system

Abstract

To provide a system that enables a user to efficiently create high-quality presentation materials with little effort. [Solution] A system including an input means for a user to input purpose and basic information, a means for recommending a plurality of presentation templates based on the information input by the input means, a selection means for selecting the recommended template, a question posing means for interactively obtaining additional information based on the template selected by the selection means, a means for receiving the additional information and automatically generating presentation materials, a means for presenting the generated presentation materials to the user and regenerating them based on the user's requests for revisions, and an output means for finally outputting the presentation materials.

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] In today's business environment, creating presentation materials is an important task, but it is generally known that creating them requires time and effort. This difficulty increases especially when high-quality materials must be produced in a short time frame. Furthermore, to convey information accurately and effectively, specialized knowledge and design sense are also required. In this environment, there is a need for a system that allows users to quickly and easily create high-quality presentation materials. [Means for solving the problem]

[0005] This invention provides a system that includes input means for a user to input purpose and basic information, means for recommending a plurality of presentation templates based on the input information, selection means for selecting a recommended template, means for presenting questions to interactively acquire additional information based on the selected template, means for receiving the additional information and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on user requests for revisions, and output means for finally outputting the generated presentation materials. This system enables users to create high-quality presentation materials efficiently with little effort.

[0006] "Input means" is an interface for the user to input the purpose and basic information of the presentation.

[0007] The "recommendation means" is a function that suggests multiple presentation templates to the user based on information entered by the user.

[0008] The "selection means" is an interface that allows the user to select an appropriate template from the recommended templates.

[0009] The "question presentation means" is a function that interactively asks the user for additional information based on the selected template.

[0010] "Means for automatic generation" is a function that automatically creates presentation materials based on information obtained from the user.

[0011] The "regeneration means" is a function for regenerating a part or the whole of the presentation material in response to a user's request for modification of the generated presentation material.

[0012] "Output means" is a function that provides the user with the finalized presentation materials in a downloadable format. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] User Registration and Login

[0035] 1. The user accesses the login screen

[0036] The device displays a login page, and the user enters their email address and password.

[0037] 2. Authentication and Dashboard Migration

[0038] The terminal sends the entered authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server returns the user's dashboard page. The terminal displays the dashboard page.

[0039] Enter the purpose of the presentation and basic information

[0040] 1. Display the basic information input form

[0041] The device displays a form for the user to input the purpose, target audience, and deadline of the presentation.

[0042] 2. Transmission and storage of information

[0043] The user enters and submits information such as "New product promotion," "Management," and "3 days later." The device sends this information to the server, which then stores it in a database.

[0044] Template recommendations

[0045] 1. Template Presentation

[0046] The server sends a template request to the generation AI based on the saved basic information. The generation AI generates multiple templates and returns them to the server. The server displays a preview of the templates to the user.

[0047] 2. Select a template

[0048] The user selects an appropriate template from the displayed templates.

[0049] Interactive question and answer

[0050] 1. Posing the Question

[0051] The device displays the first question, "What are the features of your new product?" based on the selected template.

[0052] 2. Enter and submit your answers

[0053] The user enters "a smartphone equipped with the latest AI technology" and submits the answer. The device then sends the entered answer to the server.

[0054] 3. Show next question

[0055] The server saves the additional information and requests the next question from the generation AI, which returns the generated next question to the server, which displays it on the device.

[0056] Automatic generation of materials

[0057] 1. Sending the final data

[0058] The server sends all user responses to the generation AI.

[0059] 2. Creating and Presenting Materials

[0060] The generation AI generates presentation materials and returns them to the server, which then presents them to the user.

[0061] Final check and corrections

[0062] 1. Preview display

[0063] The terminal displays the generated presentation materials to the user.

[0064] 2. Enter the corrections and regenerate

[0065] The user types, "I would like to revise the content of slide 4." The device sends the revision instruction to the server. The server makes a request to the generation AI, and the revised document is returned to the server. The server then presents the document again.

[0066] Final Output

[0067] 1. Final Download

[0068] The user finally confirms the material that satisfies him and clicks the download link, which is displayed on the device and the user downloads the material.

[0069] This system allows users to create high-quality presentation materials in a short amount of time. Collaboration between the server and the generation AI allows for efficient and flexible generation and modification of materials.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] The user accesses the login screen. The device displays the login page. The user enters their email address and password and submits it.

[0073] Step 2:

[0074] The terminal sends the entered authentication information to the server. The server accesses the database and checks whether the user's email address and password are correct. If authentication is successful, the server issues session information to the user.

[0075] Step 3:

[0076] The server generates the user's dashboard page and returns it to the device. The device displays the dashboard page to the user. The user clicks the "Create a new presentation" button.

[0077] Step 4:

[0078] The device displays a form for the user to input the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the submit button.

[0079] Step 5:

[0080] The device sends the input information to the server. The server stores the received information in a database. The server then sends a template request to the generation AI based on the stored information.

[0081] Step 6:

[0082] The generation AI generates multiple presentation templates and returns them to the server. The server presents preview images and descriptions of the templates to the user. The device displays the preview images and allows the user to select a template.

[0083] Step 7:

[0084] The user selects an appropriate template. The device sends the selection information to the server. The server then requests the generation AI to generate questions in an interactive format based on the selected template.

[0085] Step 8:

[0086] The generation AI generates the first question and returns it to the server. The server sends the first question, "Please tell me the features of the new product," to the device. The device displays the question to the user.

[0087] Step 9:

[0088] The user enters the answer "a smartphone equipped with the latest AI technology" and clicks the send button. The device sends the answer to the server, which then stores the received answer in a database.

[0089] Step 10:

[0090] The server requests the next question from the generation AI. The generation AI generates the next question and returns it to the server. The server sends the next question to the device, which displays it to the user. This step is repeated until all the necessary information is collected.

[0091] Step 11:

[0092] Once all the information has been collected, the server requests the generation AI to generate the presentation materials. The generation AI generates the materials and returns them to the server. The server then presents the generated presentation materials to the user.

[0093] Step 12:

[0094] The user previews the document and inputs any corrections that need to be made. The device sends correction instructions to the server. The server requests correction instructions from the generation AI, which then corrects the document and returns it to the server. The server then presents the corrected document to the user again. This step is repeated until the user is finally satisfied.

[0095] Step 13:

[0096] When the user is satisfied with the final document, he / she clicks on the download link, the terminal displays the download link for the final document, and the user downloads the document.

[0097] Through the above steps, the user can create presentation materials efficiently and quickly.

[0098] Example 1

[0099] 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."

[0100] The process of creating presentation materials generally requires time and effort. This makes it difficult for users to create high-quality materials within a limited time. In addition, modifying and regenerating materials is also time-consuming, so a system that can respond flexibly is required.

[0101] 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.

[0102] In this invention, the server includes input means for a user to input purpose and basic information, means for requesting multiple presentation templates from the generative AI model based on the information input by the input means, and selection means for selecting a template recommended by the generative AI model, thereby enabling efficient generation and flexible modification of high-quality presentation materials.

[0103] A "user" is an individual or corporation that uses the system to create presentation materials.

[0104] "Input means" refers to the device or software that allows the user to input purpose and basic information.

[0105] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to automatically generate presentation templates and materials.

[0106] A "prompt" is an instruction or question input to a generative AI model, which serves as a guide for the AI ​​to return an appropriate output.

[0107] "Recommended templates" refer to multiple templates generated by a generative AI model based on user input information.

[0108] "Selection means" refers to a device or software that allows a user to select an appropriate template from among the templates recommended by the generative AI model.

[0109] A "question presenter" is a device or software for interactively asking a user for additional information based on a selected template.

[0110] "Presentation materials" refer to slides and documents created to achieve the purpose of a presentation.

[0111] "Output means" refers to a device or software for providing the final generated presentation materials to the user.

[0112] "Automatic generation means" means a device or software that automatically creates presentation materials based on input information and additional information using a generative AI model.

[0113] A "modification request" is an instruction from a user requesting changes to the content of the generated presentation materials.

[0114] A "means for requesting regeneration" is a device or software that causes a generative AI model to regenerate the content of a presentation material based on a modification request.

[0115] This system allows users to create efficient and high-quality presentation materials, and is implemented using a server, terminals, and a generative AI model.

[0116] 1. User Registration and Login

[0117] When a user accesses the login screen using a terminal, the terminal opens a browser and accesses the URL of the login page. The user enters their email address and password and presses the login button. The terminal sends the entered authentication information to the server, which then accesses the database to perform authentication. If authentication is successful, the server generates a dashboard page and sends it to the terminal. The terminal displays it.

[0118] 2. Enter the purpose of your presentation and basic information

[0119] A form is displayed on the dashboard page where the user can enter the purpose, target audience, and deadline of the presentation. For example, the user can enter information such as "New product promotion," "Management," and "3 days later." When the user submits the information, the device sends it to the server, which then stores the information in a database.

[0120] 3. Template Recommendations

[0121] The server sends a template request to the generative AI model based on the stored basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends previews of these templates to the device, which displays them to the user. When the user selects an appropriate template, the selection information is sent to the server.

[0122] 4. Interactive Question and Answer

[0123] Based on the template selected by the user, the device displays the first question, "What are the features of your new product?" The user enters the answer, "A smartphone equipped with the latest AI technology," and submits it. The device sends this answer to the server, which then requests the next question from the generative AI model. The generative AI model generates the next question and returns it to the server. The server displays the next question on the device.

[0124] 5. Automatic generation of materials

[0125] Once all user responses have been collected, the server sends this data to the generative AI model, which then generates presentation materials and returns them to the server. The server then sends the generated materials to the device, which displays them to the user.

[0126] 6. Final check and corrections

[0127] The user checks the generated presentation materials and inputs any parts that need to be corrected. For example, the user might input, "I would like to correct the content of slide 4." The device sends a correction request to the server, which then requests the generative AI model to regenerate the materials. The generative AI model returns the corrected materials to the server, which then sends them to the device. The device then displays the corrected materials to the user.

[0128] 7. Final output

[0129] When the user finally confirms the material they are satisfied with, they click the "Download" link, which the device displays and the user clicks to download the material.

[0130] Examples and prompts

[0131] Examples:

[0132] 1. User Registration and Login:

[0133] Example: A user logs in by entering an email address (example@example.com) and password (password123).

[0134] 2. Enter the purpose and basic information of your presentation:

[0135] Example: User enters "New product promotion," "Sales department," and "Presentation in 5 days."

[0136] 3. Template Recommendations:

[0137] Example: The generation AI presents two templates: a "template for introducing a new product" and a "template for a management report."

[0138] 4. Interactive Question and Answer:

[0139] Example: The first question is "What points do you want to emphasize in your presentation?" and the user enters "Safety of the latest technology."

[0140] 5. Automatic generation of materials:

[0141] Example: Generative AI generates a document consisting of three slides: "Slide 1: New product overview," "Slide 2: Technical details," and "Slide 3: Ensuring safety."

[0142] 6. Final checks and corrections:

[0143] Example: The user enters a correction such as "Please be more specific about the technical details on slide 2."

[0144] 7. Final output:

[0145] Example: User downloads revised document.

[0146] Example prompt:

[0147] I'd like to create a presentation for management to promote a new product. The purpose of the presentation is to clearly communicate the features of the new product, and the deadline is in three days. Please suggest a suitable template.

[0148] By providing specific prompts in this way, users can efficiently create materials.

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1:

[0151] When a user accesses the login screen, the terminal displays the login page. The user enters their email address and password. The terminal sends the input data to the server as an HTTP POST request. The server accesses the database and verifies the corresponding user information. If authentication is successful, the server generates HTML data for the dashboard page and sends it to the terminal. The terminal displays the received HTML data in the browser.

[0152] Enter your email address and password

[0153] Output: Dashboard page upon successful authentication

[0154] Step 2:

[0155] A user starts creating a new presentation from the dashboard page, and enters the purpose, target audience, and deadline of the presentation into a form displayed on the device. When the user submits the information, the device sends the input data as an HTTP POST request to the server, which stores it in a database.

[0156] Input: Purpose of presentation, target audience, deadline

[0157] Output: Basic information saved

[0158] Step 3:

[0159] The server sends a template request to the generative AI model based on the stored basic information. The generative AI model uses the received information as input to generate multiple presentation templates, which are then returned to the server. The server then sends a preview image and description of the template to the device, which displays it to the user.

[0160] Input: Basic information

[0161] Output: Multiple template previews

[0162] Step 4:

[0163] The user selects an appropriate template, and the selection information is sent from the terminal to the server, where it is stored.

[0164] Input: Selected template information

[0165] Output: Selection information stored on the server

[0166] Step 5:

[0167] The device displays a question to the user based on the selected template. For example, the question might be, "What are the features of the new product?" The user enters an answer, and the device sends the answer data to the server. The server stores the answer information and requests the next question from the generative AI model. The generative AI model generates the next question and returns it to the server. The server sends the next question to the device, which displays it.

[0168] Input: Template and first question

[0169] Output: User's answer and next question

[0170] Step 6:

[0171] Once the user's answers to all questions have been collected, the server sends these answers to the generative AI model, which then automatically generates presentation materials based on this data and returns the data to the server. The server then sends the generated materials to the device, which then displays them.

[0172] Input: All user responses

[0173] Output: The generated presentation

[0174] Step 7:

[0175] The user reviews the generated presentation materials and inputs correction requests as necessary. For example, the user sends a request such as "I would like to correct the content of slide 4." The device sends the correction request to the server, and the server sends a regeneration request to the generative AI model. The generative AI model generates the corrected materials and returns the data to the server. The server sends the corrected materials to the device, which displays them to the user.

[0176] Input: User modification request

[0177] Output: Revised presentation

[0178] Step 8:

[0179] When the user finally confirms the material they are satisfied with, they click the "Download" link. The terminal displays the download link, and the user clicks to download the material.

[0180] Input: User download request

[0181] Output: Downloaded presentation materials

[0182] (Application example 1)

[0183] 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."

[0184] Conventional presentation creation systems require users to spend a lot of time preparing presentation materials, making it difficult to quickly select appropriate templates and content. Furthermore, they are slow to respond to revision requests, which is inefficient in the advertising industry, where real-time responses are required. Therefore, there was a need for a system that allows users to easily and quickly generate high-quality presentation materials and make necessary revisions in real time.

[0185] 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.

[0186] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending a plurality of presentation templates based on the information input by the input means, selection means for selecting the recommended template, question presentation means for acquiring additional information in an interactive manner, means for receiving the additional information and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on a user's correction request, means for acquiring information via gaze or voice input in response to templates or questions displayed on the smart glasses, means for finally outputting the generated materials and providing them in a downloadable format, and display means for the smart glasses to display the generated presentation materials to the user. This allows a user to efficiently create high-quality presentation materials in a short amount of time and easily correct and check them by real-time operation through the smart glasses.

[0187] "Input means" refers to a device or interface that allows a user to input their purpose and basic information.

[0188] The "means for recommending" is a device or program that has the function of presenting multiple presentation templates based on input information.

[0189] The "selection means" refers to a device or interface that allows a user to select an appropriate template from the recommended templates.

[0190] A "question presenter" is a device or function for interactively gathering additional information based on a selected template.

[0191] "Automatic generation means" refers to a program or device that automatically creates presentation materials based on the collected additional information.

[0192] The "regeneration means" refers to a device or program that has the function of recreating the generated presentation materials based on a modification request from the user.

[0193] "Smart glasses" are wearable devices that allow users to input information using eye contact or voice input.

[0194] "Means for acquiring information through gaze or voice input" refers to a device or function that uses smart glasses to acquire information by analyzing the user's gaze movements and voice.

[0195] The "display means" refers to a display or interface for visually presenting the generated presentation materials to the user.

[0196] "Means for providing in a downloadable format" refers to a program or function for providing the final generated material in a format that can be downloaded by the user.

[0197] This invention provides a system that enables users to create, edit, and check presentation materials in real time using smart glasses. Specific embodiments of this system are described below.

[0198] User Registration and Login

[0199] The user puts on the smart glasses and accesses the system. A login screen is displayed through the smart glasses' display, and the user enters their email address and password using voice input or eye contact. The server authenticates the user based on this authentication information, and if authentication is successful, the user's dashboard page is displayed on the smart glasses.

[0200] Enter the purpose of the presentation and basic information

[0201] A form is displayed on the smart glasses displaying the user to input basic information such as the purpose of the presentation, the target audience, and the deadline. This information is acquired by voice or eye contact and sent to the server, which then stores the received information in a database.

[0202] Template recommendations

[0203] The server sends a template request to the generative AI based on the stored basic information. The generative AI model generates multiple templates and returns them to the server. The server then displays previews of these templates to the user through smart glasses. The user can then select an appropriate template by eye gaze or voice input.

[0204] Interactive question and answer

[0205] Based on the selected template, the server presents the user with a series of interactive questions. For example, the server displays a question such as "What are the features of the new product?", and the user responds by voice or eye contact. The server stores these responses and requests the next question from the AI ​​generator.

[0206] Automatic generation of materials

[0207] The server sends all user responses to the AI ​​generator, which then automatically generates presentation materials. The generated materials are then sent back to the server and presented to the user through the display means of the smart glasses.

[0208] Final check and corrections

[0209] The user checks the generated presentation materials and, if necessary, sends a request for revisions to the server using voice commands or eye gaze input. The server then sends this request to the generation AI, and presents the revised materials to the user again.

[0210] Final Output

[0211] The user reviews the presentation materials to their satisfaction and clicks on the final download link through the display means of the smart glasses. The server provides the materials in a downloadable format.

[0212] Hardware and software used

[0213] Smart glasses: Collect information through gaze control and voice input and display it to the user.

[0214] Server: Responsible for user authentication, data storage, question generation, document generation, and regeneration of correction requests.

[0215] Generative AI model: Generates templates and presentation materials.

[0216] Database: Stores user information and presentation data.

[0217] Examples of concrete examples and prompts

[0218] For example, when using the generative AI model GPT-4 (registered trademark), the prompt would look like this:

[0219] prompt

[0220] "Design an application that helps users create ads in real time using smart glasses. Collect information about the ad's purpose, targeting, design, and content, generate templates and questions based on that information, and then generate and display the final ad in real time. Allow the user to modify and download the ad using voice commands as needed."

[0221] This allows users to create high-quality presentation materials efficiently and in a short amount of time, and allows them to make real-time edits and checks through the smart glasses.

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] (User registration and login) The user puts on the smart glasses and the login screen appears on the display of the smart glasses. The user enters their email address and password using voice input or eye contact. The server receives the entered authentication information and accesses the database to authenticate the user. If authentication is successful, the user's dashboard page is displayed through the smart glasses.

[0225] Input: Email address, password

[0226] Data processing: database access, authentication processing

[0227] Output: Dashboard page displayed

[0228] Step 2:

[0229] (Inputting the purpose of the presentation and basic information) The server displays a form on the smart glasses to input the purpose of the presentation, target audience, deadline, etc. The user inputs this information using voice input or eye gaze input. The server receives the input information and stores it in a database.

[0230] Input: Purpose of presentation, target audience, deadline

[0231] Data processing: Data storage processing

[0232] Output: Basic information saved

[0233] Step 3:

[0234] (Template recommendation) The server sends a template request to the generation AI based on the basic information stored in the database. The generation AI generates multiple templates and returns them to the server. The server displays a preview of the templates on the smart glasses. The user selects a template by eye gaze or voice input.

[0235] Input: Basic information, template request

[0236] Data processing: Template generation, preview display

[0237] Output: Selected template

[0238] Step 4:

[0239] (Interactive Questions and Answers) Based on the selected template, the server sequentially displays interactive questions to the user. For example, the server displays a question such as, "What are the features of the new product?" The user answers by voice or eye contact, and the server receives the answers and stores them in a database.

[0240] Input: Question, Answer

[0241] Data processing: Question generation, answer storage

[0242] Output: Additional information saved

[0243] Step 5:

[0244] (Automatic generation of presentation materials) The server sends all user responses to the generation AI, which then automatically generates presentation materials. The generated materials are sent back to the server and presented to the user through the display means of the smart glasses.

[0245] Input: User answer

[0246] Data processing: Data generation

[0247] Output: Generated presentation materials

[0248] Step 6:

[0249] (Final confirmation and corrections) The user checks the presentation materials displayed on the smart glasses and makes any necessary corrections by voice or eye contact. The server sends these correction instructions to the generation AI, which then regenerates the corrected materials. The corrected materials are then sent back to the server and presented to the user again.

[0250] Input: Correction instructions

[0251] Data processing: Reflection of correction instructions, regeneration

[0252] Output: Revised presentation

[0253] Step 7:

[0254] (Final Output) The user finally checks the presentation materials to their satisfaction and clicks the final download link through the display means of the smart glasses. The server provides the materials in a downloadable format, and the user downloads the materials.

[0255] Input: Download instructions

[0256] Data processing: Converting materials into downloadable format

[0257] Output: Downloadable materials

[0258] 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.

[0259] User Registration and Login

[0260] 1. The user accesses the login screen

[0261] The device displays a login page, and the user enters their email address and password and submits it.

[0262] 2. Authentication and Dashboard Migration

[0263] The device sends authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server generates the user's dashboard page and returns it to the device. The device displays the dashboard page. The user clicks "Create a new presentation."

[0264] Enter the purpose of the presentation and basic information

[0265] 1. Display the basic information input form

[0266] The device displays a form where you can enter the purpose of the presentation, the target audience, and the deadline.

[0267] 2. Transmission and storage of information

[0268] The user enters information such as "New product promotion," "Management," and "3 days later," and submits it. The device sends the information to the server, which stores it in a database.

[0269] Template recommendations

[0270] 1. Template Presentation

[0271] The server sends a template request to the generation AI based on basic information. The generation AI generates multiple templates and returns them to the server. The server presents preview images and descriptions of the templates to the user. The device displays the preview images, and the user can select the appropriate template.

[0272] Conversational Questions and Emotion Recognition

[0273] 1. Posing the Question

[0274] The device displays the first question based on the selected template: "What are the features of your new product?"

[0275] 2. Emotion recognition and answer input

[0276] The device acquires the user's facial recognition data or voice data and sends it to the server, which uses an emotion engine to determine the user's emotional state.

[0277] The device receives the user's response, "A smartphone equipped with the latest AI technology," and sends it to the server.

[0278] 3. Generate and display the next question

[0279] The server requests the next question from the generation AI. The generation AI creates a question based on the emotional state recognized by the emotion engine. The server then sends the next question to the device, which displays it to the user. This process is repeated until all necessary information is collected.

[0280] Automatically generate materials and adjust them based on emotions

[0281] 1. Sending the final data

[0282] The server sends all information to the generating AI.

[0283] 2. Creation and adjustment of materials

[0284] The generative AI generates presentation materials, and the emotion engine adjusts the design and content according to the user's emotional state. The adjusted materials are then returned to the server.

[0285] 3. Presentation of materials

[0286] The server presents the generated presentation materials to the user, and the terminal displays the materials as a preview.

[0287] Final check and corrections

[0288] 1. Preview display

[0289] The terminal displays the generated presentation materials to the user.

[0290] 2. Enter the corrections and regenerate

[0291] The user types, "I would like to revise the content of slide 4." The device sends the revision instructions to the server. The server requests revision instructions from the generation AI, which then revises the document and returns it to the server. The server then presents the revised document to the user again. This process is repeated until the user is finally satisfied.

[0292] Final Output

[0293] 1. Final Download

[0294] The user checks the material to find it satisfactory and clicks on the download link.

[0295] The terminal displays a download link, and the user downloads the material.

[0296] This system allows users to efficiently create high-quality presentation materials. In particular, by utilizing the emotion engine, questions and materials are adjusted according to the user's emotional state, providing more appropriate and effective presentation materials.

[0297] The processing flow will be explained below.

[0298] Step 1:

[0299] The user accesses the login screen. The device displays the login page. The user enters their email address and password and clicks the submit button.

[0300] Step 2:

[0301] The terminal sends the entered authentication information to the server. The server accesses the database and checks whether the user's email address and password are correct. If authentication is successful, the server issues session information.

[0302] Step 3:

[0303] The server generates the user's dashboard page and returns it to the device. The device displays the dashboard page. The user clicks the "Create a new presentation" button.

[0304] Step 4:

[0305] The device displays a form for inputting the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the submit button.

[0306] Step 5:

[0307] The device sends the input information to the server. The server stores the received information in a database. The server then sends a template request to the generation AI based on the stored information.

[0308] Step 6:

[0309] The generation AI generates multiple presentation templates and returns them to the server. The server then presents preview images and descriptions of the templates to the user. The device displays the preview images, and the user selects the appropriate template.

[0310] Step 7:

[0311] The user selects a template. The device sends the selection information to the server. The server requests the generation AI to generate interactive questions based on the selected template.

[0312] Step 8:

[0313] The generation AI generates the first question and returns it to the server. The server sends the question, "Please tell me the features of the new product," to the device. The device displays the question to the user.

[0314] Step 9:

[0315] The user answers the question by typing "a smartphone equipped with the latest AI technology" and clicks the send button. The device sends the answer to the server, which then stores it in a database.

[0316] Step 10:

[0317] The device acquires the user's facial recognition data or voice data and sends it to the server, which uses an emotion engine to determine the user's emotional state.

[0318] Step 11:

[0319] The server requests the next question from the generation AI based on the emotional state recognized by the emotion engine. The generation AI returns the generated next question to the server, which then sends it to the device. The device displays the next question to the user. This step is repeated until all necessary information is collected.

[0320] Step 12:

[0321] Once all the information is collected, the server requests the generation AI to generate presentation materials. The generation AI generates the materials, and the emotion engine adjusts the design and content according to the user's emotional state. The adjusted materials are then returned to the server.

[0322] Step 13:

[0323] The server presents the generated presentation materials to the user, and the terminal displays a preview of the materials.

[0324] Step 14:

[0325] The user checks the document and indicates the parts that need to be corrected. The device sends the correction instructions to the server. The server requests the generation AI to make corrections, and the generation AI regenerates the document and returns it to the server. The server then presents the corrected document to the user again. This step is repeated until the user is finally satisfied.

[0326] Step 15:

[0327] If the user is satisfied with the final document, he / she clicks on the download link, and the terminal displays the download link for the final document, and the user downloads the document.

[0328] Example 2

[0329] 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."

[0330] Conventional presentation creation systems have the problem that even if a user inputs information and selects a template, it is difficult to generate efficient, high-quality materials in the subsequent document creation process. Another issue is that there is no system that can create optimal materials according to the user's emotional state. This makes it difficult to maximize the effectiveness of presentations, ultimately hindering business success and effective communication.

[0331] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0332] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending a plurality of presentation templates based on the information input by the input means, selection means for selecting the recommended template, question posing means for acquiring additional information in an interactive format, means for receiving the additional information and adjusting the question content based on the user's emotional state using emotion recognition technology, means for transmitting all information to a generative AI model and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on the user's requested revisions, and output means for finally outputting the presentation materials. This enables users to efficiently create high-quality presentation materials and generate materials optimal for their emotional state.

[0333] The "input means for the user to input the purpose and basic information" is an interface for the user to input basic information such as the purpose, target audience, and deadline of the presentation.

[0334] "Means for recommending multiple presentation templates" is a function that suggests the most suitable presentation template based on basic information entered by the user.

[0335] The "selection means for selecting a recommended template" is an operation method for selecting an appropriate template from a plurality of templates presented to the user.

[0336] The "means for presenting questions to acquire additional information in an interactive manner" is a function for displaying questions to collect additional information necessary for presentation through a dialogue with the user.

[0337] "Emotion recognition technology" is a technology that analyzes a user's facial recognition data and voice data to determine the user's emotional state.

[0338] The "means for adjusting the content of the question based on the emotional state" is a function for changing the content and format of the question depending on the emotional state of the user.

[0339] A "generative AI model" is an artificial intelligence model that analyzes data based on input information and generates new information and materials.

[0340] The "means for automatically generating presentation materials" is a system that automatically creates presentation materials based on collected information.

[0341] The "means for presenting the generated presentation materials to the user and regenerating them based on the user's revision requests" is a function for displaying the initially generated materials to the user and then generating the materials again based on subsequent revision requests.

[0342] The "output means for finally outputting the presentation materials" refers to a download link or file saving function for providing the user with the finalized presentation materials.

[0343] This invention relates to a system for generating presentation materials efficiently and with high quality. The system generates optimal presentation materials by allowing users to input their purpose and basic information, proposing appropriate templates, and adjusting questions based on the user's emotional state. This system is realized using a terminal, a server, and a generation AI model.

[0344] Input Method

[0345] The user accesses the system's login page from a web browser on their terminal. Authentication is performed by entering their email address and password and clicking the login button. The server verifies the authentication information using a database (for example, MySQL (registered trademark)), and if authentication is successful, it generates the user's dashboard and returns it to the terminal. Next, the user clicks "Create a new presentation" to display a form for entering basic information such as the purpose of the presentation, target audience, and deadline. The user enters information such as "New product promotion," "Management," and "3 days later" into this form and submits it.

[0346] Presentation template recommendation method

[0347] The server sends a template generation request to a generation AI (e.g., OpenAI (registered trademark) GPT-4) based on the basic information entered by the user. The generation AI generates multiple templates and returns the results to the server. The server then creates preview images and descriptions of these templates in HTML format and sends them to the device. The device then displays these preview images and descriptions to the user, providing an interface for selecting an appropriate template.

[0348] Question presentation method and emotion recognition method

[0349] When the user selects a template, the device displays the first question based on the selected template: "What are the features of the new product?" At the same time, the device acquires the user's facial recognition data and voice data and sends them to the server. The server uses emotion recognition technology (for example, Microsoft® Azure® Emotion API) to determine the user's emotional state. When the user enters and submits the answer, "A smartphone equipped with the latest AI technology," that information is also sent to the server.

[0350] Information adjustment means

[0351] The server then requests the AI ​​to generate the next question, adjusting the question based on emotion recognition. The server then sends the generated question to the device, which displays it to the user. This process is repeated until all the information needed for the presentation is gathered.

[0352] A means of automatically generating presentation materials

[0353] Once all the information is collected, the server sends it to a generative AI model, which then generates presentation materials based on the collected information. The generated materials are then adjusted in design and content using emotion recognition technology. The adjusted materials are then returned to the server.

[0354] Material presentation means and reproduction means

[0355] The server sends the generated presentation materials to the device, which displays them as a preview to the user. The user checks the preview and enters, for example, "I would like to revise the contents of slide 4." The device receives the revision instructions and sends them to the server. The server then sends a regeneration instruction to the generation AI, causing it to generate the materials again. The revised materials are then returned to the server and displayed to the user via the device. This process is repeated until the user is satisfied.

[0356] Final output method

[0357] When the user finally finds the material that satisfies him, he clicks on the download link, and the terminal displays the download link, allowing the user to download the material.

[0358] The above is an embodiment of the present invention. This system allows users to efficiently and effectively create high-quality presentation materials. The following is a specific example of a prompt sentence to be input to the generative AI model:

[0359] "Please create a presentation to promote our new product. It's for management and needs to be completed in three days."

[0360] "Feature: 'Smartphone equipped with the latest AI technology', Emotion: Excitement, What should I ask next?"

[0361] These prompts will generate more specific and personalized presentation materials.

[0362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0363] Step 1:

[0364] A user accesses the system's login page from a web browser. The user enters their email address and password and clicks the "Login" button. The terminal sends this authentication information to the server, which then verifies the user information using a database (e.g., MySQL). If authentication is successful, the server generates the user's dashboard and sends the HTML data to the terminal. The terminal receives it and displays it to the user. The input is the user's authentication information, and the output is the HTML data of the dashboard.

[0365] Step 2:

[0366] The user clicks the "Create a new presentation" button on the dashboard. The device displays a form for entering the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the "Submit" button. The device sends this information to the server, which saves it in a database. The input is the basic information about the presentation, and the output is a response indicating that it was saved successfully.

[0367] Step 3:

[0368] The server uses the stored basic information to send a template request to a generative AI model (e.g., OpenAI GPT-4). The generative AI model generates a template and returns its preview image and description to the server. The server receives these, formats them into HTML, and sends them to the device. The device displays multiple templates to the user and allows the user to select one. The input is the basic information, and the output is the template preview image and description.

[0369] Step 4:

[0370] The user selects a template. Based on the selected template, the device displays the first question, "What are the features of your new product?" The user answers, "A smartphone equipped with the latest AI technology." The device then acquires facial recognition data and voice data and sends them to the server. The server uses emotion recognition technology to recognize the user's emotional state. The input is the template selection and the user's emotional data, and the output is the emotional state.

[0371] Step 5:

[0372] The server requests the next question from the generative AI model and receives the question content adjusted by emotion recognition technology from the generative AI model. The new question is sent from the server to the device, which displays it to the user. The user answers the question, and the device sends the answer to the server. This process is repeated until all necessary information is collected. The input is the previous question and the user's answer, and the output is the next question.

[0373] Step 6:

[0374] After all the information is collected, the server sends it to the generative AI model, which generates the presentation materials. The generative AI model generates the materials, adjusts them based on emotion recognition technology, and returns the results to the server. The server receives the generated presentation materials and sends them to the device, which displays a preview for the user. The input is the collected information, and the output is the generated presentation materials.

[0375] Step 7:

[0376] The user checks the preview and, if necessary, inputs a correction request, such as "I would like to revise the content of slide 4." The device sends the correction request to the server. The server sends correction instructions to the generative AI model and receives a regenerated document. The new document is sent from the server to the device and previewed again by the user. This process is repeated until the user is satisfied. The input is the correction request, and the output is the revised presentation document.

[0377] Step 8:

[0378] When the user is finally satisfied with the presentation materials, he or she clicks the download link. The terminal displays the download link, allowing the user to download the materials. The input is the final confirmation and clicking the download link, and the output is the final presentation materials.

[0379] The above is the flow of specific processing steps of the program of this system.

[0380] (Application example 2)

[0381] 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."

[0382] Many conventional presentation production systems automatically generate presentations based solely on input information, without considering the user's emotional state. This makes it difficult to generate appropriate questions or materials based on the user's emotional changes, resulting in a lack of improved user experience. Furthermore, surveillance systems lack technology that uses emotion recognition to instantly issue security alerts, making it difficult to respond quickly and accurately.

[0383] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0384] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending multiple presentation templates based on the input information, selection means for selecting a recommended template, question presentation means for acquiring additional information in an interactive format, emotion recognition means for determining the user's emotional state based on the additional information and facial recognition data or voice data, a generative AI model for adjusting the questions based on the emotional state determined by the emotion recognition means, means for presenting questions generated by the generative AI model to the user, receiving the additional information, and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on user requests for revisions, and output means for finally outputting the presentation materials. This enables appropriate question presentation and material generation that take the user's emotional state into consideration, as well as rapid and accurate security response using emotion recognition in surveillance systems.

[0385] "Input means" refers to a device or interface through which a user inputs objectives and basic information.

[0386] The "recommending means" is a device or program for recommending a plurality of presentation templates based on information input by the input means.

[0387] The "selection means" is a device or interface that allows the user to select a recommended template.

[0388] The "question presenting means" is a device or program that displays a question for acquiring additional information in an interactive manner based on the template selected by the selection means.

[0389] "Emotion recognition means" refers to a device or program for determining the emotional state of a user based on facial recognition data or voice data.

[0390] A "generative AI model" is an artificial intelligence model that tailors questions based on the emotional state determined by the emotion recognition means.

[0391] "Means for automatic generation" means a device or program for receiving additional information and generating presentation materials based on questions generated by a generative AI model.

[0392] The "regenerating means" is a device or program for presenting the generated presentation materials to the user and regenerating the materials based on the user's modification requests.

[0393] "Output means" refers to a device or program for providing the final generated presentation materials to the user in a displayable or downloadable format.

[0394] MODE FOR CARRYING OUT THE INVENTION

[0395] A specific system for implementing the present invention is configured as follows.

[0396] User Registration and Login

[0397] The device that the user accesses displays a login screen for entering an email address and password. When the user enters and submits the information, the device sends the authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server generates a dashboard page for the user and returns it to the device. The device displays the dashboard page and allows the user to select "Create a new presentation."

[0398] Enter the purpose of the presentation and basic information

[0399] When a user clicks "Create a new presentation" on the dashboard, a basic information input form is displayed on the device. The user enters information such as the purpose of the presentation, target audience, and deadline into this form and submits it. The entered information is sent from the device to the server, which then stores it in a database.

[0400] Template recommendations

[0401] The server sends a template request to the generative AI model based on the basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends preview images and descriptions of the templates to the device, allowing the user to select one.

[0402] Conversational Questions and Emotion Recognition

[0403] After the user selects a template, the device displays the first question based on the selected template: "Please tell us the features of the new product." The device acquires facial recognition data or voice data and sends it to the server. The server uses emotion recognition means to determine the user's emotional state. The user's answer to the question displayed on the device is entered and sent to the server. The server requests the next question from the generative AI model, and a new question is generated based on the user's emotional state. This process is repeated until all necessary information is collected.

[0404] Automatically generate materials and adjust them based on emotions

[0405] The server sends all information to the generative AI model, which then generates the presentation materials. Furthermore, the emotion recognition means adjusts the design and content according to the user's emotional state. The adjusted materials are then sent back to the server, which presents them to the user. The device displays the materials as a preview.

[0406] Final check and corrections

[0407] The user previews the generated presentation materials and, if any corrections are needed, inputs instructions such as "I would like to revise the content of slide 4." The device sends this instruction to the server, which then requests corrections from the generative AI model. The generative AI model then corrects the materials and sends them back to the server. The server then presents the corrected materials to the user again. This process is repeated until the user is satisfied.

[0408] Final Output

[0409] When the user confirms the material that satisfies him and clicks on the download link, the terminal displays the download link and the user can download the material.

[0410] Hardware and software used

[0411] Hardware: Smartphones, smart glasses, head-mounted displays, robots.

[0412] Software: Python, OpenCV, Keras, and the required server and database systems.

[0413] Specific examples

[0414] For example, by installing this system at the entrance to an office, it can instantly detect suspicious or nervous individuals and send an alert to the security team.

[0415] Prompt Sentence Examples

[0416] Enter the following prompt into the generative AI model:

[0417] "Generate a template for building a security alert system based on an emotion engine. The template should be Python code that performs face detection and emotion recognition and sends an alert when an anomaly is detected. The template should use a cascade classifier and a Keras model to perform face detection and emotion recognition."

[0418] This system configuration enables flexible creation of presentation materials based on the user's emotional state and quick and accurate security response.

[0419] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0420] Step 1:

[0421] User Registration and Login

[0422] The user enters and submits their email address and password. The device sends this authentication information to the server. The server references the database and authenticates the user. If authentication is successful, the server generates a dashboard page for the user and sends its contents back to the device. The device displays the dashboard page and allows the user to select "Create a new presentation."

[0423] Input: Email address, password

[0424] Output: Dashboard page

[0425] Step 2:

[0426] Enter the purpose of the presentation and basic information

[0427] When a user clicks "Create a new presentation" on the dashboard, the device displays a form for inputting the purpose, target audience, and deadline of the presentation. The user fills out the form and submits it. The device sends this information to the server, which stores it in a database.

[0428] Input: Purpose of presentation, target audience, deadline

[0429] Output: Basic information saved

[0430] Step 3:

[0431] Template recommendations

[0432] The server sends a template request to the generative AI model based on the basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends preview images and descriptions of the templates to the device, allowing the user to select one.

[0433] Input: Basic information

[0434] Output: Template preview image and description

[0435] Step 4:

[0436] Conversational Questions and Emotion Recognition

[0437] After the user selects a template, the device displays the first question: "What are the features of your new product?" The device captures facial recognition or voice data and sends it to the server. The server uses emotion recognition means to determine the user's emotional state. Based on this emotional state, the generative AI model generates the next question and returns it to the server. The device displays the next question, and the user enters and submits the answer. This process is repeated until all necessary information is collected.

[0438] Input: Facial recognition data or voice data, user response

[0439] Output: Next question based on emotional state

[0440] Step 5:

[0441] Automatically generate materials and adjust them based on emotions

[0442] The server sends all information to a generative AI model, which then generates the presentation materials. The emotion recognition means adjusts the design and content according to the user's emotional state. The adjusted materials are then sent back to the server, which then sends them to the device for the user to preview.

[0443] Input: All information

[0444] Output: Adjusted presentation material

[0445] Step 6:

[0446] Final check and corrections

[0447] The user previews the generated presentation materials and inputs any necessary corrections. The device sends these instructions to the server, which then requests corrections from the generative AI model. The generative AI model then corrects the materials and sends them back to the server. The server then presents the corrected materials to the user again. This process is repeated until the user is satisfied.

[0448] Input: Correction instructions

[0449] Output: Revised presentation

[0450] Step 7:

[0451] Final Output

[0452] When the user confirms the material that satisfies him and clicks on the download link, the terminal displays the download link and the user can download the material.

[0453] Input: Click on the download link

[0454] Output: Downloaded presentation

[0455] 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.

[0456] 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.

[0457] 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.

[0458] [Second embodiment]

[0459] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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).

[0465] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0470] 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."

[0471] User Registration and Login

[0472] 1. The user accesses the login screen

[0473] The device displays a login page, and the user enters their email address and password.

[0474] 2. Authentication and Dashboard Migration

[0475] The terminal sends the entered authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server returns the user's dashboard page. The terminal displays the dashboard page.

[0476] Enter the purpose of the presentation and basic information

[0477] 1. Display the basic information input form

[0478] The device displays a form for the user to input the purpose, target audience, and deadline of the presentation.

[0479] 2. Transmission and storage of information

[0480] The user enters and submits information such as "New product promotion," "Management," and "3 days later." The device sends this information to the server, which then stores it in a database.

[0481] Template recommendations

[0482] 1. Template Presentation

[0483] The server sends a template request to the generation AI based on the saved basic information. The generation AI generates multiple templates and returns them to the server. The server displays a preview of the templates to the user.

[0484] 2. Select a template

[0485] The user selects an appropriate template from the displayed templates.

[0486] Interactive question and answer

[0487] 1. Posing the Question

[0488] The device displays the first question, "What are the features of your new product?" based on the selected template.

[0489] 2. Enter and submit your answers

[0490] The user enters "a smartphone equipped with the latest AI technology" and submits the answer. The device then sends the entered answer to the server.

[0491] 3. Show next question

[0492] The server saves the additional information and requests the next question from the generation AI, which returns the generated next question to the server, which displays it on the device.

[0493] Automatic generation of materials

[0494] 1. Sending the final data

[0495] The server sends all user responses to the generation AI.

[0496] 2. Creating and Presenting Materials

[0497] The generation AI generates presentation materials and returns them to the server, which then presents them to the user.

[0498] Final check and corrections

[0499] 1. Preview display

[0500] The terminal displays the generated presentation materials to the user.

[0501] 2. Enter the corrections and regenerate

[0502] The user types, "I would like to revise the content of slide 4." The device sends the revision instruction to the server. The server makes a request to the generation AI, and the revised document is returned to the server. The server then presents the document again.

[0503] Final Output

[0504] 1. Final Download

[0505] The user finally confirms the material that satisfies him and clicks the download link, which is displayed on the device and the user downloads the material.

[0506] This system allows users to create high-quality presentation materials in a short amount of time. Collaboration between the server and the generation AI allows for efficient and flexible generation and modification of materials.

[0507] The processing flow will be explained below.

[0508] Step 1:

[0509] The user accesses the login screen. The device displays the login page. The user enters their email address and password and submits it.

[0510] Step 2:

[0511] The terminal sends the entered authentication information to the server. The server accesses the database and checks whether the user's email address and password are correct. If authentication is successful, the server issues session information to the user.

[0512] Step 3:

[0513] The server generates the user's dashboard page and returns it to the device. The device displays the dashboard page to the user. The user clicks the "Create a new presentation" button.

[0514] Step 4:

[0515] The device displays a form for the user to input the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the submit button.

[0516] Step 5:

[0517] The device sends the input information to the server. The server stores the received information in a database. The server then sends a template request to the generation AI based on the stored information.

[0518] Step 6:

[0519] The generation AI generates multiple presentation templates and returns them to the server. The server presents preview images and descriptions of the templates to the user. The device displays the preview images and allows the user to select a template.

[0520] Step 7:

[0521] The user selects an appropriate template. The device sends the selection information to the server. The server then requests the generation AI to generate questions in an interactive format based on the selected template.

[0522] Step 8:

[0523] The generation AI generates the first question and returns it to the server. The server sends the first question, "Please tell me the features of the new product," to the device. The device displays the question to the user.

[0524] Step 9:

[0525] The user enters the answer "a smartphone equipped with the latest AI technology" and clicks the send button. The device sends the answer to the server, which then stores the received answer in a database.

[0526] Step 10:

[0527] The server requests the next question from the generation AI. The generation AI generates the next question and returns it to the server. The server sends the next question to the device, which displays it to the user. This step is repeated until all the necessary information is collected.

[0528] Step 11:

[0529] Once all the information has been collected, the server requests the generation AI to generate the presentation materials. The generation AI generates the materials and returns them to the server. The server then presents the generated presentation materials to the user.

[0530] Step 12:

[0531] The user previews the document and inputs any corrections that need to be made. The device sends correction instructions to the server. The server requests correction instructions from the generation AI, which then corrects the document and returns it to the server. The server then presents the corrected document to the user again. This step is repeated until the user is finally satisfied.

[0532] Step 13:

[0533] When the user is satisfied with the final document, he / she clicks on the download link, the terminal displays the download link for the final document, and the user downloads the document.

[0534] Through the above steps, the user can create presentation materials efficiently and quickly.

[0535] Example 1

[0536] 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."

[0537] The process of creating presentation materials generally requires time and effort. This makes it difficult for users to create high-quality materials within a limited time. In addition, modifying and regenerating materials is also time-consuming, so a system that can respond flexibly is required.

[0538] 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.

[0539] In this invention, the server includes input means for a user to input purpose and basic information, means for requesting multiple presentation templates from the generative AI model based on the information input by the input means, and selection means for selecting a template recommended by the generative AI model, thereby enabling efficient generation and flexible modification of high-quality presentation materials.

[0540] A "user" is an individual or corporation that uses the system to create presentation materials.

[0541] "Input means" refers to the device or software that allows the user to input purpose and basic information.

[0542] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to automatically generate presentation templates and materials.

[0543] A "prompt" is an instruction or question input to a generative AI model, which serves as a guide for the AI ​​to return an appropriate output.

[0544] "Recommended templates" refer to multiple templates generated by a generative AI model based on user input information.

[0545] "Selection means" refers to a device or software that allows a user to select an appropriate template from among the templates recommended by the generative AI model.

[0546] A "question presenter" is a device or software for interactively asking a user for additional information based on a selected template.

[0547] "Presentation materials" refer to slides and documents created to achieve the purpose of a presentation.

[0548] "Output means" refers to a device or software for providing the final generated presentation materials to the user.

[0549] "Automatic generation means" means a device or software that automatically creates presentation materials based on input information and additional information using a generative AI model.

[0550] A "modification request" is an instruction from a user requesting changes to the content of the generated presentation materials.

[0551] A "means for requesting regeneration" is a device or software that causes a generative AI model to regenerate the content of a presentation material based on a modification request.

[0552] This system allows users to create efficient and high-quality presentation materials, and is implemented using a server, terminals, and a generative AI model.

[0553] 1. User Registration and Login

[0554] When a user accesses the login screen using a terminal, the terminal opens a browser and accesses the URL of the login page. The user enters their email address and password and presses the login button. The terminal sends the entered authentication information to the server, which then accesses the database to perform authentication. If authentication is successful, the server generates a dashboard page and sends it to the terminal. The terminal displays it.

[0555] 2. Enter the purpose of your presentation and basic information

[0556] A form is displayed on the dashboard page where the user can enter the purpose, target audience, and deadline of the presentation. For example, the user can enter information such as "New product promotion," "Management," and "3 days later." When the user submits the information, the device sends it to the server, which then stores the information in a database.

[0557] 3. Template Recommendations

[0558] The server sends a template request to the generative AI model based on the stored basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends previews of these templates to the device, which displays them to the user. When the user selects an appropriate template, the selection information is sent to the server.

[0559] 4. Interactive Question and Answer

[0560] Based on the template selected by the user, the device displays the first question, "What are the features of your new product?" The user enters the answer, "A smartphone equipped with the latest AI technology," and submits it. The device sends this answer to the server, which then requests the next question from the generative AI model. The generative AI model generates the next question and returns it to the server. The server displays the next question on the device.

[0561] 5. Automatic generation of materials

[0562] Once all user responses have been collected, the server sends this data to the generative AI model, which then generates presentation materials and returns them to the server. The server then sends the generated materials to the device, which displays them to the user.

[0563] 6. Final check and corrections

[0564] The user checks the generated presentation materials and inputs any parts that need to be corrected. For example, the user might input, "I would like to correct the content of slide 4." The device sends a correction request to the server, which then requests the generative AI model to regenerate the materials. The generative AI model returns the corrected materials to the server, which then sends them to the device. The device then displays the corrected materials to the user.

[0565] 7. Final output

[0566] When the user finally confirms the material they are satisfied with, they click the "Download" link, which the device displays and the user clicks to download the material.

[0567] Examples and prompts

[0568] Examples:

[0569] 1. User Registration and Login:

[0570] Example: A user logs in by entering an email address (example@example.com) and password (password123).

[0571] 2. Enter the purpose and basic information of your presentation:

[0572] Example: User enters "New product promotion," "Sales department," and "Presentation in 5 days."

[0573] 3. Template Recommendations:

[0574] Example: The generation AI presents two templates: a "template for introducing a new product" and a "template for a management report."

[0575] 4. Interactive Question and Answer:

[0576] Example: The first question is "What points do you want to emphasize in your presentation?" and the user enters "Safety of the latest technology."

[0577] 5. Automatic generation of materials:

[0578] Example: Generative AI generates a document consisting of three slides: "Slide 1: New product overview," "Slide 2: Technical details," and "Slide 3: Ensuring safety."

[0579] 6. Final checks and corrections:

[0580] Example: The user enters a correction such as "Please be more specific about the technical details on slide 2."

[0581] 7. Final output:

[0582] Example: User downloads revised document.

[0583] Example prompt:

[0584] I'd like to create a presentation for management to promote a new product. The purpose of the presentation is to clearly communicate the features of the new product, and the deadline is in three days. Please suggest a suitable template.

[0585] By providing specific prompts in this way, users can efficiently create materials.

[0586] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0587] Step 1:

[0588] When a user accesses the login screen, the terminal displays the login page. The user enters their email address and password. The terminal sends the input data to the server as an HTTP POST request. The server accesses the database and verifies the corresponding user information. If authentication is successful, the server generates HTML data for the dashboard page and sends it to the terminal. The terminal displays the received HTML data in the browser.

[0589] Enter your email address and password

[0590] Output: Dashboard page upon successful authentication

[0591] Step 2:

[0592] A user starts creating a new presentation from the dashboard page, and enters the purpose, target audience, and deadline of the presentation into a form displayed on the device. When the user submits the information, the device sends the input data as an HTTP POST request to the server, which stores it in a database.

[0593] Input: Purpose of presentation, target audience, deadline

[0594] Output: Basic information saved

[0595] Step 3:

[0596] The server sends a template request to the generative AI model based on the stored basic information. The generative AI model uses the received information as input to generate multiple presentation templates, which are then returned to the server. The server then sends a preview image and description of the template to the device, which displays it to the user.

[0597] Input: Basic information

[0598] Output: Multiple template previews

[0599] Step 4:

[0600] The user selects an appropriate template, and the selection information is sent from the terminal to the server, where it is stored.

[0601] Input: Selected template information

[0602] Output: Selection information stored on the server

[0603] Step 5:

[0604] The device displays a question to the user based on the selected template. For example, the question might be, "What are the features of the new product?" The user enters an answer, and the device sends the answer data to the server. The server stores the answer information and requests the next question from the generative AI model. The generative AI model generates the next question and returns it to the server. The server sends the next question to the device, which displays it.

[0605] Input: Template and first question

[0606] Output: User's answer and next question

[0607] Step 6:

[0608] Once the user's answers to all questions have been collected, the server sends these answers to the generative AI model, which then automatically generates presentation materials based on this data and returns the data to the server. The server then sends the generated materials to the device, which then displays them.

[0609] Input: All user responses

[0610] Output: The generated presentation

[0611] Step 7:

[0612] The user reviews the generated presentation materials and inputs correction requests as necessary. For example, the user sends a request such as "I would like to correct the content of slide 4." The device sends the correction request to the server, and the server sends a regeneration request to the generative AI model. The generative AI model generates the corrected materials and returns the data to the server. The server sends the corrected materials to the device, which displays them to the user.

[0613] Input: User modification request

[0614] Output: Revised presentation

[0615] Step 8:

[0616] When the user finally confirms the material they are satisfied with, they click the "Download" link. The terminal displays the download link, and the user clicks to download the material.

[0617] Input: User download request

[0618] Output: Downloaded presentation materials

[0619] (Application example 1)

[0620] 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."

[0621] Conventional presentation creation systems require users to spend a lot of time preparing presentation materials, making it difficult to quickly select appropriate templates and content. Furthermore, they are slow to respond to revision requests, which is inefficient in the advertising industry, where real-time responses are required. Therefore, there was a need for a system that allows users to easily and quickly generate high-quality presentation materials and make necessary revisions in real time.

[0622] 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.

[0623] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending a plurality of presentation templates based on the information input by the input means, selection means for selecting the recommended template, question presentation means for acquiring additional information in an interactive manner, means for receiving the additional information and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on a user's correction request, means for acquiring information via gaze or voice input in response to templates or questions displayed on the smart glasses, means for finally outputting the generated materials and providing them in a downloadable format, and display means for the smart glasses to display the generated presentation materials to the user. This allows a user to efficiently create high-quality presentation materials in a short amount of time and easily correct and check them by real-time operation through the smart glasses.

[0624] "Input means" refers to a device or interface that allows a user to input their purpose and basic information.

[0625] The "means for recommending" is a device or program that has the function of presenting multiple presentation templates based on input information.

[0626] The "selection means" refers to a device or interface that allows a user to select an appropriate template from the recommended templates.

[0627] A "question presenter" is a device or function for interactively gathering additional information based on a selected template.

[0628] "Automatic generation means" refers to a program or device that automatically creates presentation materials based on the collected additional information.

[0629] The "regeneration means" refers to a device or program that has the function of recreating the generated presentation materials based on a modification request from the user.

[0630] "Smart glasses" are wearable devices that allow users to input information using eye contact or voice input.

[0631] "Means for acquiring information through gaze or voice input" refers to a device or function that uses smart glasses to acquire information by analyzing the user's gaze movements and voice.

[0632] The "display means" refers to a display or interface for visually presenting the generated presentation materials to the user.

[0633] "Means for providing in a downloadable format" refers to a program or function for providing the final generated material in a format that can be downloaded by the user.

[0634] This invention provides a system that enables users to create, edit, and check presentation materials in real time using smart glasses. Specific embodiments of this system are described below.

[0635] User Registration and Login

[0636] The user puts on the smart glasses and accesses the system. A login screen is displayed through the smart glasses' display, and the user enters their email address and password using voice input or eye contact. The server authenticates the user based on this authentication information, and if authentication is successful, the user's dashboard page is displayed on the smart glasses.

[0637] Enter the purpose of the presentation and basic information

[0638] A form is displayed on the smart glasses displaying the user to input basic information such as the purpose of the presentation, the target audience, and the deadline. This information is acquired by voice or eye contact and sent to the server, which then stores the received information in a database.

[0639] Template recommendations

[0640] The server sends a template request to the generative AI based on the stored basic information. The generative AI model generates multiple templates and returns them to the server. The server then displays previews of these templates to the user through smart glasses. The user can then select an appropriate template by eye gaze or voice input.

[0641] Interactive question and answer

[0642] Based on the selected template, the server presents the user with a series of interactive questions. For example, the server displays a question such as "What are the features of the new product?", and the user responds by voice or eye contact. The server stores these responses and requests the next question from the AI ​​generator.

[0643] Automatic generation of materials

[0644] The server sends all user responses to the AI ​​generator, which then automatically generates presentation materials. The generated materials are then sent back to the server and presented to the user through the display means of the smart glasses.

[0645] Final check and corrections

[0646] The user checks the generated presentation materials and, if necessary, sends a request for revisions to the server using voice commands or eye gaze input. The server then sends this request to the generation AI, and presents the revised materials to the user again.

[0647] Final Output

[0648] The user reviews the presentation materials to their satisfaction and clicks on the final download link through the display means of the smart glasses. The server provides the materials in a downloadable format.

[0649] Hardware and software used

[0650] Smart glasses: Collect information through gaze control and voice input and display it to the user.

[0651] Server: Responsible for user authentication, data storage, question generation, document generation, and regeneration of correction requests.

[0652] Generative AI model: Generates templates and presentation materials.

[0653] Database: Stores user information and presentation data.

[0654] Examples of concrete examples and prompts

[0655] For example, if you use the generative AI model GPT-4, the prompt would look like this:

[0656] prompt

[0657] "Design an application that helps users create ads in real time using smart glasses. Collect information about the ad's purpose, targeting, design, and content, generate templates and questions based on that information, and then generate and display the final ad in real time. Allow the user to modify and download the ad using voice commands as needed."

[0658] This allows users to create high-quality presentation materials efficiently and in a short amount of time, and allows them to make real-time edits and checks through the smart glasses.

[0659] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0660] Step 1:

[0661] (User registration and login) The user puts on the smart glasses and the login screen appears on the display of the smart glasses. The user enters their email address and password using voice input or eye contact. The server receives the entered authentication information and accesses the database to authenticate the user. If authentication is successful, the user's dashboard page is displayed through the smart glasses.

[0662] Input: Email address, password

[0663] Data processing: database access, authentication processing

[0664] Output: Dashboard page displayed

[0665] Step 2:

[0666] (Inputting the purpose of the presentation and basic information) The server displays a form on the smart glasses to input the purpose of the presentation, target audience, deadline, etc. The user inputs this information using voice input or eye gaze input. The server receives the input information and stores it in a database.

[0667] Input: Purpose of presentation, target audience, deadline

[0668] Data processing: Data storage processing

[0669] Output: Basic information saved

[0670] Step 3:

[0671] (Template recommendation) The server sends a template request to the generation AI based on the basic information stored in the database. The generation AI generates multiple templates and returns them to the server. The server displays a preview of the templates on the smart glasses. The user selects a template by eye gaze or voice input.

[0672] Input: Basic information, template request

[0673] Data processing: Template generation, preview display

[0674] Output: Selected template

[0675] Step 4:

[0676] (Interactive Questions and Answers) Based on the selected template, the server sequentially displays interactive questions to the user. For example, the server displays a question such as, "What are the features of the new product?" The user answers by voice or eye contact, and the server receives the answers and stores them in a database.

[0677] Input: Question, Answer

[0678] Data processing: Question generation, answer storage

[0679] Output: Additional information saved

[0680] Step 5:

[0681] (Automatic generation of presentation materials) The server sends all user responses to the generation AI, which then automatically generates presentation materials. The generated materials are sent back to the server and presented to the user through the display means of the smart glasses.

[0682] Input: User answer

[0683] Data processing: Data generation

[0684] Output: Generated presentation materials

[0685] Step 6:

[0686] (Final confirmation and corrections) The user checks the presentation materials displayed on the smart glasses and makes any necessary corrections by voice or eye contact. The server sends these correction instructions to the generation AI, which then regenerates the corrected materials. The corrected materials are then sent back to the server and presented to the user again.

[0687] Input: Correction instructions

[0688] Data processing: Reflection of correction instructions, regeneration

[0689] Output: Revised presentation

[0690] Step 7:

[0691] (Final Output) The user finally checks the presentation materials to their satisfaction and clicks the final download link through the display means of the smart glasses. The server provides the materials in a downloadable format, and the user downloads the materials.

[0692] Input: Download instructions

[0693] Data processing: Converting materials into downloadable format

[0694] Output: Downloadable materials

[0695] 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.

[0696] User Registration and Login

[0697] 1. The user accesses the login screen

[0698] The device displays a login page, and the user enters their email address and password and submits it.

[0699] 2. Authentication and Dashboard Migration

[0700] The device sends authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server generates the user's dashboard page and returns it to the device. The device displays the dashboard page. The user clicks "Create a new presentation."

[0701] Enter the purpose of the presentation and basic information

[0702] 1. Display the basic information input form

[0703] The device displays a form where you can enter the purpose of the presentation, the target audience, and the deadline.

[0704] 2. Transmission and storage of information

[0705] The user enters information such as "New product promotion," "Management," and "3 days later," and submits it. The device sends the information to the server, which stores it in a database.

[0706] Template recommendations

[0707] 1. Template Presentation

[0708] The server sends a template request to the generation AI based on basic information. The generation AI generates multiple templates and returns them to the server. The server presents preview images and descriptions of the templates to the user. The device displays the preview images, and the user can select the appropriate template.

[0709] Conversational Questions and Emotion Recognition

[0710] 1. Posing the Question

[0711] The device displays the first question based on the selected template: "What are the features of your new product?"

[0712] 2. Emotion recognition and answer input

[0713] The device acquires the user's facial recognition data or voice data and sends it to the server, which uses an emotion engine to determine the user's emotional state.

[0714] The device receives the user's response, "A smartphone equipped with the latest AI technology," and sends it to the server.

[0715] 3. Generate and display the next question

[0716] The server requests the next question from the generation AI. The generation AI creates a question based on the emotional state recognized by the emotion engine. The server then sends the next question to the device, which displays it to the user. This process is repeated until all necessary information is collected.

[0717] Automatically generate materials and adjust them based on emotions

[0718] 1. Sending the final data

[0719] The server sends all information to the generating AI.

[0720] 2. Creation and adjustment of materials

[0721] The generative AI generates presentation materials, and the emotion engine adjusts the design and content according to the user's emotional state. The adjusted materials are then returned to the server.

[0722] 3. Presentation of materials

[0723] The server presents the generated presentation materials to the user, and the terminal displays the materials as a preview.

[0724] Final check and corrections

[0725] 1. Preview display

[0726] The terminal displays the generated presentation materials to the user.

[0727] 2. Enter the corrections and regenerate

[0728] The user types, "I would like to revise the content of slide 4." The device sends the revision instructions to the server. The server requests revision instructions from the generation AI, which then revises the document and returns it to the server. The server then presents the revised document to the user again. This process is repeated until the user is finally satisfied.

[0729] Final Output

[0730] 1. Final Download

[0731] The user checks the material to find it satisfactory and clicks on the download link.

[0732] The terminal displays a download link, and the user downloads the material.

[0733] This system allows users to efficiently create high-quality presentation materials. In particular, by utilizing the emotion engine, questions and materials are adjusted according to the user's emotional state, providing more appropriate and effective presentation materials.

[0734] The processing flow will be explained below.

[0735] Step 1:

[0736] The user accesses the login screen. The device displays the login page. The user enters their email address and password and clicks the submit button.

[0737] Step 2:

[0738] The terminal sends the entered authentication information to the server. The server accesses the database and checks whether the user's email address and password are correct. If authentication is successful, the server issues session information.

[0739] Step 3:

[0740] The server generates the user's dashboard page and returns it to the device. The device displays the dashboard page. The user clicks the "Create a new presentation" button.

[0741] Step 4:

[0742] The device displays a form for inputting the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the submit button.

[0743] Step 5:

[0744] The device sends the input information to the server. The server stores the received information in a database. The server then sends a template request to the generation AI based on the stored information.

[0745] Step 6:

[0746] The generation AI generates multiple presentation templates and returns them to the server. The server then presents preview images and descriptions of the templates to the user. The device displays the preview images, and the user selects the appropriate template.

[0747] Step 7:

[0748] The user selects a template. The device sends the selection information to the server. The server requests the generation AI to generate interactive questions based on the selected template.

[0749] Step 8:

[0750] The generation AI generates the first question and returns it to the server. The server sends the question, "Please tell me the features of the new product," to the device. The device displays the question to the user.

[0751] Step 9:

[0752] The user answers the question by typing "a smartphone equipped with the latest AI technology" and clicks the send button. The device sends the answer to the server, which then stores it in a database.

[0753] Step 10:

[0754] The device acquires the user's facial recognition data or voice data and sends it to the server, which uses an emotion engine to determine the user's emotional state.

[0755] Step 11:

[0756] The server requests the next question from the generation AI based on the emotional state recognized by the emotion engine. The generation AI returns the generated next question to the server, which then sends it to the device. The device displays the next question to the user. This step is repeated until all necessary information is collected.

[0757] Step 12:

[0758] Once all the information is collected, the server requests the generation AI to generate presentation materials. The generation AI generates the materials, and the emotion engine adjusts the design and content according to the user's emotional state. The adjusted materials are then returned to the server.

[0759] Step 13:

[0760] The server presents the generated presentation materials to the user, and the terminal displays a preview of the materials.

[0761] Step 14:

[0762] The user checks the document and indicates the parts that need to be corrected. The device sends the correction instructions to the server. The server requests the generation AI to make corrections, and the generation AI regenerates the document and returns it to the server. The server then presents the corrected document to the user again. This step is repeated until the user is finally satisfied.

[0763] Step 15:

[0764] If the user is satisfied with the final document, he / she clicks on the download link, and the terminal displays the download link for the final document, and the user downloads the document.

[0765] Example 2

[0766] 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."

[0767] Conventional presentation creation systems have the problem that even if a user inputs information and selects a template, it is difficult to generate efficient, high-quality materials in the subsequent document creation process. Another issue is that there is no system that can create optimal materials according to the user's emotional state. This makes it difficult to maximize the effectiveness of presentations, ultimately hindering business success and effective communication.

[0768] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0769] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending a plurality of presentation templates based on the information input by the input means, selection means for selecting the recommended template, question posing means for acquiring additional information in an interactive format, means for receiving the additional information and adjusting the question content based on the user's emotional state using emotion recognition technology, means for transmitting all information to a generative AI model and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on the user's requested revisions, and output means for finally outputting the presentation materials. This enables users to efficiently create high-quality presentation materials and generate materials optimal for their emotional state.

[0770] The "input means for the user to input the purpose and basic information" is an interface for the user to input basic information such as the purpose, target audience, and deadline of the presentation.

[0771] "Means for recommending multiple presentation templates" is a function that suggests the most suitable presentation template based on basic information entered by the user.

[0772] The "selection means for selecting a recommended template" is an operation method for selecting an appropriate template from a plurality of templates presented to the user.

[0773] The "means for presenting questions to acquire additional information in an interactive manner" is a function for displaying questions to collect additional information necessary for presentation through a dialogue with the user.

[0774] "Emotion recognition technology" is a technology that analyzes a user's facial recognition data and voice data to determine the user's emotional state.

[0775] The "means for adjusting the content of the question based on the emotional state" is a function for changing the content and format of the question depending on the emotional state of the user.

[0776] A "generative AI model" is an artificial intelligence model that analyzes data based on input information and generates new information and materials.

[0777] The "means for automatically generating presentation materials" is a system that automatically creates presentation materials based on collected information.

[0778] The "means for presenting the generated presentation materials to the user and regenerating them based on the user's revision requests" is a function for displaying the initially generated materials to the user and then generating the materials again based on subsequent revision requests.

[0779] The "output means for finally outputting the presentation materials" refers to a download link or file saving function for providing the user with the finalized presentation materials.

[0780] This invention relates to a system for generating presentation materials efficiently and with high quality. The system generates optimal presentation materials by allowing users to input their purpose and basic information, proposing appropriate templates, and adjusting questions based on the user's emotional state. This system is realized using a terminal, a server, and a generation AI model.

[0781] Input Method

[0782] The user accesses the system's login page from a web browser on their terminal. Authentication is performed by entering their email address and password and clicking the login button. The server verifies the authentication information using a database (e.g., MySQL), and if authentication is successful, it generates the user's dashboard and returns it to the terminal. Next, the user clicks "Create a new presentation," which displays a form for entering basic information such as the purpose of the presentation, target audience, and deadline. The user enters information such as "New product promotion," "Management," and "3 days later" into this form and submits it.

[0783] Presentation template recommendation method

[0784] The server sends a template generation request to a generation AI (e.g., OpenAI GPT-4) based on the basic information entered by the user. The generation AI generates multiple templates and returns the results to the server. The server then creates preview images and descriptions of these templates in HTML format and sends them to the device. The device then displays these preview images and descriptions to the user, providing an interface for selecting an appropriate template.

[0785] Question presentation method and emotion recognition method

[0786] When the user selects a template, the device displays the first question based on the selected template: "What are the features of the new product?" At the same time, the device acquires the user's facial recognition data and voice data and sends them to the server. The server uses emotion recognition technology (for example, Microsoft Azure Emotion API) to determine the user's emotional state. When the user enters the answer "A smartphone equipped with the latest AI technology" and submits it, this information is also sent to the server.

[0787] Information adjustment means

[0788] The server then requests the AI ​​to generate the next question, adjusting the question based on emotion recognition. The server then sends the generated question to the device, which displays it to the user. This process is repeated until all the information needed for the presentation is gathered.

[0789] A means of automatically generating presentation materials

[0790] Once all the information is collected, the server sends it to a generative AI model, which then generates presentation materials based on the collected information. The generated materials are then adjusted in design and content using emotion recognition technology. The adjusted materials are then returned to the server.

[0791] Material presentation means and reproduction means

[0792] The server sends the generated presentation materials to the device, which displays them as a preview to the user. The user checks the preview and enters, for example, "I would like to revise the contents of slide 4." The device receives the revision instructions and sends them to the server. The server then sends a regeneration instruction to the generation AI, causing it to generate the materials again. The revised materials are then returned to the server and displayed to the user via the device. This process is repeated until the user is satisfied.

[0793] Final output method

[0794] When the user finally finds the material that satisfies him, he clicks on the download link, and the terminal displays the download link, allowing the user to download the material.

[0795] The above is an embodiment of the present invention. This system allows users to efficiently and effectively create high-quality presentation materials. The following is a specific example of a prompt sentence to be input to the generative AI model:

[0796] "Please create a presentation to promote our new product. It's for management and needs to be completed in three days."

[0797] "Feature: 'Smartphone equipped with the latest AI technology', Emotion: Excitement, What should I ask next?"

[0798] These prompts will generate more specific and personalized presentation materials.

[0799] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0800] Step 1:

[0801] A user accesses the system's login page from a web browser. The user enters their email address and password and clicks the "Login" button. The terminal sends this authentication information to the server, which then verifies the user information using a database (e.g., MySQL). If authentication is successful, the server generates the user's dashboard and sends the HTML data to the terminal. The terminal receives it and displays it to the user. The input is the user's authentication information, and the output is the HTML data of the dashboard.

[0802] Step 2:

[0803] The user clicks the "Create a new presentation" button on the dashboard. The device displays a form for entering the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the "Submit" button. The device sends this information to the server, which saves it in a database. The input is the basic information about the presentation, and the output is a response indicating that it was saved successfully.

[0804] Step 3:

[0805] The server uses the stored basic information to send a template request to a generative AI model (e.g., OpenAI GPT-4). The generative AI model generates a template and returns its preview image and description to the server. The server receives these, formats them into HTML, and sends them to the device. The device displays multiple templates to the user and allows the user to select one. The input is the basic information, and the output is the template preview image and description.

[0806] Step 4:

[0807] The user selects a template. Based on the selected template, the device displays the first question, "What are the features of your new product?" The user answers, "A smartphone equipped with the latest AI technology." The device then acquires facial recognition data and voice data and sends them to the server. The server uses emotion recognition technology to recognize the user's emotional state. The input is the template selection and the user's emotional data, and the output is the emotional state.

[0808] Step 5:

[0809] The server requests the next question from the generative AI model and receives the question content adjusted by emotion recognition technology from the generative AI model. The new question is sent from the server to the device, which displays it to the user. The user answers the question, and the device sends the answer to the server. This process is repeated until all necessary information is collected. The input is the previous question and the user's answer, and the output is the next question.

[0810] Step 6:

[0811] After all the information is collected, the server sends it to the generative AI model, which generates the presentation materials. The generative AI model generates the materials, adjusts them based on emotion recognition technology, and returns the results to the server. The server receives the generated presentation materials and sends them to the device, which displays a preview for the user. The input is the collected information, and the output is the generated presentation materials.

[0812] Step 7:

[0813] The user checks the preview and, if necessary, inputs a correction request, such as "I would like to revise the content of slide 4." The device sends the correction request to the server. The server sends correction instructions to the generative AI model and receives a regenerated document. The new document is sent from the server to the device and previewed again by the user. This process is repeated until the user is satisfied. The input is the correction request, and the output is the revised presentation document.

[0814] Step 8:

[0815] When the user is finally satisfied with the presentation materials, he or she clicks the download link. The terminal displays the download link, allowing the user to download the materials. The input is the final confirmation and clicking the download link, and the output is the final presentation materials.

[0816] The above is the flow of specific processing steps of the program of this system.

[0817] (Application example 2)

[0818] 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."

[0819] Many conventional presentation production systems automatically generate presentations based solely on input information, without considering the user's emotional state. This makes it difficult to generate appropriate questions or materials based on the user's emotional changes, resulting in a lack of improved user experience. Furthermore, surveillance systems lack technology that uses emotion recognition to instantly issue security alerts, making it difficult to respond quickly and accurately.

[0820] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0821] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending multiple presentation templates based on the input information, selection means for selecting a recommended template, question presentation means for acquiring additional information in an interactive format, emotion recognition means for determining the user's emotional state based on the additional information and facial recognition data or voice data, a generative AI model for adjusting the questions based on the emotional state determined by the emotion recognition means, means for presenting questions generated by the generative AI model to the user, receiving the additional information, and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on user requests for revisions, and output means for finally outputting the presentation materials. This enables appropriate question presentation and material generation that take the user's emotional state into consideration, as well as rapid and accurate security response using emotion recognition in surveillance systems.

[0822] "Input means" refers to a device or interface through which a user inputs objectives and basic information.

[0823] The "recommending means" is a device or program for recommending a plurality of presentation templates based on information input by the input means.

[0824] The "selection means" is a device or interface that allows the user to select a recommended template.

[0825] The "question presenting means" is a device or program that displays a question for acquiring additional information in an interactive manner based on the template selected by the selection means.

[0826] "Emotion recognition means" refers to a device or program for determining the emotional state of a user based on facial recognition data or voice data.

[0827] A "generative AI model" is an artificial intelligence model that tailors questions based on the emotional state determined by the emotion recognition means.

[0828] "Means for automatic generation" means a device or program for receiving additional information and generating presentation materials based on questions generated by a generative AI model.

[0829] The "regenerating means" is a device or program for presenting the generated presentation materials to the user and regenerating the materials based on the user's modification requests.

[0830] "Output means" refers to a device or program for providing the final generated presentation materials to the user in a displayable or downloadable format.

[0831] MODE FOR CARRYING OUT THE INVENTION

[0832] A specific system for implementing the present invention is configured as follows.

[0833] User Registration and Login

[0834] The device that the user accesses displays a login screen for entering an email address and password. When the user enters and submits the information, the device sends the authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server generates a dashboard page for the user and returns it to the device. The device displays the dashboard page and allows the user to select "Create a new presentation."

[0835] Enter the purpose of the presentation and basic information

[0836] When a user clicks "Create a new presentation" on the dashboard, a basic information input form is displayed on the device. The user enters information such as the purpose of the presentation, target audience, and deadline into this form and submits it. The entered information is sent from the device to the server, which then stores it in a database.

[0837] Template recommendations

[0838] The server sends a template request to the generative AI model based on the basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends preview images and descriptions of the templates to the device, allowing the user to select one.

[0839] Conversational Questions and Emotion Recognition

[0840] After the user selects a template, the device displays the first question based on the selected template: "Please tell us the features of the new product." The device acquires facial recognition data or voice data and sends it to the server. The server uses emotion recognition means to determine the user's emotional state. The user's answer to the question displayed on the device is entered and sent to the server. The server requests the next question from the generative AI model, and a new question is generated based on the user's emotional state. This process is repeated until all necessary information is collected.

[0841] Automatically generate materials and adjust them based on emotions

[0842] The server sends all information to the generative AI model, which then generates the presentation materials. Furthermore, the emotion recognition means adjusts the design and content according to the user's emotional state. The adjusted materials are then sent back to the server, which presents them to the user. The device displays the materials as a preview.

[0843] Final check and corrections

[0844] The user previews the generated presentation materials and, if any corrections are needed, inputs instructions such as "I would like to revise the content of slide 4." The device sends this instruction to the server, which then requests corrections from the generative AI model. The generative AI model then corrects the materials and sends them back to the server. The server then presents the corrected materials to the user again. This process is repeated until the user is satisfied.

[0845] Final Output

[0846] When the user confirms the material that satisfies him and clicks on the download link, the terminal displays the download link and the user can download the material.

[0847] Hardware and software used

[0848] Hardware: Smartphones, smart glasses, head-mounted displays, robots.

[0849] Software: Python, OpenCV, Keras, and the required server and database systems.

[0850] Specific examples

[0851] For example, by installing this system at the entrance to an office, it can instantly detect suspicious or nervous individuals and send an alert to the security team.

[0852] Prompt Sentence Examples

[0853] Enter the following prompt into the generative AI model:

[0854] "Generate a template for building a security alert system based on an emotion engine. The template should be Python code that performs face detection and emotion recognition and sends an alert when an anomaly is detected. The template should use a cascade classifier and a Keras model to perform face detection and emotion recognition."

[0855] This system configuration enables flexible creation of presentation materials based on the user's emotional state and quick and accurate security response.

[0856] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0857] Step 1:

[0858] User Registration and Login

[0859] The user enters and submits their email address and password. The device sends this authentication information to the server. The server references the database and authenticates the user. If authentication is successful, the server generates a dashboard page for the user and sends its contents back to the device. The device displays the dashboard page and allows the user to select "Create a new presentation."

[0860] Input: Email address, password

[0861] Output: Dashboard page

[0862] Step 2:

[0863] Enter the purpose of the presentation and basic information

[0864] When a user clicks "Create a new presentation" on the dashboard, the device displays a form for inputting the purpose, target audience, and deadline of the presentation. The user fills out the form and submits it. The device sends this information to the server, which stores it in a database.

[0865] Input: Purpose of presentation, target audience, deadline

[0866] Output: Basic information saved

[0867] Step 3:

[0868] Template recommendations

[0869] The server sends a template request to the generative AI model based on the basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends preview images and descriptions of the templates to the device, allowing the user to select one.

[0870] Input: Basic information

[0871] Output: Template preview image and description

[0872] Step 4:

[0873] Conversational Questions and Emotion Recognition

[0874] After the user selects a template, the device displays the first question: "What are the features of your new product?" The device captures facial recognition or voice data and sends it to the server. The server uses emotion recognition means to determine the user's emotional state. Based on this emotional state, the generative AI model generates the next question and returns it to the server. The device displays the next question, and the user enters and submits the answer. This process is repeated until all necessary information is collected.

[0875] Input: Facial recognition data or voice data, user response

[0876] Output: Next question based on emotional state

[0877] Step 5:

[0878] Automatically generate materials and adjust them based on emotions

[0879] The server sends all information to a generative AI model, which then generates the presentation materials. The emotion recognition means adjusts the design and content according to the user's emotional state. The adjusted materials are then sent back to the server, which then sends them to the device for the user to preview.

[0880] Input: All information

[0881] Output: Adjusted presentation material

[0882] Step 6:

[0883] Final check and corrections

[0884] The user previews the generated presentation materials and inputs any necessary corrections. The device sends these instructions to the server, which then requests corrections from the generative AI model. The generative AI model then corrects the materials and sends them back to the server. The server then presents the corrected materials to the user again. This process is repeated until the user is satisfied.

[0885] Input: Correction instructions

[0886] Output: Revised presentation

[0887] Step 7:

[0888] Final Output

[0889] When the user confirms the material that satisfies him and clicks on the download link, the terminal displays the download link and the user can download the material.

[0890] Input: Click on the download link

[0891] Output: Downloaded presentation

[0892] 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.

[0893] 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.

[0894] 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.

[0895] [Third embodiment]

[0896] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0897] 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.

[0898] 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).

[0899] 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.

[0900] 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.

[0901] 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).

[0902] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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."

[0908] User Registration and Login

[0909] 1. The user accesses the login screen

[0910] The device displays a login page, and the user enters their email address and password.

[0911] 2. Authentication and Dashboard Migration

[0912] The terminal sends the entered authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server returns the user's dashboard page. The terminal displays the dashboard page.

[0913] Enter the purpose of the presentation and basic information

[0914] 1. Display the basic information input form

[0915] The device displays a form for the user to input the purpose, target audience, and deadline of the presentation.

[0916] 2. Transmission and storage of information

[0917] The user enters and submits information such as "New product promotion," "Management," and "3 days later." The device sends this information to the server, which then stores it in a database.

[0918] Template recommendations

[0919] 1. Template Presentation

[0920] The server sends a template request to the generation AI based on the saved basic information. The generation AI generates multiple templates and returns them to the server. The server displays a preview of the templates to the user.

[0921] 2. Select a template

[0922] The user selects an appropriate template from the displayed templates.

[0923] Interactive question and answer

[0924] 1. Posing the Question

[0925] The device displays the first question, "What are the features of your new product?" based on the selected template.

[0926] 2. Enter and submit your answers

[0927] The user enters "a smartphone equipped with the latest AI technology" and submits the answer. The device then sends the entered answer to the server.

[0928] 3. Show next question

[0929] The server saves the additional information and requests the next question from the generation AI, which returns the generated next question to the server, which displays it on the device.

[0930] Automatic generation of materials

[0931] 1. Sending the final data

[0932] The server sends all user responses to the generation AI.

[0933] 2. Creating and Presenting Materials

[0934] The generation AI generates presentation materials and returns them to the server, which then presents them to the user.

[0935] Final check and corrections

[0936] 1. Preview display

[0937] The terminal displays the generated presentation materials to the user.

[0938] 2. Enter the corrections and regenerate

[0939] The user types, "I would like to revise the content of slide 4." The device sends the revision instruction to the server. The server makes a request to the generation AI, and the revised document is returned to the server. The server then presents the document again.

[0940] Final Output

[0941] 1. Final Download

[0942] The user finally confirms the material that satisfies him and clicks the download link, which is displayed on the device and the user downloads the material.

[0943] This system allows users to create high-quality presentation materials in a short amount of time. Collaboration between the server and the generation AI allows for efficient and flexible generation and modification of materials.

[0944] The processing flow will be explained below.

[0945] Step 1:

[0946] The user accesses the login screen. The device displays the login page. The user enters their email address and password and submits it.

[0947] Step 2:

[0948] The terminal sends the entered authentication information to the server. The server accesses the database and checks whether the user's email address and password are correct. If authentication is successful, the server issues session information to the user.

[0949] Step 3:

[0950] The server generates the user's dashboard page and returns it to the device. The device displays the dashboard page to the user. The user clicks the "Create a new presentation" button.

[0951] Step 4:

[0952] The device displays a form for the user to input the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the submit button.

[0953] Step 5:

[0954] The device sends the input information to the server. The server stores the received information in a database. The server then sends a template request to the generation AI based on the stored information.

[0955] Step 6:

[0956] The generation AI generates multiple presentation templates and returns them to the server. The server presents preview images and descriptions of the templates to the user. The device displays the preview images and allows the user to select a template.

[0957] Step 7:

[0958] The user selects an appropriate template. The device sends the selection information to the server. The server then requests the generation AI to generate questions in an interactive format based on the selected template.

[0959] Step 8:

[0960] The generation AI generates the first question and returns it to the server. The server sends the first question, "Please tell me the features of the new product," to the device. The device displays the question to the user.

[0961] Step 9:

[0962] The user enters the answer "a smartphone equipped with the latest AI technology" and clicks the send button. The device sends the answer to the server, which then stores the received answer in a database.

[0963] Step 10:

[0964] The server requests the next question from the generation AI. The generation AI generates the next question and returns it to the server. The server sends the next question to the device, which displays it to the user. This step is repeated until all the necessary information is collected.

[0965] Step 11:

[0966] Once all the information has been collected, the server requests the generation AI to generate the presentation materials. The generation AI generates the materials and returns them to the server. The server then presents the generated presentation materials to the user.

[0967] Step 12:

[0968] The user previews the document and inputs any corrections that need to be made. The device sends correction instructions to the server. The server requests correction instructions from the generation AI, which then corrects the document and returns it to the server. The server then presents the corrected document to the user again. This step is repeated until the user is finally satisfied.

[0969] Step 13:

[0970] When the user is satisfied with the final document, he / she clicks on the download link, the terminal displays the download link for the final document, and the user downloads the document.

[0971] Through the above steps, the user can create presentation materials efficiently and quickly.

[0972] Example 1

[0973] 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."

[0974] The process of creating presentation materials generally requires time and effort. This makes it difficult for users to create high-quality materials within a limited time. In addition, modifying and regenerating materials is also time-consuming, so a system that can respond flexibly is required.

[0975] 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.

[0976] In this invention, the server includes input means for a user to input purpose and basic information, means for requesting multiple presentation templates from the generative AI model based on the information input by the input means, and selection means for selecting a template recommended by the generative AI model, thereby enabling efficient generation and flexible modification of high-quality presentation materials.

[0977] A "user" is an individual or corporation that uses the system to create presentation materials.

[0978] "Input means" refers to the device or software that allows the user to input purpose and basic information.

[0979] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to automatically generate presentation templates and materials.

[0980] A "prompt" is an instruction or question input to a generative AI model, which serves as a guide for the AI ​​to return an appropriate output.

[0981] "Recommended templates" refer to multiple templates generated by a generative AI model based on user input information.

[0982] "Selection means" refers to a device or software that allows a user to select an appropriate template from among the templates recommended by the generative AI model.

[0983] A "question presenter" is a device or software for interactively asking a user for additional information based on a selected template.

[0984] "Presentation materials" refer to slides and documents created to achieve the purpose of a presentation.

[0985] "Output means" refers to a device or software for providing the final generated presentation materials to the user.

[0986] "Automatic generation means" means a device or software that automatically creates presentation materials based on input information and additional information using a generative AI model.

[0987] A "modification request" is an instruction from a user requesting changes to the content of the generated presentation materials.

[0988] A "means for requesting regeneration" is a device or software that causes a generative AI model to regenerate the content of a presentation material based on a modification request.

[0989] This system allows users to create efficient and high-quality presentation materials, and is implemented using a server, terminals, and a generative AI model.

[0990] 1. User Registration and Login

[0991] When a user accesses the login screen using a terminal, the terminal opens a browser and accesses the URL of the login page. The user enters their email address and password and presses the login button. The terminal sends the entered authentication information to the server, which then accesses the database to perform authentication. If authentication is successful, the server generates a dashboard page and sends it to the terminal. The terminal displays it.

[0992] 2. Enter the purpose of your presentation and basic information

[0993] A form is displayed on the dashboard page where the user can enter the purpose, target audience, and deadline of the presentation. For example, the user can enter information such as "New product promotion," "Management," and "3 days later." When the user submits the information, the device sends it to the server, which then stores the information in a database.

[0994] 3. Template Recommendations

[0995] The server sends a template request to the generative AI model based on the stored basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends previews of these templates to the device, which displays them to the user. When the user selects an appropriate template, the selection information is sent to the server.

[0996] 4. Interactive Question and Answer

[0997] Based on the template selected by the user, the device displays the first question, "What are the features of your new product?" The user enters the answer, "A smartphone equipped with the latest AI technology," and submits it. The device sends this answer to the server, which then requests the next question from the generative AI model. The generative AI model generates the next question and returns it to the server. The server displays the next question on the device.

[0998] 5. Automatic generation of materials

[0999] Once all user responses have been collected, the server sends this data to the generative AI model, which then generates presentation materials and returns them to the server. The server then sends the generated materials to the device, which displays them to the user.

[1000] 6. Final check and corrections

[1001] The user checks the generated presentation materials and inputs any parts that need to be corrected. For example, the user might input, "I would like to correct the content of slide 4." The device sends a correction request to the server, which then requests the generative AI model to regenerate the materials. The generative AI model returns the corrected materials to the server, which then sends them to the device. The device then displays the corrected materials to the user.

[1002] 7. Final output

[1003] When the user finally confirms the material they are satisfied with, they click the "Download" link, which the device displays and the user clicks to download the material.

[1004] Examples and prompts

[1005] Examples:

[1006] 1. User Registration and Login:

[1007] Example: A user logs in by entering an email address (example@example.com) and password (password123).

[1008] 2. Enter the purpose and basic information of your presentation:

[1009] Example: User enters "New product promotion," "Sales department," and "Presentation in 5 days."

[1010] 3. Template Recommendations:

[1011] Example: The generation AI presents two templates: a "template for introducing a new product" and a "template for a management report."

[1012] 4. Interactive Question and Answer:

[1013] Example: The first question is "What points do you want to emphasize in your presentation?" and the user enters "Safety of the latest technology."

[1014] 5. Automatic generation of materials:

[1015] Example: Generative AI generates a document consisting of three slides: "Slide 1: New product overview," "Slide 2: Technical details," and "Slide 3: Ensuring safety."

[1016] 6. Final checks and corrections:

[1017] Example: The user enters a correction such as "Please be more specific about the technical details on slide 2."

[1018] 7. Final output:

[1019] Example: User downloads revised document.

[1020] Example prompt:

[1021] I'd like to create a presentation for management to promote a new product. The purpose of the presentation is to clearly communicate the features of the new product, and the deadline is in three days. Please suggest a suitable template.

[1022] By providing specific prompts in this way, users can efficiently create materials.

[1023] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1024] Step 1:

[1025] When a user accesses the login screen, the terminal displays the login page. The user enters their email address and password. The terminal sends the input data to the server as an HTTP POST request. The server accesses the database and verifies the corresponding user information. If authentication is successful, the server generates HTML data for the dashboard page and sends it to the terminal. The terminal displays the received HTML data in the browser.

[1026] Enter your email address and password

[1027] Output: Dashboard page upon successful authentication

[1028] Step 2:

[1029] A user starts creating a new presentation from the dashboard page, and enters the purpose, target audience, and deadline of the presentation into a form displayed on the device. When the user submits the information, the device sends the input data as an HTTP POST request to the server, which stores it in a database.

[1030] Input: Purpose of presentation, target audience, deadline

[1031] Output: Basic information saved

[1032] Step 3:

[1033] The server sends a template request to the generative AI model based on the stored basic information. The generative AI model uses the received information as input to generate multiple presentation templates, which are then returned to the server. The server then sends a preview image and description of the template to the device, which displays it to the user.

[1034] Input: Basic information

[1035] Output: Multiple template previews

[1036] Step 4:

[1037] The user selects an appropriate template, and the selection information is sent from the terminal to the server, where it is stored.

[1038] Input: Selected template information

[1039] Output: Selection information stored on the server

[1040] Step 5:

[1041] The device displays a question to the user based on the selected template. For example, the question might be, "What are the features of the new product?" The user enters an answer, and the device sends the answer data to the server. The server stores the answer information and requests the next question from the generative AI model. The generative AI model generates the next question and returns it to the server. The server sends the next question to the device, which displays it.

[1042] Input: Template and first question

[1043] Output: User's answer and next question

[1044] Step 6:

[1045] Once the user's answers to all questions have been collected, the server sends these answers to the generative AI model, which then automatically generates presentation materials based on this data and returns the data to the server. The server then sends the generated materials to the device, which then displays them.

[1046] Input: All user responses

[1047] Output: The generated presentation

[1048] Step 7:

[1049] The user reviews the generated presentation materials and inputs correction requests as necessary. For example, the user sends a request such as "I would like to correct the content of slide 4." The device sends the correction request to the server, and the server sends a regeneration request to the generative AI model. The generative AI model generates the corrected materials and returns the data to the server. The server sends the corrected materials to the device, which displays them to the user.

[1050] Input: User modification request

[1051] Output: Revised presentation

[1052] Step 8:

[1053] When the user finally confirms the material they are satisfied with, they click the "Download" link. The terminal displays the download link, and the user clicks to download the material.

[1054] Input: User download request

[1055] Output: Downloaded presentation materials

[1056] (Application example 1)

[1057] 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."

[1058] Conventional presentation creation systems require users to spend a lot of time preparing presentation materials, making it difficult to quickly select appropriate templates and content. Furthermore, they are slow to respond to revision requests, which is inefficient in the advertising industry, where real-time responses are required. Therefore, there was a need for a system that allows users to easily and quickly generate high-quality presentation materials and make necessary revisions in real time.

[1059] 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.

[1060] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending a plurality of presentation templates based on the information input by the input means, selection means for selecting the recommended template, question presentation means for acquiring additional information in an interactive manner, means for receiving the additional information and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on a user's correction request, means for acquiring information via gaze or voice input in response to templates or questions displayed on the smart glasses, means for finally outputting the generated materials and providing them in a downloadable format, and display means for the smart glasses to display the generated presentation materials to the user. This allows a user to efficiently create high-quality presentation materials in a short amount of time and easily correct and check them by real-time operation through the smart glasses.

[1061] "Input means" refers to a device or interface that allows a user to input their purpose and basic information.

[1062] The "means for recommending" is a device or program that has the function of presenting multiple presentation templates based on input information.

[1063] The "selection means" refers to a device or interface that allows a user to select an appropriate template from the recommended templates.

[1064] A "question presenter" is a device or function for interactively gathering additional information based on a selected template.

[1065] "Automatic generation means" refers to a program or device that automatically creates presentation materials based on the collected additional information.

[1066] The "regeneration means" refers to a device or program that has the function of recreating the generated presentation materials based on a modification request from the user.

[1067] "Smart glasses" are wearable devices that allow users to input information using eye contact or voice input.

[1068] "Means for acquiring information through gaze or voice input" refers to a device or function that uses smart glasses to acquire information by analyzing the user's gaze movements and voice.

[1069] The "display means" refers to a display or interface for visually presenting the generated presentation materials to the user.

[1070] "Means for providing in a downloadable format" refers to a program or function for providing the final generated material in a format that can be downloaded by the user.

[1071] This invention provides a system that enables users to create, edit, and check presentation materials in real time using smart glasses. Specific embodiments of this system are described below.

[1072] User Registration and Login

[1073] The user puts on the smart glasses and accesses the system. A login screen is displayed through the smart glasses' display, and the user enters their email address and password using voice input or eye contact. The server authenticates the user based on this authentication information, and if authentication is successful, the user's dashboard page is displayed on the smart glasses.

[1074] Enter the purpose of the presentation and basic information

[1075] A form is displayed on the smart glasses displaying the user to input basic information such as the purpose of the presentation, the target audience, and the deadline. This information is acquired by voice or eye contact and sent to the server, which then stores the received information in a database.

[1076] Template recommendations

[1077] The server sends a template request to the generative AI based on the stored basic information. The generative AI model generates multiple templates and returns them to the server. The server then displays previews of these templates to the user through smart glasses. The user can then select an appropriate template by eye gaze or voice input.

[1078] Interactive question and answer

[1079] Based on the selected template, the server presents the user with a series of interactive questions. For example, the server displays a question such as "What are the features of the new product?", and the user responds by voice or eye contact. The server stores these responses and requests the next question from the AI ​​generator.

[1080] Automatic generation of materials

[1081] The server sends all user responses to the AI ​​generator, which then automatically generates presentation materials. The generated materials are then sent back to the server and presented to the user through the display means of the smart glasses.

[1082] Final check and corrections

[1083] The user checks the generated presentation materials and, if necessary, sends a request for revisions to the server using voice commands or eye gaze input. The server then sends this request to the generation AI, and presents the revised materials to the user again.

[1084] Final Output

[1085] The user reviews the presentation materials to their satisfaction and clicks on the final download link through the display means of the smart glasses. The server provides the materials in a downloadable format.

[1086] Hardware and software used

[1087] Smart glasses: Collect information through gaze control and voice input and display it to the user.

[1088] Server: Responsible for user authentication, data storage, question generation, document generation, and regeneration of correction requests.

[1089] Generative AI model: Generates templates and presentation materials.

[1090] Database: Stores user information and presentation data.

[1091] Examples of concrete examples and prompts

[1092] For example, if you use the generative AI model GPT-4, the prompt would look like this:

[1093] prompt

[1094] "Design an application that helps users create ads in real time using smart glasses. Collect information about the ad's purpose, targeting, design, and content, generate templates and questions based on that information, and then generate and display the final ad in real time. Allow the user to modify and download the ad using voice commands as needed."

[1095] This allows users to create high-quality presentation materials efficiently and in a short amount of time, and allows them to make real-time edits and checks through the smart glasses.

[1096] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1097] Step 1:

[1098] (User registration and login) The user puts on the smart glasses and the login screen appears on the display of the smart glasses. The user enters their email address and password using voice input or eye contact. The server receives the entered authentication information and accesses the database to authenticate the user. If authentication is successful, the user's dashboard page is displayed through the smart glasses.

[1099] Input: Email address, password

[1100] Data processing: database access, authentication processing

[1101] Output: Dashboard page displayed

[1102] Step 2:

[1103] (Inputting the purpose of the presentation and basic information) The server displays a form on the smart glasses to input the purpose of the presentation, target audience, deadline, etc. The user inputs this information using voice input or eye gaze input. The server receives the input information and stores it in a database.

[1104] Input: Purpose of presentation, target audience, deadline

[1105] Data processing: Data storage processing

[1106] Output: Basic information saved

[1107] Step 3:

[1108] (Template recommendation) The server sends a template request to the generation AI based on the basic information stored in the database. The generation AI generates multiple templates and returns them to the server. The server displays a preview of the templates on the smart glasses. The user selects a template by eye gaze or voice input.

[1109] Input: Basic information, template request

[1110] Data processing: Template generation, preview display

[1111] Output: Selected template

[1112] Step 4:

[1113] (Interactive Questions and Answers) Based on the selected template, the server sequentially displays interactive questions to the user. For example, the server displays a question such as, "What are the features of the new product?" The user answers by voice or eye contact, and the server receives the answers and stores them in a database.

[1114] Input: Question, Answer

[1115] Data processing: Question generation, answer storage

[1116] Output: Additional information saved

[1117] Step 5:

[1118] (Automatic generation of presentation materials) The server sends all user responses to the generation AI, which then automatically generates presentation materials. The generated materials are sent back to the server and presented to the user through the display means of the smart glasses.

[1119] Input: User answer

[1120] Data processing: Data generation

[1121] Output: Generated presentation materials

[1122] Step 6:

[1123] (Final confirmation and corrections) The user checks the presentation materials displayed on the smart glasses and makes any necessary corrections by voice or eye contact. The server sends these correction instructions to the generation AI, which then regenerates the corrected materials. The corrected materials are then sent back to the server and presented to the user again.

[1124] Input: Correction instructions

[1125] Data processing: Reflection of correction instructions, regeneration

[1126] Output: Revised presentation

[1127] Step 7:

[1128] (Final Output) The user finally checks the presentation materials to their satisfaction and clicks the final download link through the display means of the smart glasses. The server provides the materials in a downloadable format, and the user downloads the materials.

[1129] Input: Download instructions

[1130] Data processing: Converting materials into downloadable format

[1131] Output: Downloadable materials

[1132] 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.

[1133] User Registration and Login

[1134] 1. The user accesses the login screen

[1135] The device displays a login page, and the user enters their email address and password and submits it.

[1136] 2. Authentication and Dashboard Migration

[1137] The device sends authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server generates the user's dashboard page and returns it to the device. The device displays the dashboard page. The user clicks "Create a new presentation."

[1138] Enter the purpose of the presentation and basic information

[1139] 1. Display the basic information input form

[1140] The device displays a form where you can enter the purpose of the presentation, the target audience, and the deadline.

[1141] 2. Transmission and storage of information

[1142] The user enters information such as "New product promotion," "Management," and "3 days later," and submits it. The device sends the information to the server, which stores it in a database.

[1143] Template recommendations

[1144] 1. Template Presentation

[1145] The server sends a template request to the generation AI based on basic information. The generation AI generates multiple templates and returns them to the server. The server presents preview images and descriptions of the templates to the user. The device displays the preview images, and the user can select the appropriate template.

[1146] Conversational Questions and Emotion Recognition

[1147] 1. Posing the Question

[1148] The device displays the first question based on the selected template: "What are the features of your new product?"

[1149] 2. Emotion recognition and answer input

[1150] The device acquires the user's facial recognition data or voice data and sends it to the server, which uses an emotion engine to determine the user's emotional state.

[1151] The device receives the user's response, "A smartphone equipped with the latest AI technology," and sends it to the server.

[1152] 3. Generate and display the next question

[1153] The server requests the next question from the generation AI. The generation AI creates a question based on the emotional state recognized by the emotion engine. The server then sends the next question to the device, which displays it to the user. This process is repeated until all necessary information is collected.

[1154] Automatically generate materials and adjust them based on emotions

[1155] 1. Sending the final data

[1156] The server sends all information to the generating AI.

[1157] 2. Creation and adjustment of materials

[1158] The generative AI generates presentation materials, and the emotion engine adjusts the design and content according to the user's emotional state. The adjusted materials are then returned to the server.

[1159] 3. Presentation of materials

[1160] The server presents the generated presentation materials to the user, and the terminal displays the materials as a preview.

[1161] Final check and corrections

[1162] 1. Preview display

[1163] The terminal displays the generated presentation materials to the user.

[1164] 2. Enter the corrections and regenerate

[1165] The user types, "I would like to revise the content of slide 4." The device sends the revision instructions to the server. The server requests revision instructions from the generation AI, which then revises the document and returns it to the server. The server then presents the revised document to the user again. This process is repeated until the user is finally satisfied.

[1166] Final Output

[1167] 1. Final Download

[1168] The user checks the material to find it satisfactory and clicks on the download link.

[1169] The terminal displays a download link, and the user downloads the material.

[1170] This system allows users to efficiently create high-quality presentation materials. In particular, by utilizing the emotion engine, questions and materials are adjusted according to the user's emotional state, providing more appropriate and effective presentation materials.

[1171] The processing flow will be explained below.

[1172] Step 1:

[1173] The user accesses the login screen. The device displays the login page. The user enters their email address and password and clicks the submit button.

[1174] Step 2:

[1175] The terminal sends the entered authentication information to the server. The server accesses the database and checks whether the user's email address and password are correct. If authentication is successful, the server issues session information.

[1176] Step 3:

[1177] The server generates the user's dashboard page and returns it to the device. The device displays the dashboard page. The user clicks the "Create a new presentation" button.

[1178] Step 4:

[1179] The device displays a form for inputting the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the submit button.

[1180] Step 5:

[1181] The device sends the input information to the server. The server stores the received information in a database. The server then sends a template request to the generation AI based on the stored information.

[1182] Step 6:

[1183] The generation AI generates multiple presentation templates and returns them to the server. The server then presents preview images and descriptions of the templates to the user. The device displays the preview images, and the user selects the appropriate template.

[1184] Step 7:

[1185] The user selects a template. The device sends the selection information to the server. The server requests the generation AI to generate interactive questions based on the selected template.

[1186] Step 8:

[1187] The generation AI generates the first question and returns it to the server. The server sends the question, "Please tell me the features of the new product," to the device. The device displays the question to the user.

[1188] Step 9:

[1189] The user answers the question by typing "a smartphone equipped with the latest AI technology" and clicks the send button. The device sends the answer to the server, which then stores it in a database.

[1190] Step 10:

[1191] The device acquires the user's facial recognition data or voice data and sends it to the server, which uses an emotion engine to determine the user's emotional state.

[1192] Step 11:

[1193] The server requests the next question from the generation AI based on the emotional state recognized by the emotion engine. The generation AI returns the generated next question to the server, which then sends it to the device. The device displays the next question to the user. This step is repeated until all necessary information is collected.

[1194] Step 12:

[1195] Once all the information is collected, the server requests the generation AI to generate presentation materials. The generation AI generates the materials, and the emotion engine adjusts the design and content according to the user's emotional state. The adjusted materials are then returned to the server.

[1196] Step 13:

[1197] The server presents the generated presentation materials to the user, and the terminal displays a preview of the materials.

[1198] Step 14:

[1199] The user checks the document and indicates the parts that need to be corrected. The device sends the correction instructions to the server. The server requests the generation AI to make corrections, and the generation AI regenerates the document and returns it to the server. The server then presents the corrected document to the user again. This step is repeated until the user is finally satisfied.

[1200] Step 15:

[1201] If the user is satisfied with the final document, he / she clicks on the download link, and the terminal displays the download link for the final document, and the user downloads the document.

[1202] Example 2

[1203] 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."

[1204] Conventional presentation creation systems have the problem that even if a user inputs information and selects a template, it is difficult to generate efficient, high-quality materials in the subsequent document creation process. Another issue is that there is no system that can create optimal materials according to the user's emotional state. This makes it difficult to maximize the effectiveness of presentations, ultimately hindering business success and effective communication.

[1205] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1206] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending a plurality of presentation templates based on the information input by the input means, selection means for selecting the recommended template, question posing means for acquiring additional information in an interactive format, means for receiving the additional information and adjusting the question content based on the user's emotional state using emotion recognition technology, means for transmitting all information to a generative AI model and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on the user's requested revisions, and output means for finally outputting the presentation materials. This enables users to efficiently create high-quality presentation materials and generate materials optimal for their emotional state.

[1207] The "input means for the user to input the purpose and basic information" is an interface for the user to input basic information such as the purpose, target audience, and deadline of the presentation.

[1208] "Means for recommending multiple presentation templates" is a function that suggests the most suitable presentation template based on basic information entered by the user.

[1209] The "selection means for selecting a recommended template" is an operation method for selecting an appropriate template from a plurality of templates presented to the user.

[1210] The "means for presenting questions to acquire additional information in an interactive manner" is a function for displaying questions to collect additional information necessary for presentation through a dialogue with the user.

[1211] "Emotion recognition technology" is a technology that analyzes a user's facial recognition data and voice data to determine the user's emotional state.

[1212] The "means for adjusting the content of the question based on the emotional state" is a function for changing the content and format of the question depending on the emotional state of the user.

[1213] A "generative AI model" is an artificial intelligence model that analyzes data based on input information and generates new information and materials.

[1214] The "means for automatically generating presentation materials" is a system that automatically creates presentation materials based on collected information.

[1215] The "means for presenting the generated presentation materials to the user and regenerating them based on the user's revision requests" is a function for displaying the initially generated materials to the user and then generating the materials again based on subsequent revision requests.

[1216] The "output means for finally outputting the presentation materials" refers to a download link or file saving function for providing the user with the finalized presentation materials.

[1217] This invention relates to a system for generating presentation materials efficiently and with high quality. The system generates optimal presentation materials by allowing users to input their purpose and basic information, proposing appropriate templates, and adjusting questions based on the user's emotional state. This system is realized using a terminal, a server, and a generation AI model.

[1218] Input Method

[1219] The user accesses the system's login page from a web browser on their terminal. Authentication is performed by entering their email address and password and clicking the login button. The server verifies the authentication information using a database (e.g., MySQL), and if authentication is successful, it generates the user's dashboard and returns it to the terminal. Next, the user clicks "Create a new presentation," which displays a form for entering basic information such as the purpose of the presentation, target audience, and deadline. The user enters information such as "New product promotion," "Management," and "3 days later" into this form and submits it.

[1220] Presentation template recommendation method

[1221] The server sends a template generation request to a generation AI (e.g., OpenAI GPT-4) based on the basic information entered by the user. The generation AI generates multiple templates and returns the results to the server. The server then creates preview images and descriptions of these templates in HTML format and sends them to the device. The device then displays these preview images and descriptions to the user, providing an interface for selecting an appropriate template.

[1222] Question presentation method and emotion recognition method

[1223] When the user selects a template, the device displays the first question based on the selected template: "What are the features of the new product?" At the same time, the device acquires the user's facial recognition data and voice data and sends them to the server. The server uses emotion recognition technology (for example, Microsoft Azure Emotion API) to determine the user's emotional state. When the user enters the answer "A smartphone equipped with the latest AI technology" and submits it, this information is also sent to the server.

[1224] Information adjustment means

[1225] The server then requests the AI ​​to generate the next question, adjusting the question based on emotion recognition. The server then sends the generated question to the device, which displays it to the user. This process is repeated until all the information needed for the presentation is gathered.

[1226] A means of automatically generating presentation materials

[1227] Once all the information is collected, the server sends it to a generative AI model, which then generates presentation materials based on the collected information. The generated materials are then adjusted in design and content using emotion recognition technology. The adjusted materials are then returned to the server.

[1228] Material presentation means and reproduction means

[1229] The server sends the generated presentation materials to the device, which displays them as a preview to the user. The user checks the preview and enters, for example, "I would like to revise the contents of slide 4." The device receives the revision instructions and sends them to the server. The server then sends a regeneration instruction to the generation AI, causing it to generate the materials again. The revised materials are then returned to the server and displayed to the user via the device. This process is repeated until the user is satisfied.

[1230] Final output method

[1231] When the user finally finds the material that satisfies him, he clicks on the download link, and the terminal displays the download link, allowing the user to download the material.

[1232] The above is an embodiment of the present invention. This system allows users to efficiently and effectively create high-quality presentation materials. The following is a specific example of a prompt sentence to be input to the generative AI model:

[1233] "Please create a presentation to promote our new product. It's for management and needs to be completed in three days."

[1234] "Feature: 'Smartphone equipped with the latest AI technology', Emotion: Excitement, What should I ask next?"

[1235] These prompts will generate more specific and personalized presentation materials.

[1236] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1237] Step 1:

[1238] A user accesses the system's login page from a web browser. The user enters their email address and password and clicks the "Login" button. The terminal sends this authentication information to the server, which then verifies the user information using a database (e.g., MySQL). If authentication is successful, the server generates the user's dashboard and sends the HTML data to the terminal. The terminal receives it and displays it to the user. The input is the user's authentication information, and the output is the HTML data of the dashboard.

[1239] Step 2:

[1240] The user clicks the "Create a new presentation" button on the dashboard. The device displays a form for entering the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the "Submit" button. The device sends this information to the server, which saves it in a database. The input is the basic information about the presentation, and the output is a response indicating that it was saved successfully.

[1241] Step 3:

[1242] The server uses the stored basic information to send a template request to a generative AI model (e.g., OpenAI GPT-4). The generative AI model generates a template and returns its preview image and description to the server. The server receives these, formats them into HTML, and sends them to the device. The device displays multiple templates to the user and allows the user to select one. The input is the basic information, and the output is the template preview image and description.

[1243] Step 4:

[1244] The user selects a template. Based on the selected template, the device displays the first question, "What are the features of your new product?" The user answers, "A smartphone equipped with the latest AI technology." The device then acquires facial recognition data and voice data and sends them to the server. The server uses emotion recognition technology to recognize the user's emotional state. The input is the template selection and the user's emotional data, and the output is the emotional state.

[1245] Step 5:

[1246] The server requests the next question from the generative AI model and receives the question content adjusted by emotion recognition technology from the generative AI model. The new question is sent from the server to the device, which displays it to the user. The user answers the question, and the device sends the answer to the server. This process is repeated until all necessary information is collected. The input is the previous question and the user's answer, and the output is the next question.

[1247] Step 6:

[1248] After all the information is collected, the server sends it to the generative AI model, which generates the presentation materials. The generative AI model generates the materials, adjusts them based on emotion recognition technology, and returns the results to the server. The server receives the generated presentation materials and sends them to the device, which displays a preview for the user. The input is the collected information, and the output is the generated presentation materials.

[1249] Step 7:

[1250] The user checks the preview and, if necessary, inputs a correction request, such as "I would like to revise the content of slide 4." The device sends the correction request to the server. The server sends correction instructions to the generative AI model and receives a regenerated document. The new document is sent from the server to the device and previewed again by the user. This process is repeated until the user is satisfied. The input is the correction request, and the output is the revised presentation document.

[1251] Step 8:

[1252] When the user is finally satisfied with the presentation materials, he or she clicks the download link. The terminal displays the download link, allowing the user to download the materials. The input is the final confirmation and clicking the download link, and the output is the final presentation materials.

[1253] The above is the flow of specific processing steps of the program of this system.

[1254] (Application example 2)

[1255] 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."

[1256] Many conventional presentation production systems automatically generate presentations based solely on input information, without considering the user's emotional state. This makes it difficult to generate appropriate questions or materials based on the user's emotional changes, resulting in a lack of improved user experience. Furthermore, surveillance systems lack technology that uses emotion recognition to instantly issue security alerts, making it difficult to respond quickly and accurately.

[1257] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1258] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending multiple presentation templates based on the input information, selection means for selecting a recommended template, question presentation means for acquiring additional information in an interactive format, emotion recognition means for determining the user's emotional state based on the additional information and facial recognition data or voice data, a generative AI model for adjusting the questions based on the emotional state determined by the emotion recognition means, means for presenting questions generated by the generative AI model to the user, receiving the additional information, and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on user requests for revisions, and output means for finally outputting the presentation materials. This enables appropriate question presentation and material generation that take the user's emotional state into consideration, as well as rapid and accurate security response using emotion recognition in surveillance systems.

[1259] "Input means" refers to a device or interface through which a user inputs objectives and basic information.

[1260] The "recommending means" is a device or program for recommending a plurality of presentation templates based on information input by the input means.

[1261] The "selection means" is a device or interface that allows the user to select a recommended template.

[1262] The "question presenting means" is a device or program that displays a question for acquiring additional information in an interactive manner based on the template selected by the selection means.

[1263] "Emotion recognition means" refers to a device or program for determining the emotional state of a user based on facial recognition data or voice data.

[1264] A "generative AI model" is an artificial intelligence model that tailors questions based on the emotional state determined by the emotion recognition means.

[1265] "Means for automatic generation" means a device or program for receiving additional information and generating presentation materials based on questions generated by a generative AI model.

[1266] The "regenerating means" is a device or program for presenting the generated presentation materials to the user and regenerating the materials based on the user's modification requests.

[1267] "Output means" refers to a device or program for providing the final generated presentation materials to the user in a displayable or downloadable format.

[1268] MODE FOR CARRYING OUT THE INVENTION

[1269] A specific system for implementing the present invention is configured as follows.

[1270] User Registration and Login

[1271] The device that the user accesses displays a login screen for entering an email address and password. When the user enters and submits the information, the device sends the authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server generates a dashboard page for the user and returns it to the device. The device displays the dashboard page and allows the user to select "Create a new presentation."

[1272] Enter the purpose of the presentation and basic information

[1273] When a user clicks "Create a new presentation" on the dashboard, a basic information input form is displayed on the device. The user enters information such as the purpose of the presentation, target audience, and deadline into this form and submits it. The entered information is sent from the device to the server, which then stores it in a database.

[1274] Template recommendations

[1275] The server sends a template request to the generative AI model based on the basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends preview images and descriptions of the templates to the device, allowing the user to select one.

[1276] Conversational Questions and Emotion Recognition

[1277] After the user selects a template, the device displays the first question based on the selected template: "Please tell us the features of the new product." The device acquires facial recognition data or voice data and sends it to the server. The server uses emotion recognition means to determine the user's emotional state. The user's answer to the question displayed on the device is entered and sent to the server. The server requests the next question from the generative AI model, and a new question is generated based on the user's emotional state. This process is repeated until all necessary information is collected.

[1278] Automatically generate materials and adjust them based on emotions

[1279] The server sends all information to the generative AI model, which then generates the presentation materials. Furthermore, the emotion recognition means adjusts the design and content according to the user's emotional state. The adjusted materials are then sent back to the server, which presents them to the user. The device displays the materials as a preview.

[1280] Final check and corrections

[1281] The user previews the generated presentation materials and, if any corrections are needed, inputs instructions such as "I would like to revise the content of slide 4." The device sends this instruction to the server, which then requests corrections from the generative AI model. The generative AI model then corrects the materials and sends them back to the server. The server then presents the corrected materials to the user again. This process is repeated until the user is satisfied.

[1282] Final Output

[1283] When the user confirms the material that satisfies him and clicks on the download link, the terminal displays the download link and the user can download the material.

[1284] Hardware and software used

[1285] Hardware: Smartphones, smart glasses, head-mounted displays, robots.

[1286] Software: Python, OpenCV, Keras, and the required server and database systems.

[1287] Specific examples

[1288] For example, by installing this system at the entrance to an office, it can instantly detect suspicious or nervous individuals and send an alert to the security team.

[1289] Prompt Sentence Examples

[1290] Enter the following prompt into the generative AI model:

[1291] "Generate a template for building a security alert system based on an emotion engine. The template should be Python code that performs face detection and emotion recognition and sends an alert when an anomaly is detected. The template should use a cascade classifier and a Keras model to perform face detection and emotion recognition."

[1292] This system configuration enables flexible creation of presentation materials based on the user's emotional state and quick and accurate security response.

[1293] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1294] Step 1:

[1295] User Registration and Login

[1296] The user enters and submits their email address and password. The device sends this authentication information to the server. The server references the database and authenticates the user. If authentication is successful, the server generates a dashboard page for the user and sends its contents back to the device. The device displays the dashboard page and allows the user to select "Create a new presentation."

[1297] Input: Email address, password

[1298] Output: Dashboard page

[1299] Step 2:

[1300] Enter the purpose of the presentation and basic information

[1301] When a user clicks "Create a new presentation" on the dashboard, the device displays a form for inputting the purpose, target audience, and deadline of the presentation. The user fills out the form and submits it. The device sends this information to the server, which stores it in a database.

[1302] Input: Purpose of presentation, target audience, deadline

[1303] Output: Basic information saved

[1304] Step 3:

[1305] Template recommendations

[1306] The server sends a template request to the generative AI model based on the basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends preview images and descriptions of the templates to the device, allowing the user to select one.

[1307] Input: Basic information

[1308] Output: Template preview image and description

[1309] Step 4:

[1310] Conversational Questions and Emotion Recognition

[1311] After the user selects a template, the device displays the first question: "What are the features of your new product?" The device captures facial recognition or voice data and sends it to the server. The server uses emotion recognition means to determine the user's emotional state. Based on this emotional state, the generative AI model generates the next question and returns it to the server. The device displays the next question, and the user enters and submits the answer. This process is repeated until all necessary information is collected.

[1312] Input: Facial recognition data or voice data, user response

[1313] Output: Next question based on emotional state

[1314] Step 5:

[1315] Automatically generate materials and adjust them based on emotions

[1316] The server sends all information to a generative AI model, which then generates the presentation materials. The emotion recognition means adjusts the design and content according to the user's emotional state. The adjusted materials are then sent back to the server, which then sends them to the device for the user to preview.

[1317] Input: All information

[1318] Output: Adjusted presentation material

[1319] Step 6:

[1320] Final check and corrections

[1321] The user previews the generated presentation materials and inputs any necessary corrections. The device sends these instructions to the server, which then requests corrections from the generative AI model. The generative AI model then corrects the materials and sends them back to the server. The server then presents the corrected materials to the user again. This process is repeated until the user is satisfied.

[1322] Input: Correction instructions

[1323] Output: Revised presentation

[1324] Step 7:

[1325] Final Output

[1326] When the user confirms the material that satisfies him and clicks on the download link, the terminal displays the download link and the user can download the material.

[1327] Input: Click on the download link

[1328] Output: Downloaded presentation

[1329] 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.

[1330] 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.

[1331] 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.

[1332] [Fourth embodiment]

[1333] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1334] 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.

[1335] 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).

[1336] 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.

[1337] 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.

[1338] 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).

[1339] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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.

[1345] 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."

[1346] User Registration and Login

[1347] 1. The user accesses the login screen

[1348] The device displays a login page, and the user enters their email address and password.

[1349] 2. Authentication and Dashboard Migration

[1350] The terminal sends the entered authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server returns the user's dashboard page. The terminal displays the dashboard page.

[1351] Enter the purpose of the presentation and basic information

[1352] 1. Display the basic information input form

[1353] The device displays a form for the user to input the purpose, target audience, and deadline of the presentation.

[1354] 2. Transmission and storage of information

[1355] The user enters and submits information such as "New product promotion," "Management," and "3 days later." The device sends this information to the server, which then stores it in a database.

[1356] Template recommendations

[1357] 1. Template Presentation

[1358] The server sends a template request to the generation AI based on the saved basic information. The generation AI generates multiple templates and returns them to the server. The server displays a preview of the templates to the user.

[1359] 2. Select a template

[1360] The user selects an appropriate template from the displayed templates.

[1361] Interactive question and answer

[1362] 1. Posing the Question

[1363] The device displays the first question, "What are the features of your new product?" based on the selected template.

[1364] 2. Enter and submit your answers

[1365] The user enters "a smartphone equipped with the latest AI technology" and submits the answer. The device then sends the entered answer to the server.

[1366] 3. Show next question

[1367] The server saves the additional information and requests the next question from the generation AI, which returns the generated next question to the server, which displays it on the device.

[1368] Automatic generation of materials

[1369] 1. Sending the final data

[1370] The server sends all user responses to the generation AI.

[1371] 2. Creating and Presenting Materials

[1372] The generation AI generates presentation materials and returns them to the server, which then presents them to the user.

[1373] Final check and corrections

[1374] 1. Preview display

[1375] The terminal displays the generated presentation materials to the user.

[1376] 2. Enter the corrections and regenerate

[1377] The user types, "I would like to revise the content of slide 4." The device sends the revision instruction to the server. The server makes a request to the generation AI, and the revised document is returned to the server. The server then presents the document again.

[1378] Final Output

[1379] 1. Final Download

[1380] The user finally confirms the material that satisfies him and clicks the download link, which is displayed on the device and the user downloads the material.

[1381] This system allows users to create high-quality presentation materials in a short amount of time. Collaboration between the server and the generation AI allows for efficient and flexible generation and modification of materials.

[1382] The processing flow will be explained below.

[1383] Step 1:

[1384] The user accesses the login screen. The device displays the login page. The user enters their email address and password and submits it.

[1385] Step 2:

[1386] The terminal sends the entered authentication information to the server. The server accesses the database and checks whether the user's email address and password are correct. If authentication is successful, the server issues session information to the user.

[1387] Step 3:

[1388] The server generates the user's dashboard page and returns it to the device. The device displays the dashboard page to the user. The user clicks the "Create a new presentation" button.

[1389] Step 4:

[1390] The device displays a form for the user to input the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the submit button.

[1391] Step 5:

[1392] The device sends the input information to the server. The server stores the received information in a database. The server then sends a template request to the generation AI based on the stored information.

[1393] Step 6:

[1394] The generation AI generates multiple presentation templates and returns them to the server. The server presents preview images and descriptions of the templates to the user. The device displays the preview images and allows the user to select a template.

[1395] Step 7:

[1396] The user selects an appropriate template. The device sends the selection information to the server. The server then requests the generation AI to generate questions in an interactive format based on the selected template.

[1397] Step 8:

[1398] The generation AI generates the first question and returns it to the server. The server sends the first question, "Please tell me the features of the new product," to the device. The device displays the question to the user.

[1399] Step 9:

[1400] The user enters the answer "a smartphone equipped with the latest AI technology" and clicks the send button. The device sends the answer to the server, which then stores the received answer in a database.

[1401] Step 10:

[1402] The server requests the next question from the generation AI. The generation AI generates the next question and returns it to the server. The server sends the next question to the device, which displays it to the user. This step is repeated until all the necessary information is collected.

[1403] Step 11:

[1404] Once all the information has been collected, the server requests the generation AI to generate the presentation materials. The generation AI generates the materials and returns them to the server. The server then presents the generated presentation materials to the user.

[1405] Step 12:

[1406] The user previews the document and inputs any corrections that need to be made. The device sends correction instructions to the server. The server requests correction instructions from the generation AI, which then corrects the document and returns it to the server. The server then presents the corrected document to the user again. This step is repeated until the user is finally satisfied.

[1407] Step 13:

[1408] When the user is satisfied with the final document, he / she clicks on the download link, the terminal displays the download link for the final document, and the user downloads the document.

[1409] Through the above steps, the user can create presentation materials efficiently and quickly.

[1410] Example 1

[1411] 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."

[1412] The process of creating presentation materials generally requires time and effort. This makes it difficult for users to create high-quality materials within a limited time. In addition, modifying and regenerating materials is also time-consuming, so a system that can respond flexibly is required.

[1413] 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.

[1414] In this invention, the server includes input means for a user to input purpose and basic information, means for requesting multiple presentation templates from the generative AI model based on the information input by the input means, and selection means for selecting a template recommended by the generative AI model, thereby enabling efficient generation and flexible modification of high-quality presentation materials.

[1415] A "user" is an individual or corporation that uses the system to create presentation materials.

[1416] "Input means" refers to the device or software that allows the user to input purpose and basic information.

[1417] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to automatically generate presentation templates and materials.

[1418] A "prompt" is an instruction or question input to a generative AI model, which serves as a guide for the AI ​​to return an appropriate output.

[1419] "Recommended templates" refer to multiple templates generated by a generative AI model based on user input information.

[1420] "Selection means" refers to a device or software that allows a user to select an appropriate template from among the templates recommended by the generative AI model.

[1421] A "question presenter" is a device or software for interactively asking a user for additional information based on a selected template.

[1422] "Presentation materials" refer to slides and documents created to achieve the purpose of a presentation.

[1423] "Output means" refers to a device or software for providing the final generated presentation materials to the user.

[1424] "Automatic generation means" means a device or software that automatically creates presentation materials based on input information and additional information using a generative AI model.

[1425] A "modification request" is an instruction from a user requesting changes to the content of the generated presentation materials.

[1426] A "means for requesting regeneration" is a device or software that causes a generative AI model to regenerate the content of a presentation material based on a modification request.

[1427] This system allows users to create efficient and high-quality presentation materials, and is implemented using a server, terminals, and a generative AI model.

[1428] 1. User Registration and Login

[1429] When a user accesses the login screen using a terminal, the terminal opens a browser and accesses the URL of the login page. The user enters their email address and password and presses the login button. The terminal sends the entered authentication information to the server, which then accesses the database to perform authentication. If authentication is successful, the server generates a dashboard page and sends it to the terminal. The terminal displays it.

[1430] 2. Enter the purpose of your presentation and basic information

[1431] A form is displayed on the dashboard page where the user can enter the purpose, target audience, and deadline of the presentation. For example, the user can enter information such as "New product promotion," "Management," and "3 days later." When the user submits the information, the device sends it to the server, which then stores the information in a database.

[1432] 3. Template Recommendations

[1433] The server sends a template request to the generative AI model based on the stored basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends previews of these templates to the device, which displays them to the user. When the user selects an appropriate template, the selection information is sent to the server.

[1434] 4. Interactive Question and Answer

[1435] Based on the template selected by the user, the device displays the first question, "What are the features of your new product?" The user enters the answer, "A smartphone equipped with the latest AI technology," and submits it. The device sends this answer to the server, which then requests the next question from the generative AI model. The generative AI model generates the next question and returns it to the server. The server displays the next question on the device.

[1436] 5. Automatic generation of materials

[1437] Once all user responses have been collected, the server sends this data to the generative AI model, which then generates presentation materials and returns them to the server. The server then sends the generated materials to the device, which displays them to the user.

[1438] 6. Final check and corrections

[1439] The user checks the generated presentation materials and inputs any parts that need to be corrected. For example, the user might input, "I would like to correct the content of slide 4." The device sends a correction request to the server, which then requests the generative AI model to regenerate the materials. The generative AI model returns the corrected materials to the server, which then sends them to the device. The device then displays the corrected materials to the user.

[1440] 7. Final output

[1441] When the user finally confirms the material they are satisfied with, they click the "Download" link, which the device displays and the user clicks to download the material.

[1442] Examples and prompts

[1443] Examples:

[1444] 1. User Registration and Login:

[1445] Example: A user logs in by entering an email address (example@example.com) and password (password123).

[1446] 2. Enter the purpose and basic information of your presentation:

[1447] Example: User enters "New product promotion," "Sales department," and "Presentation in 5 days."

[1448] 3. Template Recommendations:

[1449] Example: The generation AI presents two templates: a "template for introducing a new product" and a "template for a management report."

[1450] 4. Interactive Question and Answer:

[1451] Example: The first question is "What points do you want to emphasize in your presentation?" and the user enters "Safety of the latest technology."

[1452] 5. Automatic generation of materials:

[1453] Example: Generative AI generates a document consisting of three slides: "Slide 1: New product overview," "Slide 2: Technical details," and "Slide 3: Ensuring safety."

[1454] 6. Final checks and corrections:

[1455] Example: The user enters a correction such as "Please be more specific about the technical details on slide 2."

[1456] 7. Final output:

[1457] Example: User downloads revised document.

[1458] Example prompt:

[1459] I'd like to create a presentation for management to promote a new product. The purpose of the presentation is to clearly communicate the features of the new product, and the deadline is in three days. Please suggest a suitable template.

[1460] By providing specific prompts in this way, users can efficiently create materials.

[1461] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1462] Step 1:

[1463] When a user accesses the login screen, the terminal displays the login page. The user enters their email address and password. The terminal sends the input data to the server as an HTTP POST request. The server accesses the database and verifies the corresponding user information. If authentication is successful, the server generates HTML data for the dashboard page and sends it to the terminal. The terminal displays the received HTML data in the browser.

[1464] Enter your email address and password

[1465] Output: Dashboard page upon successful authentication

[1466] Step 2:

[1467] A user starts creating a new presentation from the dashboard page, and enters the purpose, target audience, and deadline of the presentation into a form displayed on the device. When the user submits the information, the device sends the input data as an HTTP POST request to the server, which stores it in a database.

[1468] Input: Purpose of presentation, target audience, deadline

[1469] Output: Basic information saved

[1470] Step 3:

[1471] The server sends a template request to the generative AI model based on the stored basic information. The generative AI model uses the received information as input to generate multiple presentation templates, which are then returned to the server. The server then sends a preview image and description of the template to the device, which displays it to the user.

[1472] Input: Basic information

[1473] Output: Multiple template previews

[1474] Step 4:

[1475] The user selects an appropriate template, and the selection information is sent from the terminal to the server, where it is stored.

[1476] Input: Selected template information

[1477] Output: Selection information stored on the server

[1478] Step 5:

[1479] The device displays a question to the user based on the selected template. For example, the question might be, "What are the features of the new product?" The user enters an answer, and the device sends the answer data to the server. The server stores the answer information and requests the next question from the generative AI model. The generative AI model generates the next question and returns it to the server. The server sends the next question to the device, which displays it.

[1480] Input: Template and first question

[1481] Output: User's answer and next question

[1482] Step 6:

[1483] Once the user's answers to all questions have been collected, the server sends these answers to the generative AI model, which then automatically generates presentation materials based on this data and returns the data to the server. The server then sends the generated materials to the device, which then displays them.

[1484] Input: All user responses

[1485] Output: The generated presentation

[1486] Step 7:

[1487] The user reviews the generated presentation materials and inputs correction requests as necessary. For example, the user sends a request such as "I would like to correct the content of slide 4." The device sends the correction request to the server, and the server sends a regeneration request to the generative AI model. The generative AI model generates the corrected materials and returns the data to the server. The server sends the corrected materials to the device, which displays them to the user.

[1488] Input: User modification request

[1489] Output: Revised presentation

[1490] Step 8:

[1491] When the user finally confirms the material they are satisfied with, they click the "Download" link. The terminal displays the download link, and the user clicks to download the material.

[1492] Input: User download request

[1493] Output: Downloaded presentation materials

[1494] (Application example 1)

[1495] 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."

[1496] Conventional presentation creation systems require users to spend a lot of time preparing presentation materials, making it difficult to quickly select appropriate templates and content. Furthermore, they are slow to respond to revision requests, which is inefficient in the advertising industry, where real-time responses are required. Therefore, there was a need for a system that allows users to easily and quickly generate high-quality presentation materials and make necessary revisions in real time.

[1497] 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.

[1498] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending a plurality of presentation templates based on the information input by the input means, selection means for selecting the recommended template, question presentation means for acquiring additional information in an interactive manner, means for receiving the additional information and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on a user's correction request, means for acquiring information via gaze or voice input in response to templates or questions displayed on the smart glasses, means for finally outputting the generated materials and providing them in a downloadable format, and display means for the smart glasses to display the generated presentation materials to the user. This allows a user to efficiently create high-quality presentation materials in a short amount of time and easily correct and check them by real-time operation through the smart glasses.

[1499] "Input means" refers to a device or interface that allows a user to input their purpose and basic information.

[1500] The "means for recommending" is a device or program that has the function of presenting multiple presentation templates based on input information.

[1501] The "selection means" refers to a device or interface that allows a user to select an appropriate template from the recommended templates.

[1502] A "question presenter" is a device or function for interactively gathering additional information based on a selected template.

[1503] "Automatic generation means" refers to a program or device that automatically creates presentation materials based on the collected additional information.

[1504] The "regeneration means" refers to a device or program that has the function of recreating the generated presentation materials based on a modification request from the user.

[1505] "Smart glasses" are wearable devices that allow users to input information using eye contact or voice input.

[1506] "Means for acquiring information through gaze or voice input" refers to a device or function that uses smart glasses to acquire information by analyzing the user's gaze movements and voice.

[1507] The "display means" refers to a display or interface for visually presenting the generated presentation materials to the user.

[1508] "Means for providing in a downloadable format" refers to a program or function for providing the final generated material in a format that can be downloaded by the user.

[1509] This invention provides a system that enables users to create, edit, and check presentation materials in real time using smart glasses. Specific embodiments of this system are described below.

[1510] User Registration and Login

[1511] The user puts on the smart glasses and accesses the system. A login screen is displayed through the smart glasses' display, and the user enters their email address and password using voice input or eye contact. The server authenticates the user based on this authentication information, and if authentication is successful, the user's dashboard page is displayed on the smart glasses.

[1512] Enter the purpose of the presentation and basic information

[1513] A form is displayed on the smart glasses displaying the user to input basic information such as the purpose of the presentation, the target audience, and the deadline. This information is acquired by voice or eye contact and sent to the server, which then stores the received information in a database.

[1514] Template recommendations

[1515] The server sends a template request to the generative AI based on the stored basic information. The generative AI model generates multiple templates and returns them to the server. The server then displays previews of these templates to the user through smart glasses. The user can then select an appropriate template by eye gaze or voice input.

[1516] Interactive question and answer

[1517] Based on the selected template, the server presents the user with a series of interactive questions. For example, the server displays a question such as "What are the features of the new product?", and the user responds by voice or eye contact. The server stores these responses and requests the next question from the AI ​​generator.

[1518] Automatic generation of materials

[1519] The server sends all user responses to the AI ​​generator, which then automatically generates presentation materials. The generated materials are then sent back to the server and presented to the user through the display means of the smart glasses.

[1520] Final check and corrections

[1521] The user checks the generated presentation materials and, if necessary, sends a request for revisions to the server using voice commands or eye gaze input. The server then sends this request to the generation AI, and presents the revised materials to the user again.

[1522] Final Output

[1523] The user reviews the presentation materials to their satisfaction and clicks on the final download link through the display means of the smart glasses. The server provides the materials in a downloadable format.

[1524] Hardware and software used

[1525] Smart glasses: Collect information through gaze control and voice input and display it to the user.

[1526] Server: Responsible for user authentication, data storage, question generation, document generation, and regeneration of correction requests.

[1527] Generative AI model: Generates templates and presentation materials.

[1528] Database: Stores user information and presentation data.

[1529] Examples of concrete examples and prompts

[1530] For example, if you use the generative AI model GPT-4, the prompt would look like this:

[1531] prompt

[1532] "Design an application that helps users create ads in real time using smart glasses. Collect information about the ad's purpose, targeting, design, and content, generate templates and questions based on that information, and then generate and display the final ad in real time. Allow the user to modify and download the ad using voice commands as needed."

[1533] This allows users to create high-quality presentation materials efficiently and in a short amount of time, and allows them to make real-time edits and checks through the smart glasses.

[1534] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1535] Step 1:

[1536] (User registration and login) The user puts on the smart glasses and the login screen appears on the display of the smart glasses. The user enters their email address and password using voice input or eye contact. The server receives the entered authentication information and accesses the database to authenticate the user. If authentication is successful, the user's dashboard page is displayed through the smart glasses.

[1537] Input: Email address, password

[1538] Data processing: database access, authentication processing

[1539] Output: Dashboard page displayed

[1540] Step 2:

[1541] (Inputting the purpose of the presentation and basic information) The server displays a form on the smart glasses to input the purpose of the presentation, target audience, deadline, etc. The user inputs this information using voice input or eye gaze input. The server receives the input information and stores it in a database.

[1542] Input: Purpose of presentation, target audience, deadline

[1543] Data processing: Data storage processing

[1544] Output: Basic information saved

[1545] Step 3:

[1546] (Template recommendation) The server sends a template request to the generation AI based on the basic information stored in the database. The generation AI generates multiple templates and returns them to the server. The server displays a preview of the templates on the smart glasses. The user selects a template by eye gaze or voice input.

[1547] Input: Basic information, template request

[1548] Data processing: Template generation, preview display

[1549] Output: Selected template

[1550] Step 4:

[1551] (Interactive Questions and Answers) Based on the selected template, the server sequentially displays interactive questions to the user. For example, the server displays a question such as, "What are the features of the new product?" The user answers by voice or eye contact, and the server receives the answers and stores them in a database.

[1552] Input: Question, Answer

[1553] Data processing: Question generation, answer storage

[1554] Output: Additional information saved

[1555] Step 5:

[1556] (Automatic generation of presentation materials) The server sends all user responses to the generation AI, which then automatically generates presentation materials. The generated materials are sent back to the server and presented to the user through the display means of the smart glasses.

[1557] Input: User answer

[1558] Data processing: Data generation

[1559] Output: Generated presentation materials

[1560] Step 6:

[1561] (Final confirmation and corrections) The user checks the presentation materials displayed on the smart glasses and makes any necessary corrections by voice or eye contact. The server sends these correction instructions to the generation AI, which then regenerates the corrected materials. The corrected materials are then sent back to the server and presented to the user again.

[1562] Input: Correction instructions

[1563] Data processing: Reflection of correction instructions, regeneration

[1564] Output: Revised presentation

[1565] Step 7:

[1566] (Final Output) The user finally checks the presentation materials to their satisfaction and clicks the final download link through the display means of the smart glasses. The server provides the materials in a downloadable format, and the user downloads the materials.

[1567] Input: Download instructions

[1568] Data processing: Converting materials into downloadable format

[1569] Output: Downloadable materials

[1570] 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.

[1571] User Registration and Login

[1572] 1. The user accesses the login screen

[1573] The device displays a login page, and the user enters their email address and password and submits it.

[1574] 2. Authentication and Dashboard Migration

[1575] The device sends authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server generates the user's dashboard page and returns it to the device. The device displays the dashboard page. The user clicks "Create a new presentation."

[1576] Enter the purpose of the presentation and basic information

[1577] 1. Display the basic information input form

[1578] The device displays a form where you can enter the purpose of the presentation, the target audience, and the deadline.

[1579] 2. Transmission and storage of information

[1580] The user enters information such as "New product promotion," "Management," and "3 days later," and submits it. The device sends the information to the server, which stores it in a database.

[1581] Template recommendations

[1582] 1. Template Presentation

[1583] The server sends a template request to the generation AI based on basic information. The generation AI generates multiple templates and returns them to the server. The server presents preview images and descriptions of the templates to the user. The device displays the preview images, and the user can select the appropriate template.

[1584] Conversational Questions and Emotion Recognition

[1585] 1. Posing the Question

[1586] The device displays the first question based on the selected template: "What are the features of your new product?"

[1587] 2. Emotion recognition and answer input

[1588] The device acquires the user's facial recognition data or voice data and sends it to the server, which uses an emotion engine to determine the user's emotional state.

[1589] The device receives the user's response, "A smartphone equipped with the latest AI technology," and sends it to the server.

[1590] 3. Generate and display the next question

[1591] The server requests the next question from the generation AI. The generation AI creates a question based on the emotional state recognized by the emotion engine. The server then sends the next question to the device, which displays it to the user. This process is repeated until all necessary information is collected.

[1592] Automatically generate materials and adjust them based on emotions

[1593] 1. Sending the final data

[1594] The server sends all information to the generating AI.

[1595] 2. Creation and adjustment of materials

[1596] The generative AI generates presentation materials, and the emotion engine adjusts the design and content according to the user's emotional state. The adjusted materials are then returned to the server.

[1597] 3. Presentation of materials

[1598] The server presents the generated presentation materials to the user, and the terminal displays the materials as a preview.

[1599] Final check and corrections

[1600] 1. Preview display

[1601] The terminal displays the generated presentation materials to the user.

[1602] 2. Enter the corrections and regenerate

[1603] The user types, "I would like to revise the content of slide 4." The device sends the revision instructions to the server. The server requests revision instructions from the generation AI, which then revises the document and returns it to the server. The server then presents the revised document to the user again. This process is repeated until the user is finally satisfied.

[1604] Final Output

[1605] 1. Final Download

[1606] The user checks the material to find it satisfactory and clicks on the download link.

[1607] The terminal displays a download link, and the user downloads the material.

[1608] This system allows users to efficiently create high-quality presentation materials. In particular, by utilizing the emotion engine, questions and materials are adjusted according to the user's emotional state, providing more appropriate and effective presentation materials.

[1609] The processing flow will be explained below.

[1610] Step 1:

[1611] The user accesses the login screen. The device displays the login page. The user enters their email address and password and clicks the submit button.

[1612] Step 2:

[1613] The terminal sends the entered authentication information to the server. The server accesses the database and checks whether the user's email address and password are correct. If authentication is successful, the server issues session information.

[1614] Step 3:

[1615] The server generates the user's dashboard page and returns it to the device. The device displays the dashboard page. The user clicks the "Create a new presentation" button.

[1616] Step 4:

[1617] The device displays a form for inputting the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the submit button.

[1618] Step 5:

[1619] The device sends the input information to the server. The server stores the received information in a database. The server then sends a template request to the generation AI based on the stored information.

[1620] Step 6:

[1621] The generation AI generates multiple presentation templates and returns them to the server. The server then presents preview images and descriptions of the templates to the user. The device displays the preview images, and the user selects the appropriate template.

[1622] Step 7:

[1623] The user selects a template. The device sends the selection information to the server. The server requests the generation AI to generate interactive questions based on the selected template.

[1624] Step 8:

[1625] The generation AI generates the first question and returns it to the server. The server sends the question, "Please tell me the features of the new product," to the device. The device displays the question to the user.

[1626] Step 9:

[1627] The user answers the question by typing "a smartphone equipped with the latest AI technology" and clicks the send button. The device sends the answer to the server, which then stores it in a database.

[1628] Step 10:

[1629] The device acquires the user's facial recognition data or voice data and sends it to the server, which uses an emotion engine to determine the user's emotional state.

[1630] Step 11:

[1631] The server requests the next question from the generation AI based on the emotional state recognized by the emotion engine. The generation AI returns the generated next question to the server, which then sends it to the device. The device displays the next question to the user. This step is repeated until all necessary information is collected.

[1632] Step 12:

[1633] Once all the information is collected, the server requests the generation AI to generate presentation materials. The generation AI generates the materials, and the emotion engine adjusts the design and content according to the user's emotional state. The adjusted materials are then returned to the server.

[1634] Step 13:

[1635] The server presents the generated presentation materials to the user, and the terminal displays a preview of the materials.

[1636] Step 14:

[1637] The user checks the document and indicates the parts that need to be corrected. The device sends the correction instructions to the server. The server requests the generation AI to make corrections, and the generation AI regenerates the document and returns it to the server. The server then presents the corrected document to the user again. This step is repeated until the user is finally satisfied.

[1638] Step 15:

[1639] If the user is satisfied with the final document, he / she clicks on the download link, and the terminal displays the download link for the final document, and the user downloads the document.

[1640] Example 2

[1641] 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."

[1642] Conventional presentation creation systems have the problem that even if a user inputs information and selects a template, it is difficult to generate efficient, high-quality materials in the subsequent document creation process. Another issue is that there is no system that can create optimal materials according to the user's emotional state. This makes it difficult to maximize the effectiveness of presentations, ultimately hindering business success and effective communication.

[1643] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1644] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending a plurality of presentation templates based on the information input by the input means, selection means for selecting the recommended template, question posing means for acquiring additional information in an interactive format, means for receiving the additional information and adjusting the question content based on the user's emotional state using emotion recognition technology, means for transmitting all information to a generative AI model and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on the user's requested revisions, and output means for finally outputting the presentation materials. This enables users to efficiently create high-quality presentation materials and generate materials optimal for their emotional state.

[1645] The "input means for the user to input the purpose and basic information" is an interface for the user to input basic information such as the purpose, target audience, and deadline of the presentation.

[1646] "Means for recommending multiple presentation templates" is a function that suggests the most suitable presentation template based on basic information entered by the user.

[1647] The "selection means for selecting a recommended template" is an operation method for selecting an appropriate template from a plurality of templates presented to the user.

[1648] The "means for presenting questions to acquire additional information in an interactive manner" is a function for displaying questions to collect additional information necessary for presentation through a dialogue with the user.

[1649] "Emotion recognition technology" is a technology that analyzes a user's facial recognition data and voice data to determine the user's emotional state.

[1650] The "means for adjusting the content of the question based on the emotional state" is a function for changing the content and format of the question depending on the emotional state of the user.

[1651] A "generative AI model" is an artificial intelligence model that analyzes data based on input information and generates new information and materials.

[1652] The "means for automatically generating presentation materials" is a system that automatically creates presentation materials based on collected information.

[1653] The "means for presenting the generated presentation materials to the user and regenerating them based on the user's revision requests" is a function for displaying the initially generated materials to the user and then generating the materials again based on subsequent revision requests.

[1654] The "output means for finally outputting the presentation materials" refers to a download link or file saving function for providing the user with the finalized presentation materials.

[1655] This invention relates to a system for generating presentation materials efficiently and with high quality. The system generates optimal presentation materials by allowing users to input their purpose and basic information, proposing appropriate templates, and adjusting questions based on the user's emotional state. This system is realized using a terminal, a server, and a generation AI model.

[1656] Input Method

[1657] The user accesses the system's login page from a web browser on their terminal. Authentication is performed by entering their email address and password and clicking the login button. The server verifies the authentication information using a database (e.g., MySQL), and if authentication is successful, it generates the user's dashboard and returns it to the terminal. Next, the user clicks "Create a new presentation," which displays a form for entering basic information such as the purpose of the presentation, target audience, and deadline. The user enters information such as "New product promotion," "Management," and "3 days later" into this form and submits it.

[1658] Presentation template recommendation method

[1659] The server sends a template generation request to a generation AI (e.g., OpenAI GPT-4) based on the basic information entered by the user. The generation AI generates multiple templates and returns the results to the server. The server then creates preview images and descriptions of these templates in HTML format and sends them to the device. The device then displays these preview images and descriptions to the user, providing an interface for selecting an appropriate template.

[1660] Question presentation method and emotion recognition method

[1661] When the user selects a template, the device displays the first question based on the selected template: "What are the features of the new product?" At the same time, the device acquires the user's facial recognition data and voice data and sends them to the server. The server uses emotion recognition technology (for example, Microsoft Azure Emotion API) to determine the user's emotional state. When the user enters the answer "A smartphone equipped with the latest AI technology" and submits it, this information is also sent to the server.

[1662] Information adjustment means

[1663] The server then requests the AI ​​to generate the next question, adjusting the question based on emotion recognition. The server then sends the generated question to the device, which displays it to the user. This process is repeated until all the information needed for the presentation is gathered.

[1664] A means of automatically generating presentation materials

[1665] Once all the information is collected, the server sends it to a generative AI model, which then generates presentation materials based on the collected information. The generated materials are then adjusted in design and content using emotion recognition technology. The adjusted materials are then returned to the server.

[1666] Material presentation means and reproduction means

[1667] The server sends the generated presentation materials to the device, which displays them as a preview to the user. The user checks the preview and enters, for example, "I would like to revise the contents of slide 4." The device receives the revision instructions and sends them to the server. The server then sends a regeneration instruction to the generation AI, causing it to generate the materials again. The revised materials are then returned to the server and displayed to the user via the device. This process is repeated until the user is satisfied.

[1668] Final output method

[1669] When the user finally finds the material that satisfies him, he clicks on the download link, and the terminal displays the download link, allowing the user to download the material.

[1670] The above is an embodiment of the present invention. This system allows users to efficiently and effectively create high-quality presentation materials. The following is a specific example of a prompt sentence to be input to the generative AI model:

[1671] "Please create a presentation to promote our new product. It's for management and needs to be completed in three days."

[1672] "Feature: 'Smartphone equipped with the latest AI technology', Emotion: Excitement, What should I ask next?"

[1673] These prompts will generate more specific and personalized presentation materials.

[1674] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1675] Step 1:

[1676] A user accesses the system's login page from a web browser. The user enters their email address and password and clicks the "Login" button. The terminal sends this authentication information to the server, which then verifies the user information using a database (e.g., MySQL). If authentication is successful, the server generates the user's dashboard and sends the HTML data to the terminal. The terminal receives it and displays it to the user. The input is the user's authentication information, and the output is the HTML data of the dashboard.

[1677] Step 2:

[1678] The user clicks the "Create a new presentation" button on the dashboard. The device displays a form for entering the purpose, target audience, and deadline of the presentation. The user enters information such as "New product promotion," "Management," and "3 days later," and clicks the "Submit" button. The device sends this information to the server, which saves it in a database. The input is the basic information about the presentation, and the output is a response indicating that it was saved successfully.

[1679] Step 3:

[1680] The server uses the stored basic information to send a template request to a generative AI model (e.g., OpenAI GPT-4). The generative AI model generates a template and returns its preview image and description to the server. The server receives these, formats them into HTML, and sends them to the device. The device displays multiple templates to the user and allows the user to select one. The input is the basic information, and the output is the template preview image and description.

[1681] Step 4:

[1682] The user selects a template. Based on the selected template, the device displays the first question, "What are the features of your new product?" The user answers, "A smartphone equipped with the latest AI technology." The device then acquires facial recognition data and voice data and sends them to the server. The server uses emotion recognition technology to recognize the user's emotional state. The input is the template selection and the user's emotional data, and the output is the emotional state.

[1683] Step 5:

[1684] The server requests the next question from the generative AI model and receives the question content adjusted by emotion recognition technology from the generative AI model. The new question is sent from the server to the device, which displays it to the user. The user answers the question, and the device sends the answer to the server. This process is repeated until all necessary information is collected. The input is the previous question and the user's answer, and the output is the next question.

[1685] Step 6:

[1686] After all the information is collected, the server sends it to the generative AI model, which generates the presentation materials. The generative AI model generates the materials, adjusts them based on emotion recognition technology, and returns the results to the server. The server receives the generated presentation materials and sends them to the device, which displays a preview for the user. The input is the collected information, and the output is the generated presentation materials.

[1687] Step 7:

[1688] The user checks the preview and, if necessary, inputs a correction request, such as "I would like to revise the content of slide 4." The device sends the correction request to the server. The server sends correction instructions to the generative AI model and receives a regenerated document. The new document is sent from the server to the device and previewed again by the user. This process is repeated until the user is satisfied. The input is the correction request, and the output is the revised presentation document.

[1689] Step 8:

[1690] When the user is finally satisfied with the presentation materials, he or she clicks the download link. The terminal displays the download link, allowing the user to download the materials. The input is the final confirmation and clicking the download link, and the output is the final presentation materials.

[1691] The above is the flow of specific processing steps of the program of this system.

[1692] (Application example 2)

[1693] 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."

[1694] Many conventional presentation production systems automatically generate presentations based solely on input information, without considering the user's emotional state. This makes it difficult to generate appropriate questions or materials based on the user's emotional changes, resulting in a lack of improved user experience. Furthermore, surveillance systems lack technology that uses emotion recognition to instantly issue security alerts, making it difficult to respond quickly and accurately.

[1695] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1696] In this invention, the server includes input means for a user to input a purpose and basic information, means for recommending multiple presentation templates based on the input information, selection means for selecting a recommended template, question presentation means for acquiring additional information in an interactive format, emotion recognition means for determining the user's emotional state based on the additional information and facial recognition data or voice data, a generative AI model for adjusting the questions based on the emotional state determined by the emotion recognition means, means for presenting questions generated by the generative AI model to the user, receiving the additional information, and automatically generating presentation materials, means for presenting the generated presentation materials to the user and regenerating them based on user requests for revisions, and output means for finally outputting the presentation materials. This enables appropriate question presentation and material generation that take the user's emotional state into consideration, as well as rapid and accurate security response using emotion recognition in surveillance systems.

[1697] "Input means" refers to a device or interface through which a user inputs objectives and basic information.

[1698] The "recommending means" is a device or program for recommending a plurality of presentation templates based on information input by the input means.

[1699] The "selection means" is a device or interface that allows the user to select a recommended template.

[1700] The "question presenting means" is a device or program that displays a question for acquiring additional information in an interactive manner based on the template selected by the selection means.

[1701] "Emotion recognition means" refers to a device or program for determining the emotional state of a user based on facial recognition data or voice data.

[1702] A "generative AI model" is an artificial intelligence model that tailors questions based on the emotional state determined by the emotion recognition means.

[1703] "Means for automatic generation" means a device or program for receiving additional information and generating presentation materials based on questions generated by a generative AI model.

[1704] The "regenerating means" is a device or program for presenting the generated presentation materials to the user and regenerating the materials based on the user's modification requests.

[1705] "Output means" refers to a device or program for providing the final generated presentation materials to the user in a displayable or downloadable format.

[1706] MODE FOR CARRYING OUT THE INVENTION

[1707] A specific system for implementing the present invention is configured as follows.

[1708] User Registration and Login

[1709] The device that the user accesses displays a login screen for entering an email address and password. When the user enters and submits the information, the device sends the authentication information to the server. The server accesses the database and performs authentication. If authentication is successful, the server generates a dashboard page for the user and returns it to the device. The device displays the dashboard page and allows the user to select "Create a new presentation."

[1710] Enter the purpose of the presentation and basic information

[1711] When a user clicks "Create a new presentation" on the dashboard, a basic information input form is displayed on the device. The user enters information such as the purpose of the presentation, target audience, and deadline into this form and submits it. The entered information is sent from the device to the server, which then stores it in a database.

[1712] Template recommendations

[1713] The server sends a template request to the generative AI model based on the basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends preview images and descriptions of the templates to the device, allowing the user to select one.

[1714] Conversational Questions and Emotion Recognition

[1715] After the user selects a template, the device displays the first question based on the selected template: "Please tell us the features of the new product." The device acquires facial recognition data or voice data and sends it to the server. The server uses emotion recognition means to determine the user's emotional state. The user's answer to the question displayed on the device is entered and sent to the server. The server requests the next question from the generative AI model, and a new question is generated based on the user's emotional state. This process is repeated until all necessary information is collected.

[1716] Automatically generate materials and adjust them based on emotions

[1717] The server sends all information to the generative AI model, which then generates the presentation materials. Furthermore, the emotion recognition means adjusts the design and content according to the user's emotional state. The adjusted materials are then sent back to the server, which presents them to the user. The device displays the materials as a preview.

[1718] Final check and corrections

[1719] The user previews the generated presentation materials and, if any corrections are needed, inputs instructions such as "I would like to revise the content of slide 4." The device sends this instruction to the server, which then requests corrections from the generative AI model. The generative AI model then corrects the materials and sends them back to the server. The server then presents the corrected materials to the user again. This process is repeated until the user is satisfied.

[1720] Final Output

[1721] When the user confirms the material that satisfies him and clicks on the download link, the terminal displays the download link and the user can download the material.

[1722] Hardware and software used

[1723] Hardware: Smartphones, smart glasses, head-mounted displays, robots.

[1724] Software: Python, OpenCV, Keras, and the required server and database systems.

[1725] Specific examples

[1726] For example, by installing this system at the entrance to an office, it can instantly detect suspicious or nervous individuals and send an alert to the security team.

[1727] Prompt Sentence Examples

[1728] Enter the following prompt into the generative AI model:

[1729] "Generate a template for building a security alert system based on an emotion engine. The template should be Python code that performs face detection and emotion recognition and sends an alert when an anomaly is detected. The template should use a cascade classifier and a Keras model to perform face detection and emotion recognition."

[1730] This system configuration enables flexible creation of presentation materials based on the user's emotional state and quick and accurate security response.

[1731] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1732] Step 1:

[1733] User Registration and Login

[1734] The user enters and submits their email address and password. The device sends this authentication information to the server. The server references the database and authenticates the user. If authentication is successful, the server generates a dashboard page for the user and sends its contents back to the device. The device displays the dashboard page and allows the user to select "Create a new presentation."

[1735] Input: Email address, password

[1736] Output: Dashboard page

[1737] Step 2:

[1738] Enter the purpose of the presentation and basic information

[1739] When a user clicks "Create a new presentation" on the dashboard, the device displays a form for inputting the purpose, target audience, and deadline of the presentation. The user fills out the form and submits it. The device sends this information to the server, which stores it in a database.

[1740] Input: Purpose of presentation, target audience, deadline

[1741] Output: Basic information saved

[1742] Step 3:

[1743] Template recommendations

[1744] The server sends a template request to the generative AI model based on the basic information. The generative AI model generates multiple templates and returns them to the server. The server then sends preview images and descriptions of the templates to the device, allowing the user to select one.

[1745] Input: Basic information

[1746] Output: Template preview image and description

[1747] Step 4:

[1748] Conversational Questions and Emotion Recognition

[1749] After the user selects a template, the device displays the first question: "What are the features of your new product?" The device captures facial recognition or voice data and sends it to the server. The server uses emotion recognition means to determine the user's emotional state. Based on this emotional state, the generative AI model generates the next question and returns it to the server. The device displays the next question, and the user enters and submits the answer. This process is repeated until all necessary information is collected.

[1750] Input: Facial recognition data or voice data, user response

[1751] Output: Next question based on emotional state

[1752] Step 5:

[1753] Automatically generate materials and adjust them based on emotions

[1754] The server sends all information to a generative AI model, which then generates the presentation materials. The emotion recognition means adjusts the design and content according to the user's emotional state. The adjusted materials are then sent back to the server, which then sends them to the device for the user to preview.

[1755] Input: All information

[1756] Output: Adjusted presentation material

[1757] Step 6:

[1758] Final check and corrections

[1759] The user previews the generated presentation materials and inputs any necessary corrections. The device sends these instructions to the server, which then requests corrections from the generative AI model. The generative AI model then corrects the materials and sends them back to the server. The server then presents the corrected materials to the user again. This process is repeated until the user is satisfied.

[1760] Input: Correction instructions

[1761] Output: Revised presentation

[1762] Step 7:

[1763] Final Output

[1764] When the user confirms the material that satisfies him and clicks on the download link, the terminal displays the download link and the user can download the material.

[1765] Input: Click on the download link

[1766] Output: Downloaded presentation

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] 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.

[1773] 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).

[1774] 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.

[1775] 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."

[1776] 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.

[1777] 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).

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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.

[1785] 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.

[1786] 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.

[1787] 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 ...

Claims

1. an input means for a user to input purpose and basic information; means for recommending a plurality of presentation templates based on the information input by the input means; a selection means for selecting the recommended template; a question presentation means for interactively obtaining additional information based on the template selected by the selection means; means for receiving the additional information and automatically generating presentation materials; means for presenting the generated presentation materials to a user and regenerating them based on a modification request from the user; Output means for finally outputting the presentation materials A system including:

2. 2. The system of claim 1, wherein the question submitter receives instructions to regenerate some or all of the generated presentation materials.

3. The system of claim 1 , wherein the recommended template is selected based on purpose and target audience information entered by the user.

Images