific examples would help capture the audience's interest. It would also be good to provide more details about future prospects. Furthermore, the emotional data suggests that you seem a little nervous, so we recommend taking a deep breath and relaxing.

[0849] Q&A:

[0850] text

[0851] Question 1: Could you please explain the basic concepts of AI in more detail?

[0852] Question 2: Can you give some specific examples of ongoing research?

[0853] Question 3: How do you think future advances in AI technology will affect society?

[0854] Prompt Sentence Examples

[0855] Examples of prompts to input to a generative AI model might include:

[0856] text

[0857] The user entered the following announcement:

[0858] "Today, I will be presenting on the latest developments in AI technology. First, I will explain the basic concepts of AI, then talk about ongoing research and commercial applications. Finally, I will consider what the future holds."

[0859] Please generate feedback on this presentation, along with related questions and answers. Please also consider user sentiment data (high tension).

[0860] In this way, the system automatically analyzes the content of the user's presentation and provides feedback and Q&A, helping the user to give a more effective presentation.

[0861] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0862] Step 1:

[0863] The user inputs the text data of the presentation.

[0864] The user inputs the content of the presentation in text format into the terminal using a dedicated input form or a text editor (e.g., general word processing software). For emotion recognition, the user wears a device such as a heart rate monitor and connects it to the information terminal. The input data (the text of the presentation and emotion data) is sent to the terminal.

[0865] Step 2:

[0866] The terminal transmits the input text data and emotion data to the server.

[0867] The user completes the input and clicks the send button. At this point, the terminal uses the network (e.g., the Internet) to send the input data to the main control device. The input includes the text data of the announcement and the real-time emotion data obtained from the emotion device. The output is that these data are successfully sent to the server.

[0868] Step 3:

[0869] The server receives the data.

[0870] The server receives the text data and emotion data sent from the device, checks the consistency and completeness of the data, formats the input data (the text data of the announcement and the emotion data) for analysis, and outputs the formatted text data and emotion data.

[0871] Step 4:

[0872] The server analyzes the text data and the emotion data.

[0873] The server uses a large-scale language analysis model (e.g., large-scale language model) to analyze the content of text data and emotional data. It uses natural language processing technology (e.g., NLTK, SpaCy) and emotion recognition technology to break down and understand the input text sentence by sentence. The input for the analysis is organized text data and emotional data, and the output is a dataset of the analysis results.

[0874] Step 5:

[0875] The server generates feedback based on the analysis results.

[0876] Based on the analysis results, a large language analysis model is used to generate feedback on the user's post. The feedback includes an evaluation of the post and specific suggestions for improvement, and is adjusted based on the user's emotional state. The input is a dataset of the analysis results, and the output is text feedback for the user.

[0877] Step 6:

[0878] The server generates questions and answers based on the text data and the emotion data.

[0879] The server automatically generates possible questions and answers based on the presentation content and emotional data. The generation process uses large-scale language models and emotion recognition technology. The input is a dataset of analysis results, and the output is text data of the questions and answers.

[0880] Step 7:

[0881] The server transmits the generated feedback and questions and answers to the terminal.

[0882] The server returns the generated feedback and Q&A data to the terminal via the network. The input is the generated feedback and Q&A text data, and the output is that these data are successfully sent to the terminal.

[0883] Step 8:

[0884] The terminal displays feedback and questions to the user.

[0885] The terminal receives feedback and questions from the server and displays them in a format that is easy for the user to view. A web browser or a dedicated application is used here. The input is the text data of the feedback and questions received from the server, and the output is to display it for the user.

[0886] (Application example 2)

[0887] 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."

[0888] Conventional presentation feedback systems do not take the user's emotional state into account when generating feedback or Q&A, resulting in insufficient feedback when users practice presentations and inefficient improvement of presentation skills. Furthermore, because they are unable to recognize emotions in real time and adjust feedback based on the results, it is difficult to reduce the presenter's psychological burden. Similar problems occur when employees explain products, resulting in inconsistent quality of customer service.

[0889] 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.

[0890] In this invention, the server includes means for receiving text data and emotional data of the presentation content entered by the user, means for analyzing the text data and emotional data to generate feedback regarding the presentation, means for generating Q&A based on the text data and emotional data, means for providing the generated feedback and Q&A to the user, and means for adjusting the content of the feedback and Q&A based on the user's emotional state. This makes it possible to provide high-quality feedback and Q&A in real time that takes the user's emotional state into consideration, thereby improving the user's presentation skills and reducing psychological burden. It also improves the quality of customer service when employees are explaining products.

[0891] A "user" is a person who uses this system to input text data of the presentation content.

[0892] "Presentation content" refers to text data entered by the user, and refers to an explanation or report of information based on a specific theme.

[0893] "Text data" refers to character string information that a user inputs as content to be presented.

[0894] "Emotion data" refers to data that indicates the user's emotional state, and is psychological information that is acquired in real time.

[0895] "Feedback" refers to information entered by the user, including evaluations of the presentation content and suggestions for improvement.

[0896] "Questions and answers" refers to questions and corresponding answers generated based on the content of the presentation.

[0897] A "server" is a computer system that receives text data and emotion data sent by users, analyzes them, and generates feedback and questions and answers.

[0898] "Terminal" refers to a device through which a user inputs text data, transmits it to a server, and receives feedback and questions and answers from the server.

[0899] A "large-scale language model" refers to advanced algorithms and techniques that learn from large amounts of text data in natural language processing to generate and analyze text.

[0900] The "emotion engine" is a system that recognizes emotions from the user's facial expressions, tone of voice, etc., and generates that data.

[0901] This embodiment of the present invention handles the text data of the presentation content entered by the user and the user's emotional data in detail to generate feedback and Q&A for the user's presentation content, and also makes adjustments according to the user's emotional state. A specific implementation method of this system is described below.

[0902] Program Components

[0903] The system consists of the following main modules:

[0904] 1. Data receiving module:

[0905] Receive text data of the presentation content entered by the user, for example, using a dedicated input form or text editor.

[0906] 2. Emotion Recognition Module:

[0907] Emotion data is collected to analyze the user's emotions in real time. For this purpose, emotion recognition devices such as cameras and microphones are used. For example, software such as EmotionRecognizer is used.

[0908] 3. Data Analysis Module:

[0909] The received text data and emotion data are sent to a server for analysis. A large-scale language model (LLM) is used for the analysis. Possible applications include OpenAI's API.

[0910] 4. Feedback and Q&A generation module:

[0911] Feedback and Q&A are generated based on text and emotion data using a generative AI model, which is then sent from the server to the device.

[0912] 5. Data transmission module:

[0913] The generated feedback and Q&A data is sent to the user's device, for example, via an AWS S3 bucket.

[0914] Hardware and software used

[0915] Smart glasses (e.g. Google Glass):

[0916] The user wears it to input text and collect emotion recognition data.

[0917] Cameras (e.g., in smart glasses):

[0918] It captures the user's facial expressions in real time and uses them to recognize emotions.

[0919] Server (e.g. AWS):

[0920] Receives, analyzes, and generates feedback on text and emotion data.

[0921] Generative AI models (e.g., OpenAI GPT):

[0922] Analyze text and sentiment data to generate feedback and Q&A.

[0923] Program processing

[0924] The server receives the text data of the presentation and the user's emotional data sent from the device. It then analyzes the received data and generates feedback and Q&A using a generative AI model. The generated feedback and Q&A are then sent back to the device and provided to the user. The content of the feedback and Q&A is also adjusted based on the emotional data.

[0925] Specific examples

[0926] For example, if a user enters the following announcement:

[0927] Today, I'll discuss the latest technology trends. First, I'll explain the basic concepts, then I'll talk about new research and applications. Finally, I'll discuss future prospects.

[0928] During this time, the emotion engine analyzes the user's emotional state and collects data. The server receives and analyzes this text and emotion data to generate feedback and Q&A, such as:

[0929] feedback:

[0930] The presentation structure is clear, but adding more concrete examples will help keep the audience engaged. Also, the emotional data suggests that you are a little nervous, so it would be good to incorporate some relaxation techniques.

[0931] Q&A:

[0932] Question 1: What are some specific application examples of the latest technology trends?

[0933] Question 2: What research do you expect to see in the future?

[0934] Question 3: Could you please elaborate on your future outlook?

[0935] Example prompt sentence:

[0936] User's emotional state: slightly nervous

[0937] Text data:

[0938] Today, I'll discuss the latest technology trends. First, I'll explain the basic concepts, then I'll talk about new research and applications. Finally, I'll discuss future prospects.

[0939] Please generate feedback and relevant questions and answers in the following format:

[0940] feedback:

[0941] Q&A:

[0942] This invention provides high-quality feedback and Q&A in real time while taking into account the user's emotional state, enabling more effective presentation practice and customer service. By using this system, users can improve their skills while reducing their psychological burden.

[0943] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0944] Step 1:

[0945] The user inputs the text data of the presentation.

[0946] Specifically, the user inputs the content of the presentation in text format using an input device attached to the smart glasses. The input text data is then saved in the terminal.

[0947] Step 2:

[0948] Recognize the user's emotional state in real time.

[0949] While the user is making a presentation, the device's built-in camera and emotion analysis software (e.g., EmotionRecognizer) are used to analyze the user's facial expressions and tone of voice. Emotion data is generated as a result of this analysis and stored on the device.

[0950] Step 3:

[0951] The terminal transmits the text data and the emotion data to the server.

[0952] The input text data and emotion data are sent from the device to the server via a network connection, allowing the server to prepare for analysis.

[0953] Step 4:

[0954] The server analyzes the received data.

[0955] The server uses the received text data and emotion data to perform analysis using a large-scale language model (e.g., OpenAI GPT). This analysis involves understanding the content of the text data and evaluating the emotion data, and generating optimal feedback and questions and answers for the user. The inputs for the analysis are text data and emotion data, and the outputs are feedback and questions and answers.

[0956] Step 5:

[0957] The server generates feedback and questions and answers.

[0958] Based on the analysis results of the large-scale language model, the server generates specific feedback and Q&A. Using the generative AI model, it evaluates the presentation content, suggests areas for improvement, and generates anticipated Q&A. The generated feedback and Q&A are stored on the server.

[0959] Step 6:

[0960] The server transmits the generated feedback and questions and answers to the terminal.

[0961] The feedback and questions are stored on the server and sent to the terminal via the network, allowing the user to check the results in real time.

[0962] Step 7:

[0963] The terminal displays feedback and questions and answers to the user.

[0964] The device receives feedback and Q&A from the server and displays it to the user. The feedback and Q&A are displayed in real time on the smart glasses display, allowing the user to review and revise their presentation.

[0965] This completes all processing steps, allowing the user to understand the evaluation of the presentation content and areas for improvement, and prepare for a question and answer session.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] [Third embodiment]

[0970] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0971] 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.

[0972] 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).

[0973] 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.

[0974] 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.

[0975] 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).

[0976] 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.

[0977] 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.

[0978] 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.

[0979] 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.

[0980] 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.

[0981] 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."

[0982] The present invention relates to a system that automatically generates and provides feedback and Q&A based on the text data of a presentation input by a user. This system helps users evaluate and improve their presentation content, and is an effective tool for achieving high-quality rehearsals.

[0983] Basic system configuration

[0984] The user inputs the content of the presentation into their device. The device sends this text data to the server. The server receives the input text data and analyzes it using a large-scale language model (LLM). After analyzing, the server generates feedback for the user and questions and answers related to the presentation content. The generated feedback and questions and answers are sent back to the device, which displays them to the user.

[0985] Program Overview

[0986] The program of this system consists of the following main modules:

[0987] 1. Data receiving module: Receives text data entered by the user.

[0988] 2. Data analysis module: Analyzes the received text data and generates feedback and questions and answers.

[0989] 3. Feedback generation module: Generates specific feedback based on the presentation content.

[0990] 4. Question and Answer Generation Module: Generates questions and answers related to the presentation content.

[0991] 5. Data transmission module: Sends the generated feedback and questions and answers to the user.

[0992] Processing Description

[0993] The user inputs the text data of the presentation content, for example, using a text editor or a dedicated input form.

[0994] The terminal sends the input text data to the server, which communicates via the network and passes the text data to the server.

[0995] The server analyzes the received text data. The server uses a large-scale language model to understand and analyze the content of the text data. This analysis process is carried out using natural language processing technology.

[0996] The server generates feedback based on the analysis results, including specific evaluations and suggestions for improvement regarding the content, structure, and behavior of the presentation.

[0997] The server generates a Q&A based on the text data, which includes anticipated questions related to the presentation and their answers.

[0998] The server sends the generated feedback and Q&A to the terminal, allowing the user to receive the evaluation results in real time.

[0999] The device displays feedback and Q&A to the user, who can use this information to improve their presentation and use it for their next rehearsal.

[1000] Specific examples

[1001] For example, if a user enters the following announcement:

[1002] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1003] The server receives this text and analyzes it using a large language model, which generates feedback and questions like this:

[1004] feedback:

[1005] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[1006] Q&A:

[1007] Question 1: Could you please explain the basic concepts of AI in more detail?

[1008] Question 2: Can you give some specific examples of ongoing research?

[1009] Question 3: How do you think future advances in AI technology will affect society?

[1010] Once users receive this feedback, they can take the improvements into account and revise their presentation. By preparing answers for questions, they can feel more confident when they give their presentation.

[1011] The processing flow will be explained below.

[1012] Step 1:

[1013] The user inputs the text data of the presentation. The user uses a dedicated input form or text editor to input the content of the presentation in text format into the terminal.

[1014] Step 2:

[1015] The terminal transmits the input text data to the server. When the user completes input and clicks the send button, the terminal transmits the text data to the server via the network.

[1016] Step 3:

[1017] The server receives the text data. The server successfully receives the data sent from the device and prepares it for analysis.

[1018] Step 4:

[1019] The server analyzes the text data. Using a large-scale language model, the server analyzes the received text data based on its content and deepens its understanding of the structure and expression of the presentation.

[1020] Step 5:

[1021] The server generates feedback based on the analysis results, including an evaluation of the presentation and suggestions for improvement, such as advice on the presentation structure, adding concrete examples, and visual representation methods.

[1022] Step 6:

[1023] The server generates questions and answers based on the text data. The server automatically generates anticipated questions and answers related to the presentation content. This generation process also uses a large-scale language model.

[1024] Step 7:

[1025] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[1026] Step 8:

[1027] The terminal displays the feedback and Q&A to the user. The terminal analyzes the data received from the server and displays it in a format that is easy for the user to view.

[1028] Step 9:

[1029] Users can revise and improve their presentations based on feedback and Q&A. Users can use the feedback they receive to improve their presentations and rehearse again.

[1030] Example 1

[1031] 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."

[1032] Previously, human feedback was required to evaluate and improve presentation content, which was problematic in that it was time-consuming and labor-intensive. Furthermore, while responding to anticipated questions is also important for a high-quality rehearsal, there was no automated system for doing so appropriately. This made it difficult for presenters to prepare efficiently and effectively.

[1033] 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.

[1034] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data using a generative AI model that uses a large-scale language model to generate feedback about the presentation, means for generating questions and answers based on the text data, and means for providing the generated feedback and questions and answers to the user, thereby enabling the user to automatically receive high-quality feedback and questions and answers.

[1035] A "user" is an individual or group that inputs text data of their own presentation content.

[1036] "Text data" is data in the form of text entered by the user as the content of the presentation.

[1037] A "generative AI model" is an algorithm that uses artificial intelligence techniques, including large-scale language models, to analyze text data and generate feedback and questions and answers.

[1038] "Feedback" refers to evaluation of the presentation content and specific instructions or suggestions for improvement.

[1039] "Questions and Answers" refers to anticipated questions related to the content of the presentation and their answers.

[1040] The "server" is a central computer system that receives text data sent by users and performs analysis and generation processing using generative AI models.

[1041] A "terminal" is a device on which a user inputs the content of their presentation, sends the data to the server, and receives and displays feedback and questions from the server.

[1042] "Data analysis" is the process of inputting text data into a generative AI model, understanding and analyzing its content, and generating feedback and questions and answers.

[1043] A "prompt" refers to an instruction or question that is input into a generative AI model, and the AI ​​analyzes and generates based on this.

[1044] The present invention relates to a system that allows users to input text data of their presentation content and automatically generates and provides feedback and Q&A based on that data. This system is an effective tool for helping users evaluate and improve their presentation content and achieving high-quality rehearsals. Specific embodiments of the system are described below.

[1045] Basic system configuration

[1046] Users input their presentation content into their own devices. For example, they can use a text editor or a web application input form. This input text data flows through the system in the following steps:

[1047] The terminal sends the input text data to the server, typically as an HTTP request over the Internet.

[1048] The server uses a large-scale language model (generative AI model) to analyze the received text data, such as OpenAI's GPT-3, which utilizes natural language processing technology.

[1049] The server uses a generative AI model to analyze the content of the input text data and generate feedback, including the presentation content, structure, specific evaluations, and suggestions for improvement.

[1050] Furthermore, the server generates a question and answer session based on the text data, which includes anticipated questions related to the presentation content and their answers.

[1051] The generated feedback and questions are then sent back to the device, again via network communication.

[1052] Finally, the terminal displays the received feedback and questions and answers to the user, preferably in a visually easy-to-understand format through a user interface.

[1053] Specific examples

[1054] For example, if a user enters the following announcement:

[1055] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1056] When this input is sent from the device to the server, the server analyzes it using a large-scale language model. The prompt sentence is input to the generative AI model as follows:

[1057] Please analyze the following sentence: Today, I will be presenting the latest trends in AI technology...

[1058] The server uses this analysis to generate feedback such as:

[1059] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[1060] Additionally, the following questions and answers are generated:

[1061] Question 1: Could you please explain the basic concepts of AI in more detail?

[1062] Question 2: Can you give some specific examples of ongoing research?

[1063] Question 3: How do you think future advances in AI technology will affect society?

[1064] This feedback and Q&A is sent to the device and ultimately displayed to the user, who can use it to improve their presentation and prepare for their next rehearsal.

[1065] Thus, the present invention is a system that allows users to efficiently prepare presentations and receive high quality feedback and questions and answers.

[1066] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1067] Step 1:

[1068] The user inputs the text data of the presentation using a text editor or an input form in a web application. The input data is saved as the original text of the presentation.

[1069] input:

[1070] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1071] output:

[1072] Input text data

[1073] Specific behavior:

[1074] The user types the content of the presentation into the input form.

[1075] Step 2:

[1076] The device sends the entered text data to the server. This operation is performed using network communication, specifically an HTTP POST request. The device creates a packet to send the text data to the server and sends it over the Internet.

[1077] input:

[1078] Text data entered by the user

[1079] output:

[1080] Text data sent to the server

[1081] Specific behavior:

[1082] The device generates and sends an HTTP request like this:

[1083] POST / analyze HTTP / 1.1

[1084] Host: example.com

[1085] Content-Type: application / json

[1086] Content-Length: 123

[1087] {

[1088] "text": "Today, I'll be presenting the latest developments in AI technology..."

[1089] }

[1090] Step 3:

[1091] The server analyzes the received text data. The server uses a generative AI model to generate prompts and analyze the data. In this process, the text data is input into the model to understand its content.

[1092] input:

[1093] Text data sent from the device

[1094] output:

[1095] Text data analysis results

[1096] Specific behavior:

[1097] The server inputs the following prompt into the generative AI model:

[1098] Please analyze the following sentence: Today, I will be presenting the latest trends in AI technology...

[1099] Step 4:

[1100] The server generates feedback based on the analysis results. This is the process of generating feedback statements that include specific evaluations and suggestions for improvement of the presentation content based on the analysis results obtained from the generative AI model.

[1101] input:

[1102] Text data analysis results

[1103] output:

[1104] Generated Feedback

[1105] Specific behavior:

[1106] The server generates feedback like this:

[1107] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[1108] Step 5:

[1109] The server generates a Q&A based on the text data. The Q&A consists of anticipated questions related to the presentation content and their answers, and is generated using a generative AI model.

[1110] input:

[1111] Text data analysis results

[1112] output:

[1113] Generated Q&A

[1114] Specific behavior:

[1115] The server generates a question and answer like this:

[1116] Question 1: Could you please explain the basic concepts of AI in more detail?

[1117] Question 2: Can you give some specific examples of ongoing research?

[1118] Question 3: How do you think future advances in AI technology will affect society?

[1119] Step 6:

[1120] The server sends the generated feedback and Q&A to the terminal. This operation also uses network communication and is sent as an HTTP response.

[1121] input:

[1122] Generated feedback and Q&A

[1123] output:

[1124] Feedback and Q&A sent to device

[1125] Specific behavior:

[1126] The server generates an HTTP response like this and sends it to the device:

[1127] HTTP / 1.1 200 OK

[1128] Content-Type: application / json

[1129] Content-Length: 345

[1130] {

[1131] "feedback": "The presentation is clearly structured and easy to understand...",

[1132] "qna": [

[1133] {"question": "Please explain the basic concepts of AI in more detail.", "answer": "..."},

[1134] {"question": "Please give some specific examples of ongoing research.", "answer": "..."}

[1135] ]

[1136] }

[1137] Step 7:

[1138] The device displays the received feedback and Q&A to the user in a visually easy-to-understand format using a user interface.

[1139] input:

[1140] Server-submitted feedback and questions

[1141] output:

[1142] Feedback and Q&A displayed to the user

[1143] Specific behavior:

[1144] The terminal generates an interface that displays the data as follows:

[1145] feedback:

[1146] "The presentation is clearly structured and easy to understand. However, adding more concrete examples would have helped to hold the audience's interest..."

[1147] Q&A:

[1148] Question 1: Could you please explain the basic concepts of AI in more detail?

[1149] Question 2: Can you give some specific examples of ongoing research?

[1150] (Application example 1)

[1151] 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."

[1152] In the past, it was not easy to effectively introduce new products and services in presentations at physical stores. It was especially difficult for inexperienced employees to deliver accurate presentations and respond promptly to questions and answers on the spot. Furthermore, the lack of preparation for immediate feedback and Q&A sessions led to inconsistent presentation quality.

[1153] 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.

[1154] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data and generating feedback regarding the presentation, means for generating questions and answers based on the text data, means for providing the generated feedback and questions and answers to the user, means for generating feedback to improve the effectiveness of the presentation, and means for receiving feedback in real time during the presentation, thereby enabling employees to improve the quality of their presentations, receive immediate feedback, and prepare for questions and answers.

[1155] A "user" is an individual or group that uses the system to input text data of the presentation content.

[1156] "Presentation content" refers to information and data presented as a presentation, and is primarily entered in text format.

[1157] "Text data" refers to character string data entered by the user, and includes specific sentences and explanations of the content of the presentation.

[1158] The "server" is a central processing unit that analyzes the received text data, generates feedback and questions and answers, and sends them to the terminal.

[1159] "Analysis" is the process of understanding the content of text data and evaluating and breaking down that content using natural language processing techniques.

[1160] "Feedback" includes evaluations and advice regarding the content, structure, and areas for improvement of the presentation, and is provided to the user.

[1161] "Questions and Answers" are anticipated questions and answers related to the presentation content, and are provided to help users prepare.

[1162] "Real-time" refers to the time period in which processing and feedback are immediate, and applies during a user's presentation.

[1163] "Presentation effectiveness" refers to the success of a user's presentation and its ability to gain the understanding and interest of the audience.

[1164] A "terminal" is a device through which a user inputs text data, sends it to the server, and displays and receives feedback and questions and answers.

[1165] A "large-scale language model" is a type of artificial intelligence trained from large amounts of text data, and is a model for analyzing and generating natural language.

[1166] The system for implementing this invention receives text data of presentation content entered by a user, analyzes it, and automatically generates feedback and Q&A. This system functions as a support tool for users to make their presentations more effective.

[1167] System Configuration

[1168] The system consists of the following main modules:

[1169] 1. Data receiving module: Receives the text data of the presentation entered by the user into the terminal.

[1170] 2. Data transmission module: The terminal transmits the received text data of the announcement to the server.

[1171] 3. Data analysis module: The server analyzes the received text data and generates feedback on the presentation and Q&A using natural language processing techniques and large-scale language models (e.g., OpenAI GPT-3).

[1172] 4. Feedback generation module: Based on the presentation content, specific feedback is generated to improve the quality of the presentation.

[1173] 5. Q&A generation module: Generates anticipated questions and answers based on the presentation content.

[1174] 6. Real-time feedback module: Provides real-time feedback during presentations.

[1175] 7. Data transmission module: The generated feedback and questions and answers are transmitted to the terminal and provided to the user.

[1176] Hardware and Software

[1177] Hardware: The system consists of a device used by the user (such as a smartphone or tablet) and a server that performs analysis and generation processing. The device has a user interface and data communication functions.

[1178] Software: The system includes modules for receiving, sending, and analyzing text data, generating feedback and Q&A, and providing real-time feedback. These modules are implemented in programming languages ​​such as Python and JavaScript. Large-scale language models such as OpenAI GPT-3 are used for analysis.

[1179] System Operation

[1180] 1. Text data input by the user: The user inputs the text data of the presentation using a dedicated application on their smartphone.

[1181] 2. Sending and receiving data: The entered text data is sent from the terminal to the server via the network.

[1182] 3. Data analysis and generation: The server analyzes the text data using a large-scale language model such as OpenAI GPT-3 and generates presentation feedback and Q&A.

[1183] 4. Providing feedback and Q&A: The generated feedback and Q&A are sent back to the terminal via the network and provided to the user, who can use this information to improve the presentation content.

[1184] 5. Providing real-time feedback: If real-time feedback is required during a presentation, the information is sent immediately from the server to the terminal and provided to the user.

[1185] Specific examples

[1186] For example, if a user enters the following presentation content:

[1187] "We'll introduce the new smartphone features. First, we'll talk about improved camera performance. Second, we'll talk about improved battery life. And finally, we'll talk about new software features."

[1188] Based on this text data, the server analyzes it and generates feedback and questions like the following:

[1189] feedback:

[1190] The presentation is well-structured, but it would be more effective if it included concrete use cases and a more detailed explanation of the new software features.

[1191] Q&A:

[1192] Question 1: What exactly are the improvements to camera performance?

[1193] Question 2: How much longer does the battery life increase?

[1194] Question 3: What benefits do the new software features provide?

[1195] This process allows users to receive real-time feedback and improve the quality of their presentations.

[1196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1197] Step 1:

[1198] The user inputs the presentation content as text data using a dedicated application.

[1199] Input: The user enters the presentation content in text format.

[1200] Output: The text data is saved to the device.

[1201] Specific operation: The user launches a dedicated application on their smartphone and enters the presentation content into the input form.

[1202] Step 2:

[1203] The terminal transmits the input text data to the server.

[1204] Input: Text data entered by the user.

[1205] Output: The text data is sent over the network to the server.

[1206] Specific operation: The device sends the entered text data to the server via internet communication, where the data is encrypted for security reasons.

[1207] Step 3:

[1208] The server analyzes the received text data and generates feedback and questions and answers.

[1209] Input: Text data sent from the terminal.

[1210] Output: Feedback and Q&A are generated.

[1211] How it works: The server analyzes the text data using a large-scale language model (e.g., OpenAI GPT-3). This analysis uses natural language processing techniques. Based on the analysis results, it generates an evaluation of the presentation, feedback on areas for improvement, and related Q&A.

[1212] Step 4:

[1213] After generating the feedback and questions and answers, the server sends them to the terminal.

[1214] Input: Generated feedback and questions and answers.

[1215] Output: Feedback and Q&A are sent to the terminal.

[1216] Specific operation: The server sends the generated feedback and Q&A to the user's terminal via the network.

[1217] Step 5:

[1218] The terminal displays the received feedback and questions and answers to the user.

[1219] Input: Feedback and questions sent by the server.

[1220] Output: Feedback and questions are displayed visually to the user.

[1221] Specific operation: The device displays the received feedback and Q&A on the user interface of a dedicated application, allowing the user to view the feedback and prepare for potential questions and improve their presentation.

[1222] Step 6:

[1223] Provide real-time feedback during presentations.

[1224] Input: User presentation data collected in real time.

[1225] Output: Real-time feedback is provided to the user.

[1226] Specific operation: During a presentation, the device transmits the user's presentation content and progress to the server in real time, and the server immediately analyzes it using a large-scale language model. Based on the analysis results, feedback is generated in real time and sent to the device for display.

[1227] 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.

[1228] The present invention relates to a system that allows users to input text data of their presentations, automatically generates feedback and Q&A based on the data, and further adjusts the content by recognizing the user's emotions. This system is an effective tool for helping users evaluate and improve their presentations and providing feedback that takes into account the user's emotional state.

[1229] Basic system configuration

[1230] The user inputs their speech content into their device and then activates an emotion engine to recognize the user's emotional state. The device then sends this data to a server. The server receives the input text data and emotion data and analyzes the data using a large-scale language model (LLM). After analysis, the server generates feedback for the user and questions and answers related to the speech content. The generated feedback and questions and answers are also adjusted based on the user's emotional state. The generated feedback and questions and answers are then sent back to the device, which displays them to the user.

[1231] Program Overview

[1232] The program of this system consists of the following main modules:

[1233] 1. Data receiving module: Receives the text data and emotion data of the presentation entered by the user.

[1234] 2. Emotion Recognition Module: Analyzes user emotions in real time and collects the data.

[1235] 3. Data analysis module: Analyzes the received text data and sentiment data and generates feedback and questions and answers.

[1236] 4. Feedback generation module: Generates specific feedback based on the announcement and user sentiment.

[1237] 5. Question and Answer Generation Module: Generates relevant questions and answers based on the presentation content and sentiment data.

[1238] 6. Data transmission module: Sends the generated feedback and questions and answers to the user.

[1239] Processing Description

[1240] The user inputs the text data of the presentation. The user uses a dedicated input form or text editor to input the content of the presentation in text format into the terminal. In some cases, the user also wears a device for emotion recognition.

[1241] The device sends the entered text data and emotion data to the server. When the user completes the input and clicks the send button, the device sends this data to the server via the network.

[1242] The server receives the text data and emotion data. The server successfully receives the data sent from the device and prepares it for analysis.

[1243] The server analyzes the text data and emotion data. The server uses a large-scale language model to understand and analyze the content of the text data and emotion data. This analysis process is carried out using natural language processing technology and emotion recognition technology.

[1244] The server generates feedback based on the analysis results, including an evaluation of the presentation content and suggestions for improvement. By taking emotional data into account, the server generates content that takes into account the user's emotional state.

[1245] The server generates questions and answers based on text data and emotion data. The server automatically generates possible questions and answers related to the presentation content and emotion data. This generation process also uses large-scale language models and emotion recognition technology.

[1246] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[1247] The terminal displays the feedback and Q&A to the user. The terminal analyzes the data received from the server and displays it in a format that is easy for the user to view.

[1248] Specific examples

[1249] For example, if a user enters the following announcement:

[1250] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1251] Meanwhile, the emotion engine monitors the user's stress level and emotional state in real time, collecting data. The server receives and analyzes this text and emotion data. Based on the analysis, feedback and questions are generated, such as:

[1252] feedback:

[1253] The presentation's structure is clear and easy to understand. However, adding more specific examples would help capture the audience's interest. It would also be good to provide a more detailed explanation of future prospects. Furthermore, the emotional data suggests that you seem a little nervous, so we recommend taking a deep breath and relaxing.

[1254] Q&A:

[1255] Question 1: Could you please explain the basic concepts of AI in more detail?

[1256] Question 2: Can you give some specific examples of ongoing research?

[1257] Question 3: How do you think future advances in AI technology will affect society?

[1258] As soon as users receive this feedback, they can take the points for improvement into account and revise their presentation content. By preparing answers for questions, they can approach their actual presentation with greater confidence. Furthermore, based on emotional feedback, they can manage their own psychological state as they practice.

[1259] The processing flow will be explained below.

[1260] Step 1:

[1261] The user inputs the text data of the presentation. The user inputs the content of the presentation into the terminal using a dedicated input form or text editor. In addition, devices such as the camera and microphone are enabled for emotion recognition.

[1262] Step 2:

[1263] The terminal transmits the input text data and emotion data to the server. When the user clicks the "Send" button, the terminal transmits the text data and initial emotion data to the server via the network.

[1264] Step 3:

[1265] The server receives the text data and emotion data. The server successfully receives the data sent from the device and prepares for analysis.

[1266] Step 4:

[1267] The server analyzes the text data and uses a large-scale language model to analyze the content of the received text data and generate specific feedback about the presentation.

[1268] Step 5:

[1269] The server analyzes the emotional data. The server uses an emotion recognition engine to analyze the user's emotional state (tension, anxiety, joy, etc.). The analysis results include stress levels and emotional fluctuations.

[1270] Step 6:

[1271] The server generates feedback based on the analysis results. The server combines the results of the text data analysis and the emotional data analysis to create detailed feedback on the user's presentation. The feedback includes specific suggestions for improvement and instructions that take into account the user's emotional state.

[1272] Step 7:

[1273] The server generates questions and answers based on text data and emotional data. The server automatically generates anticipated questions and answers related to the presentation content, and these responses also take emotional data into consideration.

[1274] Step 8:

[1275] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[1276] Step 9:

[1277] The terminal displays the feedback and Q&A to the user. The terminal analyzes the feedback and Q&A received from the server and displays them in a format that is easy for the user to view.

[1278] Step 10:

[1279] Users can revise and improve their presentation content based on feedback and Q&A. Users can refer to the feedback they receive to improve their presentation content and manage their own psychological state based on emotional feedback.

[1280] Example 2

[1281] 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."

[1282] Conventional presentation support systems generate feedback and Q&A without considering the user's emotional state, making it difficult for users to make effective corrections or preparations when they are feeling nervous or stressed. Furthermore, the content of Q&A is simply generated based on the presentation content, which can lead to a lack of depth.

[1283] 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.

[1284] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data to generate feedback regarding the presentation, means for generating questions and answers based on the text data, means for adjusting the content of the feedback and questions and answers based on the emotional state of the user, and means for providing the generated feedback and questions and answers to the user, thereby making it possible to provide effective and specific feedback and questions and answers while taking the emotional state of the user into consideration.

[1285] A "user" is someone who uses the system to input presentation content and receive feedback and questions.

[1286] "Presentation content" is text data of a presentation or speech entered by the user.

[1287] "Text data" refers to the content of a presentation expressed as text information.

[1288] The term "means" refers to a specific device or module provided for performing a predetermined function.

[1289] "Analysis" is the process of understanding the content of input data and generating appropriate feedback and questions and answers.

[1290] "Feedback" is information that includes evaluation of the user's presentation and advice on how to improve it.

[1291] "Questions and Answers" is information that includes anticipated questions and answers based on the content of the presentation.

[1292] "Emotional state" refers to the user's psychological state and emotional response, including, for example, the degree of tension or stress.

[1293] A "large-scale language analysis model" is a large-scale machine learning model used for natural language processing, which learns language patterns and meanings from large amounts of text data.

[1294] An "information terminal" is an electronic device that users use to input presentation content and receive feedback and questions.

[1295] The "main control unit" is a central unit that analyzes the received data, generates feedback and questions and answers, and sends them to the information terminals.

[1296] This invention relates to a system that allows users to input text data of their presentations, automatically generates feedback and Q&A based on the data, and further adjusts the content by recognizing the user's emotions. This system is an effective tool for helping users evaluate and improve their presentations and providing feedback that takes into account the user's emotional state.

[1297] Basic system configuration

[1298] A user inputs a speech into his / her information terminal, and then activates a device for recognizing the user's emotional state. The terminal transmits this data to a main control device. The main control device receives the input text data and emotional data and analyzes the data using a large-scale language analysis model. After analysis, the main control device generates feedback for the user and questions and answers related to the speech. The generated feedback and questions and answers are also adjusted based on the user's emotional state. The generated feedback and questions and answers are then transmitted back to the terminal, which displays them to the user.

[1299] Examples of hardware and software:

[1300] Input device: The device that the user uses to input their presentation (e.g., personal computer, tablet, smartphone)

[1301] Emotion recognizers: devices that recognize the user's emotional state (e.g., heart rate monitors, wearable devices)

[1302] Master controller: A server or cloud service (e.g., a cloud computing platform) that analyzes input data and generates feedback and questions and answers.

[1303] Large language analysis models: AI models for analyzing natural language data (e.g., large-scale language models)

[1304] Communication network: A network (e.g., the Internet) for transmitting and receiving data between the terminal and the main control unit.

[1305] Specific operation explanation

[1306] The user inputs the contents of the presentation in text format into the terminal using a dedicated input form or a text editor (e.g., general word processing software). For emotion recognition, the user wears a device such as a heart rate monitor and connects it to the information terminal.

[1307] The terminal collects the input text data and emotion data and transmits them to the main control device via a network (e.g., the Internet).

[1308] The master controller uses large language analysis models to analyze the received text and emotion data. This process leverages natural language processing techniques (e.g., AI models) and emotion recognition techniques.

[1309] The master controller generates feedback based on the analysis, including a rating of the presentation and specific suggestions for improvement, and adjusts the feedback based on the user's emotional state.

[1310] The master controller generates relevant questions and answers based on the text data and the emotion data, which include possible questions related to the presentation and their answers.

[1311] The main control device sends the generated feedback and questions and answers back to the terminal again via the network.

[1312] The terminal displays the feedback and Q&A received from the main control device, allowing the user to revise their presentation based on the feedback and prepare answers for Q&A. Furthermore, the emotional feedback allows the user to manage their own psychological state as they practice.

[1313] Specific examples

[1314] For example, if a user enters the following announcement:

[1315] text

[1316] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1317] Meanwhile, the emotion engine monitors the user's stress level and heart rate in real time and collects data. The master controller receives and analyzes this text and emotion data. Based on the analysis results, feedback and Q&A are generated, such as:

[1318] feedback:

[1319] text

[1320] The presentation is clearly structured and easy to understand. However, adding more specific examples would help capture the audience's interest. It would also be good to provide more details about future prospects. Furthermore, the emotional data suggests that you seem a little nervous, so we recommend taking a deep breath and relaxing.

[1321] Q&A:

[1322] text

[1323] Question 1: Could you please explain the basic concepts of AI in more detail?

[1324] Question 2: Can you give some specific examples of ongoing research?

[1325] Question 3: How do you think future advances in AI technology will affect society?

[1326] Prompt Sentence Examples

[1327] Examples of prompts to input to a generative AI model might include:

[1328] text

[1329] The user entered the following announcement:

[1330] "Today, I will be presenting on the latest developments in AI technology. First, I will explain the basic concepts of AI, then talk about ongoing research and commercial applications. Finally, I will consider what the future holds."

[1331] Please generate feedback on this presentation, along with related questions and answers. Please also consider user sentiment data (high tension).

[1332] In this way, the system automatically analyzes the content of the user's presentation and provides feedback and Q&A, helping the user to give a more effective presentation.

[1333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1334] Step 1:

[1335] The user inputs the text data of the presentation.

[1336] The user inputs the content of the presentation in text format into the terminal using a dedicated input form or a text editor (e.g., general word processing software). For emotion recognition, the user wears a device such as a heart rate monitor and connects it to the information terminal. The input data (the text of the presentation and emotion data) is sent to the terminal.

[1337] Step 2:

[1338] The terminal transmits the input text data and emotion data to the server.

[1339] The user completes the input and clicks the send button. At this point, the terminal uses the network (e.g., the Internet) to send the input data to the main control device. The input includes the text data of the announcement and the real-time emotion data obtained from the emotion device. The output is that these data are successfully sent to the server.

[1340] Step 3:

[1341] The server receives the data.

[1342] The server receives the text data and emotion data sent from the device, checks the consistency and completeness of the data, formats the input data (the text data of the announcement and the emotion data) for analysis, and outputs the formatted text data and emotion data.

[1343] Step 4:

[1344] The server analyzes the text data and the emotion data.

[1345] The server uses a large-scale language analysis model (e.g., large-scale language model) to analyze the content of text data and emotional data. It uses natural language processing technology (e.g., NLTK, SpaCy) and emotion recognition technology to break down and understand the input text sentence by sentence. The input for the analysis is organized text data and emotional data, and the output is a dataset of the analysis results.

[1346] Step 5:

[1347] The server generates feedback based on the analysis results.

[1348] Based on the analysis results, a large language analysis model is used to generate feedback on the user's post. The feedback includes an evaluation of the post and specific suggestions for improvement, and is adjusted based on the user's emotional state. The input is a dataset of the analysis results, and the output is text feedback for the user.

[1349] Step 6:

[1350] The server generates questions and answers based on the text data and the emotion data.

[1351] The server automatically generates possible questions and answers based on the presentation content and emotional data. The generation process uses large-scale language models and emotion recognition technology. The input is a dataset of analysis results, and the output is text data of the questions and answers.

[1352] Step 7:

[1353] The server transmits the generated feedback and questions and answers to the terminal.

[1354] The server returns the generated feedback and Q&A data to the terminal via the network. The input is the generated feedback and Q&A text data, and the output is that these data are successfully sent to the terminal.

[1355] Step 8:

[1356] The terminal displays feedback and questions to the user.

[1357] The terminal receives feedback and questions from the server and displays them in a format that is easy for the user to view. A web browser or a dedicated application is used here. The input is the text data of the feedback and questions received from the server, and the output is to display it for the user.

[1358] (Application example 2)

[1359] 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."

[1360] Conventional presentation feedback systems do not take the user's emotional state into account when generating feedback or Q&A, resulting in insufficient feedback when users practice presentations and inefficient improvement of presentation skills. Furthermore, because they are unable to recognize emotions in real time and adjust feedback based on the results, it is difficult to reduce the presenter's psychological burden. Similar problems occur when employees explain products, resulting in inconsistent quality of customer service.

[1361] 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.

[1362] In this invention, the server includes means for receiving text data and emotional data of the presentation content entered by the user, means for analyzing the text data and emotional data to generate feedback regarding the presentation, means for generating Q&A based on the text data and emotional data, means for providing the generated feedback and Q&A to the user, and means for adjusting the content of the feedback and Q&A based on the user's emotional state. This makes it possible to provide high-quality feedback and Q&A in real time that takes the user's emotional state into consideration, thereby improving the user's presentation skills and reducing psychological burden. It also improves the quality of customer service when employees are explaining products.

[1363] A "user" is a person who uses this system to input text data of the presentation content.

[1364] "Presentation content" refers to text data entered by the user, and refers to an explanation or report of information based on a specific theme.

[1365] "Text data" refers to character string information that a user inputs as content to be presented.

[1366] "Emotion data" refers to data that indicates the user's emotional state, and is psychological information that is acquired in real time.

[1367] "Feedback" refers to information entered by the user, including evaluations of the presentation content and suggestions for improvement.

[1368] "Questions and answers" refers to questions and corresponding answers generated based on the content of the presentation.

[1369] A "server" is a computer system that receives text data and emotion data sent by users, analyzes them, and generates feedback and questions and answers.

[1370] "Terminal" refers to a device through which a user inputs text data, transmits it to a server, and receives feedback and questions and answers from the server.

[1371] A "large-scale language model" refers to advanced algorithms and techniques that learn from large amounts of text data in natural language processing to generate and analyze text.

[1372] The "emotion engine" is a system that recognizes emotions from the user's facial expressions, tone of voice, etc., and generates that data.

[1373] This embodiment of the present invention handles the text data of the presentation content entered by the user and the user's emotional data in detail to generate feedback and Q&A for the user's presentation content, and also makes adjustments according to the user's emotional state. A specific implementation method of this system is described below.

[1374] Program Components

[1375] The system consists of the following main modules:

[1376] 1. Data receiving module:

[1377] Receive text data of the presentation content entered by the user, for example, using a dedicated input form or text editor.

[1378] 2. Emotion Recognition Module:

[1379] Emotion data is collected to analyze the user's emotions in real time. For this purpose, emotion recognition devices such as cameras and microphones are used. For example, software such as EmotionRecognizer is used.

[1380] 3. Data Analysis Module:

[1381] The received text data and emotion data are sent to a server for analysis. A large-scale language model (LLM) is used for the analysis. Possible applications include OpenAI's API.

[1382] 4. Feedback and Q&A generation module:

[1383] Feedback and Q&A are generated based on text and emotion data using a generative AI model, which is then sent from the server to the device.

[1384] 5. Data transmission module:

[1385] The generated feedback and Q&A data is sent to the user's device, for example, via an AWS S3 bucket.

[1386] Hardware and software used

[1387] Smart glasses (e.g. Google Glass):

[1388] The user wears it to input text and collect emotion recognition data.

[1389] Cameras (e.g., in smart glasses):

[1390] It captures the user's facial expressions in real time and uses them to recognize emotions.

[1391] Server (e.g. AWS):

[1392] Receives, analyzes, and generates feedback on text and emotion data.

[1393] Generative AI models (e.g., OpenAI GPT):

[1394] Analyze text and sentiment data to generate feedback and Q&A.

[1395] Program processing

[1396] The server receives the text data of the presentation and the user's emotional data sent from the device. It then analyzes the received data and generates feedback and Q&A using a generative AI model. The generated feedback and Q&A are then sent back to the device and provided to the user. The content of the feedback and Q&A is also adjusted based on the emotional data.

[1397] Specific examples

[1398] For example, if a user enters the following announcement:

[1399] Today, I'll discuss the latest technology trends. First, I'll explain the basic concepts, then I'll talk about new research and applications. Finally, I'll discuss future prospects.

[1400] During this time, the emotion engine analyzes the user's emotional state and collects data. The server receives and analyzes this text and emotion data to generate feedback and Q&A, such as:

[1401] feedback:

[1402] The presentation structure is clear, but adding more concrete examples will help keep the audience engaged. Also, the emotional data suggests that you are a little nervous, so it would be good to incorporate some relaxation techniques.

[1403] Q&A:

[1404] Question 1: What are some specific application examples of the latest technology trends?

[1405] Question 2: What research do you expect to see in the future?

[1406] Question 3: Could you please elaborate on your future outlook?

[1407] Example prompt sentence:

[1408] User's emotional state: slightly nervous

[1409] Text data:

[1410] Today, I'll discuss the latest technology trends. First, I'll explain the basic concepts, then I'll talk about new research and applications. Finally, I'll discuss future prospects.

[1411] Please generate feedback and relevant questions and answers in the following format:

[1412] feedback:

[1413] Q&A:

[1414] This invention provides high-quality feedback and Q&A in real time while taking into account the user's emotional state, enabling more effective presentation practice and customer service. By using this system, users can improve their skills while reducing their psychological burden.

[1415] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1416] Step 1:

[1417] The user inputs the text data of the presentation.

[1418] Specifically, the user inputs the content of the presentation in text format using an input device attached to the smart glasses. The input text data is then saved in the terminal.

[1419] Step 2:

[1420] Recognize the user's emotional state in real time.

[1421] While the user is making a presentation, the device's built-in camera and emotion analysis software (e.g., EmotionRecognizer) are used to analyze the user's facial expressions and tone of voice. Emotion data is generated as a result of this analysis and stored on the device.

[1422] Step 3:

[1423] The terminal transmits the text data and the emotion data to the server.

[1424] The input text data and emotion data are sent from the device to the server via a network connection, allowing the server to prepare for analysis.

[1425] Step 4:

[1426] The server analyzes the received data.

[1427] The server uses the received text data and emotion data to perform analysis using a large-scale language model (e.g., OpenAI GPT). This analysis involves understanding the content of the text data and evaluating the emotion data, and generating optimal feedback and questions and answers for the user. The inputs for the analysis are text data and emotion data, and the outputs are feedback and questions and answers.

[1428] Step 5:

[1429] The server generates feedback and questions and answers.

[1430] Based on the analysis results of the large-scale language model, the server generates specific feedback and Q&A. Using the generative AI model, it evaluates the presentation content, suggests areas for improvement, and generates anticipated Q&A. The generated feedback and Q&A are stored on the server.

[1431] Step 6:

[1432] The server transmits the generated feedback and questions and answers to the terminal.

[1433] The feedback and questions are stored on the server and sent to the terminal via the network, allowing the user to check the results in real time.

[1434] Step 7:

[1435] The terminal displays feedback and questions and answers to the user.

[1436] The device receives feedback and Q&A from the server and displays it to the user. The feedback and Q&A are displayed in real time on the smart glasses display, allowing the user to review and revise their presentation.

[1437] This completes all processing steps, allowing the user to understand the evaluation of the presentation content and areas for improvement, and prepare for a question and answer session.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] [Fourth embodiment]

[1442] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1443] 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.

[1444] 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).

[1445] 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.

[1446] 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.

[1447] 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).

[1448] 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.

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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."

[1455] The present invention relates to a system that automatically generates and provides feedback and Q&A based on the text data of a presentation input by a user. This system helps users evaluate and improve their presentation content, and is an effective tool for achieving high-quality rehearsals.

[1456] Basic system configuration

[1457] The user inputs the content of the presentation into their device. The device sends this text data to the server. The server receives the input text data and analyzes it using a large-scale language model (LLM). After analyzing, the server generates feedback for the user and questions and answers related to the presentation content. The generated feedback and questions and answers are sent back to the device, which displays them to the user.

[1458] Program Overview

[1459] The program of this system consists of the following main modules:

[1460] 1. Data receiving module: Receives text data entered by the user.

[1461] 2. Data analysis module: Analyzes the received text data and generates feedback and questions and answers.

[1462] 3. Feedback generation module: Generates specific feedback based on the presentation content.

[1463] 4. Question and Answer Generation Module: Generates questions and answers related to the presentation content.

[1464] 5. Data transmission module: Sends the generated feedback and questions and answers to the user.

[1465] Processing Description

[1466] The user inputs the text data of the presentation content, for example, using a text editor or a dedicated input form.

[1467] The terminal sends the input text data to the server, which communicates via the network and passes the text data to the server.

[1468] The server analyzes the received text data. The server uses a large-scale language model to understand and analyze the content of the text data. This analysis process is carried out using natural language processing technology.

[1469] The server generates feedback based on the analysis results, including specific evaluations and suggestions for improvement regarding the content, structure, and behavior of the presentation.

[1470] The server generates a Q&A based on the text data, which includes anticipated questions related to the presentation and their answers.

[1471] The server sends the generated feedback and Q&A to the terminal, allowing the user to receive the evaluation results in real time.

[1472] The device displays feedback and Q&A to the user, who can use this information to improve their presentation and use it for their next rehearsal.

[1473] Specific examples

[1474] For example, if a user enters the following announcement:

[1475] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1476] The server receives this text and analyzes it using a large language model, which generates feedback and questions like this:

[1477] feedback:

[1478] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[1479] Q&A:

[1480] Question 1: Could you please explain the basic concepts of AI in more detail?

[1481] Question 2: Can you give some specific examples of ongoing research?

[1482] Question 3: How do you think future advances in AI technology will affect society?

[1483] Once users receive this feedback, they can take the improvements into account and revise their presentation. By preparing answers for questions, they can feel more confident when they give their presentation.

[1484] The processing flow will be explained below.

[1485] Step 1:

[1486] The user inputs the text data of the presentation. The user uses a dedicated input form or text editor to input the content of the presentation in text format into the terminal.

[1487] Step 2:

[1488] The terminal transmits the input text data to the server. When the user completes input and clicks the send button, the terminal transmits the text data to the server via the network.

[1489] Step 3:

[1490] The server receives the text data. The server successfully receives the data sent from the device and prepares it for analysis.

[1491] Step 4:

[1492] The server analyzes the text data. Using a large-scale language model, the server analyzes the received text data based on its content and deepens its understanding of the structure and expression of the presentation.

[1493] Step 5:

[1494] The server generates feedback based on the analysis results, including an evaluation of the presentation and suggestions for improvement, such as advice on the presentation structure, adding concrete examples, and visual representation methods.

[1495] Step 6:

[1496] The server generates questions and answers based on the text data. The server automatically generates anticipated questions and answers related to the presentation content. This generation process also uses a large-scale language model.

[1497] Step 7:

[1498] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[1499] Step 8:

[1500] The terminal displays the feedback and Q&A to the user. The terminal analyzes the data received from the server and displays it in a format that is easy for the user to view.

[1501] Step 9:

[1502] Users can revise and improve their presentations based on feedback and Q&A. Users can use the feedback they receive to improve their presentations and rehearse again.

[1503] Example 1

[1504] 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."

[1505] Previously, human feedback was required to evaluate and improve presentation content, which was problematic in that it was time-consuming and labor-intensive. Furthermore, while responding to anticipated questions is also important for a high-quality rehearsal, there was no automated system for doing so appropriately. This made it difficult for presenters to prepare efficiently and effectively.

[1506] 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.

[1507] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data using a generative AI model that uses a large-scale language model to generate feedback about the presentation, means for generating questions and answers based on the text data, and means for providing the generated feedback and questions and answers to the user, thereby enabling the user to automatically receive high-quality feedback and questions and answers.

[1508] A "user" is an individual or group that inputs text data of their own presentation content.

[1509] "Text data" is data in the form of text entered by the user as the content of the presentation.

[1510] A "generative AI model" is an algorithm that uses artificial intelligence techniques, including large-scale language models, to analyze text data and generate feedback and questions and answers.

[1511] "Feedback" refers to evaluation of the presentation content and specific instructions or suggestions for improvement.

[1512] "Questions and Answers" refers to anticipated questions related to the content of the presentation and their answers.

[1513] The "server" is a central computer system that receives text data sent by users and performs analysis and generation processing using generative AI models.

[1514] A "terminal" is a device on which a user inputs the content of their presentation, sends the data to the server, and receives and displays feedback and questions from the server.

[1515] "Data analysis" is the process of inputting text data into a generative AI model, understanding and analyzing its content, and generating feedback and questions and answers.

[1516] A "prompt" refers to an instruction or question that is input into a generative AI model, and the AI ​​analyzes and generates based on this.

[1517] The present invention relates to a system that allows users to input text data of their presentation content and automatically generates and provides feedback and Q&A based on that data. This system is an effective tool for helping users evaluate and improve their presentation content and achieving high-quality rehearsals. Specific embodiments of the system are described below.

[1518] Basic system configuration

[1519] Users input their presentation content into their own devices. For example, they can use a text editor or a web application input form. This input text data flows through the system in the following steps:

[1520] The terminal sends the input text data to the server, typically as an HTTP request over the Internet.

[1521] The server uses a large-scale language model (generative AI model) to analyze the received text data, such as OpenAI's GPT-3, which utilizes natural language processing technology.

[1522] The server uses a generative AI model to analyze the content of the input text data and generate feedback, including the presentation content, structure, specific evaluations, and suggestions for improvement.

[1523] Furthermore, the server generates a question and answer session based on the text data, which includes anticipated questions related to the presentation content and their answers.

[1524] The generated feedback and questions are then sent back to the device, again via network communication.

[1525] Finally, the terminal displays the received feedback and questions and answers to the user, preferably in a visually easy-to-understand format through a user interface.

[1526] Specific examples

[1527] For example, if a user enters the following announcement:

[1528] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1529] When this input is sent from the device to the server, the server analyzes it using a large-scale language model. The prompt sentence is input to the generative AI model as follows:

[1530] Please analyze the following sentence: Today, I will be presenting the latest trends in AI technology...

[1531] The server uses this analysis to generate feedback such as:

[1532] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[1533] Additionally, the following questions and answers are generated:

[1534] Question 1: Could you please explain the basic concepts of AI in more detail?

[1535] Question 2: Can you give some specific examples of ongoing research?

[1536] Question 3: How do you think future advances in AI technology will affect society?

[1537] This feedback and Q&A is sent to the device and ultimately displayed to the user, who can use it to improve their presentation and prepare for their next rehearsal.

[1538] Thus, the present invention is a system that allows users to efficiently prepare presentations and receive high quality feedback and questions and answers.

[1539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1540] Step 1:

[1541] The user inputs the text data of the presentation using a text editor or an input form in a web application. The input data is saved as the original text of the presentation.

[1542] input:

[1543] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1544] output:

[1545] Input text data

[1546] Specific behavior:

[1547] The user types the content of the presentation into the input form.

[1548] Step 2:

[1549] The device sends the entered text data to the server. This operation is performed using network communication, specifically an HTTP POST request. The device creates a packet to send the text data to the server and sends it over the Internet.

[1550] input:

[1551] Text data entered by the user

[1552] output:

[1553] Text data sent to the server

[1554] Specific behavior:

[1555] The device generates and sends an HTTP request like this:

[1556] POST / analyze HTTP / 1.1

[1557] Host: example.com

[1558] Content-Type: application / json

[1559] Content-Length: 123

[1560] {

[1561] "text": "Today, I'll be presenting the latest developments in AI technology..."

[1562] }

[1563] Step 3:

[1564] The server analyzes the received text data. The server uses a generative AI model to generate prompts and analyze the data. In this process, the text data is input into the model to understand its content.

[1565] input:

[1566] Text data sent from the device

[1567] output:

[1568] Text data analysis results

[1569] Specific behavior:

[1570] The server inputs the following prompt into the generative AI model:

[1571] Please analyze the following sentence: Today, I will be presenting the latest trends in AI technology...

[1572] Step 4:

[1573] The server generates feedback based on the analysis results. This is the process of generating feedback statements that include specific evaluations and suggestions for improvement of the presentation content based on the analysis results obtained from the generative AI model.

[1574] input:

[1575] Text data analysis results

[1576] output:

[1577] Generated Feedback

[1578] Specific behavior:

[1579] The server generates feedback like this:

[1580] The presentation is clearly structured and easy to understand, but adding a few more concrete examples would have helped to engage the audience and perhaps provide a more detailed explanation of the future outlook.

[1581] Step 5:

[1582] The server generates a Q&A based on the text data. The Q&A consists of anticipated questions related to the presentation content and their answers, and is generated using a generative AI model.

[1583] input:

[1584] Text data analysis results

[1585] output:

[1586] Generated Q&A

[1587] Specific behavior:

[1588] The server generates a question and answer like this:

[1589] Question 1: Could you please explain the basic concepts of AI in more detail?

[1590] Question 2: Can you give some specific examples of ongoing research?

[1591] Question 3: How do you think future advances in AI technology will affect society?

[1592] Step 6:

[1593] The server sends the generated feedback and Q&A to the terminal. This operation also uses network communication and is sent as an HTTP response.

[1594] input:

[1595] Generated feedback and Q&A

[1596] output:

[1597] Feedback and Q&A sent to device

[1598] Specific behavior:

[1599] The server generates an HTTP response like this and sends it to the device:

[1600] HTTP / 1.1 200 OK

[1601] Content-Type: application / json

[1602] Content-Length: 345

[1603] {

[1604] "feedback": "The presentation is clearly structured and easy to understand...",

[1605] "qna": [

[1606] {"question": "Please explain the basic concepts of AI in more detail.", "answer": "..."},

[1607] {"question": "Please give some specific examples of ongoing research.", "answer": "..."}

[1608] ]

[1609] }

[1610] Step 7:

[1611] The device displays the received feedback and Q&A to the user in a visually easy-to-understand format using a user interface.

[1612] input:

[1613] Server-submitted feedback and questions

[1614] output:

[1615] Feedback and Q&A displayed to the user

[1616] Specific behavior:

[1617] The terminal generates an interface that displays the data as follows:

[1618] feedback:

[1619] "The presentation is clearly structured and easy to understand. However, adding more concrete examples would have helped to hold the audience's interest..."

[1620] Q&A:

[1621] Question 1: Could you please explain the basic concepts of AI in more detail?

[1622] Question 2: Can you give some specific examples of ongoing research?

[1623] (Application example 1)

[1624] 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."

[1625] In the past, it was not easy to effectively introduce new products and services in presentations at physical stores. It was especially difficult for inexperienced employees to deliver accurate presentations and respond promptly to questions and answers on the spot. Furthermore, the lack of preparation for immediate feedback and Q&A sessions led to inconsistent presentation quality.

[1626] 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.

[1627] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data and generating feedback regarding the presentation, means for generating questions and answers based on the text data, means for providing the generated feedback and questions and answers to the user, means for generating feedback to improve the effectiveness of the presentation, and means for receiving feedback in real time during the presentation, thereby enabling employees to improve the quality of their presentations, receive immediate feedback, and prepare for questions and answers.

[1628] A "user" is an individual or group that uses the system to input text data of the presentation content.

[1629] "Presentation content" refers to information and data presented as a presentation, and is primarily entered in text format.

[1630] "Text data" refers to character string data entered by the user, and includes specific sentences and explanations of the content of the presentation.

[1631] The "server" is a central processing unit that analyzes the received text data, generates feedback and questions and answers, and sends them to the terminal.

[1632] "Analysis" is the process of understanding the content of text data and evaluating and breaking down that content using natural language processing techniques.

[1633] "Feedback" includes evaluations and advice regarding the content, structure, and areas for improvement of the presentation, and is provided to the user.

[1634] "Questions and Answers" are anticipated questions and answers related to the presentation content, and are provided to help users prepare.

[1635] "Real-time" refers to the time period in which processing and feedback are immediate, and applies during a user's presentation.

[1636] "Presentation effectiveness" refers to the success of a user's presentation and its ability to gain the understanding and interest of the audience.

[1637] A "terminal" is a device through which a user inputs text data, sends it to the server, and displays and receives feedback and questions and answers.

[1638] A "large-scale language model" is a type of artificial intelligence trained from large amounts of text data, and is a model for analyzing and generating natural language.

[1639] The system for implementing this invention receives text data of presentation content entered by a user, analyzes it, and automatically generates feedback and Q&A. This system functions as a support tool for users to make their presentations more effective.

[1640] System Configuration

[1641] The system consists of the following main modules:

[1642] 1. Data receiving module: Receives the text data of the presentation entered by the user into the terminal.

[1643] 2. Data transmission module: The terminal transmits the received text data of the announcement to the server.

[1644] 3. Data analysis module: The server analyzes the received text data and generates feedback on the presentation and Q&A using natural language processing techniques and large-scale language models (e.g., OpenAI GPT-3).

[1645] 4. Feedback generation module: Based on the presentation content, specific feedback is generated to improve the quality of the presentation.

[1646] 5. Q&A generation module: Generates anticipated questions and answers based on the presentation content.

[1647] 6. Real-time feedback module: Provides real-time feedback during presentations.

[1648] 7. Data transmission module: The generated feedback and questions and answers are transmitted to the terminal and provided to the user.

[1649] Hardware and Software

[1650] Hardware: The system consists of a device used by the user (such as a smartphone or tablet) and a server that performs analysis and generation processing. The device has a user interface and data communication functions.

[1651] Software: The system includes modules for receiving, sending, and analyzing text data, generating feedback and Q&A, and providing real-time feedback. These modules are implemented in programming languages ​​such as Python and JavaScript. Large-scale language models such as OpenAI GPT-3 are used for analysis.

[1652] System Operation

[1653] 1. Text data input by the user: The user inputs the text data of the presentation using a dedicated application on their smartphone.

[1654] 2. Sending and receiving data: The entered text data is sent from the terminal to the server via the network.

[1655] 3. Data analysis and generation: The server analyzes the text data using a large-scale language model such as OpenAI GPT-3 and generates presentation feedback and Q&A.

[1656] 4. Providing feedback and Q&A: The generated feedback and Q&A are sent back to the terminal via the network and provided to the user, who can use this information to improve the presentation content.

[1657] 5. Providing real-time feedback: If real-time feedback is required during a presentation, the information is sent immediately from the server to the terminal and provided to the user.

[1658] Specific examples

[1659] For example, if a user enters the following presentation content:

[1660] "We'll introduce the new smartphone features. First, we'll talk about improved camera performance. Second, we'll talk about improved battery life. And finally, we'll talk about new software features."

[1661] Based on this text data, the server analyzes it and generates feedback and questions like the following:

[1662] feedback:

[1663] The presentation is well-structured, but it would be more effective if it included concrete use cases and a more detailed explanation of the new software features.

[1664] Q&A:

[1665] Question 1: What exactly are the improvements to camera performance?

[1666] Question 2: How much longer does the battery life increase?

[1667] Question 3: What benefits do the new software features provide?

[1668] This process allows users to receive real-time feedback and improve the quality of their presentations.

[1669] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1670] Step 1:

[1671] The user inputs the presentation content as text data using a dedicated application.

[1672] Input: The user enters the presentation content in text format.

[1673] Output: The text data is saved to the device.

[1674] Specific operation: The user launches a dedicated application on their smartphone and enters the presentation content into the input form.

[1675] Step 2:

[1676] The terminal transmits the input text data to the server.

[1677] Input: Text data entered by the user.

[1678] Output: The text data is sent over the network to the server.

[1679] Specific operation: The device sends the entered text data to the server via internet communication, where the data is encrypted for security reasons.

[1680] Step 3:

[1681] The server analyzes the received text data and generates feedback and questions and answers.

[1682] Input: Text data sent from the terminal.

[1683] Output: Feedback and Q&A are generated.

[1684] How it works: The server analyzes the text data using a large-scale language model (e.g., OpenAI GPT-3). This analysis uses natural language processing techniques. Based on the analysis results, it generates an evaluation of the presentation, feedback on areas for improvement, and related Q&A.

[1685] Step 4:

[1686] After generating the feedback and questions and answers, the server sends them to the terminal.

[1687] Input: Generated feedback and questions and answers.

[1688] Output: Feedback and Q&A are sent to the terminal.

[1689] Specific operation: The server sends the generated feedback and Q&A to the user's terminal via the network.

[1690] Step 5:

[1691] The terminal displays the received feedback and questions and answers to the user.

[1692] Input: Feedback and questions sent by the server.

[1693] Output: Feedback and questions are displayed visually to the user.

[1694] Specific operation: The device displays the received feedback and Q&A on the user interface of a dedicated application, allowing the user to view the feedback and prepare for potential questions and improve their presentation.

[1695] Step 6:

[1696] Provide real-time feedback during presentations.

[1697] Input: User presentation data collected in real time.

[1698] Output: Real-time feedback is provided to the user.

[1699] Specific operation: During a presentation, the device transmits the user's presentation content and progress to the server in real time, and the server immediately analyzes it using a large-scale language model. Based on the analysis results, feedback is generated in real time and sent to the device for display.

[1700] 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.

[1701] The present invention relates to a system that allows users to input text data of their presentations, automatically generates feedback and Q&A based on the data, and further adjusts the content by recognizing the user's emotions. This system is an effective tool for helping users evaluate and improve their presentations and providing feedback that takes into account the user's emotional state.

[1702] Basic system configuration

[1703] The user inputs their speech content into their device and then activates an emotion engine to recognize the user's emotional state. The device then sends this data to a server. The server receives the input text data and emotion data and analyzes the data using a large-scale language model (LLM). After analysis, the server generates feedback for the user and questions and answers related to the speech content. The generated feedback and questions and answers are also adjusted based on the user's emotional state. The generated feedback and questions and answers are then sent back to the device, which displays them to the user.

[1704] Program Overview

[1705] The program of this system consists of the following main modules:

[1706] 1. Data receiving module: Receives the text data and emotion data of the presentation entered by the user.

[1707] 2. Emotion Recognition Module: Analyzes user emotions in real time and collects the data.

[1708] 3. Data analysis module: Analyzes the received text data and sentiment data and generates feedback and questions and answers.

[1709] 4. Feedback generation module: Generates specific feedback based on the announcement and user sentiment.

[1710] 5. Question and Answer Generation Module: Generates relevant questions and answers based on the presentation content and sentiment data.

[1711] 6. Data transmission module: Sends the generated feedback and questions and answers to the user.

[1712] Processing Description

[1713] The user inputs the text data of the presentation. The user uses a dedicated input form or text editor to input the content of the presentation in text format into the terminal. In some cases, the user also wears a device for emotion recognition.

[1714] The device sends the entered text data and emotion data to the server. When the user completes the input and clicks the send button, the device sends this data to the server via the network.

[1715] The server receives the text data and emotion data. The server successfully receives the data sent from the device and prepares it for analysis.

[1716] The server analyzes the text data and emotion data. The server uses a large-scale language model to understand and analyze the content of the text data and emotion data. This analysis process is carried out using natural language processing technology and emotion recognition technology.

[1717] The server generates feedback based on the analysis results, including an evaluation of the presentation content and suggestions for improvement. By taking emotional data into account, the server generates content that takes into account the user's emotional state.

[1718] The server generates questions and answers based on text data and emotion data. The server automatically generates possible questions and answers related to the presentation content and emotion data. This generation process also uses large-scale language models and emotion recognition technology.

[1719] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[1720] The terminal displays the feedback and Q&A to the user. The terminal analyzes the data received from the server and displays it in a format that is easy for the user to view.

[1721] Specific examples

[1722] For example, if a user enters the following announcement:

[1723] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1724] Meanwhile, the emotion engine monitors the user's stress level and emotional state in real time, collecting data. The server receives and analyzes this text and emotion data. Based on the analysis, feedback and questions are generated, such as:

[1725] feedback:

[1726] The presentation's structure is clear and easy to understand. However, adding more specific examples would help capture the audience's interest. It would also be good to provide a more detailed explanation of future prospects. Furthermore, the emotional data suggests that you seem a little nervous, so we recommend taking a deep breath and relaxing.

[1727] Q&A:

[1728] Question 1: Could you please explain the basic concepts of AI in more detail?

[1729] Question 2: Can you give some specific examples of ongoing research?

[1730] Question 3: How do you think future advances in AI technology will affect society?

[1731] As soon as users receive this feedback, they can take the points for improvement into account and revise their presentation content. By preparing answers for questions, they can approach their actual presentation with greater confidence. Furthermore, based on emotional feedback, they can manage their own psychological state as they practice.

[1732] The processing flow will be explained below.

[1733] Step 1:

[1734] The user inputs the text data of the presentation. The user inputs the content of the presentation into the terminal using a dedicated input form or text editor. In addition, devices such as the camera and microphone are enabled for emotion recognition.

[1735] Step 2:

[1736] The terminal transmits the input text data and emotion data to the server. When the user clicks the "Send" button, the terminal transmits the text data and initial emotion data to the server via the network.

[1737] Step 3:

[1738] The server receives the text data and emotion data. The server successfully receives the data sent from the device and prepares for analysis.

[1739] Step 4:

[1740] The server analyzes the text data and uses a large-scale language model to analyze the content of the received text data and generate specific feedback about the presentation.

[1741] Step 5:

[1742] The server analyzes the emotional data. The server uses an emotion recognition engine to analyze the user's emotional state (tension, anxiety, joy, etc.). The analysis results include stress levels and emotional fluctuations.

[1743] Step 6:

[1744] The server generates feedback based on the analysis results. The server combines the results of the text data analysis and the emotional data analysis to create detailed feedback on the user's presentation. The feedback includes specific suggestions for improvement and instructions that take into account the user's emotional state.

[1745] Step 7:

[1746] The server generates questions and answers based on text data and emotional data. The server automatically generates anticipated questions and answers related to the presentation content, and these responses also take emotional data into consideration.

[1747] Step 8:

[1748] The server sends the generated feedback and Q&A to the terminal, and the server sends the generated data back to the terminal via the network.

[1749] Step 9:

[1750] The terminal displays the feedback and Q&A to the user. The terminal analyzes the feedback and Q&A received from the server and displays them in a format that is easy for the user to view.

[1751] Step 10:

[1752] Users can revise and improve their presentation content based on feedback and Q&A. Users can refer to the feedback they receive to improve their presentation content and manage their own psychological state based on emotional feedback.

[1753] Example 2

[1754] 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."

[1755] Conventional presentation support systems generate feedback and Q&A without considering the user's emotional state, making it difficult for users to make effective corrections or preparations when they are feeling nervous or stressed. Furthermore, the content of Q&A is simply generated based on the presentation content, which can lead to a lack of depth.

[1756] 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.

[1757] In this invention, the server includes means for receiving text data of the presentation content entered by the user, means for analyzing the text data to generate feedback regarding the presentation, means for generating questions and answers based on the text data, means for adjusting the content of the feedback and questions and answers based on the emotional state of the user, and means for providing the generated feedback and questions and answers to the user, thereby making it possible to provide effective and specific feedback and questions and answers while taking the emotional state of the user into consideration.

[1758] A "user" is someone who uses the system to input presentation content and receive feedback and questions.

[1759] "Presentation content" is text data of a presentation or speech entered by the user.

[1760] "Text data" refers to the content of a presentation expressed as text information.

[1761] The term "means" refers to a specific device or module provided for performing a predetermined function.

[1762] "Analysis" is the process of understanding the content of input data and generating appropriate feedback and questions and answers.

[1763] "Feedback" is information that includes evaluation of the user's presentation and advice on how to improve it.

[1764] "Questions and Answers" is information that includes anticipated questions and answers based on the content of the presentation.

[1765] "Emotional state" refers to the user's psychological state and emotional response, including, for example, the degree of tension or stress.

[1766] A "large-scale language analysis model" is a large-scale machine learning model used for natural language processing, which learns language patterns and meanings from large amounts of text data.

[1767] An "information terminal" is an electronic device that users use to input presentation content and receive feedback and questions.

[1768] The "main control unit" is a central unit that analyzes the received data, generates feedback and questions and answers, and sends them to the information terminals.

[1769] This invention relates to a system that allows users to input text data of their presentations, automatically generates feedback and Q&A based on the data, and further adjusts the content by recognizing the user's emotions. This system is an effective tool for helping users evaluate and improve their presentations and providing feedback that takes into account the user's emotional state.

[1770] Basic system configuration

[1771] A user inputs a speech into his / her information terminal, and then activates a device for recognizing the user's emotional state. The terminal transmits this data to a main control device. The main control device receives the input text data and emotional data and analyzes the data using a large-scale language analysis model. After analysis, the main control device generates feedback for the user and questions and answers related to the speech. The generated feedback and questions and answers are also adjusted based on the user's emotional state. The generated feedback and questions and answers are then transmitted back to the terminal, which displays them to the user.

[1772] Examples of hardware and software:

[1773] Input device: The device that the user uses to input their presentation (e.g., personal computer, tablet, smartphone)

[1774] Emotion recognizers: devices that recognize the user's emotional state (e.g., heart rate monitors, wearable devices)

[1775] Master controller: A server or cloud service (e.g., a cloud computing platform) that analyzes input data and generates feedback and questions and answers.

[1776] Large language analysis models: AI models for analyzing natural language data (e.g., large-scale language models)

[1777] Communication network: A network (e.g., the Internet) for transmitting and receiving data between the terminal and the main control unit.

[1778] Specific operation explanation

[1779] The user inputs the contents of the presentation in text format into the terminal using a dedicated input form or a text editor (e.g., general word processing software). For emotion recognition, the user wears a device such as a heart rate monitor and connects it to the information terminal.

[1780] The terminal collects the input text data and emotion data and transmits them to the main control device via a network (e.g., the Internet).

[1781] The master controller uses large language analysis models to analyze the received text and emotion data. This process leverages natural language processing techniques (e.g., AI models) and emotion recognition techniques.

[1782] The master controller generates feedback based on the analysis, including a rating of the presentation and specific suggestions for improvement, and adjusts the feedback based on the user's emotional state.

[1783] The master controller generates relevant questions and answers based on the text data and the emotion data, which include possible questions related to the presentation and their answers.

[1784] The main control device sends the generated feedback and questions and answers back to the terminal again via the network.

[1785] The terminal displays the feedback and Q&A received from the main control device, allowing the user to revise their presentation based on the feedback and prepare answers for Q&A. Furthermore, the emotional feedback allows the user to manage their own psychological state as they practice.

[1786] Specific examples

[1787] For example, if a user enters the following announcement:

[1788] text

[1789] Today, I will talk about the latest developments in AI technology. First, I will explain the basic concepts of AI, then I will talk about ongoing research and commercial applications. Finally, I will consider the future outlook.

[1790] Meanwhile, the emotion engine monitors the user's stress level and heart rate in real time and collects data. The master controller receives and analyzes this text and emotion data. Based on the analysis results, feedback and Q&A are generated, such as:

[1791] feedback:

[1792] text

[1793] The presentation is clearly structured and easy to understand. However, adding more specific examples would help capture the audience's interest. It would also be good to provide more details about future prospects. Furthermore, the emotional data suggests that you seem a little nervous, so we recommend taking a deep breath and relaxing.

[1794] Q&A:

[1795] text

[1796] Question 1: Could you please explain the basic concepts of AI in more detail?

[1797] Question 2: Can you give some specific examples of ongoing research?

[1798] Question 3: How do you think future advances in AI technology will affect society?

[1799] Prompt Sentence Examples

[1800] Examples of prompts to input to a generative AI model might include:

[1801] text

[1802] The user entered the following announcement:

[1803] "Today, I will be presenting on the latest developments in AI technology. First, I will explain the basic concepts of AI, then talk about ongoing research and commercial applications. Finally, I will consider what the future holds."

[1804] Please generate feedback on this presentation, along with related questions and answers. Please also consider user sentiment data (high tension).

[1805] In this way, the system automatically analyzes the content of the user's presentation and provides feedback and Q&A, helping the user to give a more effective presentation.

[1806] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1807] Step 1:

[1808] The user inputs the text data of the presentation.

[1809] The user inputs the content of the presentation in text format into the terminal using a dedicated input form or a text editor (e.g., general word processing software). For emotion recognition, the user wears a device such as a heart rate monitor and connects it to the information terminal. The input data (the text of the presentation and emotion data) is sent to the terminal.

[1810] Step 2:

[1811] The terminal transmits the input text data and emotion data to the server.

[1812] The user completes the input and clicks the send button. At this point, the terminal uses the network (e.g., the Internet) to send the input data to the main control device. The input includes the text data of the announcement and the real-time emotion data obtained from the emotion device. The output is that these data are successfully sent to the server.

[1813] Step 3:

[1814] The server receives the data.

[1815] The server receives the text data and emotion data sent from the device, checks the consistency and completeness of the data, formats the input data (the text data of the announcement and the emotion data) for analysis, and outputs the formatted text data and emotion data.

[1816] Step 4:

[1817] The server analyzes the text data and the emotion data.

[1818] The server uses a large-scale language analysis model (e.g., large-scale language model) to analyze the content of text data and emotional data. It uses natural language processing technology (e.g., NLTK, SpaCy) and emotion recognition technology to break down and understand the input text sentence by sentence. The input for the analysis is organized text data and emotional data, and the output is a dataset of the analysis results.

[1819] Step 5:

[1820] The server generates feedback based on the analysis results.

[1821] Based on the analysis results, a large language analysis model is used to generate feedback on the user's post. The feedback includes an evaluation of the post and specific suggestions for improvement, and is adjusted based on the user's emotional state. The input is a dataset of the analysis results, and the output is text feedback for the user.

[1822] Step 6:

[1823] The server generates questions and answers based on the text data and the emotion data.

[1824] The server automatically generates possible questions and answers based on the presentation content and emotional data. The generation process uses large-scale language models and emotion recognition technology. The input is a dataset of analysis results, and the output is text data of the questions and answers.

[1825] Step 7:

[1826] The server transmits the generated feedback and questions and answers to the terminal.

[1827] The server returns the generated feedback and Q&A data to the terminal via the network. The input is the generated feedback and Q&A text data, and the output is that these data are successfully sent to the terminal.

[1828] Step 8:

[1829] The terminal displays feedback and questions to the user.

[1830] The terminal receives feedback and questions from the server and displays them in a format that is easy for the user to view. A web browser or a dedicated application is used here. The input is the text data of the feedback and questions received from the server, and the output is to display it for the user.

[1831] (Application example 2)

[1832] 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."

[1833] Conventional presentation feedback systems do not take the user's emotional state into account when generating feedback or Q&A, resulting in insufficient feedback when users practice presentations and inefficient improvement of presentation skills. Furthermore, because they are unable to recognize emotions in real time and adjust feedback based on the results, it is difficult to reduce the presenter's psychological burden. Similar problems occur when employees explain products, resulting in inconsistent quality of customer service.

[1834] 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.

[1835] In this invention, the server includes means for receiving text data and emotional data of the presentation content entered by the user, means for analyzing the text data and emotional data to generate feedback regarding the presentation, means for generating Q&A based on the text data and emotional data, means for providing the generated feedback and Q&A to the user, and means for adjusting the content of the feedback and Q&A based on the user's emotional state. This makes it possible to provide high-quality feedback and Q&A in real time that takes the user's emotional state into consideration, thereby improving the user's presentation skills and reducing psychological burden. It also improves the quality of customer service when employees are explaining products.

[1836] A "user" is a person who uses this system to input text data of the presentation content.

[1837] "Presentation content" refers to text data entered by the user, and refers to an explanation or report of information based on a specific theme.

[1838] "Text data" refers to character string information that a user inputs as content to be presented.

[1839] "Emotion data" refers to data that indicates the user's emotional state, and is psychological information that is acquired in real time.

[1840] "Feedback" refers to information entered by the user, including evaluations of the presentation content and suggestions for improvement.

[1841] "Questions and answers" refers to questions and corresponding answers generated based on the content of the presentation.

[1842] A "server" is a computer system that receives text data and emotion data sent by users, analyzes them, and generates feedback and questions and answers.

[1843] "Terminal" refers to a device through which a user inputs text data, transmits it to a server, and receives feedback and questions and answers from the server.

[1844] A "large-scale language model" refers to advanced algorithms and techniques that learn from large amounts of text data in natural language processing to generate and analyze text.

[1845] The "emotion engine" is a system that recognizes emotions from the user's facial expressions, tone of voice, etc., and generates that data.

[1846] This embodiment of the present invention handles the text data of the presentation content entered by the user and the user's emotional data in detail to generate feedback and Q&A for the user's presentation content, and also makes adjustments according to the user's emotional state. A specific implementation method of this system is described below.

[1847] Program Components

[1848] The system consists of the following main modules:

[1849] 1. Data receiving module:

[1850] Receive text data of the presentation content entered by the user, for example, using a dedicated input form or text editor.

[1851] 2. Emotion Recognition Module:

[1852] Emotion data is collected to analyze the user's emotions in real time. For this purpose, emotion recognition devices such as cameras and microphones are used. For example, software such as EmotionRecognizer is used.

[1853] 3. Data Analysis Module:

[1854] The received text data and emotion data are sent to a server for analysis. A large-scale language model (LLM) is used for the analysis. Possible applications include OpenAI's API.

[1855] 4. Feedback and Q&A generation module:

[1856] Feedback and Q&A are generated based on text and emotion data using a generative AI model, which is then sent from the server to the device.

[1857] 5. Data transmission module:

[1858] The generated feedback and Q&A data is sent to the user's device, for example, via an AWS S3 bucket.

[1859] Hardware and software used

[1860] Smart glasses (e.g. Google Glass):

[1861] The user wears it to input text and collect emotion recognition data.

[1862] Cameras (e.g., in smart glasses):

[1863] It captures the user's facial expressions in real time and uses them to recognize emotions.

[1864] Server (e.g. AWS):

[1865] Receives, analyzes, and generates feedback on text and emotion data.

[1866] Generative AI models (e.g., OpenAI GPT):

[1867] Analyze text and sentiment data to generate feedback and Q&A.

[1868] Program processing

[1869] The server receives the text data of the presentation and the user's emotional data sent from the device. It then analyzes the received data and generates feedback and Q&A using a generative AI model. The generated feedback and Q&A are then sent back to the device and provided to the user. The content of the feedback and Q&A is also adjusted based on the emotional data.

[1870] Specific examples

[1871] For example, if a user enters the following announcement:

[1872] Today, I'll discuss the latest technology trends. First, I'll explain the basic concepts, then I'll talk about new research and applications. Finally, I'll discuss future prospects.

[1873] During this time, the emotion engine analyzes the user's emotional state and collects data. The server receives and analyzes this text and emotion data to generate feedback and Q&A, such as:

[1874] feedback:

[1875] The presentation structure is clear, but adding more concrete examples will help keep the audience engaged. Also, the emotional data suggests that you are a little nervous, so it would be good to incorporate some relaxation techniques.

[1876] Q&A:

[1877] Question 1: What are some specific application examples of the latest technology trends?

[1878] Question 2: What research do you expect to see in the future?

[1879] Question 3: Could you please elaborate on your future outlook?

[1880] Example prompt sentence:

[1881] User's emotional state: slightly nervous

[1882] Text data:

[1883] Today, I'll discuss the latest technology trends. First, I'll explain the basic concepts, then I'll talk about new research and applications. Finally, I'll discuss future prospects.

[1884] Please generate feedback and relevant questions and answers in the following format:

[1885] feedback:

[1886] Q&A:

[1887] This invention provides high-quality feedback and Q&A in real time while taking into account the user's emotional state, enabling more effective presentation practice and customer service. By using this system, users can improve their skills while reducing their psychological burden.

[1888] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1889] Step 1:

[1890] The user inputs the text data of the presentation.

[1891] Specifically, the user inputs the content of the presentation in text format using an input device attached to the smart glasses. The input text data is then saved in the terminal.

[1892] Step 2:

[1893] Recognize the user's emotional state in real time.

[1894] While the user is making a presentation, the device's built-in camera and emotion analysis software (e.g., EmotionRecognizer) are used to analyze the user's facial expressions and tone of voice. Emotion data is generated as a result of this analysis and stored on the device.

[1895] Step 3:

[1896] The terminal transmits the text data and the emotion data to the server.

[1897] The input text data and emotion data are sent from the device to the server via a network connection, allowing the server to prepare for analysis.

[1898] Step 4:

[1899] The server analyzes the received data.

[1900] The server uses the received text data and emotion data to perform analysis using a large-scale language model (e.g., OpenAI GPT). This analysis involves understanding the content of the text data and evaluating the emotion data, and generating optimal feedback and questions and answers for the user. The inputs for the analysis are text data and emotion data, and the outputs are feedback and questions and answers.

[1901] Step 5:

[1902] The server generates feedback and questions and answers.

[1903] Based on the analysis results of the large-scale language model, the server generates specific feedback and Q&A. Using the generative AI model, it evaluates the presentation content, suggests areas for improvement, and generates anticipated Q&A. The generated feedback and Q&A are stored on the server.

[1904] Step 6:

[1905] The server transmits the generated feedback and questions and answers to the terminal.

[1906] The feedback and questions are stored on the server and sent to the terminal via the network, allowing the user to check the results in real time.

[1907] Step 7:

[1908] The terminal displays feedback and questions and answers to the user.

[1909] The device receives feedback and Q&A from the server and displays it to the user. The feedback and Q&A are displayed in real time on the smart glasses display, allowing the user to review and revise their presentation.

[1910] This completes all processing steps, allowing the user to understand the evaluation of the presentation content and areas for improvement, and prepare for a question and answer session.

[1911] 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.

[1912] 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.

[1913] 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.

[1914] 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.

[1915] FIG. 9 is a diagram illustrating 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 actions 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.

[1916] 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.

[1917] 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).

[1918] 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.

[1919] 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."

[1920] 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.

[1921] 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).

[1922] 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.

[1923] 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.

[1924] 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.

[1925] 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.

[1926] 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.

[1927] 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.

[1928] 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.

[1929] 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.

[1930] 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.

[1931] 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.

[1932] The following is further disclosed regarding the above embodiment.

[1933] (Claim 1)

[1934] means for receiving text data of the presentation content input by the user;

[1935] means for analyzing the text data to generate feedback regarding the presentation;

[1936] means for generating a question and answer based on the text data;

[1937] means for providing said generated feedback and questions and answers to a user;

[1938] A system including:

[1939] (Claim 2)

[1940] 10. The system of claim 1, further comprising means for utilizing a large-scale language model to generate said feedback and questions and answers.

[1941] (Claim 3)

[1942] 10. The system of claim 1, further comprising a terminal including means for transmitting text data received from the user to a server, and means for receiving feedback and questions and answers from the server.

[1943] "Example 1"

[1944] (Claim 1)

[1945] means for receiving text data of the presentation content input by the user;

[1946] means for analyzing the text data to generate feedback regarding the presentation;

[1947] means for generating a question and answer based on the text data;

[1948] said analysis using a generative AI model;

[1949] means for providing said generated feedback and questions and answers to a user;

[1950] A system including:

[1951] (Claim 2)

[1952] 2. The system of claim 1, further comprising: means for transmitting text data received from the user to a server; and means for receiving feedback and questions and answers from the server.

[1953] (Claim 3)

[1954] 10. The system of claim 1, further comprising means for utilizing prompt sentences to generate said feedback and question and answer.

[1955] "Application Example 1"

[1956] (Claim 1)

[1957] means for receiving text data of the presentation content input by the user;

[1958] means for analyzing the text data to generate feedback regarding the presentation;

[1959] means for generating a question and answer based on the text data;

[1960] means for providing said generated feedback and questions and answers to a user;

[1961] a means of generating feedback to improve the effectiveness of the presentation;

[1962] A way to receive real-time feedback as you present, and

[1963] A system including:

[1964] (Claim 2)

[1965] 10. The system of claim 1, further comprising means for utilizing a large-scale language model to generate said feedback and questions and answers.

[1966] (Claim 3)

[1967] 10. The system of claim 1, further comprising a terminal including means for transmitting text data received from the user to a server, and means for receiving feedback and questions and answers from the server.

[1968] "Example 2: Combining Emotion Engines"

[1969] (Claim 1)

[1970] means for receiving text data of the presentation content input by the user;

[1971] means for analyzing the text data to generate feedback regarding the presentation;

[1972] means for generating a question and answer based on the text data;

[1973] means for adjusting the content of the feedback and Q&A based on the emotional state of the user;

[1974] means for providing said generated feedback and questions and answers to a user;

[1975] A system including:

[1976] (Claim 2)

[1977] 10. The system of claim 1, further comprising means for utilizing a large language analysis model to generate said feedback and questions and answers.

[1978] (Claim 3)

[1979] 10. The system of claim 1, further comprising an information terminal including means for transmitting text data received from the user to a master controller and means for receiving feedback and questions and answers from the master controller.

[1980] "Application example 2 when combining emotion engines"

[1981] (Claim 1)

[1982] means for receiving text data of the presentation content input by the user;

[1983] means for analyzing the text data and user sentiment to generate feedback regarding the presentation;

[1984] means for generating questions and answers based on the text data and the user's emotions;

[1985] means for providing said generated feedback and questions and answers to a user;

[1986] means for adjusting the content of the feedback and questions and answers based on the emotional state of the user;

[1987] A system including:

[1988] (Claim 2)

[1989] 10. The system of claim 1, further comprising means for utilizing a large-scale language model for generating and adjusting said feedback and questions and answers.

[1990] (Claim 3)

[1991] 10. The system of claim 1, further comprising a terminal including means for transmitting the text data and emotion data received from the user to a server, and means for receiving feedback and questions and answers from the server. [Explanation of symbols]

[1992] 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 text data of the presentation content input by the user; means for analyzing the text data to generate feedback regarding the presentation; means for generating a question and answer based on the text data; means for providing said generated feedback and questions and answers to a user; A system including:

2. The system of claim 1 further comprising means for utilizing a large-scale language model to generate said feedback and questions and answers.

3. 2. The system of claim 1, further comprising a terminal including means for transmitting text data received from said user to a server, and means for receiving feedback and questions and answers from said server.

Images