system
The system addresses the challenge of creating high-quality presentation materials by using an AI model to generate materials and provide advice, enabling efficient and effective presentation preparation.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2026-03-04
AI Technical Summary
Creating high-quality presentation materials in a short time is challenging, and the quality often depends on individual experience and skills, requiring specialized instruction that is not easily accessible.
A system that includes an input means for theme, purpose, and audience information, a generation means for automatic material creation using an AI model, a provision means for material delivery, and an advice means for presentation techniques, supporting users in preparing effective presentations.
Enables users to create high-quality presentation materials quickly and improve their presentation skills through automated material generation and comprehensive advice on storytelling, non-verbal communication, and Q&A.
Smart Images

Figure 2026035286000001_ABST
Abstract
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] The traditional process of creating and delivering a presentation requires a lot of time and effort, making it difficult to prepare high-quality presentation materials and effective presentation techniques in a short period of time. Furthermore, the quality of a presentation often depends on the presenter's individual experience and skills, which can lead to a lack of consistency. Furthermore, improving presentation skills requires specialized instruction, and a method for providing this information easily and efficiently is needed. To solve these issues, a system is needed that automatically generates presentation materials and provides comprehensive instruction on presentation techniques. [Means for solving the problem]
[0005] The present invention solves the above problem by providing a system that includes an input means for a user to input the presentation theme, purpose, target audience, and information to be provided, a generation means for generating presentation materials based on the information received from the input means, a provision means for providing the presentation materials generated by the generation means to the user, and an advice means for giving advice on presentation techniques based on the presentation materials.
[0006] Specifically, the generation unit automatically generates high-quality presentation materials using an AI model trained by presentation professionals with specialized knowledge. The advice unit supports users in delivering effective presentations by providing them with advice on storytelling, non-verbal communication, and Q&A. In this way, users can prepare high-quality presentation materials in a short period of time and acquire practical techniques.
[0007] "Input means" refers to a device or interface through which a user inputs the presentation's theme, purpose, target audience, and information to be provided.
[0008] The "generation means" is a device or program for generating presentation materials based on the information received from the input means.
[0009] The "providing means" is a device or program for providing the generated presentation materials to the user.
[0010] The "advice means" is a device or program for giving advice on presentation techniques based on presentation materials.
[0011] "Presentation materials" refers to slides and documents that visually and writtenly represent the content of a presentation.
[0012] "User" refers to an individual or organization that uses this system to create presentation materials and receive advice on presentation techniques.
[0013] "Theme" refers to the main topic or agenda of a presentation.
[0014] "Purpose" refers to the reason for giving the presentation and the goal you are trying to achieve.
[0015] "Target audience" refers to the attributes and characteristics of the audience that will listen to the presentation.
[0016] "Information to be provided" refers to the specific content and data that should be included in the presentation materials.
[0017] "AI model" refers to a model trained using artificial intelligence technology to generate presentation materials and provide advice.
[0018] "Storytelling" refers to the technique of structuring and developing a story to effectively convey information in a presentation.
[0019] "Nonverbal communication" refers to techniques for conveying information using means other than words, such as gestures, eye contact, and facial expressions.
[0020] "Q&A" refers to the process of answering questions from the audience after a presentation. [Brief explanation of the drawings]
[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION
[0022] 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.
[0023] First, the terms used in the following description will be explained.
[0024] 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).
[0025] 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.
[0026] 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.
[0027] 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.
[0028] 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."
[0029] [First embodiment]
[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.
[0031] 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.
[0032] 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).
[0033] 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.
[0034] 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.
[0035] 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.
[0036] 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.
[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0038] 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.
[0039] 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.
[0040] 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.
[0041] 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."
[0042] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses an AI model to generate presentation materials based on basic information entered by the user, and also provides comprehensive advice to improve the user's presentation techniques.
[0043] System configuration
[0044] The system consists of the following components:
[0045] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[0046] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0047] 3. AI model: An artificial intelligence model trained to generate professional presentation materials and provide advice on presentation techniques.
[0048] Program processing
[0049] The user enters basic information
[0050] Device:
[0051] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[0052] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[0053] The server generates the materials
[0054] server:
[0055] The server receives the basic information sent from the terminal.
[0056] Based on the received information, the AI model is asked to generate presentation materials.
[0057] The AI model automatically generates a slide deck based on its expert knowledge. For example, it might generate the following slide structure:
[0058] 1. Title slide (new product name and logo)
[0059] 2. Slides introducing the main features of the product
[0060] 3. Slides explaining technological superiority
[0061] 4. Market Potential Analysis Slide
[0062] 5. Summary and Next Steps
[0063] User checks and modifies the materials
[0064] Device:
[0065] The generated presentation materials are displayed on the device.
[0066] The user checks each slide and modifies or adds text, images, and graphs as necessary.
[0067] Once the edits are complete, the slide is saved and sent to the server.
[0068] server:
[0069] Receive corrected data and update presentation materials.
[0070] Updated materials will be provided to users again.
[0071] The server will give you advice on the key points of your presentation.
[0072] server:
[0073] Based on the completed presentation, the AI model generates advice on storytelling, non-verbal communication, and Q&A.
[0074] For example: how to talk through each slide, how to emphasize key points, how to move your eyes, anticipated questions and how to deal with them, etc.
[0075] Users practice and prepare
[0076] Device:
[0077] The user practices the presentation based on the advice provided.
[0078] As a concrete example, a presentation is rehearsed and advice from the server is reflected.
[0079] As described above, this system enables users to create high-quality presentation materials in a short amount of time and deliver effective presentations based on them. Each component works together to streamline the presentation preparation process and help users improve their skills.
[0080] The processing flow will be explained below.
[0081] Step 1:
[0082] The user enters basic information.
[0083] User: Log in to the device and click the Create New Presentation button.
[0084] Terminal: Display the screen for entering basic information about the presentation.
[0085] User: Enter the theme, purpose, target audience, and information to provide.
[0086] For example: Theme: "Features of the new product", Objective: "Pitching the new product to investors", Target audience: "Technology-savvy investors", Information provided: "Key product features, technological advantages, and market potential".
[0087] User: Click the "Next" button.
[0088] Step 2:
[0089] A server receives the information and generates a presentation.
[0090] Terminal: Sends the entered basic information to the server.
[0091] Server: Provides the received basic information to the AI model.
[0092] AI model: Generate presentation materials. For example, the following slide structure:
[0093] 1. Title Slide
[0094] 2. Slides introducing the main features of the product
[0095] 3. Technological advantage explanation slides
[0096] 4. Market Potential Analysis Slide
[0097] 5. Summary and Next Steps Slide
[0098] Server: Temporarily stores the generated materials and sends them to the user's device as preview data.
[0099] Step 3:
[0100] The user can review and modify the generated materials.
[0101] Device: Shows a preview of the generated presentation.
[0102] User: Review the content of each slide and select the slide they want to edit.
[0103] Terminal: Switches to edit mode and provides an interface for users to enter information to be modified or added.
[0104] For example: modify the text, add a chart, insert an image, etc.
[0105] User: Clicks the "Save" button for the slide after editing is complete.
[0106] Device: Sends the saved correction data to the server.
[0107] Step 4:
[0108] The server updates the presentation materials to reflect the corrected data.
[0109] Server: Receives the correction data sent by the user.
[0110] Server: Update the presentation materials based on the revised data.
[0111] Server: The updated presentation materials are again temporarily saved and resent to the user.
[0112] Step 5:
[0113] The server will give you advice on the key points of your presentation.
[0114] Server: The AI model analyzes the completed presentation materials.
[0115] AI model: Generates advice for each slide on how to handle storytelling, non-verbal communication, and Q&A.
[0116] For example: how to talk about each slide, how to emphasize points, how to move your eyes, anticipated questions and how to prepare for them.
[0117] Server: Sends the generated advice in text format to the user terminal.
[0118] Step 6:
[0119] Users practice and prepare.
[0120] Terminal: Displays advice sent from the server.
[0121] Users: Review the advice on each slide and practice your presentation.
[0122] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[0123] User: Make final preparations for the presentation.
[0124] These are the specific processing steps of this system. At each step, the user, terminal, and server work together to efficiently and effectively support the creation of presentation materials and preparation for presentations.
[0125] Example 1
[0126] 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."
[0127] Currently, there are many tools on the market for creating presentation materials effectively, but they have the following problems: Creating presentation materials takes time, and it is difficult to create high-quality materials in a short amount of time. Furthermore, if the user does not have specialized knowledge or skills in presentation techniques, it is difficult to give an effective presentation. As a result, there is a demand for a system that allows users to create presentation materials effectively and quickly without requiring much effort or time, and also to improve their presentation techniques.
[0128] 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.
[0129] In this invention, the server includes input means for a user to input the presentation theme, purpose, target audience, and information to be provided, generation means for generating presentation materials based on the information received from the input means, provision means for providing the presentation materials generated by the generation means to the user, advice means for providing presentation technique advice based on the presentation materials, editing means for the user to check and correct the generated presentation materials, and update means for receiving the data corrected by the editing means and updating the presentation materials, thereby enabling the user to create high-quality presentation materials in a short period of time and improve their own presentation techniques.
[0130] "Input means" refers to a device or interface that allows a user to input the theme, purpose, target audience, and information to be provided for the presentation.
[0131] The "generation means" refers to a device or software that automatically generates presentation materials based on information received from the input means.
[0132] The "providing means" refers to a device or interface for presenting and providing the presentation materials generated by the generating means to the user.
[0133] The "advice means" is a device or software that provides the user with advice on presentation techniques based on the created presentation materials.
[0134] "Editing means" refers to a device or interface that allows a user to check and modify the generated presentation materials.
[0135] The "updating means" refers to a device or software that receives the data corrected by the editing means again and updates the presentation materials.
[0136] A "generative artificial intelligence model" is an artificial intelligence model that learns from presentation professionals with specialized knowledge and is used to automatically generate presentation materials.
[0137] "Storytelling" is a technique for effectively conveying information using stories.
[0138] "Nonverbal communication" is a method of conveying information and emotions using means other than words (gestures, facial expressions, gaze, etc.).
[0139] "Question and answer" is a technique for appropriately answering questions from the audience during a presentation.
[0140] The present invention is a system that enables users to create high-quality presentation materials in a short period of time and deliver effective presentations. This system uses a generative AI model to generate presentation materials based on basic information entered by the user, and also provides comprehensive advice to help the user improve their presentation techniques. Details for specifically implementing the present invention are provided below.
[0141] System configuration
[0142] The system consists of the following components:
[0143] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[0144] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0145] 3. AI model: A generative AI model trained by presentation professionals with expert knowledge.
[0146] Program processing
[0147] The user enters basic information
[0148] Terminal: The user uses the terminal's dedicated application or web browser to input the presentation topic, purpose, target audience, and information to be provided. For example, input the following information:
[0149] Theme: New product features
[0150] Purpose: Pitching new products to investors
[0151] Target audience: Tech-savvy investors
[0152] Information provided: Product's main features, technical advantages, market potential
[0153] The server generates the materials
[0154] Server: Receives basic information sent from the device. Based on the received information, it requests the generative AI model to generate presentation materials. Based on specialized knowledge, the generative AI model automatically generates presentation materials with the following slide structure:
[0155] 1. Title slide (new product name and logo)
[0156] 2. Slides introducing the main features of the product
[0157] 3. Slides explaining technological superiority
[0158] 4. Market Potential Analysis Slide
[0159] 5. Summary and Next Steps
[0160] User checks and modifies the materials
[0161] Device: The generated presentation materials are displayed on the device. The user can check each slide and use a dedicated editor to edit or add text, images, and graphs. Once edited, the slide is saved and sent to the server.
[0162] The server will give you advice on the key points of your presentation.
[0163] Server: Receives the corrected data and updates the presentation. Based on the completed presentation, the generative AI model generates advice on storytelling, non-verbal communication, and Q&A. For example, it provides advice such as:
[0164] How to talk about each slide
[0165] How to emphasize key points
[0166] How to move your eyes
[0167] Anticipated questions and how to address them
[0168] Users practice and prepare
[0169] Terminal: The user practices the presentation based on the advice provided. For example, the user rehearses the presentation and reflects the advice from the server in the actual presentation.
[0170] As described above, this system enables users to create high-quality presentation materials in a short amount of time and deliver effective presentations based on them. Each component works together to streamline the presentation preparation process and help users improve their skills.
[0171] Specific prompt examples
[0172] Here is an example of a prompt that a user might enter to begin creating a presentation:
[0173] Presentation theme: New product features
[0174] Purpose: Pitching new products to investors
[0175] Target audience: Tech-savvy investors
[0176] Information provided: Product's main features, technical advantages, market potential
[0177] The above processing flow allows the user to efficiently prepare for a presentation.
[0178] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0179] Step 1:
[0180] The user enters the presentation topic, purpose, target audience, and information to be provided
[0181] Input: The user enters information into an input form using a dedicated application or a web browser.
[0182] Specific operation: The user inputs the following information, for example:
[0183] Theme: New product features
[0184] Purpose: Pitching new products to investors
[0185] Target audience: Tech-savvy investors
[0186] Information provided: Product's main features, technical advantages, market potential
[0187] Output: Input data is saved to the device
[0188] Step 2:
[0189] The device sends the input information to the server
[0190] Input: Basic information entered by the user
[0191] Specific operation: Send data from the device to the server using a secure communication protocol (e.g. HTTPS).
[0192] Output: The input information is saved on the server.
[0193] Step 3:
[0194] The server requests the AI model to generate presentation materials based on the received information.
[0195] Input: Presentation topic, purpose, target audience, and information to provide sent from your device
[0196] Specific operation: The server encodes the data to the generative AI model and sends it as a prompt for generating presentation materials.
[0197] Output: Presentation materials generated by the generative AI model are output.
[0198] Step 4:
[0199] Generative AI model generates presentation materials
[0200] Input: Prompt and basic information sent from the server
[0201] How it works: The generative AI model automatically generates content for each slide in a presentation, including:
[0202] 1. Title slide (new product name and logo)
[0203] 2. Slides introducing the main features of the product
[0204] 3. Slides explaining technological superiority
[0205] 4. Market Potential Analysis Slide
[0206] 5. Summary and Next Steps
[0207] Output: The generated presentation material is sent to the server.
[0208] Step 5:
[0209] The server sends the generated presentation materials to the terminal.
[0210] Input: Presentation materials generated by the generative AI model
[0211] Specific operation: The server converts the generated slide deck into a Pedia format (PDF, PPTX, etc.) and sends it to the device.
[0212] Output: Presentation materials are displayed on the device.
[0213] Step 6:
[0214] User checks and modifies the materials
[0215] Input: Presentation materials sent from the server
[0216] Specific actions: Users can use the dedicated editor on their devices to review and modify the text, images, and graphs on each slide, for example, adding descriptions of the product's main features.
[0217] Output: The revised presentation material will be saved on your device.
[0218] Step 7:
[0219] The device sends the correction data to the server
[0220] Input: User-modified presentation
[0221] Specific operation: The corrected document is sent to the server using a secure communication protocol (e.g., HTTPS).
[0222] Output: The modified data is saved on the server.
[0223] Step 8:
[0224] The server reflects the corrected data and updates the presentation materials.
[0225] Input: Correction data sent from the terminal
[0226] Specific operation: The server updates the document based on the revised data and saves the final version.
[0227] Output: The updated presentation material is saved on the server.
[0228] Step 9:
[0229] The server will give you advice on the key points of your presentation.
[0230] Input: Finished presentation materials
[0231] Specific actions: Based on the generative AI model, the server generates advice on storytelling, non-verbal communication, and Q&A, such as how to talk about each slide and how to emphasize key points.
[0232] Output: The generated advice is saved on the server.
[0233] Step 10:
[0234] Users practice and prepare
[0235] Input: Advice provided by the server
[0236] Specific operation: The user rehearses the presentation on the device based on the advice. For example, they practice the questions they anticipate will be asked during the actual presentation and how to deal with them.
[0237] Output: Users will be better prepared and have better presentation skills
[0238] The above is the specific processing flow in the system program.
[0239] (Application example 1)
[0240] 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."
[0241] Creating presentation materials requires a lot of time and effort, making it difficult to quickly create high-quality materials. It is also difficult for users who lack knowledge and experience in presentation techniques to give effective presentations. Therefore, there is a demand for a system that can create high-quality presentation materials in a short amount of time and support effective presentations.
[0242] 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.
[0243] In this invention, the server includes input means for a user to input the presentation theme, purpose, target audience, and information to be provided, generation means for generating presentation materials based on the information received from the input means, provision means for providing the presentation materials generated by the generation means to the user, advice means for giving advice on presentation techniques based on the presentation materials, advice means for providing effective ways of speaking and question-and-answer sessions in the presentation, and means for providing technique guidance to the user based on the presentation. This enables the user to create high-quality presentation materials and prepare for an effective presentation in a short period of time.
[0244] "Input means" refers to a device or software that allows a user to input the presentation's theme, purpose, target audience, and information to be provided.
[0245] The "generation means" is a device or software that has the function of automatically generating presentation materials based on the information received from the input means.
[0246] The "providing means" is a device or software having a function for providing the presentation materials generated by the generating means to the user.
[0247] An "advice means" is a device or software that has the function of giving advice to a user on presentation techniques based on presentation materials.
[0248] The "means for providing advice on how to speak and how to answer questions" refers to a device or software that has the function of providing specific guidance to the user on how to speak effectively in a presentation and how to answer questions.
[0249] The "means for providing instruction in techniques" refers to a device or software that has the function of providing instruction to users in presentation techniques based on the presentation.
[0250] The present invention relates to a system including: an input means for a user to input the theme, purpose, target audience, and information to be provided of a presentation; a generation means for generating presentation materials based on the information received from the input means; a provision means for providing the generated presentation materials to a user; and an advice means for providing advice on presentation techniques based on the presentation materials. The system also includes an advice means for providing effective ways of speaking and question-and-answer sessions during the presentation, and a means for providing instruction on the techniques to a user based on the presentation.
[0251] System Configuration
[0252] The system consists of the following main components:
[0253] 1. Terminal: A device through which a user enters information (e.g., smartphone, computer, tablet).
[0254] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0255] 3. AI model: An artificial intelligence model trained to generate presentation materials and provide advice on presentation techniques.
[0256] Implementation details
[0257] The user inputs basic information about the presentation (e.g., theme, purpose, target audience, and information to be provided) using a dedicated application or web browser on the device. For example, the user inputs "features of a new product" as the theme, "selling the new product to investors" as the purpose, "investors knowledgeable about technology" as the target audience, and "major functions, technological advantages, and market potential of the product" as the information to be provided.
[0258] The server receives the basic information sent from the device and requests the AI model to generate presentation materials. The AI model automatically generates a slide deck based on specialized knowledge. For example, the following slide structure is generated:
[0259] 1. Title slide (new product name and logo)
[0260] 2. Slides introducing the main features of the product
[0261] 3. Slides explaining technological superiority
[0262] 4. Market Potential Analysis Slide
[0263] 5. Summary and Next Steps
[0264] The generated presentation materials are sent back to the terminal, where they are reviewed and revised by the user. The user reviews each slide and makes corrections or additions to text, images, and graphs as necessary. Once the revisions are complete, the slides are saved and sent back to the server.
[0265] The server receives the corrected data and updates the presentation materials, which are then provided to the user again. Based on the completed presentation materials, the AI model generates advice on storytelling, non-verbal communication, and Q&A.
[0266] The user practices the presentation based on the advice provided. For example, the user rehearses the presentation and reflects the advice from the server.
[0267] Hardware and software used
[0268] Hardware:
[0269] 1. Smartphone or tablet
[0270] 2. Server equipment
[0271] software:
[0272] 1. Python and related libraries (such as requests)
[0273] 2. OpenAI® API
[0274] Prompt Sentence Examples
[0275] Theme: Cybersecurity measures
[0276] Objective: To propose new security solutions to customers.
[0277] Target audience: Security personnel
[0278] Information provided: Features of new security tools, technical advantages, and benefits of their implementation
[0279] Use this to generate presentation slides.
[0280] This invention enables users to create high-quality presentation materials in a short time and deliver effective presentations based on them. Each component works in conjunction with the others to streamline the presentation preparation process and help users improve their skills.
[0281] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0282] Step 1:
[0283] The user inputs basic information about the presentation (theme, purpose, target audience, information to be provided) using a dedicated application or web browser on the device. This information is then sent from the device to the server. Specifically, this includes a function to format the input information such as theme and purpose and send it to the server. An example of input data is "Theme: Features of a new product," and this information is sent to the server.
[0284] Step 2:
[0285] The server receives basic information sent from the device. The received information is used as input data for generating presentation materials. This data is stored in the server's storage and becomes the material for generating prompts for the AI model. The server analyzes the received data and formats it as needed.
[0286] Step 3:
[0287] The server creates a prompt to request the AI model to generate presentation materials based on the received basic information. Specifically, it uses Python to generate a prompt based on the basic information. It sends this prompt to the OpenAI API and receives a response from the AI model. An example of a prompt is "Topic: Cybersecurity measures, Objective: Propose new security solutions to customers."
[0288] Step 4:
[0289] The AI model automatically generates a presentation based on the provided prompts. The generated presentation is sent back to the server. The AI model generates the content for each slide based on the input prompts and sends the results in text format to the server.
[0290] Step 5:
[0291] The server receives the response from the AI model, formats the content, and sends it to the device as a presentation. Specifically, it converts the received text into slides and formats it in a way that is easy for the user to review. This allows the user to view the generated presentation on their device.
[0292] Step 6:
[0293] The user can check the presentation materials created on their device and make corrections or additions as necessary. Specifically, they can correct text and add images and graphs. After the user makes the corrections, the revised data is sent back to the server.
[0294] Step 7:
[0295] The server receives the modified data from the user and updates the presentation materials. The updated materials are then provided to the user again. The server then generates the latest materials that reflect the updated data and sends them to the terminal.
[0296] Step 8:
[0297] Based on the completed presentation materials, the server generates advice on presentation techniques, including advice on storytelling, non-verbal communication, and Q&A. The server then generates prompts for the AI model again to obtain appropriate advice.
[0298] Step 9:
[0299] The user practices the presentation based on the advice provided. Specifically, the user rehearses the presentation and incorporates the advice provided by the server. The user practices using the terminal and acquires effective presentation techniques.
[0300] This series of processing steps enables users to efficiently create high-quality presentation materials and prepare for their presentations effectively.
[0301] 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.
[0302] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses an AI model to generate presentation materials based on basic information entered by the user, and also recognizes the user's emotions and provides comprehensive advice on adapting presentation techniques.
[0303] System configuration
[0304] The system consists of the following components:
[0305] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[0306] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0307] 3. AI model: An artificial intelligence model trained to generate professional presentation materials and provide advice on presentation techniques.
[0308] 4. Emotion engine: A device or program that recognizes the user's emotions and adapts presentation materials and advice.
[0309] Program processing
[0310] The user enters basic information
[0311] Device:
[0312] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[0313] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[0314] The server generates the materials
[0315] server:
[0316] The server receives the basic information sent from the terminal.
[0317] Based on the received information, the AI model is asked to generate presentation materials.
[0318] The AI model automatically generates a slide deck based on its expert knowledge, resulting in a slide structure like this:
[0319] 1. Title slide (new product name and logo)
[0320] 2. Slides introducing the main features of the product
[0321] 3. Slides explaining technological superiority
[0322] 4. Market Potential Analysis Slide
[0323] 5. Summary and Next Steps Slide
[0324] The server temporarily stores the generated materials and transmits them to the user terminal as preview data.
[0325] User checks and modifies the materials
[0326] Device:
[0327] The generated presentation materials are displayed on the device.
[0328] Users can check each slide, select the one they want to edit, and modify or add text, images, and graphs.
[0329] For example: modify the text, add a chart, insert an image, etc.
[0330] When the user clicks the "Save" button for the slide after completing the editing, the modified data is sent to the server.
[0331] server:
[0332] The presentation materials are updated by receiving the corrected data sent by the user.
[0333] The updated presentation materials are provided to the user again.
[0334] The server will give you advice on the key points of your presentation.
[0335] server:
[0336] The completed presentation materials are analyzed by an AI model.
[0337] For each slide, the AI model generates advice on storytelling, non-verbal communication, and how to handle questions and answers.
[0338] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[0339] The server recognizes the user's emotions
[0340] Emotion Engine:
[0341] When a user practices a presentation, the emotion engine analyzes the user's voice, facial expressions, and biometric signals to recognize their emotions.
[0342] The recognized emotion data is sent to a server.
[0343] Coordinating and providing advice
[0344] server:
[0345] Adapt presentation materials and advice based on emotional data from the emotion engine.
[0346] Example: If the user is nervous, give them advice on how to relax or suggest slide corrections.
[0347] The adjusted advice is transmitted to the user terminal.
[0348] Users practice and prepare
[0349] Device:
[0350] The user practices the presentation based on the advice provided.
[0351] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[0352] Make final preparations for the presentation.
[0353] As described above, this system helps users to efficiently create high-quality presentation materials and optimize their presentation techniques based on emotion recognition data, thereby helping users to give effective presentations.
[0354] The processing flow will be explained below.
[0355] Step 1:
[0356] The user enters basic information.
[0357] User: Log in to the device and click the Create New Presentation button.
[0358] Terminal: Display the screen for entering basic information about the presentation.
[0359] User: Enter the theme, purpose, target audience, and information to provide.
[0360] For example: Theme: "Features of the new product", Objective: "Pitching the new product to investors", Target audience: "Technology-savvy investors", Information provided: "Key product features, technological advantages, and market potential".
[0361] User: Click the "Next" button.
[0362] Step 2:
[0363] A server receives the information and generates a presentation.
[0364] Terminal: Sends the entered basic information to the server.
[0365] Server: Provides the received basic information to the AI model.
[0366] AI model: Generate presentation materials. For example, the following slide structure:
[0367] 1. Title Slide
[0368] 2. Slides introducing the main features of the product
[0369] 3. Technological advantage explanation slides
[0370] 4. Market Potential Analysis Slide
[0371] 5. Summary and Next Steps Slide
[0372] Server: Temporarily stores the generated materials and sends them to the user's device as preview data.
[0373] Step 3:
[0374] The user can review and modify the generated materials.
[0375] Device: Shows a preview of the generated presentation.
[0376] User: Review the content of each slide and select the slide they want to edit.
[0377] Terminal: Switches to edit mode and provides an interface for users to enter information to be modified or added.
[0378] For example: modify the text, add a chart, insert an image, etc.
[0379] User: Clicks the "Save" button for the slide after editing is complete.
[0380] Device: Sends the saved correction data to the server.
[0381] Step 4:
[0382] The server updates the presentation materials to reflect the corrected data.
[0383] Server: Receives the correction data sent by the user.
[0384] Server: Update the presentation materials based on the revised data.
[0385] Server: The updated presentation materials are again temporarily saved and resent to the user.
[0386] Step 5:
[0387] The server will give you advice on the key points of your presentation.
[0388] Server: The AI model analyzes the completed presentation materials.
[0389] AI model: Generates advice for each slide on how to handle storytelling, non-verbal communication, and Q&A.
[0390] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[0391] Server: Sends the generated advice to the user terminal.
[0392] Step 6:
[0393] The server recognizes the user's emotions.
[0394] Terminal: The emotion engine runs when the user practices their presentation.
[0395] Emotion engine: Recognizes emotions by analyzing the user's voice, facial expressions, and biometric signals.
[0396] Emotion Engine: Sends the recognized emotion data to the server.
[0397] Example: If the user is nervous, the degree of nervousness is converted into a numerical value and sent to the server.
[0398] Step 7:
[0399] Coordinating and providing advice.
[0400] Server: Analyzes emotion recognition data and adapts presentation materials and advice content.
[0401] For example: If the user is nervous, give them advice on how to relax or suggest revisions to make the slides more understandable.
[0402] Server: Sends the adjusted advice to the user terminal.
[0403] Step 8:
[0404] Users practice and prepare.
[0405] Terminal: Displays advice sent from the server.
[0406] Users: Review the advice on each slide and practice your presentation.
[0407] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[0408] User: Make final preparations for the presentation.
[0409] These are the specific processing steps of this system. The user, device, and server work together to improve the efficiency and quality of the presentation preparation process based on emotion recognition.
[0410] Example 2
[0411] 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."
[0412] Conventional presentation creation systems make it difficult for users to create high-quality presentations in a short amount of time. Furthermore, there are no systems that provide presentation technique advice that takes into account the user's emotional state, making it difficult to maximize the effectiveness of a presentation. This lack of optimal advice is particularly problematic for users who are unfamiliar with presentations or who tend to get nervous.
[0413] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for a user to input the theme, purpose, target audience, and information to be provided of the presentation, a generation means for generating presentation materials based on the information received from the input means, a provision means for providing the presentation materials generated by the generation means to the user, an advice means for giving advice on presentation techniques based on the presentation materials, and an emotion recognition means for recognizing the user's emotions and adapting the advice on presentation techniques. This enables the user to create high-quality presentation materials in a short period of time and receive advice on optimal presentation techniques according to the user's emotional state.
[0414] "Presentation materials" refers to slides or documents containing information or content that a user uses when giving a presentation.
[0415] "Input means" refers to an interface or device that allows a user to input the presentation's theme, purpose, target audience, and information to be provided.
[0416] The "generation means" refers to a mechanism or program for generating presentation materials based on the information received from the input means.
[0417] The "providing means" refers to a mechanism or method for providing the presentation materials generated by the generating means to the user.
[0418] "Advice means" refers to a mechanism or program for giving advice on presentation techniques based on the presentation materials.
[0419] The "emotion recognition means" refers to a mechanism or program for recognizing the user's emotions and adapting the presentation technique advice.
[0420] A "user" is someone who creates presentation materials and gives a presentation.
[0421] The term "server" refers to a central processing unit including the input means, generation means, provision means, advice means, and emotion recognition means.
[0422] An "AI model" is an artificial intelligence model that has learned from presentation professionals with specialized knowledge.
[0423] "Voice, facial expression, and biological signals" refers to the user's voice data, facial expression data, and biological activity data used by the emotion recognition means to detect the user's emotions.
[0424] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses a generative AI model to generate presentation materials based on basic information entered by the user, and also recognizes the user's emotions and provides comprehensive advice on adapting presentation techniques.
[0425] System configuration
[0426] The system consists of the following components:
[0427] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[0428] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0429] 3. AI model: An artificial intelligence model trained by presentation professionals with specialized knowledge.
[0430] 4. Emotion recognition means: A device or program that recognizes the user's emotions and adapts presentation materials or advice accordingly.
[0431] Program processing
[0432] The user enters basic information
[0433] Device:
[0434] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[0435] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[0436] The server generates the materials
[0437] server:
[0438] The server receives the basic information sent from the terminal.
[0439] Based on the received information, the AI model is asked to generate presentation materials.
[0440] The AI model automatically generates a slide deck based on its expert knowledge, resulting in a slide structure like this:
[0441] 1. Title slide (new product name and logo)
[0442] 2. Slides introducing the main features of the product
[0443] 3. Slides explaining technological superiority
[0444] 4. Market Potential Analysis Slide
[0445] 5. Summary and Next Steps Slide
[0446] The server temporarily stores the generated materials and transmits them to the user terminal as preview data.
[0447] User checks and modifies the materials
[0448] Device:
[0449] The generated presentation materials are displayed on the device.
[0450] Users can check each slide, select the one they want to edit, and modify or add text, images, and graphs.
[0451] For example: modify the text, add a chart, insert an image, etc.
[0452] When the user clicks the "Save" button for the slide after completing the editing, the modified data is sent to the server.
[0453] server:
[0454] The presentation materials are updated by receiving the corrected data sent by the user.
[0455] The updated presentation materials are provided to the user again.
[0456] The server will give you advice on the key points of your presentation.
[0457] server:
[0458] The completed presentation materials are analyzed by an AI model.
[0459] For each slide, the AI model generates advice on storytelling, non-verbal communication, and how to handle questions and answers.
[0460] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[0461] The server recognizes the user's emotions
[0462] Emotion recognition means:
[0463] When a user practices a presentation, their emotions are recognized by analyzing their voice, facial expressions, and biometric signals.
[0464] The recognized emotion data is sent to a server.
[0465] Coordinating and providing advice
[0466] server:
[0467] The presentation materials and advice content are adapted based on the emotional data from the emotion recognition means.
[0468] Example: If the user is nervous, give them advice on how to relax or suggest slide corrections.
[0469] The adjusted advice is transmitted to the user terminal.
[0470] Users practice and prepare
[0471] Device:
[0472] The user practices the presentation based on the advice provided.
[0473] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[0474] Make final preparations for the presentation.
[0475] Examples of concrete examples and prompts
[0476] Below are some examples and prompts:
[0477] Specific examples
[0478] 1. User input:
[0479] Theme: "Environmentally friendly new energy technology"
[0480] Purpose: "Introducing technology to the new energy sector of companies"
[0481] Target audience: "Engineers with knowledge of environmental technology"
[0482] Information provided: "Technology characteristics, environmental impacts, economic benefits"
[0483] 2. Generated slide configuration:
[0484] Title slide (technology name and logo)
[0485] Slide introducing the features of the technology
[0486] Environmental Impact Slides
[0487] Economic benefits slide
[0488] Summary and next steps slide
[0489] 3. Specific examples of advice:
[0490] "It's important to focus the audience's attention on this slide and emphasize the technical features."
[0491] "When explaining economic benefits, using concrete figures helps capture the audience's attention."
[0492] Prompt Sentence Examples
[0493] "Please create a presentation that explains the features of the new product."
[0494] "Provide advice on slides that highlight the environmental impact and economic benefits."
[0495] "Please advise the user on how to relax if they are nervous."
[0496] In this way, by using prompt sentences, we have created a system that provides information in a format that is easy to input into the generative AI model, allowing participants to receive advice on more effective presentation materials and presentation techniques.
[0497] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0498] Now, let me explain the process of the system program step by step.
[0499] Processing Steps
[0500] Step 1: User enters basic information
[0501] Step 2: The server generates the materials
[0502] Step 3: User checks and modifies the materials
[0503] Step 4: The server gives advice on key points of the presentation
[0504] Step 5: The server recognizes the user's emotion
[0505] Step 6: Coordinating and providing advice
[0506] Step 7: User Practice and Preparation
[0507] Step-by-step instructions
[0508] Step 1: User enters basic information
[0509] Device:
[0510] Input: The user enters the presentation topic, purpose, target audience, and information to be provided.
[0511] How it works: The user launches a dedicated application or web browser on their device and enters the necessary information into the input form. For example, they enter "new product features" as the presentation topic, "selling the new product to investors" as the purpose, "technology-savvy investors" as the target audience, and "the product's main functions, technological advantages, and market potential" as the information to be provided.
[0512] Output: The entered information is sent to the server.
[0513] Step 2: The server generates the materials
[0514] server:
[0515] Input: Basic information sent from the device.
[0516] How it works: The server receives the HTTP POST request and temporarily stores it in a database. It then uses the received information to request the generative AI model to generate presentation materials. Specifically, it sends an API request to the AI model and receives the generated slide deck data.
[0517] Output: The generated presentation materials are temporarily saved and sent to the user's device as preview data.
[0518] Step 3: User checks and modifies the materials
[0519] Device:
[0520] Input: Preview data of presentation materials sent from the server.
[0521] How it works: The generated presentation materials are displayed on the device. The user can review each slide, select the one they want to edit, and modify or add text, images, or graphs. For example, they can modify text, add graphs, or insert images, and then click the "Save" button for the slide they've completed editing.
[0522] Output: The modified data is sent to the server.
[0523] server:
[0524] Input: Correction data submitted by the user.
[0525] Operation: Receives the revised data sent by the user and updates the presentation materials. Specifically, it updates the database and generates new slide data.
[0526] Output: The updated presentation is provided to the user again.
[0527] Step 4: The server gives advice on key points of the presentation
[0528] server:
[0529] Input: The completed presentation.
[0530] Operation: The completed presentation materials are analyzed by the AI model. The data is sent to the analysis endpoint of the AI model, and the advice data returned by the AI model is formatted and integrated back into the presentation materials.
[0531] Output: For each slide, advice data is generated on how to handle storytelling, non-verbal communication, and questions and answers.
[0532] Step 5: The server recognizes the user's emotion
[0533] Emotion recognition means:
[0534] Input: Speech, facial expression, and biometric data collected as users practice their presentations.
[0535] How it works: Data is collected from cameras, microphones, and wearable devices, and fed into an emotion analysis algorithm. The analysis results are sent to a server in real time.
[0536] Output: The recognized emotion data is generated and sent to the server.
[0537] Step 6: Coordinating and providing advice
[0538] server:
[0539] Input: Emotion data from emotion recognition instrument.
[0540] Behavior: Analyzes emotional data and adapts presentation materials and advice. For example, if the user is nervous, the system will suggest ways to relax.
[0541] Output: The adjusted advice is generated and sent to the user terminal.
[0542] Step 7: User Practice and Preparation
[0543] Device:
[0544] Input: Tailored advice and updated presentation materials.
[0545] Action: The user practices their presentation based on the provided advice. For example, they record their own presentation using the audio recording function and try to demonstrate it according to the advice. This allows them to make final checks in preparation for the actual presentation.
[0546] Output: The user is ready to give an effective presentation.
[0547] (Application example 2)
[0548] 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."
[0549] In modern logistics centers, it is necessary to create presentation materials to quickly and effectively report improvements in work efficiency and the effects of new deployment systems. However, it is a major challenge for workers to create high-quality presentation materials and effectively communicate their content while performing their daily tasks. It is also difficult to properly manage the presenter's emotions and tension to maximize performance. Therefore, a system that can reflect the on-site situation in real time and use emotion recognition to improve the quality of presentations is needed.
[0550] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: input means for a user to input the presentation theme, purpose, target audience, and information to be provided; generation means for generating presentation materials based on the information received from the input means; provision means for providing the presentation materials generated by the generation means to the user; advice means for providing presentation technique advice based on the presentation materials; emotion recognition means for recognizing the user's emotions and adapting the presentation materials and advice; and means for checking and correcting the presentation materials via a smart device. This not only enables workers at a logistics center to quickly create presentation materials that reflect on-site video and data in real time, but also improves the quality of presentations and enables more effective reporting through emotion recognition technology.
[0551] "Input means" refers to a device or system that allows a user to input the theme, purpose, target audience, and information to be provided for the presentation.
[0552] The "generation means" is a device or system for automatically creating presentation materials based on the information received from the input means.
[0553] The "providing means" is a device or system that provides the presentation materials created by the generating means to the user, allowing them to be viewed and modified.
[0554] The "advice means" is a device or system that provides guidance to the user on presentation techniques based on the presentation materials and suggests areas for improvement.
[0555] "Emotion recognition means" refers to a device or program that analyzes the user's voice, facial expressions, etc., and recognizes their emotional state.
[0556] A "smart device" is a device that has Internet connectivity and allows users to view and operate information visually or audibly.
[0557] "Presentation materials" refers to documents and slides that illustrate or describe the content that a user will present.
[0558] The system that realizes this application example allows users to create presentation materials in real time at a logistics center, and then confirm and modify the contents to make effective presentations.
[0559] The present invention is implemented using the following hardware and software:
[0560] 1. Smart device (e.g., smart glasses): A device that allows users to input the presentation topic, purpose, target audience, and information to be provided, and to review and modify presentation materials.
[0561] 2. Camera module: A device built into the smart glasses for capturing on-site footage.
[0562] 3. Server: A central processing unit that generates and provides presentation materials based on information received from the input means and gives advice on presentation techniques.
[0563] 4. AI model (e.g., PresentationAI): An artificial intelligence model trained from presentation professionals with specialized knowledge, used to automatically generate presentation materials.
[0564] 5. Emotion recognition software (e.g., EmotionEngine): Software that analyzes the user's emotions and recognizes their state.
[0565] The server first receives the presentation's theme, purpose, target audience, and information sent from the smart device. Based on this information, it uses an AI model to automatically generate presentation materials. The generated presentation materials are then provided to the user via their smart device, who can review the materials in real time and make edits to the text and images as needed.
[0566] Next, emotion recognition software analyzes data such as the user's voice and facial expressions to recognize their emotions. Based on the results, the server adapts the presentation materials and advice provided. This process allows the user to improve the quality of their presentation by offering advice on how to relax or suggesting slide revisions if they are nervous.
[0567] As a concrete example, consider a scenario in which an efficiency improvement report for a new warehouse allocation system is created. A user wears smart glasses and captures video of the warehouse. OCR technology is used to extract text data from the video, and an AI model automatically generates a slide deck based on this data. The generated slides include an overview of the new warehouse allocation system, the efficiency improvement status, and cost reduction effects. The user checks the slides on the smart glasses' display and makes any necessary corrections. If emotion recognition software detects that the user is tense, advice such as encouraging deep breathing is displayed.
[0568] An example prompt is, "Generate a presentation to create an efficiency improvement report for a new warehouse layout system. Key areas to focus on include efficiency gains, cost savings, and staff satisfaction after the layout change."
[0569] As described above, this system supports the efficient and effective creation and presentation of presentation materials at logistics centers.
[0570] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0571] Step 1:
[0572] The user uses a smart device (e.g., smart glasses) to input the presentation topic, objectives, target audience, and information to be provided. The input information is sent from the smart device to the server. Examples of input data include "improving the efficiency of the logistics center," "presentation on business improvement," "manager," and "improving the efficiency of a new warehouse layout system."
[0573] Step 2:
[0574] The server automatically generates presentation materials using a generative AI model (e.g., PresentationAI) based on the received input data. Specifically, it creates an appropriate slide structure based on the theme and purpose, and embeds the content. For example, it generates slides such as a "title slide," a "slide explaining the efficiency improvement after the layout change," and a "slide showing the cost reduction effect." The output is the automatically generated presentation materials.
[0575] Step 3:
[0576] The server provides the generated presentation materials to the smart device. The user checks the presentation materials on the smart device's display and operates the interface to modify text, images, and charts as necessary. The entered modification data is then sent to the server. The input here is the user's modification instructions, and the output is the modified presentation materials.
[0577] Step 4:
[0578] The server updates the presentation materials based on the corrections sent by the user. The updated presentation materials are then sent back to the smart device, where the user can review and make final adjustments. The final presentation materials are then output.
[0579] Step 5:
[0580] When a user rehearses a presentation, emotion recognition software (e.g., EmotionEngine) on the smart device analyzes the user's voice and facial expressions to recognize emotional data. Based on this, the user's state of tension or relaxation is analyzed. The input data is the user's voice and facial expression data, and the output data is the analyzed emotional information.
[0581] Step 6:
[0582] The server adjusts the content of the presentation materials and advice based on the emotional data sent from the emotion recognition software. For example, if the user is nervous, the server may suggest relaxation techniques such as encouraging deep breathing or change the slide structure. The adjusted advice and presentation materials are then output.
[0583] Step 7:
[0584] The user receives final advice via their smart device and makes final adjustments while rehearsing their presentation. This process prepares the user for the actual presentation. The final output is a quality-improved presentation document and advice for the user.
[0585] The above are the specific processing steps of the system that realizes the application example.
[0586] 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.
[0587] 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.
[0588] 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.
[0589] [Second embodiment]
[0590] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0591] 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.
[0592] 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).
[0593] 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.
[0594] 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.
[0595] 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).
[0596] 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. 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.
[0597] 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.
[0598] 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.
[0599] 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.
[0600] In the smart glasses 214, 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.
[0601] 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."
[0602] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses an AI model to generate presentation materials based on basic information entered by the user, and also provides comprehensive advice to improve the user's presentation techniques.
[0603] System configuration
[0604] The system consists of the following components:
[0605] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[0606] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0607] 3. AI model: An artificial intelligence model trained to generate professional presentation materials and provide advice on presentation techniques.
[0608] Program processing
[0609] The user enters basic information
[0610] Device:
[0611] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[0612] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[0613] The server generates the materials
[0614] server:
[0615] The server receives the basic information sent from the terminal.
[0616] Based on the received information, the AI model is asked to generate presentation materials.
[0617] The AI model automatically generates a slide deck based on its expert knowledge. For example, it might generate the following slide structure:
[0618] 1. Title slide (new product name and logo)
[0619] 2. Slides introducing the main features of the product
[0620] 3. Slides explaining technological superiority
[0621] 4. Market Potential Analysis Slide
[0622] 5. Summary and Next Steps
[0623] User checks and modifies the materials
[0624] Device:
[0625] The generated presentation materials are displayed on the device.
[0626] The user checks each slide and modifies or adds text, images, and graphs as necessary.
[0627] Once the edits are complete, the slide is saved and sent to the server.
[0628] server:
[0629] Receive corrected data and update presentation materials.
[0630] Updated materials will be provided to users again.
[0631] The server will give you advice on the key points of your presentation.
[0632] server:
[0633] Based on the completed presentation, the AI model generates advice on storytelling, non-verbal communication, and Q&A.
[0634] For example: how to talk through each slide, how to emphasize key points, how to move your eyes, anticipated questions and how to deal with them, etc.
[0635] Users practice and prepare
[0636] Device:
[0637] The user practices the presentation based on the advice provided.
[0638] As a concrete example, a presentation is rehearsed and advice from the server is reflected.
[0639] As described above, this system enables users to create high-quality presentation materials in a short amount of time and deliver effective presentations based on them. Each component works together to streamline the presentation preparation process and help users improve their skills.
[0640] The processing flow will be explained below.
[0641] Step 1:
[0642] The user enters basic information.
[0643] User: Log in to the device and click the Create New Presentation button.
[0644] Terminal: Display the screen for entering basic information about the presentation.
[0645] User: Enter the theme, purpose, target audience, and information to provide.
[0646] For example: Theme: "Features of the new product", Objective: "Pitching the new product to investors", Target audience: "Technology-savvy investors", Information provided: "Key product features, technological advantages, and market potential".
[0647] User: Click the "Next" button.
[0648] Step 2:
[0649] A server receives the information and generates a presentation.
[0650] Terminal: Sends the entered basic information to the server.
[0651] Server: Provides the received basic information to the AI model.
[0652] AI model: Generate presentation materials. For example, the following slide structure:
[0653] 1. Title Slide
[0654] 2. Slides introducing the main features of the product
[0655] 3. Technological advantage explanation slides
[0656] 4. Market Potential Analysis Slide
[0657] 5. Summary and Next Steps Slide
[0658] Server: Temporarily stores the generated materials and sends them to the user's device as preview data.
[0659] Step 3:
[0660] The user can review and modify the generated materials.
[0661] Device: Shows a preview of the generated presentation.
[0662] User: Review the content of each slide and select the slide they want to edit.
[0663] Terminal: Switches to edit mode and provides an interface for users to enter information to be modified or added.
[0664] For example: modify the text, add a chart, insert an image, etc.
[0665] User: Clicks the "Save" button for the slide after editing is complete.
[0666] Device: Sends the saved correction data to the server.
[0667] Step 4:
[0668] The server updates the presentation materials to reflect the corrected data.
[0669] Server: Receives the correction data sent by the user.
[0670] Server: Update the presentation materials based on the revised data.
[0671] Server: The updated presentation materials are again temporarily saved and resent to the user.
[0672] Step 5:
[0673] The server will give you advice on the key points of your presentation.
[0674] Server: The AI model analyzes the completed presentation materials.
[0675] AI model: Generates advice for each slide on how to handle storytelling, non-verbal communication, and Q&A.
[0676] For example: how to talk about each slide, how to emphasize points, how to move your eyes, anticipated questions and how to prepare for them.
[0677] Server: Sends the generated advice in text format to the user terminal.
[0678] Step 6:
[0679] Users practice and prepare.
[0680] Terminal: Displays advice sent from the server.
[0681] Users: Review the advice on each slide and practice your presentation.
[0682] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[0683] User: Make final preparations for the presentation.
[0684] These are the specific processing steps of this system. At each step, the user, terminal, and server work together to efficiently and effectively support the creation of presentation materials and preparation for presentations.
[0685] Example 1
[0686] 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."
[0687] Currently, there are many tools on the market for creating presentation materials effectively, but they have the following problems: Creating presentation materials takes time, and it is difficult to create high-quality materials in a short amount of time. Furthermore, if the user does not have specialized knowledge or skills in presentation techniques, it is difficult to give an effective presentation. As a result, there is a demand for a system that allows users to create presentation materials effectively and quickly without requiring much effort or time, and also to improve their presentation techniques.
[0688] 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.
[0689] In this invention, the server includes input means for a user to input the presentation theme, purpose, target audience, and information to be provided, generation means for generating presentation materials based on the information received from the input means, provision means for providing the presentation materials generated by the generation means to the user, advice means for providing presentation technique advice based on the presentation materials, editing means for the user to check and correct the generated presentation materials, and update means for receiving the data corrected by the editing means and updating the presentation materials, thereby enabling the user to create high-quality presentation materials in a short period of time and improve their own presentation techniques.
[0690] "Input means" refers to a device or interface that allows a user to input the theme, purpose, target audience, and information to be provided for the presentation.
[0691] The "generation means" refers to a device or software that automatically generates presentation materials based on information received from the input means.
[0692] The "providing means" refers to a device or interface for presenting and providing the presentation materials generated by the generating means to the user.
[0693] The "advice means" is a device or software that provides the user with advice on presentation techniques based on the created presentation materials.
[0694] "Editing means" refers to a device or interface that allows a user to check and modify the generated presentation materials.
[0695] The "updating means" refers to a device or software that receives the data corrected by the editing means again and updates the presentation materials.
[0696] A "generative artificial intelligence model" is an artificial intelligence model that learns from presentation professionals with specialized knowledge and is used to automatically generate presentation materials.
[0697] "Storytelling" is a technique for effectively conveying information using stories.
[0698] "Nonverbal communication" is a method of conveying information and emotions using means other than words (gestures, facial expressions, gaze, etc.).
[0699] "Question and answer" is a technique for appropriately answering questions from the audience during a presentation.
[0700] The present invention is a system that enables users to create high-quality presentation materials in a short period of time and deliver effective presentations. This system uses a generative AI model to generate presentation materials based on basic information entered by the user, and also provides comprehensive advice to help the user improve their presentation techniques. Details for specifically implementing the present invention are provided below.
[0701] System configuration
[0702] The system consists of the following components:
[0703] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[0704] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0705] 3. AI model: A generative AI model trained by presentation professionals with expert knowledge.
[0706] Program processing
[0707] The user enters basic information
[0708] Terminal: The user uses the terminal's dedicated application or web browser to input the presentation topic, purpose, target audience, and information to be provided. For example, input the following information:
[0709] Theme: New product features
[0710] Purpose: Pitching new products to investors
[0711] Target audience: Tech-savvy investors
[0712] Information provided: Product's main features, technical advantages, market potential
[0713] The server generates the materials
[0714] Server: Receives basic information sent from the device. Based on the received information, it requests the generative AI model to generate presentation materials. Based on specialized knowledge, the generative AI model automatically generates presentation materials with the following slide structure:
[0715] 1. Title slide (new product name and logo)
[0716] 2. Slides introducing the main features of the product
[0717] 3. Slides explaining technological superiority
[0718] 4. Market Potential Analysis Slide
[0719] 5. Summary and Next Steps
[0720] User checks and modifies the materials
[0721] Device: The generated presentation materials are displayed on the device. The user can check each slide and use a dedicated editor to edit or add text, images, and graphs. Once edited, the slide is saved and sent to the server.
[0722] The server will give you advice on the key points of your presentation.
[0723] Server: Receives the corrected data and updates the presentation. Based on the completed presentation, the generative AI model generates advice on storytelling, non-verbal communication, and Q&A. For example, it provides advice such as:
[0724] How to talk about each slide
[0725] How to emphasize key points
[0726] How to move your eyes
[0727] Anticipated questions and how to address them
[0728] Users practice and prepare
[0729] Terminal: The user practices the presentation based on the advice provided. For example, the user rehearses the presentation and reflects the advice from the server in the actual presentation.
[0730] As described above, this system enables users to create high-quality presentation materials in a short amount of time and deliver effective presentations based on them. Each component works together to streamline the presentation preparation process and help users improve their skills.
[0731] Specific prompt examples
[0732] Here is an example of a prompt that a user might enter to begin creating a presentation:
[0733] Presentation theme: New product features
[0734] Purpose: Pitching new products to investors
[0735] Target audience: Tech-savvy investors
[0736] Information provided: Product's main features, technical advantages, market potential
[0737] The above processing flow allows the user to efficiently prepare for a presentation.
[0738] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0739] Step 1:
[0740] The user enters the presentation topic, purpose, target audience, and information to be provided
[0741] Input: The user enters information into an input form using a dedicated application or a web browser.
[0742] Specific operation: The user inputs the following information, for example:
[0743] Theme: New product features
[0744] Purpose: Pitching new products to investors
[0745] Target audience: Tech-savvy investors
[0746] Information provided: Product's main features, technical advantages, market potential
[0747] Output: Input data is saved to the device
[0748] Step 2:
[0749] The device sends the input information to the server
[0750] Input: Basic information entered by the user
[0751] Specific operation: Send data from the device to the server using a secure communication protocol (e.g. HTTPS).
[0752] Output: The input information is saved on the server.
[0753] Step 3:
[0754] The server requests the AI model to generate presentation materials based on the received information.
[0755] Input: Presentation topic, purpose, target audience, and information to provide sent from your device
[0756] Specific operation: The server encodes the data to the generative AI model and sends it as a prompt for generating presentation materials.
[0757] Output: Presentation materials generated by the generative AI model are output.
[0758] Step 4:
[0759] Generative AI model generates presentation materials
[0760] Input: Prompt and basic information sent from the server
[0761] How it works: The generative AI model automatically generates content for each slide in a presentation, including:
[0762] 1. Title slide (new product name and logo)
[0763] 2. Slides introducing the main features of the product
[0764] 3. Slides explaining technological superiority
[0765] 4. Market Potential Analysis Slide
[0766] 5. Summary and Next Steps
[0767] Output: The generated presentation material is sent to the server.
[0768] Step 5:
[0769] The server sends the generated presentation materials to the terminal.
[0770] Input: Presentation materials generated by the generative AI model
[0771] Specific operation: The server converts the generated slide deck into a Pedia format (PDF, PPTX, etc.) and sends it to the device.
[0772] Output: Presentation materials are displayed on the device.
[0773] Step 6:
[0774] User checks and modifies the materials
[0775] Input: Presentation materials sent from the server
[0776] Specific actions: Users can use the dedicated editor on their devices to review and modify the text, images, and graphs on each slide, for example, adding descriptions of the product's main features.
[0777] Output: The revised presentation material will be saved on your device.
[0778] Step 7:
[0779] The device sends the correction data to the server
[0780] Input: User-modified presentation
[0781] Specific operation: The corrected document is sent to the server using a secure communication protocol (e.g., HTTPS).
[0782] Output: The modified data is saved on the server.
[0783] Step 8:
[0784] The server reflects the corrected data and updates the presentation materials.
[0785] Input: Correction data sent from the terminal
[0786] Specific operation: The server updates the document based on the revised data and saves the final version.
[0787] Output: The updated presentation material is saved on the server.
[0788] Step 9:
[0789] The server will give you advice on the key points of your presentation.
[0790] Input: Finished presentation materials
[0791] Specific actions: Based on the generative AI model, the server generates advice on storytelling, non-verbal communication, and Q&A, such as how to talk about each slide and how to emphasize key points.
[0792] Output: The generated advice is saved on the server.
[0793] Step 10:
[0794] Users practice and prepare
[0795] Input: Advice provided by the server
[0796] Specific operation: The user rehearses the presentation on the device based on the advice. For example, they practice the questions they anticipate will be asked during the actual presentation and how to deal with them.
[0797] Output: Users will be better prepared and have better presentation skills
[0798] The above is the specific processing flow in the system program.
[0799] (Application example 1)
[0800] 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."
[0801] Creating presentation materials requires a lot of time and effort, making it difficult to quickly create high-quality materials. It is also difficult for users who lack knowledge and experience in presentation techniques to give effective presentations. Therefore, there is a demand for a system that can create high-quality presentation materials in a short amount of time and support effective presentations.
[0802] 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.
[0803] In this invention, the server includes input means for a user to input the presentation theme, purpose, target audience, and information to be provided, generation means for generating presentation materials based on the information received from the input means, provision means for providing the presentation materials generated by the generation means to the user, advice means for giving advice on presentation techniques based on the presentation materials, advice means for providing effective ways of speaking and question-and-answer sessions in the presentation, and means for providing technique guidance to the user based on the presentation. This enables the user to create high-quality presentation materials and prepare for an effective presentation in a short period of time.
[0804] "Input means" refers to a device or software that allows a user to input the presentation's theme, purpose, target audience, and information to be provided.
[0805] The "generation means" is a device or software that has the function of automatically generating presentation materials based on the information received from the input means.
[0806] The "providing means" is a device or software having a function for providing the presentation materials generated by the generating means to the user.
[0807] An "advice means" is a device or software that has the function of giving advice to a user on presentation techniques based on presentation materials.
[0808] The "means for providing advice on how to speak and how to answer questions" refers to a device or software that has the function of providing specific guidance to the user on how to speak effectively in a presentation and how to answer questions.
[0809] The "means for providing instruction in techniques" refers to a device or software that has the function of providing instruction to users in presentation techniques based on the presentation.
[0810] The present invention relates to a system including: an input means for a user to input the theme, purpose, target audience, and information to be provided of a presentation; a generation means for generating presentation materials based on the information received from the input means; a provision means for providing the generated presentation materials to a user; and an advice means for providing advice on presentation techniques based on the presentation materials. The system also includes an advice means for providing effective ways of speaking and question-and-answer sessions during the presentation, and a means for providing instruction on the techniques to a user based on the presentation.
[0811] System Configuration
[0812] The system consists of the following main components:
[0813] 1. Terminal: A device through which a user enters information (e.g., smartphone, computer, tablet).
[0814] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0815] 3. AI model: An artificial intelligence model trained to generate presentation materials and provide advice on presentation techniques.
[0816] Implementation details
[0817] The user inputs basic information about the presentation (e.g., theme, purpose, target audience, and information to be provided) using a dedicated application or web browser on the device. For example, the user inputs "features of a new product" as the theme, "selling the new product to investors" as the purpose, "investors knowledgeable about technology" as the target audience, and "major functions, technological advantages, and market potential of the product" as the information to be provided.
[0818] The server receives the basic information sent from the device and requests the AI model to generate presentation materials. The AI model automatically generates a slide deck based on specialized knowledge. For example, the following slide structure is generated:
[0819] 1. Title slide (new product name and logo)
[0820] 2. Slides introducing the main features of the product
[0821] 3. Slides explaining technological superiority
[0822] 4. Market Potential Analysis Slide
[0823] 5. Summary and Next Steps
[0824] The generated presentation materials are sent back to the terminal, where they are reviewed and revised by the user. The user reviews each slide and makes corrections or additions to text, images, and graphs as necessary. Once the revisions are complete, the slides are saved and sent back to the server.
[0825] The server receives the corrected data and updates the presentation materials, which are then provided to the user again. Based on the completed presentation materials, the AI model generates advice on storytelling, non-verbal communication, and Q&A.
[0826] The user practices the presentation based on the advice provided. For example, the user rehearses the presentation and reflects the advice from the server.
[0827] Hardware and software used
[0828] Hardware:
[0829] 1. Smartphone or tablet
[0830] 2. Server equipment
[0831] software:
[0832] 1. Python and related libraries (such as requests)
[0833] 2. OpenAI API
[0834] Prompt Sentence Examples
[0835] Theme: Cybersecurity measures
[0836] Objective: To propose new security solutions to customers.
[0837] Target audience: Security personnel
[0838] Information provided: Features of new security tools, technical advantages, and benefits of their implementation
[0839] Use this to generate presentation slides.
[0840] This invention enables users to create high-quality presentation materials in a short time and deliver effective presentations based on them. Each component works in conjunction with the others to streamline the presentation preparation process and help users improve their skills.
[0841] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0842] Step 1:
[0843] The user inputs basic information about the presentation (theme, purpose, target audience, information to be provided) using a dedicated application or web browser on the device. This information is then sent from the device to the server. Specifically, this includes a function to format the input information such as theme and purpose and send it to the server. An example of input data is "Theme: Features of a new product," and this information is sent to the server.
[0844] Step 2:
[0845] The server receives basic information sent from the device. The received information is used as input data for generating presentation materials. This data is stored in the server's storage and becomes the material for generating prompts for the AI model. The server analyzes the received data and formats it as needed.
[0846] Step 3:
[0847] The server creates a prompt to request the AI model to generate presentation materials based on the received basic information. Specifically, it uses Python to generate a prompt based on the basic information. It sends this prompt to the OpenAI API and receives a response from the AI model. An example of a prompt is "Topic: Cybersecurity measures, Objective: Propose new security solutions to customers."
[0848] Step 4:
[0849] The AI model automatically generates a presentation based on the provided prompts. The generated presentation is sent back to the server. The AI model generates the content for each slide based on the input prompts and sends the results in text format to the server.
[0850] Step 5:
[0851] The server receives the response from the AI model, formats the content, and sends it to the device as a presentation. Specifically, it converts the received text into slides and formats it in a way that is easy for the user to review. This allows the user to view the generated presentation on their device.
[0852] Step 6:
[0853] The user can check the presentation materials created on their device and make corrections or additions as necessary. Specifically, they can correct text and add images and graphs. After the user makes the corrections, the revised data is sent back to the server.
[0854] Step 7:
[0855] The server receives the modified data from the user and updates the presentation materials. The updated materials are then provided to the user again. The server then generates the latest materials that reflect the updated data and sends them to the terminal.
[0856] Step 8:
[0857] Based on the completed presentation materials, the server generates advice on presentation techniques, including advice on storytelling, non-verbal communication, and Q&A. The server then generates prompts for the AI model again to obtain appropriate advice.
[0858] Step 9:
[0859] The user practices the presentation based on the advice provided. Specifically, the user rehearses the presentation and incorporates the advice provided by the server. The user practices using the terminal and acquires effective presentation techniques.
[0860] This series of processing steps enables users to efficiently create high-quality presentation materials and prepare for their presentations effectively.
[0861] 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.
[0862] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses an AI model to generate presentation materials based on basic information entered by the user, and also recognizes the user's emotions and provides comprehensive advice on adapting presentation techniques.
[0863] System configuration
[0864] The system consists of the following components:
[0865] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[0866] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0867] 3. AI model: An artificial intelligence model trained to generate professional presentation materials and provide advice on presentation techniques.
[0868] 4. Emotion engine: A device or program that recognizes the user's emotions and adapts presentation materials and advice.
[0869] Program processing
[0870] The user enters basic information
[0871] Device:
[0872] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[0873] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[0874] The server generates the materials
[0875] server:
[0876] The server receives the basic information sent from the terminal.
[0877] Based on the received information, the AI model is asked to generate presentation materials.
[0878] The AI model automatically generates a slide deck based on its expert knowledge, resulting in a slide structure like this:
[0879] 1. Title slide (new product name and logo)
[0880] 2. Slides introducing the main features of the product
[0881] 3. Slides explaining technological superiority
[0882] 4. Market Potential Analysis Slide
[0883] 5. Summary and Next Steps Slide
[0884] The server temporarily stores the generated materials and transmits them to the user terminal as preview data.
[0885] User checks and modifies the materials
[0886] Device:
[0887] The generated presentation materials are displayed on the device.
[0888] Users can check each slide, select the one they want to edit, and modify or add text, images, and graphs.
[0889] For example: modify the text, add a chart, insert an image, etc.
[0890] When the user clicks the "Save" button for the slide after completing the editing, the modified data is sent to the server.
[0891] server:
[0892] The presentation materials are updated by receiving the corrected data sent by the user.
[0893] The updated presentation materials are provided to the user again.
[0894] The server will give you advice on the key points of your presentation.
[0895] server:
[0896] The completed presentation materials are analyzed by an AI model.
[0897] For each slide, the AI model generates advice on storytelling, non-verbal communication, and how to handle questions and answers.
[0898] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[0899] The server recognizes the user's emotions
[0900] Emotion Engine:
[0901] When a user practices a presentation, the emotion engine analyzes the user's voice, facial expressions, and biometric signals to recognize their emotions.
[0902] The recognized emotion data is sent to a server.
[0903] Coordinating and providing advice
[0904] server:
[0905] Adapt presentation materials and advice based on emotional data from the emotion engine.
[0906] Example: If the user is nervous, give them advice on how to relax or suggest slide corrections.
[0907] The adjusted advice is transmitted to the user terminal.
[0908] Users practice and prepare
[0909] Device:
[0910] The user practices the presentation based on the advice provided.
[0911] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[0912] Make final preparations for the presentation.
[0913] As described above, this system helps users to efficiently create high-quality presentation materials and optimize their presentation techniques based on emotion recognition data, thereby helping users to give effective presentations.
[0914] The processing flow will be explained below.
[0915] Step 1:
[0916] The user enters basic information.
[0917] User: Log in to the device and click the Create New Presentation button.
[0918] Terminal: Display the screen for entering basic information about the presentation.
[0919] User: Enter the theme, purpose, target audience, and information to provide.
[0920] For example: Theme: "Features of the new product", Objective: "Pitching the new product to investors", Target audience: "Technology-savvy investors", Information provided: "Key product features, technological advantages, and market potential".
[0921] User: Click the "Next" button.
[0922] Step 2:
[0923] A server receives the information and generates a presentation.
[0924] Terminal: Sends the entered basic information to the server.
[0925] Server: Provides the received basic information to the AI model.
[0926] AI model: Generate presentation materials. For example, the following slide structure:
[0927] 1. Title Slide
[0928] 2. Slides introducing the main features of the product
[0929] 3. Technological advantage explanation slides
[0930] 4. Market Potential Analysis Slide
[0931] 5. Summary and Next Steps Slide
[0932] Server: Temporarily stores the generated materials and sends them to the user's device as preview data.
[0933] Step 3:
[0934] The user can review and modify the generated materials.
[0935] Device: Shows a preview of the generated presentation.
[0936] User: Review the content of each slide and select the slide they want to edit.
[0937] Terminal: Switches to edit mode and provides an interface for users to enter information to be modified or added.
[0938] For example: modify the text, add a chart, insert an image, etc.
[0939] User: Clicks the "Save" button for the slide after editing is complete.
[0940] Device: Sends the saved correction data to the server.
[0941] Step 4:
[0942] The server updates the presentation materials to reflect the corrected data.
[0943] Server: Receives the correction data sent by the user.
[0944] Server: Update the presentation materials based on the revised data.
[0945] Server: The updated presentation materials are again temporarily saved and resent to the user.
[0946] Step 5:
[0947] The server will give you advice on the key points of your presentation.
[0948] Server: The AI model analyzes the completed presentation materials.
[0949] AI model: Generates advice for each slide on how to handle storytelling, non-verbal communication, and Q&A.
[0950] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[0951] Server: Sends the generated advice to the user terminal.
[0952] Step 6:
[0953] The server recognizes the user's emotions.
[0954] Terminal: The emotion engine runs when the user practices their presentation.
[0955] Emotion engine: Recognizes emotions by analyzing the user's voice, facial expressions, and biometric signals.
[0956] Emotion Engine: Sends the recognized emotion data to the server.
[0957] Example: If the user is nervous, the degree of nervousness is converted into a numerical value and sent to the server.
[0958] Step 7:
[0959] Coordinating and providing advice.
[0960] Server: Analyzes emotion recognition data and adapts presentation materials and advice content.
[0961] For example: If the user is nervous, give them advice on how to relax or suggest revisions to make the slides more understandable.
[0962] Server: Sends the adjusted advice to the user terminal.
[0963] Step 8:
[0964] Users practice and prepare.
[0965] Terminal: Displays advice sent from the server.
[0966] Users: Review the advice on each slide and practice your presentation.
[0967] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[0968] User: Make final preparations for the presentation.
[0969] These are the specific processing steps of this system. The user, device, and server work together to improve the efficiency and quality of the presentation preparation process based on emotion recognition.
[0970] Example 2
[0971] 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."
[0972] Conventional presentation creation systems make it difficult for users to create high-quality presentations in a short amount of time. Furthermore, there are no systems that provide presentation technique advice that takes into account the user's emotional state, making it difficult to maximize the effectiveness of a presentation. This lack of optimal advice is particularly problematic for users who are unfamiliar with presentations or who tend to get nervous.
[0973] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for a user to input the theme, purpose, target audience, and information to be provided of the presentation, a generation means for generating presentation materials based on the information received from the input means, a provision means for providing the presentation materials generated by the generation means to the user, an advice means for giving advice on presentation techniques based on the presentation materials, and an emotion recognition means for recognizing the user's emotions and adapting the advice on presentation techniques. This enables the user to create high-quality presentation materials in a short period of time and receive advice on optimal presentation techniques according to the user's emotional state.
[0974] "Presentation materials" refers to slides or documents containing information or content that a user uses when giving a presentation.
[0975] "Input means" refers to an interface or device that allows a user to input the presentation's theme, purpose, target audience, and information to be provided.
[0976] The "generation means" refers to a mechanism or program for generating presentation materials based on the information received from the input means.
[0977] The "providing means" refers to a mechanism or method for providing the presentation materials generated by the generating means to the user.
[0978] "Advice means" refers to a mechanism or program for giving advice on presentation techniques based on the presentation materials.
[0979] The "emotion recognition means" refers to a mechanism or program for recognizing the user's emotions and adapting the presentation technique advice.
[0980] A "user" is someone who creates presentation materials and gives a presentation.
[0981] The term "server" refers to a central processing unit including the input means, generation means, provision means, advice means, and emotion recognition means.
[0982] An "AI model" is an artificial intelligence model that has learned from presentation professionals with specialized knowledge.
[0983] "Voice, facial expression, and biological signals" refers to the user's voice data, facial expression data, and biological activity data used by the emotion recognition means to detect the user's emotions.
[0984] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses a generative AI model to generate presentation materials based on basic information entered by the user, and also recognizes the user's emotions and provides comprehensive advice on adapting presentation techniques.
[0985] System configuration
[0986] The system consists of the following components:
[0987] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[0988] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[0989] 3. AI model: An artificial intelligence model trained by presentation professionals with specialized knowledge.
[0990] 4. Emotion recognition means: A device or program that recognizes the user's emotions and adapts presentation materials or advice accordingly.
[0991] Program processing
[0992] The user enters basic information
[0993] Device:
[0994] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[0995] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[0996] The server generates the materials
[0997] server:
[0998] The server receives the basic information sent from the terminal.
[0999] Based on the received information, the AI model is asked to generate presentation materials.
[1000] The AI model automatically generates a slide deck based on its expert knowledge, resulting in a slide structure like this:
[1001] 1. Title slide (new product name and logo)
[1002] 2. Slides introducing the main features of the product
[1003] 3. Slides explaining technological superiority
[1004] 4. Market Potential Analysis Slide
[1005] 5. Summary and Next Steps Slide
[1006] The server temporarily stores the generated materials and transmits them to the user terminal as preview data.
[1007] User checks and modifies the materials
[1008] Device:
[1009] The generated presentation materials are displayed on the device.
[1010] Users can check each slide, select the one they want to edit, and modify or add text, images, and graphs.
[1011] For example: modify the text, add a chart, insert an image, etc.
[1012] When the user clicks the "Save" button for the slide after completing the editing, the modified data is sent to the server.
[1013] server:
[1014] The presentation materials are updated by receiving the corrected data sent by the user.
[1015] The updated presentation materials are provided to the user again.
[1016] The server will give you advice on the key points of your presentation.
[1017] server:
[1018] The completed presentation materials are analyzed by an AI model.
[1019] For each slide, the AI model generates advice on storytelling, non-verbal communication, and how to handle questions and answers.
[1020] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[1021] The server recognizes the user's emotions
[1022] Emotion recognition means:
[1023] When a user practices a presentation, their emotions are recognized by analyzing their voice, facial expressions, and biometric signals.
[1024] The recognized emotion data is sent to a server.
[1025] Coordinating and providing advice
[1026] server:
[1027] The presentation materials and advice content are adapted based on the emotional data from the emotion recognition means.
[1028] Example: If the user is nervous, give them advice on how to relax or suggest slide corrections.
[1029] The adjusted advice is transmitted to the user terminal.
[1030] Users practice and prepare
[1031] Device:
[1032] The user practices the presentation based on the advice provided.
[1033] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[1034] Make final preparations for the presentation.
[1035] Examples of concrete examples and prompts
[1036] Below are some examples and prompts:
[1037] Specific examples
[1038] 1. User input:
[1039] Theme: "Environmentally friendly new energy technology"
[1040] Purpose: "Introducing technology to the new energy sector of companies"
[1041] Target audience: "Engineers with knowledge of environmental technology"
[1042] Information provided: "Technology characteristics, environmental impacts, economic benefits"
[1043] 2. Generated slide configuration:
[1044] Title slide (technology name and logo)
[1045] Slide introducing the features of the technology
[1046] Environmental Impact Slides
[1047] Economic benefits slide
[1048] Summary and next steps slide
[1049] 3. Specific examples of advice:
[1050] "It's important to focus the audience's attention on this slide and emphasize the technical features."
[1051] "When explaining economic benefits, using concrete figures helps capture the audience's attention."
[1052] Prompt Sentence Examples
[1053] "Please create a presentation that explains the features of the new product."
[1054] "Provide advice on slides that highlight the environmental impact and economic benefits."
[1055] "Please advise the user on how to relax if they are nervous."
[1056] In this way, by using prompt sentences, we have created a system that provides information in a format that is easy to input into the generative AI model, allowing participants to receive advice on more effective presentation materials and presentation techniques.
[1057] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1058] Now, let me explain the process of the system program step by step.
[1059] Processing Steps
[1060] Step 1: User enters basic information
[1061] Step 2: The server generates the materials
[1062] Step 3: User checks and modifies the materials
[1063] Step 4: The server gives advice on key points of the presentation
[1064] Step 5: The server recognizes the user's emotion
[1065] Step 6: Coordinating and providing advice
[1066] Step 7: User Practice and Preparation
[1067] Step-by-step instructions
[1068] Step 1: User enters basic information
[1069] Device:
[1070] Input: The user enters the presentation topic, purpose, target audience, and information to be provided.
[1071] How it works: The user launches a dedicated application or web browser on their device and enters the necessary information into the input form. For example, they enter "new product features" as the presentation topic, "selling the new product to investors" as the purpose, "technology-savvy investors" as the target audience, and "the product's main functions, technological advantages, and market potential" as the information to be provided.
[1072] Output: The entered information is sent to the server.
[1073] Step 2: The server generates the materials
[1074] server:
[1075] Input: Basic information sent from the device.
[1076] How it works: The server receives the HTTP POST request and temporarily stores it in a database. It then uses the received information to request the generative AI model to generate presentation materials. Specifically, it sends an API request to the AI model and receives the generated slide deck data.
[1077] Output: The generated presentation materials are temporarily saved and sent to the user's device as preview data.
[1078] Step 3: User checks and modifies the materials
[1079] Device:
[1080] Input: Preview data of presentation materials sent from the server.
[1081] How it works: The generated presentation materials are displayed on the device. The user can review each slide, select the one they want to edit, and modify or add text, images, or graphs. For example, they can modify text, add graphs, or insert images, and then click the "Save" button for the slide they've completed editing.
[1082] Output: The modified data is sent to the server.
[1083] server:
[1084] Input: Correction data submitted by the user.
[1085] Operation: Receives the revised data sent by the user and updates the presentation materials. Specifically, it updates the database and generates new slide data.
[1086] Output: The updated presentation is provided to the user again.
[1087] Step 4: The server gives advice on key points of the presentation
[1088] server:
[1089] Input: The completed presentation.
[1090] Operation: The completed presentation materials are analyzed by the AI model. The data is sent to the analysis endpoint of the AI model, and the advice data returned by the AI model is formatted and integrated back into the presentation materials.
[1091] Output: For each slide, advice data is generated on how to handle storytelling, non-verbal communication, and questions and answers.
[1092] Step 5: The server recognizes the user's emotion
[1093] Emotion recognition means:
[1094] Input: Speech, facial expression, and biometric data collected as users practice their presentations.
[1095] How it works: Data is collected from cameras, microphones, and wearable devices, and fed into an emotion analysis algorithm. The analysis results are sent to a server in real time.
[1096] Output: The recognized emotion data is generated and sent to the server.
[1097] Step 6: Coordinating and providing advice
[1098] server:
[1099] Input: Emotion data from emotion recognition instrument.
[1100] Behavior: Analyzes emotional data and adapts presentation materials and advice. For example, if the user is nervous, the system will suggest ways to relax.
[1101] Output: The adjusted advice is generated and sent to the user terminal.
[1102] Step 7: User Practice and Preparation
[1103] Device:
[1104] Input: Tailored advice and updated presentation materials.
[1105] Action: The user practices their presentation based on the provided advice. For example, they record their own presentation using the audio recording function and try to demonstrate it according to the advice. This allows them to make final checks in preparation for the actual presentation.
[1106] Output: The user is ready to give an effective presentation.
[1107] (Application example 2)
[1108] 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."
[1109] In modern logistics centers, it is necessary to create presentation materials to quickly and effectively report improvements in work efficiency and the effects of new deployment systems. However, it is a major challenge for workers to create high-quality presentation materials and effectively communicate their content while performing their daily tasks. It is also difficult to properly manage the presenter's emotions and tension to maximize performance. Therefore, a system that can reflect the on-site situation in real time and use emotion recognition to improve the quality of presentations is needed.
[1110] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: input means for a user to input the presentation theme, purpose, target audience, and information to be provided; generation means for generating presentation materials based on the information received from the input means; provision means for providing the presentation materials generated by the generation means to the user; advice means for providing presentation technique advice based on the presentation materials; emotion recognition means for recognizing the user's emotions and adapting the presentation materials and advice; and means for checking and correcting the presentation materials via a smart device. This not only enables workers at a logistics center to quickly create presentation materials that reflect on-site video and data in real time, but also improves the quality of presentations and enables more effective reporting through emotion recognition technology.
[1111] "Input means" refers to a device or system that allows a user to input the theme, purpose, target audience, and information to be provided for the presentation.
[1112] The "generation means" is a device or system for automatically creating presentation materials based on the information received from the input means.
[1113] The "providing means" is a device or system that provides the presentation materials created by the generating means to the user, allowing them to be viewed and modified.
[1114] The "advice means" is a device or system that provides guidance to the user on presentation techniques based on the presentation materials and suggests areas for improvement.
[1115] "Emotion recognition means" refers to a device or program that analyzes the user's voice, facial expressions, etc., and recognizes their emotional state.
[1116] A "smart device" is a device that has Internet connectivity and allows users to view and operate information visually or audibly.
[1117] "Presentation materials" refers to documents and slides that illustrate or describe the content that a user will present.
[1118] The system that realizes this application example allows users to create presentation materials in real time at a logistics center, and then confirm and modify the contents to make effective presentations.
[1119] The present invention is implemented using the following hardware and software:
[1120] 1. Smart device (e.g., smart glasses): A device that allows users to input the presentation topic, purpose, target audience, and information to be provided, and to review and modify presentation materials.
[1121] 2. Camera module: A device built into the smart glasses for capturing on-site footage.
[1122] 3. Server: A central processing unit that generates and provides presentation materials based on information received from the input means and gives advice on presentation techniques.
[1123] 4. AI model (e.g., PresentationAI): An artificial intelligence model trained from presentation professionals with specialized knowledge, used to automatically generate presentation materials.
[1124] 5. Emotion recognition software (e.g., EmotionEngine): Software that analyzes the user's emotions and recognizes their state.
[1125] The server first receives the presentation's theme, purpose, target audience, and information sent from the smart device. Based on this information, it uses an AI model to automatically generate presentation materials. The generated presentation materials are then provided to the user via their smart device, who can review the materials in real time and make edits to the text and images as needed.
[1126] Next, emotion recognition software analyzes data such as the user's voice and facial expressions to recognize their emotions. Based on the results, the server adapts the presentation materials and advice provided. This process allows the user to improve the quality of their presentation by offering advice on how to relax or suggesting slide revisions if they are nervous.
[1127] As a concrete example, consider a scenario in which an efficiency improvement report for a new warehouse allocation system is created. A user wears smart glasses and captures video of the warehouse. OCR technology is used to extract text data from the video, and an AI model automatically generates a slide deck based on this data. The generated slides include an overview of the new warehouse allocation system, the efficiency improvement status, and cost reduction effects. The user checks the slides on the smart glasses' display and makes any necessary corrections. If emotion recognition software detects that the user is tense, advice such as encouraging deep breathing is displayed.
[1128] An example prompt is, "Generate a presentation to create an efficiency improvement report for a new warehouse layout system. Key areas to focus on include efficiency gains, cost savings, and staff satisfaction after the layout change."
[1129] As described above, this system supports the efficient and effective creation and presentation of presentation materials at logistics centers.
[1130] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1131] Step 1:
[1132] The user uses a smart device (e.g., smart glasses) to input the presentation topic, objectives, target audience, and information to be provided. The input information is sent from the smart device to the server. Examples of input data include "improving the efficiency of the logistics center," "presentation on business improvement," "manager," and "improving the efficiency of a new warehouse layout system."
[1133] Step 2:
[1134] The server automatically generates presentation materials using a generative AI model (e.g., PresentationAI) based on the received input data. Specifically, it creates an appropriate slide structure based on the theme and purpose, and embeds the content. For example, it generates slides such as a "title slide," a "slide explaining the efficiency improvement after the layout change," and a "slide showing the cost reduction effect." The output is the automatically generated presentation materials.
[1135] Step 3:
[1136] The server provides the generated presentation materials to the smart device. The user checks the presentation materials on the smart device's display and operates the interface to modify text, images, and charts as necessary. The entered modification data is then sent to the server. The input here is the user's modification instructions, and the output is the modified presentation materials.
[1137] Step 4:
[1138] The server updates the presentation materials based on the corrections sent by the user. The updated presentation materials are then sent back to the smart device, where the user can review and make final adjustments. The final presentation materials are then output.
[1139] Step 5:
[1140] When a user rehearses a presentation, emotion recognition software (e.g., EmotionEngine) on the smart device analyzes the user's voice and facial expressions to recognize emotional data. Based on this, the user's state of tension or relaxation is analyzed. The input data is the user's voice and facial expression data, and the output data is the analyzed emotional information.
[1141] Step 6:
[1142] The server adjusts the content of the presentation materials and advice based on the emotional data sent from the emotion recognition software. For example, if the user is nervous, the server may suggest relaxation techniques such as encouraging deep breathing or change the slide structure. The adjusted advice and presentation materials are then output.
[1143] Step 7:
[1144] The user receives final advice via their smart device and makes final adjustments while rehearsing their presentation. This process prepares the user for the actual presentation. The final output is a quality-improved presentation document and advice for the user.
[1145] The above are the specific processing steps of the system that realizes the application example.
[1146] 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.
[1147] 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.
[1148] 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.
[1149] [Third embodiment]
[1150] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[1151] 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.
[1152] 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).
[1153] 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.
[1154] 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.
[1155] 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).
[1156] 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. 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.
[1157] 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.
[1158] 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.
[1159] 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.
[1160] 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.
[1161] 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."
[1162] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses an AI model to generate presentation materials based on basic information entered by the user, and also provides comprehensive advice to improve the user's presentation techniques.
[1163] System configuration
[1164] The system consists of the following components:
[1165] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[1166] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1167] 3. AI model: An artificial intelligence model trained to generate professional presentation materials and provide advice on presentation techniques.
[1168] Program processing
[1169] The user enters basic information
[1170] Device:
[1171] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[1172] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[1173] The server generates the materials
[1174] server:
[1175] The server receives the basic information sent from the terminal.
[1176] Based on the received information, the AI model is asked to generate presentation materials.
[1177] The AI model automatically generates a slide deck based on its expert knowledge. For example, it might generate the following slide structure:
[1178] 1. Title slide (new product name and logo)
[1179] 2. Slides introducing the main features of the product
[1180] 3. Slides explaining technological superiority
[1181] 4. Market Potential Analysis Slide
[1182] 5. Summary and Next Steps
[1183] User checks and modifies the materials
[1184] Device:
[1185] The generated presentation materials are displayed on the device.
[1186] The user checks each slide and modifies or adds text, images, and graphs as necessary.
[1187] Once the edits are complete, the slide is saved and sent to the server.
[1188] server:
[1189] Receive corrected data and update presentation materials.
[1190] Updated materials will be provided to users again.
[1191] The server will give you advice on the key points of your presentation.
[1192] server:
[1193] Based on the completed presentation, the AI model generates advice on storytelling, non-verbal communication, and Q&A.
[1194] For example: how to talk through each slide, how to emphasize key points, how to move your eyes, anticipated questions and how to deal with them, etc.
[1195] Users practice and prepare
[1196] Device:
[1197] The user practices the presentation based on the advice provided.
[1198] As a concrete example, a presentation is rehearsed and advice from the server is reflected.
[1199] As described above, this system enables users to create high-quality presentation materials in a short amount of time and deliver effective presentations based on them. Each component works together to streamline the presentation preparation process and help users improve their skills.
[1200] The processing flow will be explained below.
[1201] Step 1:
[1202] The user enters basic information.
[1203] User: Log in to the device and click the Create New Presentation button.
[1204] Terminal: Display the screen for entering basic information about the presentation.
[1205] User: Enter the theme, purpose, target audience, and information to provide.
[1206] For example: Theme: "Features of the new product", Objective: "Pitching the new product to investors", Target audience: "Technology-savvy investors", Information provided: "Key product features, technological advantages, and market potential".
[1207] User: Click the "Next" button.
[1208] Step 2:
[1209] A server receives the information and generates a presentation.
[1210] Terminal: Sends the entered basic information to the server.
[1211] Server: Provides the received basic information to the AI model.
[1212] AI model: Generate presentation materials. For example, the following slide structure:
[1213] 1. Title Slide
[1214] 2. Slides introducing the main features of the product
[1215] 3. Technological advantage explanation slides
[1216] 4. Market Potential Analysis Slide
[1217] 5. Summary and Next Steps Slide
[1218] Server: Temporarily stores the generated materials and sends them to the user's device as preview data.
[1219] Step 3:
[1220] The user can review and modify the generated materials.
[1221] Device: Shows a preview of the generated presentation.
[1222] User: Review the content of each slide and select the slide they want to edit.
[1223] Terminal: Switches to edit mode and provides an interface for users to enter information to be modified or added.
[1224] For example: modify the text, add a chart, insert an image, etc.
[1225] User: Clicks the "Save" button for the slide after editing is complete.
[1226] Device: Sends the saved correction data to the server.
[1227] Step 4:
[1228] The server updates the presentation materials to reflect the corrected data.
[1229] Server: Receives the correction data sent by the user.
[1230] Server: Update the presentation materials based on the revised data.
[1231] Server: The updated presentation materials are again temporarily saved and resent to the user.
[1232] Step 5:
[1233] The server will give you advice on the key points of your presentation.
[1234] Server: The AI model analyzes the completed presentation materials.
[1235] AI model: Generates advice for each slide on how to handle storytelling, non-verbal communication, and Q&A.
[1236] For example: how to talk about each slide, how to emphasize points, how to move your eyes, anticipated questions and how to prepare for them.
[1237] Server: Sends the generated advice in text format to the user terminal.
[1238] Step 6:
[1239] Users practice and prepare.
[1240] Terminal: Displays advice sent from the server.
[1241] Users: Review the advice on each slide and practice your presentation.
[1242] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[1243] User: Make final preparations for the presentation.
[1244] These are the specific processing steps of this system. At each step, the user, terminal, and server work together to efficiently and effectively support the creation of presentation materials and preparation for presentations.
[1245] Example 1
[1246] 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."
[1247] Currently, there are many tools on the market for creating presentation materials effectively, but they have the following problems: Creating presentation materials takes time, and it is difficult to create high-quality materials in a short amount of time. Furthermore, if the user does not have specialized knowledge or skills in presentation techniques, it is difficult to give an effective presentation. As a result, there is a demand for a system that allows users to create presentation materials effectively and quickly without requiring much effort or time, and also to improve their presentation techniques.
[1248] 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.
[1249] In this invention, the server includes input means for a user to input the presentation theme, purpose, target audience, and information to be provided, generation means for generating presentation materials based on the information received from the input means, provision means for providing the presentation materials generated by the generation means to the user, advice means for providing presentation technique advice based on the presentation materials, editing means for the user to check and correct the generated presentation materials, and update means for receiving the data corrected by the editing means and updating the presentation materials, thereby enabling the user to create high-quality presentation materials in a short period of time and improve their own presentation techniques.
[1250] "Input means" refers to a device or interface that allows a user to input the theme, purpose, target audience, and information to be provided for the presentation.
[1251] The "generation means" refers to a device or software that automatically generates presentation materials based on information received from the input means.
[1252] The "providing means" refers to a device or interface for presenting and providing the presentation materials generated by the generating means to the user.
[1253] The "advice means" is a device or software that provides the user with advice on presentation techniques based on the created presentation materials.
[1254] "Editing means" refers to a device or interface that allows a user to check and modify the generated presentation materials.
[1255] The "updating means" refers to a device or software that receives the data corrected by the editing means again and updates the presentation materials.
[1256] A "generative artificial intelligence model" is an artificial intelligence model that learns from presentation professionals with specialized knowledge and is used to automatically generate presentation materials.
[1257] "Storytelling" is a technique for effectively conveying information using stories.
[1258] "Nonverbal communication" is a method of conveying information and emotions using means other than words (gestures, facial expressions, gaze, etc.).
[1259] "Question and answer" is a technique for appropriately answering questions from the audience during a presentation.
[1260] The present invention is a system that enables users to create high-quality presentation materials in a short period of time and deliver effective presentations. This system uses a generative AI model to generate presentation materials based on basic information entered by the user, and also provides comprehensive advice to help the user improve their presentation techniques. Details for specifically implementing the present invention are provided below.
[1261] System configuration
[1262] The system consists of the following components:
[1263] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[1264] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1265] 3. AI model: A generative AI model trained by presentation professionals with expert knowledge.
[1266] Program processing
[1267] The user enters basic information
[1268] Terminal: The user uses the terminal's dedicated application or web browser to input the presentation topic, purpose, target audience, and information to be provided. For example, input the following information:
[1269] Theme: New product features
[1270] Purpose: Pitching new products to investors
[1271] Target audience: Tech-savvy investors
[1272] Information provided: Product's main features, technical advantages, market potential
[1273] The server generates the materials
[1274] Server: Receives basic information sent from the device. Based on the received information, it requests the generative AI model to generate presentation materials. Based on specialized knowledge, the generative AI model automatically generates presentation materials with the following slide structure:
[1275] 1. Title slide (new product name and logo)
[1276] 2. Slides introducing the main features of the product
[1277] 3. Slides explaining technological superiority
[1278] 4. Market Potential Analysis Slide
[1279] 5. Summary and Next Steps
[1280] User checks and modifies the materials
[1281] Device: The generated presentation materials are displayed on the device. The user can check each slide and use a dedicated editor to edit or add text, images, and graphs. Once edited, the slide is saved and sent to the server.
[1282] The server will give you advice on the key points of your presentation.
[1283] Server: Receives the corrected data and updates the presentation. Based on the completed presentation, the generative AI model generates advice on storytelling, non-verbal communication, and Q&A. For example, it provides advice such as:
[1284] How to talk about each slide
[1285] How to emphasize key points
[1286] How to move your eyes
[1287] Anticipated questions and how to address them
[1288] Users practice and prepare
[1289] Terminal: The user practices the presentation based on the advice provided. For example, the user rehearses the presentation and reflects the advice from the server in the actual presentation.
[1290] As described above, this system enables users to create high-quality presentation materials in a short amount of time and deliver effective presentations based on them. Each component works together to streamline the presentation preparation process and help users improve their skills.
[1291] Specific prompt examples
[1292] Here is an example of a prompt that a user might enter to begin creating a presentation:
[1293] Presentation theme: New product features
[1294] Purpose: Pitching new products to investors
[1295] Target audience: Tech-savvy investors
[1296] Information provided: Product's main features, technical advantages, market potential
[1297] The above processing flow allows the user to efficiently prepare for a presentation.
[1298] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1299] Step 1:
[1300] The user enters the presentation topic, purpose, target audience, and information to be provided
[1301] Input: The user enters information into an input form using a dedicated application or a web browser.
[1302] Specific operation: The user inputs the following information, for example:
[1303] Theme: New product features
[1304] Purpose: Pitching new products to investors
[1305] Target audience: Tech-savvy investors
[1306] Information provided: Product's main features, technical advantages, market potential
[1307] Output: Input data is saved to the device
[1308] Step 2:
[1309] The device sends the input information to the server
[1310] Input: Basic information entered by the user
[1311] Specific operation: Send data from the device to the server using a secure communication protocol (e.g. HTTPS).
[1312] Output: The input information is saved on the server.
[1313] Step 3:
[1314] The server requests the AI model to generate presentation materials based on the received information.
[1315] Input: Presentation topic, purpose, target audience, and information to provide sent from your device
[1316] Specific operation: The server encodes the data to the generative AI model and sends it as a prompt for generating presentation materials.
[1317] Output: Presentation materials generated by the generative AI model are output.
[1318] Step 4:
[1319] Generative AI model generates presentation materials
[1320] Input: Prompt and basic information sent from the server
[1321] How it works: The generative AI model automatically generates content for each slide in a presentation, including:
[1322] 1. Title slide (new product name and logo)
[1323] 2. Slides introducing the main features of the product
[1324] 3. Slides explaining technological superiority
[1325] 4. Market Potential Analysis Slide
[1326] 5. Summary and Next Steps
[1327] Output: The generated presentation material is sent to the server.
[1328] Step 5:
[1329] The server sends the generated presentation materials to the terminal.
[1330] Input: Presentation materials generated by the generative AI model
[1331] Specific operation: The server converts the generated slide deck into a Pedia format (PDF, PPTX, etc.) and sends it to the device.
[1332] Output: Presentation materials are displayed on the device.
[1333] Step 6:
[1334] User checks and modifies the materials
[1335] Input: Presentation materials sent from the server
[1336] Specific actions: Users can use the dedicated editor on their devices to review and modify the text, images, and graphs on each slide, for example, adding descriptions of the product's main features.
[1337] Output: The revised presentation material will be saved on your device.
[1338] Step 7:
[1339] The device sends the correction data to the server
[1340] Input: User-modified presentation
[1341] Specific operation: The corrected document is sent to the server using a secure communication protocol (e.g., HTTPS).
[1342] Output: The modified data is saved on the server.
[1343] Step 8:
[1344] The server reflects the corrected data and updates the presentation materials.
[1345] Input: Correction data sent from the terminal
[1346] Specific operation: The server updates the document based on the revised data and saves the final version.
[1347] Output: The updated presentation material is saved on the server.
[1348] Step 9:
[1349] The server will give you advice on the key points of your presentation.
[1350] Input: Finished presentation materials
[1351] Specific actions: Based on the generative AI model, the server generates advice on storytelling, non-verbal communication, and Q&A, such as how to talk about each slide and how to emphasize key points.
[1352] Output: The generated advice is saved on the server.
[1353] Step 10:
[1354] Users practice and prepare
[1355] Input: Advice provided by the server
[1356] Specific operation: The user rehearses the presentation on the device based on the advice. For example, they practice the questions they anticipate will be asked during the actual presentation and how to deal with them.
[1357] Output: Users will be better prepared and have better presentation skills
[1358] The above is the specific processing flow in the system program.
[1359] (Application example 1)
[1360] 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."
[1361] Creating presentation materials requires a lot of time and effort, making it difficult to quickly create high-quality materials. It is also difficult for users who lack knowledge and experience in presentation techniques to give effective presentations. Therefore, there is a demand for a system that can create high-quality presentation materials in a short amount of time and support effective presentations.
[1362] 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.
[1363] In this invention, the server includes input means for a user to input the presentation theme, purpose, target audience, and information to be provided, generation means for generating presentation materials based on the information received from the input means, provision means for providing the presentation materials generated by the generation means to the user, advice means for giving advice on presentation techniques based on the presentation materials, advice means for providing effective ways of speaking and question-and-answer sessions in the presentation, and means for providing technique guidance to the user based on the presentation. This enables the user to create high-quality presentation materials and prepare for an effective presentation in a short period of time.
[1364] "Input means" refers to a device or software that allows a user to input the presentation's theme, purpose, target audience, and information to be provided.
[1365] The "generation means" is a device or software that has the function of automatically generating presentation materials based on the information received from the input means.
[1366] The "providing means" is a device or software having a function for providing the presentation materials generated by the generating means to the user.
[1367] An "advice means" is a device or software that has the function of giving advice to a user on presentation techniques based on presentation materials.
[1368] The "means for providing advice on how to speak and how to answer questions" refers to a device or software that has the function of providing specific guidance to the user on how to speak effectively in a presentation and how to answer questions.
[1369] The "means for providing instruction in techniques" refers to a device or software that has the function of providing instruction to users in presentation techniques based on the presentation.
[1370] The present invention relates to a system including: an input means for a user to input the theme, purpose, target audience, and information to be provided of a presentation; a generation means for generating presentation materials based on the information received from the input means; a provision means for providing the generated presentation materials to a user; and an advice means for providing advice on presentation techniques based on the presentation materials. The system also includes an advice means for providing effective ways of speaking and question-and-answer sessions during the presentation, and a means for providing instruction on the techniques to a user based on the presentation.
[1371] System Configuration
[1372] The system consists of the following main components:
[1373] 1. Terminal: A device through which a user enters information (e.g., smartphone, computer, tablet).
[1374] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1375] 3. AI model: An artificial intelligence model trained to generate presentation materials and provide advice on presentation techniques.
[1376] Implementation details
[1377] The user inputs basic information about the presentation (e.g., theme, purpose, target audience, and information to be provided) using a dedicated application or web browser on the device. For example, the user inputs "features of a new product" as the theme, "selling the new product to investors" as the purpose, "investors knowledgeable about technology" as the target audience, and "major functions, technological advantages, and market potential of the product" as the information to be provided.
[1378] The server receives the basic information sent from the device and requests the AI model to generate presentation materials. The AI model automatically generates a slide deck based on specialized knowledge. For example, the following slide structure is generated:
[1379] 1. Title slide (new product name and logo)
[1380] 2. Slides introducing the main features of the product
[1381] 3. Slides explaining technological superiority
[1382] 4. Market Potential Analysis Slide
[1383] 5. Summary and Next Steps
[1384] The generated presentation materials are sent back to the terminal, where they are reviewed and revised by the user. The user reviews each slide and makes corrections or additions to text, images, and graphs as necessary. Once the revisions are complete, the slides are saved and sent back to the server.
[1385] The server receives the corrected data and updates the presentation materials, which are then provided to the user again. Based on the completed presentation materials, the AI model generates advice on storytelling, non-verbal communication, and Q&A.
[1386] The user practices the presentation based on the advice provided. For example, the user rehearses the presentation and reflects the advice from the server.
[1387] Hardware and software used
[1388] Hardware:
[1389] 1. Smartphone or tablet
[1390] 2. Server equipment
[1391] software:
[1392] 1. Python and related libraries (such as requests)
[1393] 2. OpenAI API
[1394] Prompt Sentence Examples
[1395] Theme: Cybersecurity measures
[1396] Objective: To propose new security solutions to customers.
[1397] Target audience: Security personnel
[1398] Information provided: Features of new security tools, technical advantages, and benefits of their implementation
[1399] Use this to generate presentation slides.
[1400] This invention enables users to create high-quality presentation materials in a short time and deliver effective presentations based on them. Each component works in conjunction with the others to streamline the presentation preparation process and help users improve their skills.
[1401] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1402] Step 1:
[1403] The user inputs basic information about the presentation (theme, purpose, target audience, information to be provided) using a dedicated application or web browser on the device. This information is then sent from the device to the server. Specifically, this includes a function to format the input information such as theme and purpose and send it to the server. An example of input data is "Theme: Features of a new product," and this information is sent to the server.
[1404] Step 2:
[1405] The server receives basic information sent from the device. The received information is used as input data for generating presentation materials. This data is stored in the server's storage and becomes the material for generating prompts for the AI model. The server analyzes the received data and formats it as needed.
[1406] Step 3:
[1407] The server creates a prompt to request the AI model to generate presentation materials based on the received basic information. Specifically, it uses Python to generate a prompt based on the basic information. It sends this prompt to the OpenAI API and receives a response from the AI model. An example of a prompt is "Topic: Cybersecurity measures, Objective: Propose new security solutions to customers."
[1408] Step 4:
[1409] The AI model automatically generates a presentation based on the provided prompts. The generated presentation is sent back to the server. The AI model generates the content for each slide based on the input prompts and sends the results in text format to the server.
[1410] Step 5:
[1411] The server receives the response from the AI model, formats the content, and sends it to the device as a presentation. Specifically, it converts the received text into slides and formats it in a way that is easy for the user to review. This allows the user to view the generated presentation on their device.
[1412] Step 6:
[1413] The user can check the presentation materials created on their device and make corrections or additions as necessary. Specifically, they can correct text and add images and graphs. After the user makes the corrections, the revised data is sent back to the server.
[1414] Step 7:
[1415] The server receives the modified data from the user and updates the presentation materials. The updated materials are then provided to the user again. The server then generates the latest materials that reflect the updated data and sends them to the terminal.
[1416] Step 8:
[1417] Based on the completed presentation materials, the server generates advice on presentation techniques, including advice on storytelling, non-verbal communication, and Q&A. The server then generates prompts for the AI model again to obtain appropriate advice.
[1418] Step 9:
[1419] The user practices the presentation based on the advice provided. Specifically, the user rehearses the presentation and incorporates the advice provided by the server. The user practices using the terminal and acquires effective presentation techniques.
[1420] This series of processing steps enables users to efficiently create high-quality presentation materials and prepare for their presentations effectively.
[1421] 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.
[1422] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses an AI model to generate presentation materials based on basic information entered by the user, and also recognizes the user's emotions and provides comprehensive advice on adapting presentation techniques.
[1423] System configuration
[1424] The system consists of the following components:
[1425] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[1426] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1427] 3. AI model: An artificial intelligence model trained to generate professional presentation materials and provide advice on presentation techniques.
[1428] 4. Emotion engine: A device or program that recognizes the user's emotions and adapts presentation materials and advice.
[1429] Program processing
[1430] The user enters basic information
[1431] Device:
[1432] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[1433] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[1434] The server generates the materials
[1435] server:
[1436] The server receives the basic information sent from the terminal.
[1437] Based on the received information, the AI model is asked to generate presentation materials.
[1438] The AI model automatically generates a slide deck based on its expert knowledge, resulting in a slide structure like this:
[1439] 1. Title slide (new product name and logo)
[1440] 2. Slides introducing the main features of the product
[1441] 3. Slides explaining technological superiority
[1442] 4. Market Potential Analysis Slide
[1443] 5. Summary and Next Steps Slide
[1444] The server temporarily stores the generated materials and transmits them to the user terminal as preview data.
[1445] User checks and modifies the materials
[1446] Device:
[1447] The generated presentation materials are displayed on the device.
[1448] Users can check each slide, select the one they want to edit, and modify or add text, images, and graphs.
[1449] For example: modify the text, add a chart, insert an image, etc.
[1450] When the user clicks the "Save" button for the slide after completing the editing, the modified data is sent to the server.
[1451] server:
[1452] The presentation materials are updated by receiving the corrected data sent by the user.
[1453] The updated presentation materials are provided to the user again.
[1454] The server will give you advice on the key points of your presentation.
[1455] server:
[1456] The completed presentation materials are analyzed by an AI model.
[1457] For each slide, the AI model generates advice on storytelling, non-verbal communication, and how to handle questions and answers.
[1458] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[1459] The server recognizes the user's emotions
[1460] Emotion Engine:
[1461] When a user practices a presentation, the emotion engine analyzes the user's voice, facial expressions, and biometric signals to recognize their emotions.
[1462] The recognized emotion data is sent to a server.
[1463] Coordinating and providing advice
[1464] server:
[1465] Adapt presentation materials and advice based on emotional data from the emotion engine.
[1466] Example: If the user is nervous, give them advice on how to relax or suggest slide corrections.
[1467] The adjusted advice is transmitted to the user terminal.
[1468] Users practice and prepare
[1469] Device:
[1470] The user practices the presentation based on the advice provided.
[1471] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[1472] Make final preparations for the presentation.
[1473] As described above, this system helps users to efficiently create high-quality presentation materials and optimize their presentation techniques based on emotion recognition data, thereby helping users to give effective presentations.
[1474] The processing flow will be explained below.
[1475] Step 1:
[1476] The user enters basic information.
[1477] User: Log in to the device and click the Create New Presentation button.
[1478] Terminal: Display the screen for entering basic information about the presentation.
[1479] User: Enter the theme, purpose, target audience, and information to provide.
[1480] For example: Theme: "Features of the new product", Objective: "Pitching the new product to investors", Target audience: "Technology-savvy investors", Information provided: "Key product features, technological advantages, and market potential".
[1481] User: Click the "Next" button.
[1482] Step 2:
[1483] A server receives the information and generates a presentation.
[1484] Terminal: Sends the entered basic information to the server.
[1485] Server: Provides the received basic information to the AI model.
[1486] AI model: Generate presentation materials. For example, the following slide structure:
[1487] 1. Title Slide
[1488] 2. Slides introducing the main features of the product
[1489] 3. Technological advantage explanation slides
[1490] 4. Market Potential Analysis Slide
[1491] 5. Summary and Next Steps Slide
[1492] Server: Temporarily stores the generated materials and sends them to the user's device as preview data.
[1493] Step 3:
[1494] The user can review and modify the generated materials.
[1495] Device: Shows a preview of the generated presentation.
[1496] User: Review the content of each slide and select the slide they want to edit.
[1497] Terminal: Switches to edit mode and provides an interface for users to enter information to be modified or added.
[1498] For example: modify the text, add a chart, insert an image, etc.
[1499] User: Clicks the "Save" button for the slide after editing is complete.
[1500] Device: Sends the saved correction data to the server.
[1501] Step 4:
[1502] The server updates the presentation materials to reflect the corrected data.
[1503] Server: Receives the correction data sent by the user.
[1504] Server: Update the presentation materials based on the revised data.
[1505] Server: The updated presentation materials are again temporarily saved and resent to the user.
[1506] Step 5:
[1507] The server will give you advice on the key points of your presentation.
[1508] Server: The AI model analyzes the completed presentation materials.
[1509] AI model: Generates advice for each slide on how to handle storytelling, non-verbal communication, and Q&A.
[1510] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[1511] Server: Sends the generated advice to the user terminal.
[1512] Step 6:
[1513] The server recognizes the user's emotions.
[1514] Terminal: The emotion engine runs when the user practices their presentation.
[1515] Emotion engine: Recognizes emotions by analyzing the user's voice, facial expressions, and biometric signals.
[1516] Emotion Engine: Sends the recognized emotion data to the server.
[1517] Example: If the user is nervous, the degree of nervousness is converted into a numerical value and sent to the server.
[1518] Step 7:
[1519] Coordinating and providing advice.
[1520] Server: Analyzes emotion recognition data and adapts presentation materials and advice content.
[1521] For example: If the user is nervous, give them advice on how to relax or suggest revisions to make the slides more understandable.
[1522] Server: Sends the adjusted advice to the user terminal.
[1523] Step 8:
[1524] Users practice and prepare.
[1525] Terminal: Displays advice sent from the server.
[1526] Users: Review the advice on each slide and practice your presentation.
[1527] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[1528] User: Make final preparations for the presentation.
[1529] These are the specific processing steps of this system. The user, device, and server work together to improve the efficiency and quality of the presentation preparation process based on emotion recognition.
[1530] Example 2
[1531] 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."
[1532] Conventional presentation creation systems make it difficult for users to create high-quality presentations in a short amount of time. Furthermore, there are no systems that provide presentation technique advice that takes into account the user's emotional state, making it difficult to maximize the effectiveness of a presentation. This lack of optimal advice is particularly problematic for users who are unfamiliar with presentations or who tend to get nervous.
[1533] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for a user to input the theme, purpose, target audience, and information to be provided of the presentation, a generation means for generating presentation materials based on the information received from the input means, a provision means for providing the presentation materials generated by the generation means to the user, an advice means for giving advice on presentation techniques based on the presentation materials, and an emotion recognition means for recognizing the user's emotions and adapting the advice on presentation techniques. This enables the user to create high-quality presentation materials in a short period of time and receive advice on optimal presentation techniques according to the user's emotional state.
[1534] "Presentation materials" refers to slides or documents containing information or content that a user uses when giving a presentation.
[1535] "Input means" refers to an interface or device that allows a user to input the presentation's theme, purpose, target audience, and information to be provided.
[1536] The "generation means" refers to a mechanism or program for generating presentation materials based on the information received from the input means.
[1537] The "providing means" refers to a mechanism or method for providing the presentation materials generated by the generating means to the user.
[1538] "Advice means" refers to a mechanism or program for giving advice on presentation techniques based on the presentation materials.
[1539] The "emotion recognition means" refers to a mechanism or program for recognizing the user's emotions and adapting the presentation technique advice.
[1540] A "user" is someone who creates presentation materials and gives a presentation.
[1541] The term "server" refers to a central processing unit including the input means, generation means, provision means, advice means, and emotion recognition means.
[1542] An "AI model" is an artificial intelligence model that has learned from presentation professionals with specialized knowledge.
[1543] "Voice, facial expression, and biological signals" refers to the user's voice data, facial expression data, and biological activity data used by the emotion recognition means to detect the user's emotions.
[1544] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses a generative AI model to generate presentation materials based on basic information entered by the user, and also recognizes the user's emotions and provides comprehensive advice on adapting presentation techniques.
[1545] System configuration
[1546] The system consists of the following components:
[1547] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[1548] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1549] 3. AI model: An artificial intelligence model trained by presentation professionals with specialized knowledge.
[1550] 4. Emotion recognition means: A device or program that recognizes the user's emotions and adapts presentation materials or advice accordingly.
[1551] Program processing
[1552] The user enters basic information
[1553] Device:
[1554] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[1555] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[1556] The server generates the materials
[1557] server:
[1558] The server receives the basic information sent from the terminal.
[1559] Based on the received information, the AI model is asked to generate presentation materials.
[1560] The AI model automatically generates a slide deck based on its expert knowledge, resulting in a slide structure like this:
[1561] 1. Title slide (new product name and logo)
[1562] 2. Slides introducing the main features of the product
[1563] 3. Slides explaining technological superiority
[1564] 4. Market Potential Analysis Slide
[1565] 5. Summary and Next Steps Slide
[1566] The server temporarily stores the generated materials and transmits them to the user terminal as preview data.
[1567] User checks and modifies the materials
[1568] Device:
[1569] The generated presentation materials are displayed on the device.
[1570] Users can check each slide, select the one they want to edit, and modify or add text, images, and graphs.
[1571] For example: modify the text, add a chart, insert an image, etc.
[1572] When the user clicks the "Save" button for the slide after completing the editing, the modified data is sent to the server.
[1573] server:
[1574] The presentation materials are updated by receiving the corrected data sent by the user.
[1575] The updated presentation materials are provided to the user again.
[1576] The server will give you advice on the key points of your presentation.
[1577] server:
[1578] The completed presentation materials are analyzed by an AI model.
[1579] For each slide, the AI model generates advice on storytelling, non-verbal communication, and how to handle questions and answers.
[1580] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[1581] The server recognizes the user's emotions
[1582] Emotion recognition means:
[1583] When a user practices a presentation, their emotions are recognized by analyzing their voice, facial expressions, and biometric signals.
[1584] The recognized emotion data is sent to a server.
[1585] Coordinating and providing advice
[1586] server:
[1587] The presentation materials and advice content are adapted based on the emotional data from the emotion recognition means.
[1588] Example: If the user is nervous, give them advice on how to relax or suggest slide corrections.
[1589] The adjusted advice is transmitted to the user terminal.
[1590] Users practice and prepare
[1591] Device:
[1592] The user practices the presentation based on the advice provided.
[1593] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[1594] Make final preparations for the presentation.
[1595] Examples of concrete examples and prompts
[1596] Below are some examples and prompts:
[1597] Specific examples
[1598] 1. User input:
[1599] Theme: "Environmentally friendly new energy technology"
[1600] Purpose: "Introducing technology to the new energy sector of companies"
[1601] Target audience: "Engineers with knowledge of environmental technology"
[1602] Information provided: "Technology characteristics, environmental impacts, economic benefits"
[1603] 2. Generated slide configuration:
[1604] Title slide (technology name and logo)
[1605] Slide introducing the features of the technology
[1606] Environmental Impact Slides
[1607] Economic benefits slide
[1608] Summary and next steps slide
[1609] 3. Specific examples of advice:
[1610] "It's important to focus the audience's attention on this slide and emphasize the technical features."
[1611] "When explaining economic benefits, using concrete figures helps capture the audience's attention."
[1612] Prompt Sentence Examples
[1613] "Please create a presentation that explains the features of the new product."
[1614] "Provide advice on slides that highlight the environmental impact and economic benefits."
[1615] "Please advise the user on how to relax if they are nervous."
[1616] In this way, by using prompt sentences, we have created a system that provides information in a format that is easy to input into the generative AI model, allowing participants to receive advice on more effective presentation materials and presentation techniques.
[1617] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1618] Now, let me explain the process of the system program step by step.
[1619] Processing Steps
[1620] Step 1: User enters basic information
[1621] Step 2: The server generates the materials
[1622] Step 3: User checks and modifies the materials
[1623] Step 4: The server gives advice on key points of the presentation
[1624] Step 5: The server recognizes the user's emotion
[1625] Step 6: Coordinating and providing advice
[1626] Step 7: User Practice and Preparation
[1627] Step-by-step instructions
[1628] Step 1: User enters basic information
[1629] Device:
[1630] Input: The user enters the presentation topic, purpose, target audience, and information to be provided.
[1631] How it works: The user launches a dedicated application or web browser on their device and enters the necessary information into the input form. For example, they enter "new product features" as the presentation topic, "selling the new product to investors" as the purpose, "technology-savvy investors" as the target audience, and "the product's main functions, technological advantages, and market potential" as the information to be provided.
[1632] Output: The entered information is sent to the server.
[1633] Step 2: The server generates the materials
[1634] server:
[1635] Input: Basic information sent from the device.
[1636] How it works: The server receives the HTTP POST request and temporarily stores it in a database. It then uses the received information to request the generative AI model to generate presentation materials. Specifically, it sends an API request to the AI model and receives the generated slide deck data.
[1637] Output: The generated presentation materials are temporarily saved and sent to the user's device as preview data.
[1638] Step 3: User checks and modifies the materials
[1639] Device:
[1640] Input: Preview data of presentation materials sent from the server.
[1641] How it works: The generated presentation materials are displayed on the device. The user can review each slide, select the one they want to edit, and modify or add text, images, or graphs. For example, they can modify text, add graphs, or insert images, and then click the "Save" button for the slide they've completed editing.
[1642] Output: The modified data is sent to the server.
[1643] server:
[1644] Input: Correction data submitted by the user.
[1645] Operation: Receives the revised data sent by the user and updates the presentation materials. Specifically, it updates the database and generates new slide data.
[1646] Output: The updated presentation is provided to the user again.
[1647] Step 4: The server gives advice on key points of the presentation
[1648] server:
[1649] Input: The completed presentation.
[1650] Operation: The completed presentation materials are analyzed by the AI model. The data is sent to the analysis endpoint of the AI model, and the advice data returned by the AI model is formatted and integrated back into the presentation materials.
[1651] Output: For each slide, advice data is generated on how to handle storytelling, non-verbal communication, and questions and answers.
[1652] Step 5: The server recognizes the user's emotion
[1653] Emotion recognition means:
[1654] Input: Speech, facial expression, and biometric data collected as users practice their presentations.
[1655] How it works: Data is collected from cameras, microphones, and wearable devices, and fed into an emotion analysis algorithm. The analysis results are sent to a server in real time.
[1656] Output: The recognized emotion data is generated and sent to the server.
[1657] Step 6: Coordinating and providing advice
[1658] server:
[1659] Input: Emotion data from emotion recognition instrument.
[1660] Behavior: Analyzes emotional data and adapts presentation materials and advice. For example, if the user is nervous, the system will suggest ways to relax.
[1661] Output: The adjusted advice is generated and sent to the user terminal.
[1662] Step 7: User Practice and Preparation
[1663] Device:
[1664] Input: Tailored advice and updated presentation materials.
[1665] Action: The user practices their presentation based on the provided advice. For example, they record their own presentation using the audio recording function and try to demonstrate it according to the advice. This allows them to make final checks in preparation for the actual presentation.
[1666] Output: The user is ready to give an effective presentation.
[1667] (Application example 2)
[1668] 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."
[1669] In modern logistics centers, it is necessary to create presentation materials to quickly and effectively report improvements in work efficiency and the effects of new deployment systems. However, it is a major challenge for workers to create high-quality presentation materials and effectively communicate their content while performing their daily tasks. It is also difficult to properly manage the presenter's emotions and tension to maximize performance. Therefore, a system that can reflect the on-site situation in real time and use emotion recognition to improve the quality of presentations is needed.
[1670] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: input means for a user to input the presentation theme, purpose, target audience, and information to be provided; generation means for generating presentation materials based on the information received from the input means; provision means for providing the presentation materials generated by the generation means to the user; advice means for providing presentation technique advice based on the presentation materials; emotion recognition means for recognizing the user's emotions and adapting the presentation materials and advice; and means for checking and correcting the presentation materials via a smart device. This not only enables workers at a logistics center to quickly create presentation materials that reflect on-site video and data in real time, but also improves the quality of presentations and enables more effective reporting through emotion recognition technology.
[1671] "Input means" refers to a device or system that allows a user to input the theme, purpose, target audience, and information to be provided for the presentation.
[1672] The "generation means" is a device or system for automatically creating presentation materials based on the information received from the input means.
[1673] The "providing means" is a device or system that provides the presentation materials created by the generating means to the user, allowing them to be viewed and modified.
[1674] The "advice means" is a device or system that provides guidance to the user on presentation techniques based on the presentation materials and suggests areas for improvement.
[1675] "Emotion recognition means" refers to a device or program that analyzes the user's voice, facial expressions, etc., and recognizes their emotional state.
[1676] A "smart device" is a device that has Internet connectivity and allows users to view and operate information visually or audibly.
[1677] "Presentation materials" refers to documents and slides that illustrate or describe the content that a user will present.
[1678] The system that realizes this application example allows users to create presentation materials in real time at a logistics center, and then confirm and modify the contents to make effective presentations.
[1679] The present invention is implemented using the following hardware and software:
[1680] 1. Smart device (e.g., smart glasses): A device that allows users to input the presentation topic, purpose, target audience, and information to be provided, and to review and modify presentation materials.
[1681] 2. Camera module: A device built into the smart glasses for capturing on-site footage.
[1682] 3. Server: A central processing unit that generates and provides presentation materials based on information received from the input means and gives advice on presentation techniques.
[1683] 4. AI model (e.g., PresentationAI): An artificial intelligence model trained from presentation professionals with specialized knowledge, used to automatically generate presentation materials.
[1684] 5. Emotion recognition software (e.g., EmotionEngine): Software that analyzes the user's emotions and recognizes their state.
[1685] The server first receives the presentation's theme, purpose, target audience, and information sent from the smart device. Based on this information, it uses an AI model to automatically generate presentation materials. The generated presentation materials are then provided to the user via their smart device, who can review the materials in real time and make edits to the text and images as needed.
[1686] Next, emotion recognition software analyzes data such as the user's voice and facial expressions to recognize their emotions. Based on the results, the server adapts the presentation materials and advice provided. This process allows the user to improve the quality of their presentation by offering advice on how to relax or suggesting slide revisions if they are nervous.
[1687] As a concrete example, consider a scenario in which an efficiency improvement report for a new warehouse allocation system is created. A user wears smart glasses and captures video of the warehouse. OCR technology is used to extract text data from the video, and an AI model automatically generates a slide deck based on this data. The generated slides include an overview of the new warehouse allocation system, the efficiency improvement status, and cost reduction effects. The user checks the slides on the smart glasses' display and makes any necessary corrections. If emotion recognition software detects that the user is tense, advice such as encouraging deep breathing is displayed.
[1688] An example prompt is, "Generate a presentation to create an efficiency improvement report for a new warehouse layout system. Key areas to focus on include efficiency gains, cost savings, and staff satisfaction after the layout change."
[1689] As described above, this system supports the efficient and effective creation and presentation of presentation materials at logistics centers.
[1690] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1691] Step 1:
[1692] The user uses a smart device (e.g., smart glasses) to input the presentation topic, objectives, target audience, and information to be provided. The input information is sent from the smart device to the server. Examples of input data include "improving the efficiency of the logistics center," "presentation on business improvement," "manager," and "improving the efficiency of a new warehouse layout system."
[1693] Step 2:
[1694] The server automatically generates presentation materials using a generative AI model (e.g., PresentationAI) based on the received input data. Specifically, it creates an appropriate slide structure based on the theme and purpose, and embeds the content. For example, it generates slides such as a "title slide," a "slide explaining the efficiency improvement after the layout change," and a "slide showing the cost reduction effect." The output is the automatically generated presentation materials.
[1695] Step 3:
[1696] The server provides the generated presentation materials to the smart device. The user checks the presentation materials on the smart device's display and operates the interface to modify text, images, and charts as necessary. The entered modification data is then sent to the server. The input here is the user's modification instructions, and the output is the modified presentation materials.
[1697] Step 4:
[1698] The server updates the presentation materials based on the corrections sent by the user. The updated presentation materials are then sent back to the smart device, where the user can review and make final adjustments. The final presentation materials are then output.
[1699] Step 5:
[1700] When a user rehearses a presentation, emotion recognition software (e.g., EmotionEngine) on the smart device analyzes the user's voice and facial expressions to recognize emotional data. Based on this, the user's state of tension or relaxation is analyzed. The input data is the user's voice and facial expression data, and the output data is the analyzed emotional information.
[1701] Step 6:
[1702] The server adjusts the content of the presentation materials and advice based on the emotional data sent from the emotion recognition software. For example, if the user is nervous, the server may suggest relaxation techniques such as encouraging deep breathing or change the slide structure. The adjusted advice and presentation materials are then output.
[1703] Step 7:
[1704] The user receives final advice via their smart device and makes final adjustments while rehearsing their presentation. This process prepares the user for the actual presentation. The final output is a quality-improved presentation document and advice for the user.
[1705] The above are the specific processing steps of the system that realizes the application example.
[1706] 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.
[1707] 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.
[1708] 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.
[1709] [Fourth embodiment]
[1710] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[1711] 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.
[1712] 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).
[1713] 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.
[1714] 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.
[1715] 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).
[1716] 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. 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.
[1717] 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.
[1718] 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.
[1719] 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.
[1720] 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.
[1721] 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.
[1722] 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."
[1723] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses an AI model to generate presentation materials based on basic information entered by the user, and also provides comprehensive advice to improve the user's presentation techniques.
[1724] System configuration
[1725] The system consists of the following components:
[1726] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[1727] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1728] 3. AI model: An artificial intelligence model trained to generate professional presentation materials and provide advice on presentation techniques.
[1729] Program processing
[1730] The user enters basic information
[1731] Device:
[1732] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[1733] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[1734] The server generates the materials
[1735] server:
[1736] The server receives the basic information sent from the terminal.
[1737] Based on the received information, the AI model is asked to generate presentation materials.
[1738] The AI model automatically generates a slide deck based on its expert knowledge. For example, it might generate the following slide structure:
[1739] 1. Title slide (new product name and logo)
[1740] 2. Slides introducing the main features of the product
[1741] 3. Slides explaining technological superiority
[1742] 4. Market Potential Analysis Slide
[1743] 5. Summary and Next Steps
[1744] User checks and modifies the materials
[1745] Device:
[1746] The generated presentation materials are displayed on the device.
[1747] The user checks each slide and modifies or adds text, images, and graphs as necessary.
[1748] Once the edits are complete, the slide is saved and sent to the server.
[1749] server:
[1750] Receive corrected data and update presentation materials.
[1751] Updated materials will be provided to users again.
[1752] The server will give you advice on the key points of your presentation.
[1753] server:
[1754] Based on the completed presentation, the AI model generates advice on storytelling, non-verbal communication, and Q&A.
[1755] For example: how to talk through each slide, how to emphasize key points, how to move your eyes, anticipated questions and how to deal with them, etc.
[1756] Users practice and prepare
[1757] Device:
[1758] The user practices the presentation based on the advice provided.
[1759] As a concrete example, a presentation is rehearsed and advice from the server is reflected.
[1760] As described above, this system enables users to create high-quality presentation materials in a short amount of time and deliver effective presentations based on them. Each component works together to streamline the presentation preparation process and help users improve their skills.
[1761] The processing flow will be explained below.
[1762] Step 1:
[1763] The user enters basic information.
[1764] User: Log in to the device and click the Create New Presentation button.
[1765] Terminal: Display the screen for entering basic information about the presentation.
[1766] User: Enter the theme, purpose, target audience, and information to provide.
[1767] For example: Theme: "Features of the new product", Objective: "Pitching the new product to investors", Target audience: "Technology-savvy investors", Information provided: "Key product features, technological advantages, and market potential".
[1768] User: Click the "Next" button.
[1769] Step 2:
[1770] A server receives the information and generates a presentation.
[1771] Terminal: Sends the entered basic information to the server.
[1772] Server: Provides the received basic information to the AI model.
[1773] AI model: Generate presentation materials. For example, the following slide structure:
[1774] 1. Title Slide
[1775] 2. Slides introducing the main features of the product
[1776] 3. Technological advantage explanation slides
[1777] 4. Market Potential Analysis Slide
[1778] 5. Summary and Next Steps Slide
[1779] Server: Temporarily stores the generated materials and sends them to the user's device as preview data.
[1780] Step 3:
[1781] The user can review and modify the generated materials.
[1782] Device: Shows a preview of the generated presentation.
[1783] User: Review the content of each slide and select the slide they want to edit.
[1784] Terminal: Switches to edit mode and provides an interface for users to enter information to be modified or added.
[1785] For example: modify the text, add a chart, insert an image, etc.
[1786] User: Clicks the "Save" button for the slide after editing is complete.
[1787] Device: Sends the saved correction data to the server.
[1788] Step 4:
[1789] The server updates the presentation materials to reflect the corrected data.
[1790] Server: Receives the correction data sent by the user.
[1791] Server: Update the presentation materials based on the revised data.
[1792] Server: The updated presentation materials are again temporarily saved and resent to the user.
[1793] Step 5:
[1794] The server will give you advice on the key points of your presentation.
[1795] Server: The AI model analyzes the completed presentation materials.
[1796] AI model: Generates advice for each slide on how to handle storytelling, non-verbal communication, and Q&A.
[1797] For example: how to talk about each slide, how to emphasize points, how to move your eyes, anticipated questions and how to prepare for them.
[1798] Server: Sends the generated advice in text format to the user terminal.
[1799] Step 6:
[1800] Users practice and prepare.
[1801] Terminal: Displays advice sent from the server.
[1802] Users: Review the advice on each slide and practice your presentation.
[1803] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[1804] User: Make final preparations for the presentation.
[1805] These are the specific processing steps of this system. At each step, the user, terminal, and server work together to efficiently and effectively support the creation of presentation materials and preparation for presentations.
[1806] Example 1
[1807] 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."
[1808] Currently, there are many tools on the market for creating presentation materials effectively, but they have the following problems: Creating presentation materials takes time, and it is difficult to create high-quality materials in a short amount of time. Furthermore, if the user does not have specialized knowledge or skills in presentation techniques, it is difficult to give an effective presentation. As a result, there is a demand for a system that allows users to create presentation materials effectively and quickly without requiring much effort or time, and also to improve their presentation techniques.
[1809] 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.
[1810] In this invention, the server includes input means for a user to input the presentation theme, purpose, target audience, and information to be provided, generation means for generating presentation materials based on the information received from the input means, provision means for providing the presentation materials generated by the generation means to the user, advice means for providing presentation technique advice based on the presentation materials, editing means for the user to check and correct the generated presentation materials, and update means for receiving the data corrected by the editing means and updating the presentation materials, thereby enabling the user to create high-quality presentation materials in a short period of time and improve their own presentation techniques.
[1811] "Input means" refers to a device or interface that allows a user to input the theme, purpose, target audience, and information to be provided for the presentation.
[1812] The "generation means" refers to a device or software that automatically generates presentation materials based on information received from the input means.
[1813] The "providing means" refers to a device or interface for presenting and providing the presentation materials generated by the generating means to the user.
[1814] The "advice means" is a device or software that provides the user with advice on presentation techniques based on the created presentation materials.
[1815] "Editing means" refers to a device or interface that allows a user to check and modify the generated presentation materials.
[1816] The "updating means" refers to a device or software that receives the data corrected by the editing means again and updates the presentation materials.
[1817] A "generative artificial intelligence model" is an artificial intelligence model that learns from presentation professionals with specialized knowledge and is used to automatically generate presentation materials.
[1818] "Storytelling" is a technique for effectively conveying information using stories.
[1819] "Nonverbal communication" is a method of conveying information and emotions using means other than words (gestures, facial expressions, gaze, etc.).
[1820] "Question and answer" is a technique for appropriately answering questions from the audience during a presentation.
[1821] The present invention is a system that enables users to create high-quality presentation materials in a short period of time and deliver effective presentations. This system uses a generative AI model to generate presentation materials based on basic information entered by the user, and also provides comprehensive advice to help the user improve their presentation techniques. Details for specifically implementing the present invention are provided below.
[1822] System configuration
[1823] The system consists of the following components:
[1824] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[1825] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1826] 3. AI model: A generative AI model trained by presentation professionals with expert knowledge.
[1827] Program processing
[1828] The user enters basic information
[1829] Terminal: The user uses the terminal's dedicated application or web browser to input the presentation topic, purpose, target audience, and information to be provided. For example, input the following information:
[1830] Theme: New product features
[1831] Purpose: Pitching new products to investors
[1832] Target audience: Tech-savvy investors
[1833] Information provided: Product's main features, technical advantages, market potential
[1834] The server generates the materials
[1835] Server: Receives basic information sent from the device. Based on the received information, it requests the generative AI model to generate presentation materials. Based on specialized knowledge, the generative AI model automatically generates presentation materials with the following slide structure:
[1836] 1. Title slide (new product name and logo)
[1837] 2. Slides introducing the main features of the product
[1838] 3. Slides explaining technological superiority
[1839] 4. Market Potential Analysis Slide
[1840] 5. Summary and Next Steps
[1841] User checks and modifies the materials
[1842] Device: The generated presentation materials are displayed on the device. The user can check each slide and use a dedicated editor to edit or add text, images, and graphs. Once edited, the slide is saved and sent to the server.
[1843] The server will give you advice on the key points of your presentation.
[1844] Server: Receives the corrected data and updates the presentation. Based on the completed presentation, the generative AI model generates advice on storytelling, non-verbal communication, and Q&A. For example, it provides advice such as:
[1845] How to talk about each slide
[1846] How to emphasize key points
[1847] How to move your eyes
[1848] Anticipated questions and how to address them
[1849] Users practice and prepare
[1850] Terminal: The user practices the presentation based on the advice provided. For example, the user rehearses the presentation and reflects the advice from the server in the actual presentation.
[1851] As described above, this system enables users to create high-quality presentation materials in a short amount of time and deliver effective presentations based on them. Each component works together to streamline the presentation preparation process and help users improve their skills.
[1852] Specific prompt examples
[1853] Here is an example of a prompt that a user might enter to begin creating a presentation:
[1854] Presentation theme: New product features
[1855] Purpose: Pitching new products to investors
[1856] Target audience: Tech-savvy investors
[1857] Information provided: Product's main features, technical advantages, market potential
[1858] The above processing flow allows the user to efficiently prepare for a presentation.
[1859] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1860] Step 1:
[1861] The user enters the presentation topic, purpose, target audience, and information to be provided
[1862] Input: The user enters information into an input form using a dedicated application or a web browser.
[1863] Specific operation: The user inputs the following information, for example:
[1864] Theme: New product features
[1865] Purpose: Pitching new products to investors
[1866] Target audience: Tech-savvy investors
[1867] Information provided: Product's main features, technical advantages, market potential
[1868] Output: Input data is saved to the device
[1869] Step 2:
[1870] The device sends the input information to the server
[1871] Input: Basic information entered by the user
[1872] Specific operation: Send data from the device to the server using a secure communication protocol (e.g. HTTPS).
[1873] Output: The input information is saved on the server.
[1874] Step 3:
[1875] The server requests the AI model to generate presentation materials based on the received information.
[1876] Input: Presentation topic, purpose, target audience, and information to provide sent from your device
[1877] Specific operation: The server encodes the data to the generative AI model and sends it as a prompt for generating presentation materials.
[1878] Output: Presentation materials generated by the generative AI model are output.
[1879] Step 4:
[1880] Generative AI model generates presentation materials
[1881] Input: Prompt and basic information sent from the server
[1882] How it works: The generative AI model automatically generates content for each slide in a presentation, including:
[1883] 1. Title slide (new product name and logo)
[1884] 2. Slides introducing the main features of the product
[1885] 3. Slides explaining technological superiority
[1886] 4. Market Potential Analysis Slide
[1887] 5. Summary and Next Steps
[1888] Output: The generated presentation material is sent to the server.
[1889] Step 5:
[1890] The server sends the generated presentation materials to the terminal.
[1891] Input: Presentation materials generated by the generative AI model
[1892] Specific operation: The server converts the generated slide deck into a Pedia format (PDF, PPTX, etc.) and sends it to the device.
[1893] Output: Presentation materials are displayed on the device.
[1894] Step 6:
[1895] User checks and modifies the materials
[1896] Input: Presentation materials sent from the server
[1897] Specific actions: Users can use the dedicated editor on their devices to review and modify the text, images, and graphs on each slide, for example, adding descriptions of the product's main features.
[1898] Output: The revised presentation material will be saved on your device.
[1899] Step 7:
[1900] The device sends the correction data to the server
[1901] Input: User-modified presentation
[1902] Specific operation: The corrected document is sent to the server using a secure communication protocol (e.g., HTTPS).
[1903] Output: The modified data is saved on the server.
[1904] Step 8:
[1905] The server reflects the corrected data and updates the presentation materials.
[1906] Input: Correction data sent from the terminal
[1907] Specific operation: The server updates the document based on the revised data and saves the final version.
[1908] Output: The updated presentation material is saved on the server.
[1909] Step 9:
[1910] The server will give you advice on the key points of your presentation.
[1911] Input: Finished presentation materials
[1912] Specific actions: Based on the generative AI model, the server generates advice on storytelling, non-verbal communication, and Q&A, such as how to talk about each slide and how to emphasize key points.
[1913] Output: The generated advice is saved on the server.
[1914] Step 10:
[1915] Users practice and prepare
[1916] Input: Advice provided by the server
[1917] Specific operation: The user rehearses the presentation on the device based on the advice. For example, they practice the questions they anticipate will be asked during the actual presentation and how to deal with them.
[1918] Output: Users will be better prepared and have better presentation skills
[1919] The above is the specific processing flow in the system program.
[1920] (Application example 1)
[1921] 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."
[1922] Creating presentation materials requires a lot of time and effort, making it difficult to quickly create high-quality materials. It is also difficult for users who lack knowledge and experience in presentation techniques to give effective presentations. Therefore, there is a demand for a system that can create high-quality presentation materials in a short amount of time and support effective presentations.
[1923] 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.
[1924] In this invention, the server includes input means for a user to input the presentation theme, purpose, target audience, and information to be provided, generation means for generating presentation materials based on the information received from the input means, provision means for providing the presentation materials generated by the generation means to the user, advice means for giving advice on presentation techniques based on the presentation materials, advice means for providing effective ways of speaking and question-and-answer sessions in the presentation, and means for providing technique guidance to the user based on the presentation. This enables the user to create high-quality presentation materials and prepare for an effective presentation in a short period of time.
[1925] "Input means" refers to a device or software that allows a user to input the presentation's theme, purpose, target audience, and information to be provided.
[1926] The "generation means" is a device or software that has the function of automatically generating presentation materials based on the information received from the input means.
[1927] The "providing means" is a device or software having a function for providing the presentation materials generated by the generating means to the user.
[1928] An "advice means" is a device or software that has the function of giving advice to a user on presentation techniques based on presentation materials.
[1929] The "means for providing advice on how to speak and how to answer questions" refers to a device or software that has the function of providing specific guidance to the user on how to speak effectively in a presentation and how to answer questions.
[1930] The "means for providing instruction in techniques" refers to a device or software that has the function of providing instruction to users in presentation techniques based on the presentation.
[1931] The present invention relates to a system including: an input means for a user to input the theme, purpose, target audience, and information to be provided of a presentation; a generation means for generating presentation materials based on the information received from the input means; a provision means for providing the generated presentation materials to a user; and an advice means for providing advice on presentation techniques based on the presentation materials. The system also includes an advice means for providing effective ways of speaking and question-and-answer sessions during the presentation, and a means for providing instruction on the techniques to a user based on the presentation.
[1932] System Configuration
[1933] The system consists of the following main components:
[1934] 1. Terminal: A device through which a user enters information (e.g., smartphone, computer, tablet).
[1935] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1936] 3. AI model: An artificial intelligence model trained to generate presentation materials and provide advice on presentation techniques.
[1937] Implementation details
[1938] The user inputs basic information about the presentation (e.g., theme, purpose, target audience, and information to be provided) using a dedicated application or web browser on the device. For example, the user inputs "features of a new product" as the theme, "selling the new product to investors" as the purpose, "investors knowledgeable about technology" as the target audience, and "major functions, technological advantages, and market potential of the product" as the information to be provided.
[1939] The server receives the basic information sent from the device and requests the AI model to generate presentation materials. The AI model automatically generates a slide deck based on specialized knowledge. For example, the following slide structure is generated:
[1940] 1. Title slide (new product name and logo)
[1941] 2. Slides introducing the main features of the product
[1942] 3. Slides explaining technological superiority
[1943] 4. Market Potential Analysis Slide
[1944] 5. Summary and Next Steps
[1945] The generated presentation materials are sent back to the terminal, where they are reviewed and revised by the user. The user reviews each slide and makes corrections or additions to text, images, and graphs as necessary. Once the revisions are complete, the slides are saved and sent back to the server.
[1946] The server receives the corrected data and updates the presentation materials, which are then provided to the user again. Based on the completed presentation materials, the AI model generates advice on storytelling, non-verbal communication, and Q&A.
[1947] The user practices the presentation based on the advice provided. For example, the user rehearses the presentation and reflects the advice from the server.
[1948] Hardware and software used
[1949] Hardware:
[1950] 1. Smartphone or tablet
[1951] 2. Server equipment
[1952] software:
[1953] 1. Python and related libraries (such as requests)
[1954] 2. OpenAI API
[1955] Prompt Sentence Examples
[1956] Theme: Cybersecurity measures
[1957] Objective: To propose new security solutions to customers.
[1958] Target audience: Security personnel
[1959] Information provided: Features of new security tools, technical advantages, and benefits of their implementation
[1960] Use this to generate presentation slides.
[1961] This invention enables users to create high-quality presentation materials in a short time and deliver effective presentations based on them. Each component works in conjunction with the others to streamline the presentation preparation process and help users improve their skills.
[1962] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1963] Step 1:
[1964] The user inputs basic information about the presentation (theme, purpose, target audience, information to be provided) using a dedicated application or web browser on the device. This information is then sent from the device to the server. Specifically, this includes a function to format the input information such as theme and purpose and send it to the server. An example of input data is "Theme: Features of a new product," and this information is sent to the server.
[1965] Step 2:
[1966] The server receives basic information sent from the device. The received information is used as input data for generating presentation materials. This data is stored in the server's storage and becomes the material for generating prompts for the AI model. The server analyzes the received data and formats it as needed.
[1967] Step 3:
[1968] The server creates a prompt to request the AI model to generate presentation materials based on the received basic information. Specifically, it uses Python to generate a prompt based on the basic information. It sends this prompt to the OpenAI API and receives a response from the AI model. An example of a prompt is "Topic: Cybersecurity measures, Objective: Propose new security solutions to customers."
[1969] Step 4:
[1970] The AI model automatically generates a presentation based on the provided prompts. The generated presentation is sent back to the server. The AI model generates the content for each slide based on the input prompts and sends the results in text format to the server.
[1971] Step 5:
[1972] The server receives the response from the AI model, formats the content, and sends it to the device as a presentation. Specifically, it converts the received text into slides and formats it in a way that is easy for the user to review. This allows the user to view the generated presentation on their device.
[1973] Step 6:
[1974] The user can check the presentation materials created on their device and make corrections or additions as necessary. Specifically, they can correct text and add images and graphs. After the user makes the corrections, the revised data is sent back to the server.
[1975] Step 7:
[1976] The server receives the modified data from the user and updates the presentation materials. The updated materials are then provided to the user again. The server then generates the latest materials that reflect the updated data and sends them to the terminal.
[1977] Step 8:
[1978] Based on the completed presentation materials, the server generates advice on presentation techniques, including advice on storytelling, non-verbal communication, and Q&A. The server then generates prompts for the AI model again to obtain appropriate advice.
[1979] Step 9:
[1980] The user practices the presentation based on the advice provided. Specifically, the user rehearses the presentation and incorporates the advice provided by the server. The user practices using the terminal and acquires effective presentation techniques.
[1981] This series of processing steps enables users to efficiently create high-quality presentation materials and prepare for their presentations effectively.
[1982] 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.
[1983] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses an AI model to generate presentation materials based on basic information entered by the user, and also recognizes the user's emotions and provides comprehensive advice on adapting presentation techniques.
[1984] System configuration
[1985] The system consists of the following components:
[1986] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[1987] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[1988] 3. AI model: An artificial intelligence model trained to generate professional presentation materials and provide advice on presentation techniques.
[1989] 4. Emotion engine: A device or program that recognizes the user's emotions and adapts presentation materials and advice.
[1990] Program processing
[1991] The user enters basic information
[1992] Device:
[1993] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[1994] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[1995] The server generates the materials
[1996] server:
[1997] The server receives the basic information sent from the terminal.
[1998] Based on the received information, the AI model is asked to generate presentation materials.
[1999] The AI model automatically generates a slide deck based on its expert knowledge, resulting in a slide structure like this:
[2000] 1. Title slide (new product name and logo)
[2001] 2. Slides introducing the main features of the product
[2002] 3. Slides explaining technological superiority
[2003] 4. Market Potential Analysis Slide
[2004] 5. Summary and Next Steps Slide
[2005] The server temporarily stores the generated materials and transmits them to the user terminal as preview data.
[2006] User checks and modifies the materials
[2007] Device:
[2008] The generated presentation materials are displayed on the device.
[2009] Users can check each slide, select the one they want to edit, and modify or add text, images, and graphs.
[2010] For example: modify the text, add a chart, insert an image, etc.
[2011] When the user clicks the "Save" button for the slide after completing the editing, the modified data is sent to the server.
[2012] server:
[2013] The presentation materials are updated by receiving the corrected data sent by the user.
[2014] The updated presentation materials are provided to the user again.
[2015] The server will give you advice on the key points of your presentation.
[2016] server:
[2017] The completed presentation materials are analyzed by an AI model.
[2018] For each slide, the AI model generates advice on storytelling, non-verbal communication, and how to handle questions and answers.
[2019] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[2020] The server recognizes the user's emotions
[2021] Emotion Engine:
[2022] When a user practices a presentation, the emotion engine analyzes the user's voice, facial expressions, and biometric signals to recognize their emotions.
[2023] The recognized emotion data is sent to a server.
[2024] Coordinating and providing advice
[2025] server:
[2026] Adapt presentation materials and advice based on emotional data from the emotion engine.
[2027] Example: If the user is nervous, give them advice on how to relax or suggest slide corrections.
[2028] The adjusted advice is transmitted to the user terminal.
[2029] Users practice and prepare
[2030] Device:
[2031] The user practices the presentation based on the advice provided.
[2032] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[2033] Make final preparations for the presentation.
[2034] As described above, this system helps users to efficiently create high-quality presentation materials and optimize their presentation techniques based on emotion recognition data, thereby helping users to give effective presentations.
[2035] The processing flow will be explained below.
[2036] Step 1:
[2037] The user enters basic information.
[2038] User: Log in to the device and click the Create New Presentation button.
[2039] Terminal: Display the screen for entering basic information about the presentation.
[2040] User: Enter the theme, purpose, target audience, and information to provide.
[2041] For example: Theme: "Features of the new product", Objective: "Pitching the new product to investors", Target audience: "Technology-savvy investors", Information provided: "Key product features, technological advantages, and market potential".
[2042] User: Click the "Next" button.
[2043] Step 2:
[2044] A server receives the information and generates a presentation.
[2045] Terminal: Sends the entered basic information to the server.
[2046] Server: Provides the received basic information to the AI model.
[2047] AI model: Generate presentation materials. For example, the following slide structure:
[2048] 1. Title Slide
[2049] 2. Slides introducing the main features of the product
[2050] 3. Technological advantage explanation slides
[2051] 4. Market Potential Analysis Slide
[2052] 5. Summary and Next Steps Slide
[2053] Server: Temporarily stores the generated materials and sends them to the user's device as preview data.
[2054] Step 3:
[2055] The user can review and modify the generated materials.
[2056] Device: Shows a preview of the generated presentation.
[2057] User: Review the content of each slide and select the slide they want to edit.
[2058] Terminal: Switches to edit mode and provides an interface for users to enter information to be modified or added.
[2059] For example: modify the text, add a chart, insert an image, etc.
[2060] User: Clicks the "Save" button for the slide after editing is complete.
[2061] Device: Sends the saved correction data to the server.
[2062] Step 4:
[2063] The server updates the presentation materials to reflect the corrected data.
[2064] Server: Receives the correction data sent by the user.
[2065] Server: Update the presentation materials based on the revised data.
[2066] Server: The updated presentation materials are again temporarily saved and resent to the user.
[2067] Step 5:
[2068] The server will give you advice on the key points of your presentation.
[2069] Server: The AI model analyzes the completed presentation materials.
[2070] AI model: Generates advice for each slide on how to handle storytelling, non-verbal communication, and Q&A.
[2071] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[2072] Server: Sends the generated advice to the user terminal.
[2073] Step 6:
[2074] The server recognizes the user's emotions.
[2075] Terminal: The emotion engine runs when the user practices their presentation.
[2076] Emotion engine: Recognizes emotions by analyzing the user's voice, facial expressions, and biometric signals.
[2077] Emotion Engine: Sends the recognized emotion data to the server.
[2078] Example: If the user is nervous, the degree of nervousness is converted into a numerical value and sent to the server.
[2079] Step 7:
[2080] Coordinating and providing advice.
[2081] Server: Analyzes emotion recognition data and adapts presentation materials and advice content.
[2082] For example: If the user is nervous, give them advice on how to relax or suggest revisions to make the slides more understandable.
[2083] Server: Sends the adjusted advice to the user terminal.
[2084] Step 8:
[2085] Users practice and prepare.
[2086] Terminal: Displays advice sent from the server.
[2087] Users: Review the advice on each slide and practice your presentation.
[2088] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[2089] User: Make final preparations for the presentation.
[2090] These are the specific processing steps of this system. The user, device, and server work together to improve the efficiency and quality of the presentation preparation process based on emotion recognition.
[2091] Example 2
[2092] 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."
[2093] Conventional presentation creation systems make it difficult for users to create high-quality presentations in a short amount of time. Furthermore, there are no systems that provide presentation technique advice that takes into account the user's emotional state, making it difficult to maximize the effectiveness of a presentation. This lack of optimal advice is particularly problematic for users who are unfamiliar with presentations or who tend to get nervous.
[2094] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for a user to input the theme, purpose, target audience, and information to be provided of the presentation, a generation means for generating presentation materials based on the information received from the input means, a provision means for providing the presentation materials generated by the generation means to the user, an advice means for giving advice on presentation techniques based on the presentation materials, and an emotion recognition means for recognizing the user's emotions and adapting the advice on presentation techniques. This enables the user to create high-quality presentation materials in a short period of time and receive advice on optimal presentation techniques according to the user's emotional state.
[2095] "Presentation materials" refers to slides or documents containing information or content that a user uses when giving a presentation.
[2096] "Input means" refers to an interface or device that allows a user to input the presentation's theme, purpose, target audience, and information to be provided.
[2097] The "generation means" refers to a mechanism or program for generating presentation materials based on the information received from the input means.
[2098] The "providing means" refers to a mechanism or method for providing the presentation materials generated by the generating means to the user.
[2099] "Advice means" refers to a mechanism or program for giving advice on presentation techniques based on the presentation materials.
[2100] The "emotion recognition means" refers to a mechanism or program for recognizing the user's emotions and adapting the presentation technique advice.
[2101] A "user" is someone who creates presentation materials and gives a presentation.
[2102] The term "server" refers to a central processing unit including the input means, generation means, provision means, advice means, and emotion recognition means.
[2103] An "AI model" is an artificial intelligence model that has learned from presentation professionals with specialized knowledge.
[2104] "Voice, facial expression, and biological signals" refers to the user's voice data, facial expression data, and biological activity data used by the emotion recognition means to detect the user's emotions.
[2105] This invention relates to a system that enables users to create high-quality presentation materials in a short time and give effective presentations. This system uses a generative AI model to generate presentation materials based on basic information entered by the user, and also recognizes the user's emotions and provides comprehensive advice on adapting presentation techniques.
[2106] System configuration
[2107] The system consists of the following components:
[2108] 1. Terminal: A device (e.g., computer, smartphone, tablet) through which a user enters information.
[2109] 2. Server: A central processing unit for receiving input information, generating presentation materials, and providing advice on presentation techniques.
[2110] 3. AI model: An artificial intelligence model trained by presentation professionals with specialized knowledge.
[2111] 4. Emotion recognition means: A device or program that recognizes the user's emotions and adapts presentation materials or advice accordingly.
[2112] Program processing
[2113] The user enters basic information
[2114] Device:
[2115] The user uses a dedicated application or web browser on the terminal to input the presentation theme, purpose, target audience, and information to be provided.
[2116] Example: Enter "Features of the new product" as the theme, "Pitching the new product to investors" as the purpose, "Technology-savvy investors" as the target audience, and "Key product functions, technological advantages, and market potential" as the information to be provided.
[2117] The server generates the materials
[2118] server:
[2119] The server receives the basic information sent from the terminal.
[2120] Based on the received information, the AI model is asked to generate presentation materials.
[2121] The AI model automatically generates a slide deck based on its expert knowledge, resulting in a slide structure like this:
[2122] 1. Title slide (new product name and logo)
[2123] 2. Slides introducing the main features of the product
[2124] 3. Slides explaining technological superiority
[2125] 4. Market Potential Analysis Slide
[2126] 5. Summary and Next Steps Slide
[2127] The server temporarily stores the generated materials and transmits them to the user terminal as preview data.
[2128] User checks and modifies the materials
[2129] Device:
[2130] The generated presentation materials are displayed on the device.
[2131] Users can check each slide, select the one they want to edit, and modify or add text, images, and graphs.
[2132] For example: modify the text, add a chart, insert an image, etc.
[2133] When the user clicks the "Save" button for the slide after completing the editing, the modified data is sent to the server.
[2134] server:
[2135] The presentation materials are updated by receiving the corrected data sent by the user.
[2136] The updated presentation materials are provided to the user again.
[2137] The server will give you advice on the key points of your presentation.
[2138] server:
[2139] The completed presentation materials are analyzed by an AI model.
[2140] For each slide, the AI model generates advice on storytelling, non-verbal communication, and how to handle questions and answers.
[2141] For example, we will give advice on how to talk about each slide, how to emphasize key points, how to move the speaker's eyes, and what questions to expect and how to prepare for them.
[2142] The server recognizes the user's emotions
[2143] Emotion recognition means:
[2144] When a user practices a presentation, their emotions are recognized by analyzing their voice, facial expressions, and biometric signals.
[2145] The recognized emotion data is sent to a server.
[2146] Coordinating and providing advice
[2147] server:
[2148] The presentation materials and advice content are adapted based on the emotional data from the emotion recognition means.
[2149] Example: If the user is nervous, give them advice on how to relax or suggest slide corrections.
[2150] The adjusted advice is transmitted to the user terminal.
[2151] Users practice and prepare
[2152] Device:
[2153] The user practices the presentation based on the advice provided.
[2154] For example: rehearsing the actual presentation, practicing vocalizations and gestures based on advice, and practicing answers to predicted questions.
[2155] Make final preparations for the presentation.
[2156] Examples of concrete examples and prompts
[2157] Below are some examples and prompts:
[2158] Specific examples
[2159] 1. User input:
[2160] Theme: "Environmentally friendly new energy technology"
[2161] Purpose: "Introducing technology to the new energy sector of companies"
[2162] Target audience: "Engineers with knowledge of environmental technology"
[2163] Information provided: "Technology characteristics, environmental impacts, economic benefits"
[2164] 2. Generated slide configuration:
[2165] Title slide (technology name and logo)
[2166] Slide introducing the features of the technology
[2167] Environmental Impact Slides
[2168] Economic benefits slide
[2169] Summary and next steps slide
[2170] 3. Specific examples of advice:
[2171] "It's important to focus the audience's attention on this slide and emphasize the technical features."
[2172] "When explaining economic benefits, using concrete figures helps capture the audience's attention."
[2173] Prompt Sentence Examples
[2174] "Please create a presentation that explains the features of the new product."
[2175] "Provide advice on slides that highlight the environmental impact and economic benefits."
[2176] "Please advise the user on how to relax if they are nervous."
[2177] In this way, by using prompt sentences, we have created a system that provides information in a format that is easy to input into the generative AI model, allowing participants to receive advice on more effective presentation materials and presentation techniques.
[2178] The flow of the identification process in the second embodiment will be described with reference to FIG.
[2179] Now, let me explain the process of the system program step by step.
[2180] Processing Steps
[2181] Step 1: User enters basic information
[2182] Step 2: The server generates the materials
[2183] Step 3: User checks and modifies the materials
[2184] Step 4: The server gives advice on key points of the presentation
[2185] Step 5: The server recognizes the user's emotion
[2186] Step 6: Coordinating and providing advice
[2187] Step 7: User Practice and Preparation
[2188] Step-by-step instructions
[2189] Step 1: User enters basic information
[2190] Device:
[2191] Input: The user enters the presentation topic, purpose, target audience, and information to be provided.
[2192] How it works: The user launches a dedicated application or web browser on their device and enters the necessary information into the input form. For example, they enter "new product features" as the presentation topic, "selling the new product to investors" as the purpose, "technology-savvy investors" as the target audience, and "the product's main functions, technological advantages, and market potential" as the information to be provided.
[2193] Output: The entered information is sent to the server.
[2194] Step 2: The server generates the materials
[2195] server:
[2196] Input: Basic information sent from the device.
[2197] How it works: The server receives the HTTP POST request and temporarily stores it in a database. It then uses the received information to request the generative AI model to generate presentation materials. Specifically, it sends an API request to the AI model and receives the generated slide deck data.
[2198] Output: The generated presentation materials are temporarily saved and sent to the user's device as preview data.
[2199] Step 3: User checks and modifies the materials
[2200] Device:
[2201] Input: Preview data of presentation materials sent from the server.
[2202] How it works: The generated presentation materials are displayed on the device. The user can review each slide, select the one they want to edit, and modify or add text, images, or graphs. For example, they can modify text, add graphs, or insert images, and then click the "Save" button for the slide they've completed editing.
[2203] Output: The modified data is sent to the server.
[2204] server:
[2205] Input: Correction data submitted by the user.
[2206] Operation: Receives the revised data sent by the user and updates the presentation materials. Specifically, it updates the database and generates new slide data.
[2207] Output: The updated presentation is provided to the user again.
[2208] Step 4: The server gives advice on key points of the presentation
[2209] server:
[2210] Input: The completed presentation.
[2211] Operation: The completed presentation materials are analyzed by the AI model. The data is sent to the analysis endpoint of the AI model, and the advice data returned by the AI model is formatted and integrated back into the presentation materials.
[2212] Output: For each slide, advice data is generated on how to handle storytelling, non-verbal communication, and questions and answers.
[2213] Step 5: The server recognizes the user's emotion
[2214] Emotion recognition means:
[2215] Input: Speech, facial expression, and biometric data collected as users practice their presentations.
[2216] How it works: Data is collected from cameras, microphones, and wearable devices, and fed into an emotion analysis algorithm. The analysis results are sent to a server in real time.
[2217] Output: The recognized emotion data is generated and sent to the server.
[2218] Step 6: Coordinating and providing advice
[2219] server:
[2220] Input: Emotion data from emotion recognition instrument.
[2221] Behavior: Analyzes emotional data and adapts presentation materials and advice. For example, if the user is nervous, the system will suggest ways to relax.
[2222] Output: The adjusted advice is generated and sent to the user terminal.
[2223] Step 7: User Practice and Preparation
[2224] Device:
[2225] Input: Tailored advice and updated presentation materials.
[2226] Action: The user practices their presentation based on the provided advice. For example, they record their own presentation using the audio recording function and try to demonstrate it according to the advice. This allows them to make final checks in preparation for the actual presentation.
[2227] Output: The user is ready to give an effective presentation.
[2228] (Application example 2)
[2229] 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."
[2230] In modern logistics centers, it is necessary to create presentation materials to quickly and effectively report improvements in work efficiency and the effects of new deployment systems. However, it is a major challenge for workers to create high-quality presentation materials and effectively communicate their content while performing their daily tasks. It is also difficult to properly manage the presenter's emotions and tension to maximize performance. Therefore, a system that can reflect the on-site situation in real time and use emotion recognition to improve the quality of presentations is needed.
[2231] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: input means for a user to input the presentation theme, purpose, target audience, and information to be provided; generation means for generating presentation materials based on the information received from the input means; provision means for providing the presentation materials generated by the generation means to the user; advice means for providing presentation technique advice based on the presentation materials; emotion recognition means for recognizing the user's emotions and adapting the presentation materials and advice; and means for checking and correcting the presentation materials via a smart device. This not only enables workers at a logistics center to quickly create presentation materials that reflect on-site video and data in real time, but also improves the quality of presentations and enables more effective reporting through emotion recognition technology.
[2232] "Input means" refers to a device or system that allows a user to input the theme, purpose, target audience, and information to be provided for the presentation.
[2233] The "generation means" is a device or system for automatically creating presentation materials based on the information received from the input means.
[2234] The "providing means" is a device or system that provides the presentation materials created by the generating means to the user, allowing them to be viewed and modified.
[2235] The "advice means" is a device or system that provides guidance to the user on presentation techniques based on the presentation materials and suggests areas for improvement.
[2236] "Emotion recognition means" refers to a device or program that analyzes the user's voice, facial expressions, etc., and recognizes their emotional state.
[2237] A "smart device" is a device that has Internet connectivity and allows users to view and operate information visually or audibly.
[2238] "Presentation materials" refers to documents and slides that illustrate or describe the content that a user will present.
[2239] The system that realizes this application example allows users to create presentation materials in real time at a logistics center, and then confirm and modify the contents to make effective presentations.
[2240] The present invention is implemented using the following hardware and software:
[2241] 1. Smart device (e.g., smart glasses): A device that allows users to input the presentation topic, purpose, target audience, and information to be provided, and to review and modify presentation materials.
[2242] 2. Camera module: A device built into the smart glasses for capturing on-site footage.
[2243] 3. Server: A central processing unit that generates and provides presentation materials based on information received from the input means and gives advice on presentation techniques.
[2244] 4. AI model (e.g., PresentationAI): An artificial intelligence model trained from presentation professionals with specialized knowledge, used to automatically generate presentation materials.
[2245] 5. Emotion recognition software (e.g., EmotionEngine): Software that analyzes the user's emotions and recognizes their state.
[2246] The server first receives the presentation's theme, purpose, target audience, and information sent from the smart device. Based on this information, it uses an AI model to automatically generate presentation materials. The generated presentation materials are then provided to the user via their smart device, who can review the materials in real time and make edits to the text and images as needed.
[2247] Next, emotion recognition software analyzes data such as the user's voice and facial expressions to recognize their emotions. Based on the results, the server adapts the presentation materials and advice provided. This process allows the user to improve the quality of their presentation by offering advice on how to relax or suggesting slide revisions if they are nervous.
[2248] As a concrete example, consider a scenario in which an efficiency improvement report for a new warehouse allocation system is created. A user wears smart glasses and captures video of the warehouse. OCR technology is used to extract text data from the video, and an AI model automatically generates a slide deck based on this data. The generated slides include an overview of the new warehouse allocation system, the efficiency improvement status, and cost reduction effects. The user checks the slides on the smart glasses' display and makes any necessary corrections. If emotion recognition software detects that the user is tense, advice such as encouraging deep breathing is displayed.
[2249] An example prompt is, "Generate a presentation to create an efficiency improvement report for a new warehouse layout system. Key areas to focus on include efficiency gains, cost savings, and staff satisfaction after the layout change."
[2250] As described above, this system supports the efficient and effective creation and presentation of presentation materials at logistics centers.
[2251] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[2252] Step 1:
[2253] The user uses a smart device (e.g., smart glasses) to input the presentation topic, objectives, target audience, and information to be provided. The input information is sent from the smart device to the server. Examples of input data include "improving the efficiency of the logistics center," "presentation on business improvement," "manager," and "improving the efficiency of a new warehouse layout system."
[2254] Step 2:
[2255] The server automatically generates presentation materials using a generative AI model (e.g., PresentationAI) based on the received input data. Specifically, it creates an appropriate slide structure based on the theme and purpose, and embeds the content. For example, it generates slides such as a "title slide," a "slide explaining the efficiency improvement after the layout change," and a "slide showing the cost reduction effect." The output is the automatically generated presentation materials.
[2256] Step 3:
[2257] The server provides the generated presentation materials to the smart device. The user checks the presentation materials on the smart device's display and operates the interface to modify text, images, and charts as necessary. The entered modification data is then sent to the server. The input here is the user's modification instructions, and the output is the modified presentation materials.
[2258] Step 4:
[2259] The server updates the presentation materials based on the corrections sent by the user. The updated presentation materials are then sent back to the smart device, where the user can review and make final adjustments. The final presentation materials are then output.
[2260] Step 5:
[2261] When a user rehearses a presentation, emotion recognition software (e.g., EmotionEngine) on the smart device analyzes the user's voice and facial expressions to recognize emotional data. Based on this, the user's state of tension or relaxation is analyzed. The input data is the user's voice and facial expression data, and the output data is the analyzed emotional information.
[2262] Step 6:
[2263] The server adjusts the content of the presentation materials and advice based on the emotional data sent from the emotion recognition software. For example, if the user is nervous, the server may suggest relaxation techniques such as encouraging deep breathing or change the slide structure. The adjusted advice and presentation materials are then output.
[2264] Step 7:
[2265] The user receives final advice via their smart device and makes final adjustments while rehearsing their presentation. This process prepares the user for the actual presentation. The final output is a quality-improved presentation document and advice for the user.
[2266] The above are the specific processing steps of the system that realizes the application example.
[2267] 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.
[2268] 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.
[2269] 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.
[2270] 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.
[2271] 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.
[2272] 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.
[2273] 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).
[2274] 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.
[2275] 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."
[2276] 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.
[2277] 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).
[2278] 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.
[2279] 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.
[2280] 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.
[2281] 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.
[2282] 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.
[2283] 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.
[2284] 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.
[2285] 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.
[2286] 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.
[2287] 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.
[2288] The following is further disclosed regarding the above embodiment.
[2289] (Claim 1)
[2290] input means for a user to input the topic, purpose, target audience, and information to be provided for the presentation;
[2291] a generating means for generating presentation materials based on the information received from the input means;
[2292] providing means for providing the presentation materials generated by the generating means to a user;
[2293] an advising means for giving advice on presentation techniques based on the presentation materials;
[2294] A system including:
[2295] (Claim 2)
[2296] 2. The system of claim 1, wherein the generating means uses an AI model trained from presentation professionals with specialized knowledge.
[2297] (Claim 3)
[2298] 10. The system of claim 1, wherein the advice means provides the user with advice on storytelling, non-verbal communication, and question and answering.
[2299] "Example 1"
[2300] (Claim 1)
[2301] input means for a user to...
Claims
1. input means for a user to input the topic, purpose, target audience, and information to be provided for the presentation; a generating means for generating presentation materials based on the information received from the input means; providing means for providing the presentation materials generated by the generating means to a user; an advising means for giving advice on presentation techniques based on the presentation materials; A system including:
2. The system of claim 1 , wherein the generating means uses an AI model trained from presentation professionals with specialized knowledge.
3. The system of claim 1 , wherein the advice means provides the user with advice regarding storytelling, non-verbal communication, and question and answering.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A