System

Abstract

A system is provided.SOLUTION: The system includes a means for inputting target information, a means for inputting commodity explanation, a means for transmitting the inputted target information and commodity explanation to a server, a means for learning past advertisement cases by the server and generating an advertisement plan easy to hit a target, a means for displaying the generated advertisement plan, a means for selecting and approving the advertisement plan by a user, a means for automatically generating a presentation material and voice on the basis of the approved advertisement plan, and a means for providing the generated presentation moving image to the user and automatically uploading it on a Web.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Modern advertising design requires sophisticated targeting and rapid production, which takes a lot of time and effort. It is also inefficient for advertising designers to come up with new ideas and create presentations for each campaign. The process of quickly generating numerous advertising proposals, selecting the best one, and then creating a presentation video based on that proposal is particularly time-consuming. There is a need to dramatically improve the efficiency of advertising design by improving this process. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. First, a means for inputting target information and a means for inputting product descriptions is provided. Next, a means for transmitting the input target information and product descriptions to a server is provided. The server has the function of learning from past advertising examples and generating advertising proposals that are likely to appeal to the target. The generated advertising proposals are displayed to the user in a card format or the like. The user has a means for selecting the most appropriate proposal from multiple advertising proposals and approving it. Based on the selected advertising proposal, presentation materials and audio are automatically generated and provided to the user in the form of a presentation video. Finally, this presentation video is automatically uploaded to the Web, enabling fast and efficient advertising design and presentation creation.

[0006] "Target information" is information that indicates the attributes (e.g., age, gender, occupation, etc.) of the consumer demographic targeted by the advertisement.

[0007] "Product description" is information that explains the characteristics and benefits of the advertised product or service.

[0008] A "server" is a computer system that processes requests from clients (terminals) and performs the necessary calculations and data processing.

[0009] An "advertising proposal" is a concrete expression of an advertising idea or concept that will resonate with the target audience (e.g., visuals, catchy slogans, etc.).

[0010] "Presentation materials" are content used to visually convey information, such as slides and images created based on advertising proposals.

[0011] A "presentation video" is content that includes presentation materials and narration and is used to visually and audibly convey an advertising proposal in video format.

[0012] "Auto-upload" is the process of automatically transferring and publishing created digital content to a designated web platform without user intervention. [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] This invention is a system that inputs and transmits target information and product descriptions, automatically generates optimal advertising proposals by referencing past advertising examples, generates presentation materials and presentation videos based on those advertising proposals, and finally automatically uploads them to the web. The specific process flow and each means are explained below.

[0035] Main processes and their operations

[0036] A means of inputting target information and product descriptions

[0037] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form.

[0038] example)

[0039] Target information: Women in their 30s, working mothers

[0040] Product description: Skin-friendly organic cosmetics

[0041] Means for sending target information and product description to the server

[0042] Terminal: Sends the entered target information and product description to the server. The data format is typically JSON.

[0043] Means for generating advertisement proposals by the server

[0044] Server: Based on the received target information and product description, the server generates optimal advertising proposals using an AI model trained from a database of past advertising cases. Ad proposals are created from multiple different perspectives, and each proposal includes visuals, catchphrases, etc.

[0045] example)

[0046] Advertisement idea 1: Elegant design using natural materials

[0047] Advertisement idea 2: Skin care that is gentle on mothers raising children

[0048] A means of displaying generated ad ideas

[0049] Terminal: Ad proposals received from the server are displayed on the user interface in card format, etc. Each ad proposal is laid out to make it easy to visually compare them.

[0050] A means of selecting and approving advertising proposals

[0051] User: Select the best ad from multiple options and approve it with a click or tap.

[0052] A means of automatically generating presentation materials and narration

[0053] Server: Using a "natural language processing tool" (for example, the API of a general office suite), the server automatically generates presentation materials based on the selected advertising proposal. The materials include product descriptions, target information, selling points, and advertising visuals. Next, an audio narration is automatically generated and incorporated into the presentation materials.

[0054] example)

[0055] Slide 1: Target Information and Product Description

[0056] Slide 2: Generated ad visual

[0057] Slide 3: Key selling points

[0058] A means to provide users with presentation videos and automatically upload them to the web

[0059] Server: The server temporarily stores the generated presentation video and provides a link or preview for the user to review. After the user has reviewed the content, they can click the approval button and the video will be automatically uploaded to the designated web platform.

[0060] This allows users to efficiently carry out a series of tasks, from generating advertising proposals to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] User: Enter target information and product description. Enter the required information in the dedicated input form and press the send button.

[0064] example)

[0065] Target information: Women in their 30s, working mothers

[0066] Product description: Skin-friendly organic cosmetics

[0067] Step 2:

[0068] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[0069] Step 3:

[0070] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[0071] Step 4:

[0072] Server: The generated multiple advertising proposals (e.g., elegant designs using natural materials, skin care products that are gentle on mothers raising children) are sent again to the device in JSON format.

[0073] Step 5:

[0074] Device: The received ad ideas are displayed in the form of cards on the user interface. Each ad idea is visually easy to understand and easy to compare.

[0075] Step 6:

[0076] User: Select the best one from the displayed ad suggestions, then click the approve button.

[0077] Step 7:

[0078] Terminal: Sends data on the advertisements selected and approved by the user to the server.

[0079] Step 8:

[0080] Server: Calls the "presentation material generation tool" and automatically generates presentation materials based on the selected advertising proposal. The materials include target information, product descriptions, advertising visuals, and selling points in slide format.

[0081] Step 9:

[0082] Server: Uses the "audio narration generation tool" to generate audio narration corresponding to the presentation materials. The generated audio file is incorporated into the presentation materials to complete the presentation video.

[0083] Step 10:

[0084] Server: Temporarily saves the completed presentation video and provides the user with a confirmation link or preview. This link is notified to the user.

[0085] Step 11:

[0086] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[0087] Step 12:

[0088] Terminal: Notifies the server of the user's final approval.

[0089] Step 13:

[0090] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[0091] Example 1

[0092] 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."

[0093] The traditional advertising creation process required a lot of manual work, which was time-consuming and labor-intensive. It was also difficult to predict the effectiveness of advertising proposals, making it difficult to quickly create advertisements that effectively appeal to the target audience. To solve these problems, a system was needed that could automatically generate advertising proposals and automatically create presentation materials and presentation videos based on those proposals.

[0094] 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.

[0095] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the server, means for the server to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, means for providing the generated presentation video to the user and automatically uploading it to the Web, means for displaying multiple advertising proposals in a card format for easy visual comparison, and means for automatically generating audio narration and incorporating it into the presentation materials.This streamlines the process from generating advertising proposals to creating presentation videos and uploading them to the Web, making it possible to quickly create advertisements that effectively appeal to the target.

[0096] The "means for inputting target information" is an interface that allows users to input information about a specific target demographic (e.g., age, gender, occupation, etc.).

[0097] The "means for inputting product description" is an interface that allows a user to input the features and benefits of a particular product.

[0098] The "means for transmitting target information and product description to the server" is a mechanism for transmitting the target information and product description entered by the user to the server.

[0099] "A means for the server to learn from past advertising examples and generate advertising proposals that are likely to resonate with the target" refers to a function in which the server uses an AI model based on past advertising data to generate optimal advertising proposals.

[0100] A "means for displaying generated ad suggestions" is a mechanism for displaying the server-generated ad suggestions in a user interface.

[0101] The "means for user to select and approve advertising proposals" is an interface that allows the user to select the most suitable one from multiple advertising proposals and confirm the selection.

[0102] The "means for automatically generating presentation materials and audio based on the approved advertising proposal" is a function for automatically generating presentation materials and audio narration based on the selected advertising proposal.

[0103] "Means for providing the generated presentation video to the user and automatically uploading it to the web" refers to a function that provides the created presentation video in a form that the user can check, and automatically uploads it to the web after approval.

[0104] The "means for displaying multiple advertising proposals in a card format for easy visual comparison" is an interface that displays the generated advertising proposals in a card format, allowing the user to intuitively compare them.

[0105] A "means for automatically generating audio narration and incorporating it into presentation materials" is an automated process that converts specified text into audio and integrates the audio into presentation materials.

[0106] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the proposals, which are then automatically uploaded to the web. This system is primarily composed of three main components: the user, the terminal, and the server.

[0107] A means of inputting target information and product descriptions

[0108] Users enter target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into a dedicated input form. The input form is provided by a web application or a dedicated desktop application.

[0109] Example: A user fills in a form with "Female, 30s, working mom" and then "Skin-friendly organic cosmetics."

[0110] Means for sending target information and product description to the server

[0111] The device sends the entered target information and product description to the server. The data format is generally JSON. By pressing the send button, the data is sent to the server as an HTTP POST request.

[0112] Means for generating advertisement proposals by the server

[0113] The server generates optimal ad proposals based on the received target information and product description using a generative AI model (e.g., GPT-4 (registered trademark)) trained from a database of past advertising cases. Ad proposals are created from multiple different perspectives, and each proposal includes visuals, catchphrases, etc.

[0114] Example prompt sentence:

[0115] "Generate an ad proposal that appeals to working mothers in their 30s. The product description is about organic cosmetics that are gentle on the skin."

[0116] A means of displaying generated ad ideas

[0117] The terminal displays the ad proposals received from the server in a card format on the user interface, with each proposal laid out in a way that makes it easy to visually compare them.

[0118] A means of selecting and approving advertising proposals

[0119] The user selects and approves the best ad from multiple ad proposals by tapping or clicking on the ad proposal card and finally pressing the "Approve" button.

[0120] A means of automatically generating presentation materials and narration

[0121] The server automatically generates presentation materials based on the selected advertising proposal. Using natural language processing tools (e.g., MICROSOFT® OFFICE® API or Google® Docs API), the materials include product descriptions, target information, selling points, advertising visuals, etc. Additionally, audio narration is automatically generated and incorporated into the presentation materials.

[0122] Example: The server forms a prompt sentence and instructs the natural language processing tool, "Generate presentation materials based on the selected advertising proposal. The materials should include product descriptions, target information, selling points, and advertising visuals."

[0123] Provision of presentation videos and automatic uploading to the web

[0124] The server temporarily saves the generated presentation video and provides a link or preview for the user to review. Once the user confirms the content and finally presses the "Approve" button, the video is automatically uploaded to the designated web platform (e.g., YouTube (registered trademark), Vimeo).

[0125] This allows users to efficiently carry out a series of tasks, from generating advertising proposals to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1:

[0128] Enter target information and product description

[0129] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form.

[0130] Specific actions: Access the web application or dedicated desktop application, enter target information such as "Woman in her 30s, working mother," and then enter the product description as "Skin-friendly organic cosmetics."

[0131] Input and Output: Target information and product description are input and this is output as a dataset for processing in the next step.

[0132] Step 2:

[0133] Sending target information and product descriptions

[0134] Terminal: Sends the entered target information and product description to the server.

[0135] Specific operation: When you click the send button, the device will send the target information and product description in JSON format to the server. The data will be sent as an HTTP POST request.

[0136] Input and Output: User input data is taken into the terminal, structured in JSON format, and sent to the server.

[0137] Step 3:

[0138] Server-generated advertising proposals

[0139] Server: Based on the received target information and product description, the optimal advertising proposal is generated using a generative AI model (e.g., GPT-4) trained from a database of past advertising cases.

[0140] Specific operation: The server creates a prompt sentence and sends it to the AI ​​model: "Please generate an ad proposal that appeals to working mothers in their 30s. The product description is organic cosmetics that are gentle on the skin." The AI ​​model generates multiple optimal ad proposals from each prompt and outputs ad proposals including visuals and catchphrases.

[0141] Input and output: The server creates a prompt based on the target information and product description received, and inputs it into the generative AI model. The generated ad proposals are output as a dataset to be displayed in the next step.

[0142] Step 4:

[0143] View generated ad ideas

[0144] Terminal: Displays the advertising proposals received from the server in the form of cards on the user interface.

[0145] What it does: Ad ideas are displayed on the screen as cards, laid out for easy visual comparison. Hovering over each card will pop up more information.

[0146] Input and Output: Receives ad proposal data from the server and displays it in a card-style UI, allowing users to visually compare ad proposals.

[0147] Step 5:

[0148] Selection and Approval of Ad Proposals

[0149] User: Selects and approves the best ad from multiple options.

[0150] Specific actions: Click on the ad card to select it, and finally click the "Approve" button.

[0151] Input and Output: The user selects one of the displayed advertisement proposals, and the selected advertisement proposal is sent to the server.

[0152] Step 6:

[0153] Automatic generation of presentation materials and narration

[0154] Server: Automatically generates presentation materials based on the selected advertising proposal. Using natural language processing tools (e.g., Microsoft Office API or Google Docs API), the materials include product descriptions, target information, selling points, advertising visuals, etc. Additionally, automatically generates voice narration and incorporates it into the presentation materials.

[0155] Specific operation: The server creates a prompt sentence and commands the natural language processing tool, "Generate presentation materials based on the selected advertising proposal. The materials should include product descriptions, target information, selling points, and advertising visuals." The generated materials are then integrated with the narration to create a presentation video.

[0156] Input and Output: The system takes the user's selected advertising proposal as input, generates presentation materials and audio narration based on it, and outputs the final presentation video.

[0157] Step 7:

[0158] Providing presentation videos and automatically uploading them to the web

[0159] Server: The server temporarily stores the generated presentation video and provides a link or preview for the user to review. Once the user confirms the content and finally presses the "Approve" button, the video is automatically uploaded to the designated web platform (e.g., YouTube, Vimeo).

[0160] Specific operation: A link to the generated presentation video is generated and provided to the user. The user clicks the link to view a preview of the video. When the user clicks the "Approve" button, the video is uploaded to the specified web platform.

[0161] Input and Output: We treat the generated presentation video as input and provide it to the user, who will upload it to the web platform after confirmation.

[0162] (Application example 1)

[0163] 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."

[0164] In the advertising industry, it is important to quickly generate optimal advertising proposals for each target audience and create effective presentation materials and videos. However, many companies rely on manual work that requires time and effort, and there is a need for greater efficiency. Furthermore, with previous systems, it was difficult for marketers to easily use smartphone apps to create and upload advertising proposals. Therefore, there is a need for an efficient system that can solve these issues.

[0165] 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.

[0166] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the server in JSON format, means for using an AI model to learn from past advertising cases and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals in card format, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, means for providing the generated presentation video to the user and automatically uploading it to the Web, and means for functioning as a smartphone application for marketers. This enables marketers to efficiently input target information and product descriptions, generate optimal advertising proposals using the AI ​​model, and quickly create presentation materials and presentation videos and upload them to the Web.

[0167] "Target information" refers to information about consumers targeted by advertising (e.g., age, gender, occupation, etc.).

[0168] "Product description" is information that indicates the features and benefits of the advertised product.

[0169] A "server" is a computer system that receives and processes data.

[0170] "JSON format" is a data description language that structures and expresses data in text format.

[0171] An "AI model" is an artificial intelligence algorithm that learns from past data and makes predictions and generates new data.

[0172] An "advertising proposal" is a proposal that includes an advertising design and catchy slogan that will appeal to the target audience.

[0173] The "card format" is a rectangular display format for displaying information in a visually easy-to-understand manner.

[0174] "Presentation materials" are slide-format documents summarizing the contents of an advertising proposal.

[0175] "Audio" refers to a narration audio accompanying the presentation materials to explain the contents.

[0176] A "presentation video" is a video presentation that incorporates audio narration.

[0177] A "smartphone application" is software that runs on a smartphone and provides specific functions or services.

[0178] A "web platform" is a system or site that provides services over the Internet.

[0179] MODE FOR CARRYING OUT THE INVENTION

[0180] The present invention provides a system that enables marketing personnel to efficiently generate advertising proposals and create presentation materials and presentation videos. The device configuration and processing procedure are described below in detail.

[0181] System Configuration

[0182] Hardware:

[0183] Smartphone

[0184] server

[0185] Cloud Storage

[0186] software:

[0187] Python

[0188] Flask

[0189] OpenAI(registered trademark) API

[0190] Database (e.g. MongoDB)

[0191] User interface frameworks (e.g., React Native)

[0192] Data entry and submission

[0193] Users use a dedicated smartphone application to input target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits). The input data is converted into JSON format and sent to the server.

[0194] Generate advertising proposals

[0195] The server generates ad suggestions using OpenAI's AI model based on the target information and product description it receives. Specifically, it passes data in the following text format as a prompt to the AI ​​model.

[0196] Example prompt sentence:

[0197] Target information: Women in their 30s, working mothers. Product description: Organic cosmetics that are gentle on the skin. Please refer to past advertising examples to generate optimal advertising proposals.

[0198] View and approve ad proposals

[0199] The generated ad proposals are displayed in the form of cards on the user interface of the smartphone application, and the user can select the best one from multiple proposals and approve it with a tap or click.

[0200] Presentation and video generation

[0201] Based on the advertising proposal approved by the user, the server automatically generates presentation materials and audio narration. The presentation materials include product descriptions, target information, selling points, advertising visuals, etc. Next, the server generates audio narration and incorporates it into the presentation materials to create a presentation video.

[0202] Providing and uploading videos

[0203] The generated presentation video is temporarily stored in cloud storage, where users can preview it or view it via a link. If there are no problems with the content, the presentation video will be automatically uploaded to the designated web platform with the user's approval.

[0204] This allows marketers to efficiently and quickly input target information and product descriptions, use AI models to generate optimal advertising ideas, and quickly create presentation materials and videos, which can then be uploaded to the web.

[0205] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0206] Step 1:

[0207] The user enters target information and product description into the smartphone application. The entered data is converted into JSON format.

[0208] Input: Target information (e.g., age, gender, occupation), product description (e.g., product features, benefits)

[0209] Output: JSON format data (e.g., {"target_info": "Woman in her 30s, working mother", "product_desc": "Skin-friendly organic cosmetics"})

[0210] Step 2:

[0211] The device sends JSON format data to the server.

[0212] Input: JSON format data

[0213] Output: Data sent to the server

[0214] Step 3:

[0215] The server converts the received data into a prompt sentence to be passed to the AI ​​model. The prompt sentence is in text format based on the target information and product description.

[0216] Input: JSON format data

[0217] Output: Prompt text (e.g., "Target information: women in their 30s, working mothers, product description: organic cosmetics that are gentle on the skin. Please generate the optimal ad proposal by referring to past advertising examples.")

[0218] Step 4:

[0219] The server uses OpenAI's API to input the prompt text into the AI ​​model and generate advertising proposals.

[0220] Input: prompt statement

[0221] Output: Generated ad ideas (e.g. text of multiple ad ideas)

[0222] Step 5:

[0223] The server returns the generated advertising proposals to the smartphone application.

[0224] Input: Generated ad ideas

[0225] Output: Data for the user interface

[0226] Step 6:

[0227] The device displays ad suggestions in the form of cards on the user interface, and the user can select and approve the best one from multiple ad suggestions.

[0228] Input: Data for the user interface

[0229] Output: ID of the ad proposal that the user accepted

[0230] Step 7:

[0231] The server automatically generates presentation materials and audio narration based on the ID of the approved advertising proposal.

[0232] Input: Approved ad proposal ID

[0233] Output: Presentation materials, audio narration

[0234] Step 8:

[0235] The server generates a presentation video based on the presentation materials and audio narration, and the generated presentation video is saved in cloud storage.

[0236] Input: Presentation materials, voice narration

[0237] Output: Presentation video

[0238] Step 9:

[0239] A preview link for the presentation video will be provided to the user, who can then review the video and approve it if there are no issues with the content.

[0240] Input: Preview link of presentation video

[0241] Output: Acknowledgement from the user

[0242] Step 10:

[0243] The server will automatically upload the approved presentation video to the designated web platform.

[0244] Input: Approval from the user

[0245] Output: Presentation video uploaded to the web platform

[0246] 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.

[0247] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the advertising proposals, which are then automatically uploaded to the web. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and collect, analyze, and reflect emotional data when selecting advertising proposals.

[0248] Main processes and their operations

[0249] A means of inputting target information and product descriptions

[0250] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form and press the send button.

[0251] example)

[0252] Target information: Women in their 30s, working mothers

[0253] Product description: Skin-friendly organic cosmetics

[0254] Means for sending target information and product description to the server

[0255] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[0256] Means for generating advertisement proposals by the server

[0257] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[0258] A means of recognizing user emotions with an emotion engine

[0259] Device: The generated ad ideas are displayed in the form of cards on the user interface. At the same time, an emotion engine is activated to collect emotional data from facial expressions, tone of voice, etc. while the user is viewing the ad ideas.

[0260] example)

[0261] Advertisement idea 1: Elegant design using natural materials

[0262] Advertisement idea 2: Skin care that is gentle on mothers raising children

[0263] Analyzing sentiment data and adjusting advertising proposals

[0264] Server: Analyzes the emotional data collected by the emotion engine and evaluates the effectiveness of advertising proposals. It has the ability to automatically adjust parts of advertising proposals (visuals and catchphrases) based on user emotions.

[0265] A means of selecting and approving advertising proposals

[0266] User: Select the best ad from the displayed suggestions. After selecting, click the approve button. At this point, a final analysis of the sentiment data is also performed.

[0267] A means of automatically generating presentation materials and narration

[0268] Server: Calls up the "natural language processing tool" and automatically generates presentation materials based on the selected advertising proposal and emotional data. The materials include target information, product descriptions, advertising visuals, and selling points in slide format. Next, an audio narration is automatically generated and incorporated into the presentation materials.

[0269] example)

[0270] Slide 1: Target Information and Product Description

[0271] Slide 2: Generated ad visual

[0272] Slide 3: Key selling points

[0273] A means to provide users with presentation videos and automatically upload them to the web

[0274] Server: Temporarily saves the generated presentation video and provides the user with a confirmation link or preview. Notifies the user of this link.

[0275] Final approval and upload of presentation video

[0276] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[0277] Terminal: Notifies the server of the user's final approval.

[0278] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[0279] This allows users to efficiently carry out a series of tasks, from generating advertising proposals incorporating emotion data to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[0280] The processing flow will be explained below.

[0281] Specific processing steps of the function

[0282] Step 1:

[0283] User: Enter target information and product description. Enter the required information in the dedicated input form (e.g., female in her 30s, skin-friendly organic cosmetics) and press the send button.

[0284] example)

[0285] Target information: Women in their 30s, working mothers

[0286] Product description: Skin-friendly organic cosmetics

[0287] Step 2:

[0288] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[0289] Step 3:

[0290] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[0291] Step 4:

[0292] Server: The generated multiple advertising proposals (e.g., elegant designs using natural materials, skin care products that are gentle on mothers raising children) are sent again to the device in JSON format.

[0293] Step 5:

[0294] Terminal: The received ad proposal is displayed in the form of a card on the user interface. At the same time, an emotion engine is activated to collect emotional data in real time from facial expressions, tone of voice, etc. while the user is viewing the ad proposal.

[0295] Step 6:

[0296] User: Expresses their feelings about the displayed ad suggestions and selects the most suitable one.

[0297] Step 7:

[0298] Emotion Engine: While the user is viewing the ad proposal, emotional data is collected from facial expressions, voice, mouse movements, etc. The collected data is temporarily stored.

[0299] Step 8:

[0300] Server: Analyzes the emotion data collected by the emotion engine and evaluates the effectiveness of the ad suggestions until the user makes a selection. If necessary, it resends optimized ad suggestions to the device.

[0301] Step 9:

[0302] User: Review the optimized ad proposals and approve the final ad proposal.

[0303] Step 10:

[0304] Terminal: After receiving the user's approval, the data of the selected advertisement proposal is sent back to the server.

[0305] Step 11:

[0306] Server: Calls the "presentation material generation tool" and "voice narration generation tool" and automatically generates presentation materials and narration based on the selected advertising proposal and emotion data.

[0307] example)

[0308] Slide 1: Target Information and Product Description

[0309] Slide 2: Generated ad visual

[0310] Slide 3: Key selling points

[0311] Step 12:

[0312] Server: Incorporates narration into presentation materials, completes the presentation video, and temporarily saves the completed presentation video.

[0313] Step 13:

[0314] Server: Provide the user with a confirmation link or preview of the completed presentation video. Notify the user of this link.

[0315] Step 14:

[0316] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[0317] Step 15:

[0318] Terminal: Notifies the server of the user's final approval.

[0319] Step 16:

[0320] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[0321] This series of processes allows users to efficiently complete tasks from generating advertising proposals incorporating emotional data to creating presentations and finally uploading them to the web.

[0322] Example 2

[0323] 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."

[0324] Conventional ad generation systems have had issues with incorporating user emotional data to evaluate the effectiveness of ads, and with insufficient feedback to optimize the accuracy and effectiveness of ads. Furthermore, there is a lack of an efficient way to automatically create presentation materials and videos based on the generated ad ideas and automatically upload them to a network.

[0325] 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.

[0326] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to a computer connected to a network, means for the computer to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for collecting user emotion data and evaluating the effectiveness of the advertising proposals, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, and means for providing the generated presentation video to the user and automatically uploading it to the network. This makes it possible to generate advertising proposals that reflect the user's emotions, and further makes it possible to efficiently create presentation materials and presentation videos based on the advertising proposals and share them seamlessly on the network.

[0327] "Target information" refers to attribute data such as age, gender, and occupation of specific advertising targets.

[0328] "Product description" refers to detailed information about the product being advertised, such as its features and benefits.

[0329] A "networked computer" refers to a computing device that is capable of communicating over a network, such as the Internet.

[0330] "Advertising Proposal" refers to an advertising idea or plan generated based on target information and product description.

[0331] "Emotion data" refers to data related to emotions collected from the user's facial expressions, tone of voice, etc.

[0332] "Presentation materials" refers to slide-format materials created to explain the contents of an advertising proposal.

[0333] "Natural language processing tools" refers to artificial intelligence techniques used to analyze, generate, and transform text data.

[0334] "Presentation video" refers to a video presentation created by incorporating audio narration into presentation materials.

[0335] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the advertising proposals, which are then automatically uploaded to the web. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and collect, analyze, and reflect emotional data when selecting advertising proposals.

[0336] The user first enters target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into a dedicated input form, and then presses the submit button. At this time, appropriate validation is performed for each field in the input form. As a specific example, the target is working mothers in their 30s, and the product description is entered as "skin-friendly organic cosmetics."

[0337] The terminal packages the information entered by the user in JSON format and sends it to the server as an HTTP request. The JSON data is generated by a JavaScript function. For example, the following prompt text can be generated:

[0338] "Please create an ad idea for organic cosmetics that are gentle on the skin and target working mothers in their 30s. Please refer to past success stories."

[0339] The server analyzes the received target information and product description and calls up a generative AI model (e.g., OpenAI GPT-3 (registered trademark)) installed on the server. The AI ​​model has learned from past advertising case data and generates advertising proposals that are likely to resonate with the target based on the input data.

[0340] The generated ad suggestions are sent to the device and displayed in the form of cards on the user interface. At the same time, the device activates an emotion engine (e.g., Microsoft Azure® Cognitive Services) to collect emotion data through facial expressions and tone of voice while the user is viewing the ad suggestions. Specific examples of generated ad suggestions include:

[0341] Advertisement idea 1: Elegant design using natural materials

[0342] Advertisement idea 2: Skin care that is gentle on mothers raising children

[0343] The server analyzes the emotional data sent from the device and evaluates the effectiveness of the proposed ad. This analysis uses collected emotional data (e.g., frequency of smiling, tone of voice). If necessary, elements of the proposed ad, such as visuals and catchy copy, are adjusted.

[0344] The user selects the best one from the multiple ad ideas provided and clicks the approval button. The selected ad idea and the final emotion data are sent to the server, and the system proceeds to the next step.

[0345] The server calls a natural language processing tool (e.g., OpenAI GPT-3) based on the selected advertising proposal and emotion data to automatically generate presentation materials. The materials are composed of slides and include target information, product descriptions, advertising visuals, and selling points. A voice synthesis engine (e.g., Amazon Polly) is also used to generate narration voices, which are incorporated into the presentation materials. For example, the following slides are generated:

[0346] Slide 1: Target Information and Product Description

[0347] Slide 2: Generated ad visual

[0348] Slide 3: Key selling points

[0349] The server temporarily saves the generated presentation video and provides a confirmation link or preview to the user. If the user checks the link or preview and determines that the content is OK, they click the final approval button.

[0350] Once final approval is given, the device notifies the server, which then automatically uploads the approved presentation video to a designated web platform (e.g., YouTube, Vimeo). If the upload is successful, the URL is sent back to the user's device.

[0351] This allows users to efficiently create advertisement proposals, create presentations, and finally upload them to the web. The system of the present invention is expected to speed up advertisement design, improve efficiency, and improve the quality of advertisement design.

[0352] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0353] Step 1:

[0354] The user enters target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into the input form and presses the submit button. The input data is for target information to be "women in their 30s, working mothers" and for product description to be "skin-friendly organic cosmetics." The input data is formatted as a JSON-formatted object.

[0355] Input: Target information, product description

[0356] Output: JSON format object (target information and product description)

[0357] Step 2:

[0358] The device packages the target information and product description entered by the user and sends it to a computer (server) connected to the network using an HTTP POST request, generating JSON format data using JavaScript.

[0359] Input: JSON formatted object

[0360] Output: HTTP POST request

[0361] Step 3:

[0362] The server analyzes the HTTP POST request received from the device and obtains target information and product description in JSON format. It then invokes a generative AI model (e.g., OpenAI GPT-3) to generate a prompt based on past advertising case data. The generated prompt is then input into the AI ​​model to generate advertising proposals.

[0363] Input: Target information and product description in JSON format

[0364] Output: Generated ad ideas

[0365] Step 4:

[0366] The device displays the generated ad suggestions received from the server in the form of cards on the user interface. At the same time, it launches an emotion engine (e.g., Microsoft Azure Cognitive Services) to collect facial expressions and tone of voice while the user is viewing the ad suggestions. The collected emotion data is temporarily stored in a local database.

[0367] Input: Generated ad ideas

[0368] Output: Display on the user interface, collected emotion data

[0369] Step 5:

[0370] The server analyzes the emotional data sent from the device and evaluates the effectiveness of the proposed advertisements. Specifically, it automatically adjusts the visuals and catchy copy of the proposed advertisements based on emotional data such as the frequency of smiling and tone of voice.

[0371] Input: Emotion data

[0372] Output: Adjusted ad proposals

[0373] Step 6:

[0374] The user selects the best ad from the multiple ad ideas displayed and clicks the approval button. The selected ad idea and the final emotion data are sent to the server for final analysis.

[0375] Input: Multiple ad ideas

[0376] Output: Selected ad ideas and final sentiment data

[0377] Step 7:

[0378] The server calls a natural language processing tool (e.g., OpenAI GPT-3) based on the selected advertising proposal and emotion data to automatically generate presentation materials. These materials are in the form of slides and include target information, product descriptions, advertising visuals, and selling points. Narration is also generated using a speech synthesis engine (e.g., Amazon Polly) and incorporated into the presentation materials.

[0379] Input: Selected ad idea, emotion data

[0380] Output: Generated presentation materials and narration audio

[0381] Step 8:

[0382] The server temporarily saves the generated presentation video and provides the user with a confirmation link or preview. The user checks the link or preview and confirms that there are no problems with the content. If there are no problems, the user clicks the final approval button.

[0383] Input: Generated presentation video

[0384] Output: Confirmation link or preview

[0385] Step 9:

[0386] The device notifies the server that the user has given final approval. The server then automatically uploads the approved presentation video to a designated web platform (e.g., YouTube, Vimeo). If the upload is successful, the URL is sent back to the device.

[0387] Input: Final approval information

[0388] Output: URL on the web platform

[0389] (Application example 2)

[0390] 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."

[0391] Conventional ad generation systems have difficulty reflecting user emotional data when generating ad proposals, making it difficult to provide optimal ad proposals for the target audience. Furthermore, there is no way to evaluate and adjust the effectiveness of generated ad proposals in real time, meaning users are unable to obtain sufficient information when selecting the optimal ad proposal. Furthermore, the process from creating ad proposals to generating presentation materials and uploading them to the web is cumbersome, making it necessary to perform the process efficiently.

[0392] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the information processing device, means for the information processing device to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for the user to select and approve the advertising proposals, means for collecting user emotion data while the generated advertising proposals are displayed, means for the information processing device to analyze the collected emotion data and adjust the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, and means for providing the generated presentation video to the user and automatically uploading it to the Web. This makes it possible to generate effective advertising proposals based on user emotion data, evaluate and adjust the advertising proposals in real time, and improve the efficiency of the entire process.

[0393] "Target information" refers to information about the person who is the target of the advertisement, specifically data such as age, gender, and occupation.

[0394] "Product description" is information that describes the features and benefits of the advertised product.

[0395] "Information processing device" refers to a computer or server that receives input data and processes and analyzes it.

[0396] "Past advertising cases" refers to data about previous advertising campaigns and their results.

[0397] An "advertising proposal" is an advertising idea or design created to effectively appeal to a target audience.

[0398] "Emotional data" refers to data relating to the user's psychological reactions collected from facial expressions, tone of voice, and the like.

[0399] "Presentation materials" are materials used to explain advertising proposals and are provided in slide or document format.

[0400] "Audio" refers to the narration and explanatory audio added to presentation materials.

[0401] The "generated presentation video" is video content that is automatically generated based on the advertising proposal.

[0402] "Automatic uploading to the web" is the process of automatically uploading the generated presentation video to a designated platform on the Internet.

[0403] MODE FOR CARRYING OUT THE INVENTION

[0404] To implement this invention, an advertising planner application using a smartphone is constructed. The program of this system and its processing are explained below.

[0405] Hardware and software used

[0406] Hardware

[0407] Smartphone (iOS or ANDROID (registered trademark))

[0408] software

[0409] Frontend: React Native, Expo

[0410] Backend: Node.js, Express

[0411] Database: MongoDB

[0412] AI model: Python (TENSORFLOW (registered trademark), PyTorch)

[0413] Emotion engine: OpenCV, DLIB

[0414] Natural Language Processing: GPT-4 API (OpenAI)

[0415] System processing flow

[0416] 1. Enter target information and product description:

[0417] Users enter target information (age, gender, occupation) and product description (product features, benefits) into the smartphone app's input form. This data is sent in JSON format to a back-end information processing device.

[0418] 2. Generate advertising ideas:

[0419] The information processing device calls the generative AI model (GPT-4) and generates optimal advertising proposals based on past advertising case data. At this time, the information processing device refers to the advertising case data stored in the database.

[0420] 3. Launching the emotion engine and collecting emotion data:

[0421] The app displays advertising ideas in the form of cards on the user interface. At the same time, it uses the smartphone's camera and microphone to collect the user's emotional data (facial expressions, tone of voice). It uses OpenCV and DLIB to recognize facial expressions, and this data is sent to an information processing device in real time.

[0422] 4. Analyze sentiment data and adjust advertising proposals:

[0423] The information processing device analyzes the collected emotional data, evaluates the effectiveness of the ad proposal, and, if necessary, automatically adjusts parts of the ad proposal (visuals and catchphrases) using a generative AI model.

[0424] 5. Automatic generation of presentation materials and narration:

[0425] Based on the selected advertising proposal, the information processing device generates presentation materials and narration using natural language processing tools (GPT-4 API).

[0426] 6. Providing a video of your presentation and uploading it to the web:

[0427] The generated presentation video is temporarily saved and a confirmation link is provided to the user. After the user gives their final approval, the presentation video is automatically uploaded to the designated web platform and the user is notified of the URL upon successful upload.

[0428] Examples of concrete examples and prompts

[0429] Specific examples

[0430] Target information: Women in their 30s, working mothers

[0431] Product description: Skin-friendly organic cosmetics

[0432] Prompt Sentence Examples

[0433] Target Information:

[0434] Age: 30s

[0435] Gender: Female

[0436] Occupation: Working mom

[0437] Product Description:

[0438] Product name: Organic cosmetics

[0439] Feature: Gentle on the skin

[0440] Advantages: Made from natural materials

[0441] Based on this target information and product description, please refer to similar past advertising examples and generate an ad proposal that will appeal to your target. The ad proposal should include visual suggestions and a catchy copy.

[0442] In this way, by implementing the present invention, users can generate effective advertising proposals based on emotional data, evaluate and adjust the advertising proposals in real time, and streamline the entire process.

[0443] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0444] Step 1:

[0445] Input and output: The user enters target information (age, gender, occupation) and product description (product features, benefits) into the smartphone app form and presses the submit button. The entered data is sent to the backend server in JSON format.

[0446] Operation: The terminal triggers a click event on the send button, packages the target information and product description in JSON format, and sends the data to the server using an HTTP POST request.

[0447] Step 2:

[0448] Input and output: Based on the target information and product description received by the server, the generative AI model (GPT-4) is called and the optimal advertising proposal is generated using past advertising case data. The output is the generated advertising proposal.

[0449] How it works: The server parses the received data and constructs a prompt. It then calls the GPT-4 API and generates ad suggestions using this prompt as input. These ad suggestions are stored in a database and ready to be sent to the frontend.

[0450] Step 3:

[0451] Input and output: The generated ad proposals are sent to the terminal and displayed in the form of cards on the app interface. The output is the displayed ad proposals.

[0452] Operation: The server sends the generated ad proposals in JSON format to the device. The device analyzes the received data and displays the ad proposals in a card format on the user interface.

[0453] Step 4:

[0454] Input and Output: When a user views an ad, emotional data is collected using a camera and microphone. The input is the user's facial expression and tone of voice, and the output is the collected emotional data.

[0455] How it works: The device displays ad suggestions and activates the smartphone's camera and microphone, then analyzes the user's facial expressions and tone of voice using OpenCV and DLIB. The collected emotional data is sent to the server in real time.

[0456] Step 5:

[0457] Input and output: The server analyzes the collected emotional data and evaluates and adjusts the effectiveness of advertising proposals. The input is the emotional data, and the output is the adjusted advertising proposals.

[0458] How it works: The server analyzes the collected emotion data and evaluates the ad suggestions. If necessary, it calls the generative AI model again to generate adjusted ad suggestions. These adjusted ad suggestions are then presented to the user again.

[0459] Step 6:

[0460] Input and Output: The user selects and approves the best ad suggestion. The input is the user's selection, and the output is the selected ad suggestion.

[0461] Operation: The terminal records the user's selection and sends the selected ad proposal data to the server, which receives the selection data and prepares to process the information again.

[0462] Step 7:

[0463] Input and output: The server automatically generates presentation materials and audio based on the selected advertising proposal. The input is the selected advertising proposal, and the output is the generated presentation materials and audio.

[0464] How it works: Based on the selected ad proposal, the server uses natural language processing tools (GPT-4 API) to generate presentation materials. The materials include target information, product descriptions, ad visuals, and selling points in slide format. Next, audio narration is automatically generated and incorporated into the video format.

[0465] Step 8:

[0466] Input and Output: The generated presentation video is temporarily saved and a confirmation link is provided to the user. The input is the generated presentation video, and the output is the confirmation link.

[0467] How it works: The server saves the generated presentation video and sends the user a preview link before finalizing it. The user clicks the link to check the content and approve or modify it.

[0468] Step 9:

[0469] Input and Output: After the user gives their final approval, the server will automatically upload the generated presentation video to the designated web platform. The input is the user's approval, and the output is the URL of the uploaded video.

[0470] How it works: After the user gives their final approval, the server will automatically upload the presentation video to the designated web platform. If the upload is successful, the URL will be sent to the user.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] [Second embodiment]

[0475] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0476] 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.

[0477] 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).

[0478] 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.

[0479] 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.

[0480] 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).

[0481] 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.

[0482] 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.

[0483] 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.

[0484] 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.

[0485] 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.

[0486] 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."

[0487] This invention is a system that inputs and transmits target information and product descriptions, automatically generates optimal advertising proposals by referencing past advertising examples, generates presentation materials and presentation videos based on those advertising proposals, and finally automatically uploads them to the web. The specific process flow and each means are explained below.

[0488] Main processes and their operations

[0489] A means of inputting target information and product descriptions

[0490] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form.

[0491] example)

[0492] Target information: Women in their 30s, working mothers

[0493] Product description: Skin-friendly organic cosmetics

[0494] Means for sending target information and product description to the server

[0495] Terminal: Sends the entered target information and product description to the server. The data format is typically JSON.

[0496] Means for generating advertisement proposals by the server

[0497] Server: Based on the received target information and product description, the server generates optimal advertising proposals using an AI model trained from a database of past advertising cases. Ad proposals are created from multiple different perspectives, and each proposal includes visuals, catchphrases, etc.

[0498] example)

[0499] Advertisement idea 1: Elegant design using natural materials

[0500] Advertisement idea 2: Skin care that is gentle on mothers raising children

[0501] A means of displaying generated ad ideas

[0502] Terminal: Ad proposals received from the server are displayed on the user interface in card format, etc. Each ad proposal is laid out to make it easy to visually compare them.

[0503] A means of selecting and approving advertising proposals

[0504] User: Select the best ad from multiple options and approve it with a click or tap.

[0505] A means of automatically generating presentation materials and narration

[0506] Server: Using a "natural language processing tool" (for example, the API of a general office suite), the server automatically generates presentation materials based on the selected advertising proposal. The materials include product descriptions, target information, selling points, and advertising visuals. Next, an audio narration is automatically generated and incorporated into the presentation materials.

[0507] example)

[0508] Slide 1: Target Information and Product Description

[0509] Slide 2: Generated ad visual

[0510] Slide 3: Key selling points

[0511] A means to provide users with presentation videos and automatically upload them to the web

[0512] Server: The server temporarily stores the generated presentation video and provides a link or preview for the user to review. After the user has reviewed the content, they can click the approval button and the video will be automatically uploaded to the designated web platform.

[0513] This allows users to efficiently carry out a series of tasks, from generating advertising proposals to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[0514] The processing flow will be explained below.

[0515] Step 1:

[0516] User: Enter target information and product description. Enter the required information in the dedicated input form and press the send button.

[0517] example)

[0518] Target information: Women in their 30s, working mothers

[0519] Product description: Skin-friendly organic cosmetics

[0520] Step 2:

[0521] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[0522] Step 3:

[0523] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[0524] Step 4:

[0525] Server: The generated multiple advertising proposals (e.g., elegant designs using natural materials, skin care products that are gentle on mothers raising children) are sent again to the device in JSON format.

[0526] Step 5:

[0527] Device: The received ad ideas are displayed in the form of cards on the user interface. Each ad idea is visually easy to understand and easy to compare.

[0528] Step 6:

[0529] User: Select the best one from the displayed ad suggestions, then click the approve button.

[0530] Step 7:

[0531] Terminal: Sends data on the advertisements selected and approved by the user to the server.

[0532] Step 8:

[0533] Server: Calls the "presentation material generation tool" and automatically generates presentation materials based on the selected advertising proposal. The materials include target information, product descriptions, advertising visuals, and selling points in slide format.

[0534] Step 9:

[0535] Server: Uses the "audio narration generation tool" to generate audio narration corresponding to the presentation materials. The generated audio file is incorporated into the presentation materials to complete the presentation video.

[0536] Step 10:

[0537] Server: Temporarily saves the completed presentation video and provides the user with a confirmation link or preview. This link is notified to the user.

[0538] Step 11:

[0539] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[0540] Step 12:

[0541] Terminal: Notifies the server of the user's final approval.

[0542] Step 13:

[0543] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[0544] Example 1

[0545] 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."

[0546] The traditional advertising creation process required a lot of manual work, which was time-consuming and labor-intensive. It was also difficult to predict the effectiveness of advertising proposals, making it difficult to quickly create advertisements that effectively appeal to the target audience. To solve these problems, a system was needed that could automatically generate advertising proposals and automatically create presentation materials and presentation videos based on those proposals.

[0547] 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.

[0548] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the server, means for the server to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, means for providing the generated presentation video to the user and automatically uploading it to the Web, means for displaying multiple advertising proposals in a card format for easy visual comparison, and means for automatically generating audio narration and incorporating it into the presentation materials.This streamlines the process from generating advertising proposals to creating presentation videos and uploading them to the Web, making it possible to quickly create advertisements that effectively appeal to the target.

[0549] The "means for inputting target information" is an interface that allows users to input information about a specific target demographic (e.g., age, gender, occupation, etc.).

[0550] The "means for inputting product description" is an interface that allows a user to input the features and benefits of a particular product.

[0551] The "means for transmitting target information and product description to the server" is a mechanism for transmitting the target information and product description entered by the user to the server.

[0552] "A means for the server to learn from past advertising examples and generate advertising proposals that are likely to resonate with the target" refers to a function in which the server uses an AI model based on past advertising data to generate optimal advertising proposals.

[0553] A "means for displaying generated ad suggestions" is a mechanism for displaying the server-generated ad suggestions in a user interface.

[0554] The "means for user to select and approve advertising proposals" is an interface that allows the user to select the most suitable one from multiple advertising proposals and confirm the selection.

[0555] The "means for automatically generating presentation materials and audio based on the approved advertising proposal" is a function for automatically generating presentation materials and audio narration based on the selected advertising proposal.

[0556] "Means for providing the generated presentation video to the user and automatically uploading it to the web" refers to a function that provides the created presentation video in a form that the user can check, and automatically uploads it to the web after approval.

[0557] The "means for displaying multiple advertising proposals in a card format for easy visual comparison" is an interface that displays the generated advertising proposals in a card format, allowing the user to intuitively compare them.

[0558] A "means for automatically generating audio narration and incorporating it into presentation materials" is an automated process that converts specified text into audio and integrates the audio into presentation materials.

[0559] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the proposals, which are then automatically uploaded to the web. This system is primarily composed of three main components: the user, the terminal, and the server.

[0560] A means of inputting target information and product descriptions

[0561] Users enter target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into a dedicated input form. The input form is provided by a web application or a dedicated desktop application.

[0562] Example: A user fills in a form with "Female, 30s, working mom" and then "Skin-friendly organic cosmetics."

[0563] Means for sending target information and product description to the server

[0564] The device sends the entered target information and product description to the server. The data format is generally JSON. By pressing the send button, the data is sent to the server as an HTTP POST request.

[0565] Means for generating advertisement proposals by the server

[0566] The server generates optimal ad proposals based on the received target information and product description using a generative AI model (e.g., GPT-4) trained from a database of past advertising cases. Ad proposals are created from multiple different perspectives, and each proposal includes visuals, catchphrases, etc.

[0567] Example prompt sentence:

[0568] "Generate an ad proposal that appeals to working mothers in their 30s. The product description is about organic cosmetics that are gentle on the skin."

[0569] A means of displaying generated ad ideas

[0570] The terminal displays the ad proposals received from the server in a card format on the user interface, with each proposal laid out in a way that makes it easy to visually compare them.

[0571] A means of selecting and approving advertising proposals

[0572] The user selects and approves the best ad from multiple ad proposals by tapping or clicking on the ad proposal card and finally pressing the "Approve" button.

[0573] A means of automatically generating presentation materials and narration

[0574] The server automatically generates presentation materials based on the selected advertising proposal. Using natural language processing tools (e.g., Microsoft Office API or Google Docs API), the materials include product descriptions, target information, selling points, advertising visuals, etc. Additionally, audio narration is automatically generated and incorporated into the presentation materials.

[0575] Example: The server forms a prompt sentence and instructs the natural language processing tool, "Generate presentation materials based on the selected advertising proposal. The materials should include product descriptions, target information, selling points, and advertising visuals."

[0576] Provision of presentation videos and automatic uploading to the web

[0577] The server temporarily saves the generated presentation video and provides a link or preview for the user to review. Once the user confirms the content and finally presses the "Approve" button, the video is automatically uploaded to the designated web platform (e.g., YouTube, Vimeo).

[0578] This allows users to efficiently carry out a series of tasks, from generating advertising proposals to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[0579] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0580] Step 1:

[0581] Enter target information and product description

[0582] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form.

[0583] Specific actions: Access the web application or dedicated desktop application, enter target information such as "Woman in her 30s, working mother," and then enter the product description as "Skin-friendly organic cosmetics."

[0584] Input and Output: Target information and product description are input and this is output as a dataset for processing in the next step.

[0585] Step 2:

[0586] Sending target information and product descriptions

[0587] Terminal: Sends the entered target information and product description to the server.

[0588] Specific operation: When you click the send button, the device will send the target information and product description in JSON format to the server. The data will be sent as an HTTP POST request.

[0589] Input and Output: User input data is taken into the terminal, structured in JSON format, and sent to the server.

[0590] Step 3:

[0591] Server-generated advertising proposals

[0592] Server: Based on the received target information and product description, the optimal advertising proposal is generated using a generative AI model (e.g., GPT-4) trained from a database of past advertising cases.

[0593] Specific operation: The server creates a prompt sentence and sends it to the AI ​​model: "Please generate an ad proposal that appeals to working mothers in their 30s. The product description is organic cosmetics that are gentle on the skin." The AI ​​model generates multiple optimal ad proposals from each prompt and outputs ad proposals including visuals and catchphrases.

[0594] Input and output: The server creates a prompt based on the target information and product description received, and inputs it into the generative AI model. The generated ad proposals are output as a dataset to be displayed in the next step.

[0595] Step 4:

[0596] View generated ad ideas

[0597] Terminal: Displays the advertising proposals received from the server in the form of cards on the user interface.

[0598] What it does: Ad ideas are displayed on the screen as cards, laid out for easy visual comparison. Hovering over each card will pop up more information.

[0599] Input and Output: Receives ad proposal data from the server and displays it in a card-style UI, allowing users to visually compare ad proposals.

[0600] Step 5:

[0601] Selection and Approval of Ad Proposals

[0602] User: Selects and approves the best ad from multiple options.

[0603] Specific actions: Click on the ad card to select it, and finally click the "Approve" button.

[0604] Input and Output: The user selects one of the displayed advertisement proposals, and the selected advertisement proposal is sent to the server.

[0605] Step 6:

[0606] Automatic generation of presentation materials and narration

[0607] Server: Automatically generates presentation materials based on the selected advertising proposal. Using natural language processing tools (e.g., Microsoft Office API or Google Docs API), the materials include product descriptions, target information, selling points, advertising visuals, etc. Additionally, automatically generates voice narration and incorporates it into the presentation materials.

[0608] Specific operation: The server creates a prompt sentence and commands the natural language processing tool, "Generate presentation materials based on the selected advertising proposal. The materials should include product descriptions, target information, selling points, and advertising visuals." The generated materials are then integrated with the narration to create a presentation video.

[0609] Input and Output: The system takes the user's selected advertising proposal as input, generates presentation materials and audio narration based on it, and outputs the final presentation video.

[0610] Step 7:

[0611] Providing presentation videos and automatically uploading them to the web

[0612] Server: The server temporarily stores the generated presentation video and provides a link or preview for the user to review. Once the user confirms the content and finally presses the "Approve" button, the video is automatically uploaded to the designated web platform (e.g., YouTube, Vimeo).

[0613] Specific operation: A link to the generated presentation video is generated and provided to the user. The user clicks the link to view a preview of the video. When the user clicks the "Approve" button, the video is uploaded to the specified web platform.

[0614] Input and Output: We treat the generated presentation video as input and provide it to the user, who will upload it to the web platform after confirmation.

[0615] (Application example 1)

[0616] 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."

[0617] In the advertising industry, it is important to quickly generate optimal advertising proposals for each target audience and create effective presentation materials and videos. However, many companies rely on manual work that requires time and effort, and there is a need for greater efficiency. Furthermore, with previous systems, it was difficult for marketers to easily use smartphone apps to create and upload advertising proposals. Therefore, there is a need for an efficient system that can solve these issues.

[0618] 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.

[0619] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the server in JSON format, means for using an AI model to learn from past advertising cases and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals in card format, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, means for providing the generated presentation video to the user and automatically uploading it to the Web, and means for functioning as a smartphone application for marketers. This enables marketers to efficiently input target information and product descriptions, generate optimal advertising proposals using the AI ​​model, and quickly create presentation materials and presentation videos and upload them to the Web.

[0620] "Target information" refers to information about consumers targeted by advertising (e.g., age, gender, occupation, etc.).

[0621] "Product description" is information that indicates the features and benefits of the advertised product.

[0622] A "server" is a computer system that receives and processes data.

[0623] "JSON format" is a data description language that structures and expresses data in text format.

[0624] An "AI model" is an artificial intelligence algorithm that learns from past data and makes predictions and generates new data.

[0625] An "advertising proposal" is a proposal that includes an advertising design and catchy slogan that will appeal to the target audience.

[0626] The "card format" is a rectangular display format for displaying information in a visually easy-to-understand manner.

[0627] "Presentation materials" are slide-format documents summarizing the contents of an advertising proposal.

[0628] "Audio" refers to a narration audio accompanying the presentation materials to explain the contents.

[0629] A "presentation video" is a video presentation that incorporates audio narration.

[0630] A "smartphone application" is software that runs on a smartphone and provides specific functions or services.

[0631] A "web platform" is a system or site that provides services over the Internet.

[0632] MODE FOR CARRYING OUT THE INVENTION

[0633] The present invention provides a system that enables marketing personnel to efficiently generate advertising proposals and create presentation materials and presentation videos. The device configuration and processing procedure are described below in detail.

[0634] System Configuration

[0635] Hardware:

[0636] Smartphone

[0637] server

[0638] Cloud Storage

[0639] software:

[0640] Python

[0641] Flask

[0642] OpenAI API

[0643] Database (e.g. MongoDB)

[0644] User interface frameworks (e.g., React Native)

[0645] Data entry and submission

[0646] Users use a dedicated smartphone application to input target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits). The input data is converted into JSON format and sent to the server.

[0647] Generate advertising proposals

[0648] The server generates ad suggestions using OpenAI's AI model based on the target information and product description it receives. Specifically, it passes data in the following text format as a prompt to the AI ​​model.

[0649] Example prompt sentence:

[0650] Target information: Women in their 30s, working mothers. Product description: Organic cosmetics that are gentle on the skin. Please refer to past advertising examples to generate optimal advertising proposals.

[0651] View and approve ad proposals

[0652] The generated ad proposals are displayed in the form of cards on the user interface of the smartphone application, and the user can select the best one from multiple proposals and approve it with a tap or click.

[0653] Presentation and video generation

[0654] Based on the advertising proposal approved by the user, the server automatically generates presentation materials and audio narration. The presentation materials include product descriptions, target information, selling points, advertising visuals, etc. Next, the server generates audio narration and incorporates it into the presentation materials to create a presentation video.

[0655] Providing and uploading videos

[0656] The generated presentation video is temporarily stored in cloud storage, where users can preview it or view it via a link. If there are no problems with the content, the presentation video will be automatically uploaded to the designated web platform with the user's approval.

[0657] This allows marketers to efficiently and quickly input target information and product descriptions, use AI models to generate optimal advertising ideas, and quickly create presentation materials and videos, which can then be uploaded to the web.

[0658] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0659] Step 1:

[0660] The user enters target information and product description into the smartphone application. The entered data is converted into JSON format.

[0661] Input: Target information (e.g., age, gender, occupation), product description (e.g., product features, benefits)

[0662] Output: JSON format data (e.g., {"target_info": "Woman in her 30s, working mother", "product_desc": "Skin-friendly organic cosmetics"})

[0663] Step 2:

[0664] The device sends JSON format data to the server.

[0665] Input: JSON format data

[0666] Output: Data sent to the server

[0667] Step 3:

[0668] The server converts the received data into a prompt sentence to be passed to the AI ​​model. The prompt sentence is in text format based on the target information and product description.

[0669] Input: JSON format data

[0670] Output: Prompt text (e.g., "Target information: women in their 30s, working mothers, product description: organic cosmetics that are gentle on the skin. Please generate the optimal ad proposal by referring to past ad examples.")

[0671] Step 4:

[0672] The server uses OpenAI's API to input the prompt text into the AI ​​model and generate advertising proposals.

[0673] Input: prompt statement

[0674] Output: Generated ad ideas (e.g. text of multiple ad ideas)

[0675] Step 5:

[0676] The server returns the generated advertising proposals to the smartphone application.

[0677] Input: Generated ad ideas

[0678] Output: Data for the user interface

[0679] Step 6:

[0680] The device displays ad suggestions in the form of cards on the user interface, and the user can select and approve the best one from multiple ad suggestions.

[0681] Input: Data for the user interface

[0682] Output: ID of the ad proposal that the user accepted

[0683] Step 7:

[0684] The server automatically generates presentation materials and audio narration based on the ID of the approved advertising proposal.

[0685] Input: Approved ad proposal ID

[0686] Output: Presentation materials, audio narration

[0687] Step 8:

[0688] The server generates a presentation video based on the presentation materials and audio narration, and the generated presentation video is saved in cloud storage.

[0689] Input: Presentation materials, voice narration

[0690] Output: Presentation video

[0691] Step 9:

[0692] A preview link for the presentation video will be provided to the user, who can then review the video and approve it if there are no issues with the content.

[0693] Input: Preview link of presentation video

[0694] Output: Acknowledgement from the user

[0695] Step 10:

[0696] The server will automatically upload the approved presentation video to the designated web platform.

[0697] Input: Approval from the user

[0698] Output: Presentation video uploaded to the web platform

[0699] 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.

[0700] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the advertising proposals, which are then automatically uploaded to the web. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and collect, analyze, and reflect emotional data when selecting advertising proposals.

[0701] Main processes and their operations

[0702] A means of inputting target information and product descriptions

[0703] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form and press the send button.

[0704] example)

[0705] Target information: Women in their 30s, working mothers

[0706] Product description: Skin-friendly organic cosmetics

[0707] Means for sending target information and product description to the server

[0708] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[0709] Means for generating advertisement proposals by the server

[0710] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[0711] A means of recognizing user emotions with an emotion engine

[0712] Device: The generated ad ideas are displayed in the form of cards on the user interface. At the same time, an emotion engine is activated to collect emotional data from facial expressions, tone of voice, etc. while the user is viewing the ad ideas.

[0713] example)

[0714] Advertisement idea 1: Elegant design using natural materials

[0715] Advertisement idea 2: Skin care that is gentle on mothers raising children

[0716] Analyzing sentiment data and adjusting advertising proposals

[0717] Server: Analyzes the emotional data collected by the emotion engine and evaluates the effectiveness of advertising proposals. It has the ability to automatically adjust parts of advertising proposals (visuals and catchphrases) based on user emotions.

[0718] A means of selecting and approving advertising proposals

[0719] User: Select the best ad from the displayed suggestions. After selecting, click the approve button. At this point, a final analysis of the sentiment data is also performed.

[0720] A means of automatically generating presentation materials and narration

[0721] Server: Calls up the "natural language processing tool" and automatically generates presentation materials based on the selected advertising proposal and emotional data. The materials include target information, product descriptions, advertising visuals, and selling points in slide format. Next, an audio narration is automatically generated and incorporated into the presentation materials.

[0722] example)

[0723] Slide 1: Target Information and Product Description

[0724] Slide 2: Generated ad visual

[0725] Slide 3: Key selling points

[0726] A means to provide users with presentation videos and automatically upload them to the web

[0727] Server: Temporarily saves the generated presentation video and provides the user with a confirmation link or preview. Notifies the user of this link.

[0728] Final approval and upload of presentation video

[0729] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[0730] Terminal: Notifies the server of the user's final approval.

[0731] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[0732] This allows users to efficiently carry out a series of tasks, from generating advertising proposals incorporating emotion data to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[0733] The processing flow will be explained below.

[0734] Specific processing steps of the function

[0735] Step 1:

[0736] User: Enter target information and product description. Enter the required information in the dedicated input form (e.g., female in her 30s, skin-friendly organic cosmetics) and press the send button.

[0737] example)

[0738] Target information: Women in their 30s, working mothers

[0739] Product description: Skin-friendly organic cosmetics

[0740] Step 2:

[0741] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[0742] Step 3:

[0743] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[0744] Step 4:

[0745] Server: The generated multiple advertising proposals (e.g., elegant designs using natural materials, skin care products that are gentle on mothers raising children) are sent again to the device in JSON format.

[0746] Step 5:

[0747] Terminal: The received ad proposal is displayed in the form of a card on the user interface. At the same time, an emotion engine is activated to collect emotional data in real time from facial expressions, tone of voice, etc. while the user is viewing the ad proposal.

[0748] Step 6:

[0749] User: Expresses their feelings about the displayed ad suggestions and selects the most suitable one.

[0750] Step 7:

[0751] Emotion Engine: While the user is viewing the ad proposal, emotional data is collected from facial expressions, voice, mouse movements, etc. The collected data is temporarily stored.

[0752] Step 8:

[0753] Server: Analyzes the emotion data collected by the emotion engine and evaluates the effectiveness of the ad suggestions until the user makes a selection. If necessary, it resends optimized ad suggestions to the device.

[0754] Step 9:

[0755] User: Review the optimized ad proposals and approve the final ad proposal.

[0756] Step 10:

[0757] Terminal: After receiving the user's approval, the data of the selected advertisement proposal is sent back to the server.

[0758] Step 11:

[0759] Server: Calls the "presentation material generation tool" and "voice narration generation tool" and automatically generates presentation materials and narration based on the selected advertising proposal and emotion data.

[0760] example)

[0761] Slide 1: Target Information and Product Description

[0762] Slide 2: Generated ad visual

[0763] Slide 3: Key selling points

[0764] Step 12:

[0765] Server: Incorporates narration into presentation materials, completes the presentation video, and temporarily saves the completed presentation video.

[0766] Step 13:

[0767] Server: Provide the user with a confirmation link or preview of the completed presentation video. Notify the user of this link.

[0768] Step 14:

[0769] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[0770] Step 15:

[0771] Terminal: Notifies the server of the user's final approval.

[0772] Step 16:

[0773] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[0774] This series of processes allows users to efficiently complete tasks from generating advertising proposals incorporating emotional data to creating presentations and finally uploading them to the web.

[0775] Example 2

[0776] 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."

[0777] Conventional ad generation systems have had issues with incorporating user emotional data to evaluate the effectiveness of ads, and with insufficient feedback to optimize the accuracy and effectiveness of ads. Furthermore, there is a lack of an efficient way to automatically create presentation materials and videos based on the generated ad ideas and automatically upload them to a network.

[0778] 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.

[0779] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to a computer connected to a network, means for the computer to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for collecting user emotion data and evaluating the effectiveness of the advertising proposals, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, and means for providing the generated presentation video to the user and automatically uploading it to the network. This makes it possible to generate advertising proposals that reflect the user's emotions, and further makes it possible to efficiently create presentation materials and presentation videos based on the advertising proposals and share them seamlessly on the network.

[0780] "Target information" refers to attribute data such as age, gender, and occupation of specific advertising targets.

[0781] "Product description" refers to detailed information about the product being advertised, such as its features and benefits.

[0782] A "networked computer" refers to a computing device that is capable of communicating over a network, such as the Internet.

[0783] "Advertising Proposal" refers to an advertising idea or plan generated based on target information and product description.

[0784] "Emotion data" refers to data related to emotions collected from the user's facial expressions, tone of voice, etc.

[0785] "Presentation materials" refers to slide-format materials created to explain the contents of an advertising proposal.

[0786] "Natural language processing tools" refers to artificial intelligence techniques used to analyze, generate, and transform text data.

[0787] "Presentation video" refers to a video presentation created by incorporating audio narration into presentation materials.

[0788] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the advertising proposals, which are then automatically uploaded to the web. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and collect, analyze, and reflect emotional data when selecting advertising proposals.

[0789] The user first enters target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into a dedicated input form, and then presses the submit button. At this time, appropriate validation is performed for each field in the input form. As a specific example, the target is working mothers in their 30s, and the product description is entered as "skin-friendly organic cosmetics."

[0790] The terminal packages the information entered by the user in JSON format and sends it to the server as an HTTP request. The JSON data is generated by a JavaScript function. For example, you can generate a prompt like this:

[0791] "Please create an ad idea for organic cosmetics that are gentle on the skin and target working mothers in their 30s. Please refer to past success stories."

[0792] The server analyzes the received target information and product description and calls up a generative AI model (e.g., OpenAI GPT-3) installed on it. The AI ​​model has learned from past advertising case data and generates advertising ideas that are likely to resonate with the target based on the input data.

[0793] The generated ad suggestions are sent to the device and displayed in the form of cards on the user interface. At the same time, the device activates an emotion engine (e.g., Microsoft Azure Cognitive Services) to collect emotional data through facial expressions and tone of voice while the user is viewing the ad suggestions. Specific examples of generated ad suggestions include:

[0794] Advertisement idea 1: Elegant design using natural materials

[0795] Advertisement idea 2: Skin care that is gentle on mothers raising children

[0796] The server analyzes the emotional data sent from the device and evaluates the effectiveness of the proposed ad. This analysis uses collected emotional data (e.g., frequency of smiling, tone of voice). If necessary, elements of the proposed ad, such as visuals and catchy copy, are adjusted.

[0797] The user selects the best one from the multiple ad ideas provided and clicks the approval button. The selected ad idea and the final emotion data are sent to the server, and the system proceeds to the next step.

[0798] The server calls a natural language processing tool (e.g., OpenAI GPT-3) based on the selected advertising proposal and emotion data to automatically generate presentation materials. The materials are composed of slides and include target information, product descriptions, advertising visuals, and selling points. A voice synthesis engine (e.g., Amazon Polly) is also used to generate narration voices, which are incorporated into the presentation materials. For example, the following slides are generated:

[0799] Slide 1: Target Information and Product Description

[0800] Slide 2: Generated ad visual

[0801] Slide 3: Key selling points

[0802] The server temporarily saves the generated presentation video and provides a confirmation link or preview to the user. If the user checks the link or preview and determines that the content is OK, they click the final approval button.

[0803] Once final approval is given, the device notifies the server, which then automatically uploads the approved presentation video to a designated web platform (e.g., YouTube, Vimeo). If the upload is successful, the URL is sent back to the user's device.

[0804] This allows users to efficiently create advertisement proposals, create presentations, and finally upload them to the web. The system of the present invention is expected to speed up advertisement design, improve efficiency, and improve the quality of advertisement design.

[0805] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0806] Step 1:

[0807] The user enters target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into the input form and presses the submit button. The input data is for target information to be "women in their 30s, working mothers" and for product description to be "skin-friendly organic cosmetics." The input data is formatted as a JSON-formatted object.

[0808] Input: Target information, product description

[0809] Output: JSON format object (target information and product description)

[0810] Step 2:

[0811] The device packages the target information and product description entered by the user and sends it to a computer (server) connected to the network using an HTTP POST request, generating JSON format data using JavaScript.

[0812] Input: JSON formatted object

[0813] Output: HTTP POST request

[0814] Step 3:

[0815] The server analyzes the HTTP POST request received from the device and obtains target information and product description in JSON format. It then invokes a generative AI model (e.g., OpenAI GPT-3) to generate a prompt based on past advertising case data. The generated prompt is then input into the AI ​​model to generate advertising proposals.

[0816] Input: Target information and product description in JSON format

[0817] Output: Generated ad ideas

[0818] Step 4:

[0819] The device displays the generated ad suggestions received from the server in the form of cards on the user interface. At the same time, it launches an emotion engine (e.g., Microsoft Azure Cognitive Services) to collect facial expressions and tone of voice while the user is viewing the ad suggestions. The collected emotion data is temporarily stored in a local database.

[0820] Input: Generated ad ideas

[0821] Output: Display on the user interface, collected emotion data

[0822] Step 5:

[0823] The server analyzes the emotional data sent from the device and evaluates the effectiveness of the proposed advertisements. Specifically, it automatically adjusts the visuals and catchy copy of the proposed advertisements based on emotional data such as the frequency of smiling and tone of voice.

[0824] Input: Emotion data

[0825] Output: Adjusted ad proposals

[0826] Step 6:

[0827] The user selects the best ad from the multiple ad ideas displayed and clicks the approval button. The selected ad idea and the final emotion data are sent to the server for final analysis.

[0828] Input: Multiple ad ideas

[0829] Output: Selected ad ideas and final sentiment data

[0830] Step 7:

[0831] The server calls a natural language processing tool (e.g., OpenAI GPT-3) based on the selected advertising proposal and emotion data to automatically generate presentation materials. These materials are in the form of slides and include target information, product descriptions, advertising visuals, and selling points. Narration is also generated using a speech synthesis engine (e.g., Amazon Polly) and incorporated into the presentation materials.

[0832] Input: Selected ad idea, emotion data

[0833] Output: Generated presentation materials and narration audio

[0834] Step 8:

[0835] The server temporarily saves the generated presentation video and provides the user with a confirmation link or preview. The user checks the link or preview and confirms that there are no problems with the content. If there are no problems, the user clicks the final approval button.

[0836] Input: Generated presentation video

[0837] Output: Confirmation link or preview

[0838] Step 9:

[0839] The device notifies the server that the user has given final approval. The server then automatically uploads the approved presentation video to a designated web platform (e.g., YouTube, Vimeo). If the upload is successful, the URL is sent back to the device.

[0840] Input: Final approval information

[0841] Output: URL on the web platform

[0842] (Application example 2)

[0843] 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."

[0844] Conventional ad generation systems have difficulty reflecting user emotional data when generating ad proposals, making it difficult to provide optimal ad proposals for the target audience. Furthermore, there is no way to evaluate and adjust the effectiveness of generated ad proposals in real time, meaning users are unable to obtain sufficient information when selecting the optimal ad proposal. Furthermore, the process from creating ad proposals to generating presentation materials and uploading them to the web is cumbersome, making it necessary to perform the process efficiently.

[0845] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the information processing device, means for the information processing device to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for the user to select and approve the advertising proposals, means for collecting user emotion data while the generated advertising proposals are displayed, means for the information processing device to analyze the collected emotion data and adjust the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, and means for providing the generated presentation video to the user and automatically uploading it to the Web. This makes it possible to generate effective advertising proposals based on user emotion data, evaluate and adjust the advertising proposals in real time, and improve the efficiency of the entire process.

[0846] "Target information" refers to information about the person who is the target of the advertisement, specifically data such as age, gender, and occupation.

[0847] "Product description" is information that describes the features and benefits of the advertised product.

[0848] "Information processing device" refers to a computer or server that receives input data and processes and analyzes it.

[0849] "Past advertising cases" refers to data about previous advertising campaigns and their results.

[0850] An "advertising proposal" is an advertising idea or design created to effectively appeal to a target audience.

[0851] "Emotional data" refers to data relating to the user's psychological reactions collected from facial expressions, tone of voice, and the like.

[0852] "Presentation materials" are materials used to explain advertising proposals and are provided in slide or document format.

[0853] "Audio" refers to the narration and explanatory audio added to presentation materials.

[0854] The "generated presentation video" is video content that is automatically generated based on the advertising proposal.

[0855] "Automatic uploading to the web" is the process of automatically uploading the generated presentation video to a designated platform on the Internet.

[0856] MODE FOR CARRYING OUT THE INVENTION

[0857] To implement this invention, an advertising planner application using a smartphone is constructed. The program of this system and its processing are explained below.

[0858] Hardware and software used

[0859] Hardware

[0860] Smartphone (iOS or Android)

[0861] software

[0862] Frontend: React Native, Expo

[0863] Backend: Node.js, Express

[0864] Database: MongoDB

[0865] AI model: Python (TensorFlow, PyTorch)

[0866] Emotion engine: OpenCV, DLIB

[0867] Natural Language Processing: GPT-4 API (OpenAI)

[0868] System processing flow

[0869] 1. Enter target information and product description:

[0870] Users enter target information (age, gender, occupation) and product description (product features, benefits) into the smartphone app's input form. This data is sent in JSON format to a back-end information processing device.

[0871] 2. Generate advertising ideas:

[0872] The information processing device calls the generative AI model (GPT-4) and generates optimal advertising proposals based on past advertising case data. At this time, the information processing device refers to the advertising case data stored in the database.

[0873] 3. Launching the emotion engine and collecting emotion data:

[0874] The app displays advertising ideas in the form of cards on the user interface. At the same time, it uses the smartphone's camera and microphone to collect the user's emotional data (facial expressions, tone of voice). It uses OpenCV and DLIB to recognize facial expressions, and this data is sent to an information processing device in real time.

[0875] 4. Analyze sentiment data and adjust advertising proposals:

[0876] The information processing device analyzes the collected emotional data, evaluates the effectiveness of the ad proposal, and, if necessary, automatically adjusts parts of the ad proposal (visuals and catchphrases) using a generative AI model.

[0877] 5. Automatic generation of presentation materials and narration:

[0878] Based on the selected advertising proposal, the information processing device generates presentation materials and narration using natural language processing tools (GPT-4 API).

[0879] 6. Providing a video of your presentation and uploading it to the web:

[0880] The generated presentation video is temporarily saved and a confirmation link is provided to the user. After the user gives their final approval, the presentation video is automatically uploaded to the designated web platform and the user is notified of the URL upon successful upload.

[0881] Examples of concrete examples and prompts

[0882] Specific examples

[0883] Target information: Women in their 30s, working mothers

[0884] Product description: Skin-friendly organic cosmetics

[0885] Prompt Sentence Examples

[0886] Target Information:

[0887] Age: 30s

[0888] Gender: Female

[0889] Occupation: Working mom

[0890] Product Description:

[0891] Product name: Organic cosmetics

[0892] Feature: Gentle on the skin

[0893] Advantages: Made from natural materials

[0894] Based on this target information and product description, please refer to similar past advertising examples and generate an ad proposal that will appeal to your target. The ad proposal should include visual suggestions and a catchy copy.

[0895] In this way, by implementing the present invention, users can generate effective advertising proposals based on emotional data, evaluate and adjust the advertising proposals in real time, and streamline the entire process.

[0896] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0897] Step 1:

[0898] Input and output: The user enters target information (age, gender, occupation) and product description (product features, benefits) into the smartphone app form and presses the submit button. The entered data is sent to the backend server in JSON format.

[0899] Operation: The terminal triggers a click event on the send button, packages the target information and product description in JSON format, and sends the data to the server using an HTTP POST request.

[0900] Step 2:

[0901] Input and output: Based on the target information and product description received by the server, the generative AI model (GPT-4) is called and the optimal advertising proposal is generated using past advertising case data. The output is the generated advertising proposal.

[0902] How it works: The server parses the received data and constructs a prompt. It then calls the GPT-4 API and generates ad suggestions using this prompt as input. These ad suggestions are stored in a database and ready to be sent to the frontend.

[0903] Step 3:

[0904] Input and output: The generated ad proposals are sent to the terminal and displayed in the form of cards on the app interface. The output is the displayed ad proposals.

[0905] Operation: The server sends the generated ad proposals in JSON format to the device. The device analyzes the received data and displays the ad proposals in a card format on the user interface.

[0906] Step 4:

[0907] Input and Output: When a user views an ad, emotional data is collected using a camera and microphone. The input is the user's facial expression and tone of voice, and the output is the collected emotional data.

[0908] How it works: The device displays ad suggestions and activates the smartphone's camera and microphone, then analyzes the user's facial expressions and tone of voice using OpenCV and DLIB. The collected emotional data is sent to the server in real time.

[0909] Step 5:

[0910] Input and output: The server analyzes the collected emotional data and evaluates and adjusts the effectiveness of advertising proposals. The input is the emotional data, and the output is the adjusted advertising proposals.

[0911] How it works: The server analyzes the collected emotion data and evaluates the ad suggestions. If necessary, it calls the generative AI model again to generate adjusted ad suggestions. These adjusted ad suggestions are then presented to the user again.

[0912] Step 6:

[0913] Input and Output: The user selects and approves the best ad suggestion. The input is the user's selection, and the output is the selected ad suggestion.

[0914] Operation: The terminal records the user's selection and sends the selected ad proposal data to the server, which receives the selection data and prepares to process the information again.

[0915] Step 7:

[0916] Input and output: The server automatically generates presentation materials and audio based on the selected advertising proposal. The input is the selected advertising proposal, and the output is the generated presentation materials and audio.

[0917] How it works: Based on the selected ad proposal, the server uses natural language processing tools (GPT-4 API) to generate presentation materials. The materials include target information, product descriptions, ad visuals, and selling points in slide format. Next, audio narration is automatically generated and incorporated into the video format.

[0918] Step 8:

[0919] Input and Output: The generated presentation video is temporarily saved and a confirmation link is provided to the user. The input is the generated presentation video, and the output is the confirmation link.

[0920] How it works: The server saves the generated presentation video and sends the user a preview link before finalizing it. The user clicks the link to check the content and approve or modify it.

[0921] Step 9:

[0922] Input and Output: After the user gives their final approval, the server will automatically upload the generated presentation video to the designated web platform. The input is the user's approval, and the output is the URL of the uploaded video.

[0923] How it works: After the user gives their final approval, the server will automatically upload the presentation video to the designated web platform. If the upload is successful, the URL will be sent to the user.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] [Third embodiment]

[0928] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0929] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0930] 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).

[0931] 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.

[0932] 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.

[0933] 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).

[0934] 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.

[0935] 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.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] 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."

[0940] This invention is a system that inputs and transmits target information and product descriptions, automatically generates optimal advertising proposals by referencing past advertising examples, generates presentation materials and presentation videos based on those advertising proposals, and finally automatically uploads them to the web. The specific process flow and each means are explained below.

[0941] Main processes and their operations

[0942] A means of inputting target information and product descriptions

[0943] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form.

[0944] example)

[0945] Target information: Women in their 30s, working mothers

[0946] Product description: Skin-friendly organic cosmetics

[0947] Means for sending target information and product description to the server

[0948] Terminal: Sends the entered target information and product description to the server. The data format is typically JSON.

[0949] Means for generating advertisement proposals by the server

[0950] Server: Based on the received target information and product description, the server generates optimal advertising proposals using an AI model trained from a database of past advertising cases. Ad proposals are created from multiple different perspectives, and each proposal includes visuals, catchphrases, etc.

[0951] example)

[0952] Advertisement idea 1: Elegant design using natural materials

[0953] Advertisement idea 2: Skin care that is gentle on mothers raising children

[0954] A means of displaying generated ad ideas

[0955] Terminal: Ad proposals received from the server are displayed on the user interface in card format, etc. Each ad proposal is laid out to make it easy to visually compare them.

[0956] A means of selecting and approving advertising proposals

[0957] User: Select the best ad from multiple options and approve it with a click or tap.

[0958] A means of automatically generating presentation materials and narration

[0959] Server: Using a "natural language processing tool" (for example, the API of a general office suite), the server automatically generates presentation materials based on the selected advertising proposal. The materials include product descriptions, target information, selling points, and advertising visuals. Next, an audio narration is automatically generated and incorporated into the presentation materials.

[0960] example)

[0961] Slide 1: Target Information and Product Description

[0962] Slide 2: Generated ad visual

[0963] Slide 3: Key selling points

[0964] A means to provide users with presentation videos and automatically upload them to the web

[0965] Server: The server temporarily stores the generated presentation video and provides a link or preview for the user to review. After the user has reviewed the content, they can click the approval button and the video will be automatically uploaded to the designated web platform.

[0966] This allows users to efficiently carry out a series of tasks, from generating advertising proposals to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[0967] The processing flow will be explained below.

[0968] Step 1:

[0969] User: Enter target information and product description. Enter the required information in the dedicated input form and press the send button.

[0970] example)

[0971] Target information: Women in their 30s, working mothers

[0972] Product description: Skin-friendly organic cosmetics

[0973] Step 2:

[0974] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[0975] Step 3:

[0976] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[0977] Step 4:

[0978] Server: The generated multiple advertising proposals (e.g., elegant designs using natural materials, skin care products that are gentle on mothers raising children) are sent again to the device in JSON format.

[0979] Step 5:

[0980] Device: The received ad ideas are displayed in the form of cards on the user interface. Each ad idea is visually easy to understand and easy to compare.

[0981] Step 6:

[0982] User: Select the best one from the displayed ad suggestions, then click the approve button.

[0983] Step 7:

[0984] Terminal: Sends data on the advertisements selected and approved by the user to the server.

[0985] Step 8:

[0986] Server: Calls the "presentation material generation tool" and automatically generates presentation materials based on the selected advertising proposal. The materials include target information, product descriptions, advertising visuals, and selling points in slide format.

[0987] Step 9:

[0988] Server: Uses the "audio narration generation tool" to generate audio narration corresponding to the presentation materials. The generated audio file is incorporated into the presentation materials to complete the presentation video.

[0989] Step 10:

[0990] Server: Temporarily saves the completed presentation video and provides the user with a confirmation link or preview. This link is notified to the user.

[0991] Step 11:

[0992] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[0993] Step 12:

[0994] Terminal: Notifies the server of the user's final approval.

[0995] Step 13:

[0996] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[0997] Example 1

[0998] 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."

[0999] The traditional advertising creation process required a lot of manual work, which was time-consuming and labor-intensive. It was also difficult to predict the effectiveness of advertising proposals, making it difficult to quickly create advertisements that effectively appeal to the target audience. To solve these problems, a system was needed that could automatically generate advertising proposals and automatically create presentation materials and presentation videos based on those proposals.

[1000] 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.

[1001] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the server, means for the server to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, means for providing the generated presentation video to the user and automatically uploading it to the Web, means for displaying multiple advertising proposals in a card format for easy visual comparison, and means for automatically generating audio narration and incorporating it into the presentation materials.This streamlines the process from generating advertising proposals to creating presentation videos and uploading them to the Web, making it possible to quickly create advertisements that effectively appeal to the target.

[1002] The "means for inputting target information" is an interface that allows users to input information about a specific target demographic (e.g., age, gender, occupation, etc.).

[1003] The "means for inputting product description" is an interface that allows a user to input the features and benefits of a particular product.

[1004] The "means for transmitting target information and product description to the server" is a mechanism for transmitting the target information and product description entered by the user to the server.

[1005] "A means for the server to learn from past advertising examples and generate advertising proposals that are likely to resonate with the target" refers to a function in which the server uses an AI model based on past advertising data to generate optimal advertising proposals.

[1006] A "means for displaying generated ad suggestions" is a mechanism for displaying the server-generated ad suggestions in a user interface.

[1007] The "means for user to select and approve advertising proposals" is an interface that allows the user to select the most suitable one from multiple advertising proposals and confirm the selection.

[1008] The "means for automatically generating presentation materials and audio based on the approved advertising proposal" is a function for automatically generating presentation materials and audio narration based on the selected advertising proposal.

[1009] "Means for providing the generated presentation video to the user and automatically uploading it to the web" refers to a function that provides the created presentation video in a form that the user can check, and automatically uploads it to the web after approval.

[1010] The "means for displaying multiple advertising proposals in a card format for easy visual comparison" is an interface that displays the generated advertising proposals in a card format, allowing the user to intuitively compare them.

[1011] A "means for automatically generating audio narration and incorporating it into presentation materials" is an automated process that converts specified text into audio and integrates the audio into presentation materials.

[1012] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the proposals, which are then automatically uploaded to the web. This system is primarily composed of three main components: the user, the terminal, and the server.

[1013] A means of inputting target information and product descriptions

[1014] Users enter target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into a dedicated input form. The input form is provided by a web application or a dedicated desktop application.

[1015] Example: A user fills in a form with "Female, 30s, working mom" and then "Skin-friendly organic cosmetics."

[1016] Means for sending target information and product description to the server

[1017] The device sends the entered target information and product description to the server. The data format is generally JSON. By pressing the send button, the data is sent to the server as an HTTP POST request.

[1018] Means for generating advertisement proposals by the server

[1019] The server generates optimal ad proposals based on the received target information and product description using a generative AI model (e.g., GPT-4) trained from a database of past advertising cases. Ad proposals are created from multiple different perspectives, and each proposal includes visuals, catchphrases, etc.

[1020] Example prompt sentence:

[1021] "Generate an ad proposal that appeals to working mothers in their 30s. The product description is about organic cosmetics that are gentle on the skin."

[1022] A means of displaying generated ad ideas

[1023] The terminal displays the ad proposals received from the server in a card format on the user interface, with each proposal laid out in a way that makes it easy to visually compare them.

[1024] A means of selecting and approving advertising proposals

[1025] The user selects and approves the best ad from multiple ad proposals by tapping or clicking on the ad proposal card and finally pressing the "Approve" button.

[1026] A means of automatically generating presentation materials and narration

[1027] The server automatically generates presentation materials based on the selected advertising proposal. Using natural language processing tools (e.g., Microsoft Office API or Google Docs API), the materials include product descriptions, target information, selling points, advertising visuals, etc. Additionally, audio narration is automatically generated and incorporated into the presentation materials.

[1028] Example: The server forms a prompt sentence and instructs the natural language processing tool, "Generate presentation materials based on the selected advertising proposal. The materials should include product descriptions, target information, selling points, and advertising visuals."

[1029] Provision of presentation videos and automatic uploading to the web

[1030] The server temporarily saves the generated presentation video and provides a link or preview for the user to review. Once the user confirms the content and finally presses the "Approve" button, the video is automatically uploaded to the designated web platform (e.g., YouTube, Vimeo).

[1031] This allows users to efficiently carry out a series of tasks, from generating advertising proposals to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[1032] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1033] Step 1:

[1034] Enter target information and product description

[1035] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form.

[1036] Specific actions: Access the web application or dedicated desktop application, enter target information such as "Woman in her 30s, working mother," and then enter the product description as "Skin-friendly organic cosmetics."

[1037] Input and Output: Target information and product description are input and this is output as a dataset for processing in the next step.

[1038] Step 2:

[1039] Sending target information and product descriptions

[1040] Terminal: Sends the entered target information and product description to the server.

[1041] Specific operation: When you click the send button, the device will send the target information and product description in JSON format to the server. The data will be sent as an HTTP POST request.

[1042] Input and Output: User input data is taken into the terminal, structured in JSON format, and sent to the server.

[1043] Step 3:

[1044] Server-generated advertising proposals

[1045] Server: Based on the received target information and product description, the optimal advertising proposal is generated using a generative AI model (e.g., GPT-4) trained from a database of past advertising cases.

[1046] Specific operation: The server creates a prompt sentence and sends it to the AI ​​model: "Please generate an ad proposal that appeals to working mothers in their 30s. The product description is organic cosmetics that are gentle on the skin." The AI ​​model generates multiple optimal ad proposals from each prompt and outputs ad proposals including visuals and catchphrases.

[1047] Input and output: The server creates a prompt based on the target information and product description received, and inputs it into the generative AI model. The generated ad proposals are output as a dataset to be displayed in the next step.

[1048] Step 4:

[1049] View generated ad ideas

[1050] Terminal: Displays the advertising proposals received from the server in the form of cards on the user interface.

[1051] What it does: Ad ideas are displayed on the screen as cards, laid out for easy visual comparison. Hovering over each card will pop up more information.

[1052] Input and Output: Receives ad proposal data from the server and displays it in a card-style UI, allowing users to visually compare ad proposals.

[1053] Step 5:

[1054] Selection and Approval of Ad Proposals

[1055] User: Selects and approves the best ad from multiple options.

[1056] Specific actions: Click on the ad card to select it, and finally click the "Approve" button.

[1057] Input and Output: The user selects one of the displayed advertisement proposals, and the selected advertisement proposal is sent to the server.

[1058] Step 6:

[1059] Automatic generation of presentation materials and narration

[1060] Server: Automatically generates presentation materials based on the selected advertising proposal. Using natural language processing tools (e.g., Microsoft Office API or Google Docs API), the materials include product descriptions, target information, selling points, advertising visuals, etc. Additionally, automatically generates voice narration and incorporates it into the presentation materials.

[1061] Specific operation: The server creates a prompt sentence and commands the natural language processing tool, "Generate presentation materials based on the selected advertising proposal. The materials should include product descriptions, target information, selling points, and advertising visuals." The generated materials are then integrated with the narration to create a presentation video.

[1062] Input and Output: The system takes the user's selected advertising proposal as input, generates presentation materials and audio narration based on it, and outputs the final presentation video.

[1063] Step 7:

[1064] Providing presentation videos and automatically uploading them to the web

[1065] Server: The server temporarily stores the generated presentation video and provides a link or preview for the user to review. Once the user confirms the content and finally presses the "Approve" button, the video is automatically uploaded to the designated web platform (e.g., YouTube, Vimeo).

[1066] Specific operation: A link to the generated presentation video is generated and provided to the user. The user clicks the link to view a preview of the video. When the user clicks the "Approve" button, the video is uploaded to the specified web platform.

[1067] Input and Output: We treat the generated presentation video as input and provide it to the user, who will upload it to the web platform after confirmation.

[1068] (Application example 1)

[1069] 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."

[1070] In the advertising industry, it is important to quickly generate optimal advertising proposals for each target audience and create effective presentation materials and videos. However, many companies rely on manual work that requires time and effort, and there is a need for greater efficiency. Furthermore, with previous systems, it was difficult for marketers to easily use smartphone apps to create and upload advertising proposals. Therefore, there is a need for an efficient system that can solve these issues.

[1071] 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.

[1072] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the server in JSON format, means for using an AI model to learn from past advertising cases and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals in card format, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, means for providing the generated presentation video to the user and automatically uploading it to the Web, and means for functioning as a smartphone application for marketers. This enables marketers to efficiently input target information and product descriptions, generate optimal advertising proposals using the AI ​​model, and quickly create presentation materials and presentation videos and upload them to the Web.

[1073] "Target information" refers to information about consumers targeted by advertising (e.g., age, gender, occupation, etc.).

[1074] "Product description" is information that indicates the features and benefits of the advertised product.

[1075] A "server" is a computer system that receives and processes data.

[1076] "JSON format" is a data description language that structures and expresses data in text format.

[1077] An "AI model" is an artificial intelligence algorithm that learns from past data and makes predictions and generates new data.

[1078] An "advertising proposal" is a proposal that includes an advertising design and catchy slogan that will appeal to the target audience.

[1079] The "card format" is a rectangular display format for displaying information in a visually easy-to-understand manner.

[1080] "Presentation materials" are slide-format documents summarizing the contents of an advertising proposal.

[1081] "Audio" refers to a narration audio accompanying the presentation materials to explain the contents.

[1082] A "presentation video" is a video presentation that incorporates audio narration.

[1083] A "smartphone application" is software that runs on a smartphone and provides specific functions or services.

[1084] A "web platform" is a system or site that provides services over the Internet.

[1085] MODE FOR CARRYING OUT THE INVENTION

[1086] The present invention provides a system that enables marketing personnel to efficiently generate advertising proposals and create presentation materials and presentation videos. The device configuration and processing procedure are described below in detail.

[1087] System Configuration

[1088] Hardware:

[1089] Smartphone

[1090] server

[1091] Cloud Storage

[1092] software:

[1093] Python

[1094] Flask

[1095] OpenAI API

[1096] Database (e.g. MongoDB)

[1097] User interface frameworks (e.g., React Native)

[1098] Data entry and submission

[1099] Users use a dedicated smartphone application to input target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits). The input data is converted into JSON format and sent to the server.

[1100] Generate advertising proposals

[1101] The server generates ad suggestions using OpenAI's AI model based on the target information and product description it receives. Specifically, it passes data in the following text format as a prompt to the AI ​​model.

[1102] Example prompt sentence:

[1103] Target information: Women in their 30s, working mothers. Product description: Organic cosmetics that are gentle on the skin. Please refer to past advertising examples to generate optimal advertising proposals.

[1104] View and approve ad proposals

[1105] The generated ad proposals are displayed in the form of cards on the user interface of the smartphone application, and the user can select the best one from multiple proposals and approve it with a tap or click.

[1106] Presentation and video generation

[1107] Based on the advertising proposal approved by the user, the server automatically generates presentation materials and audio narration. The presentation materials include product descriptions, target information, selling points, advertising visuals, etc. Next, the server generates audio narration and incorporates it into the presentation materials to create a presentation video.

[1108] Providing and uploading videos

[1109] The generated presentation video is temporarily stored in cloud storage, where users can preview it or view it via a link. If there are no problems with the content, the presentation video will be automatically uploaded to the designated web platform with the user's approval.

[1110] This allows marketers to efficiently and quickly input target information and product descriptions, use AI models to generate optimal advertising ideas, and quickly create presentation materials and videos, which can then be uploaded to the web.

[1111] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1112] Step 1:

[1113] The user enters target information and product description into the smartphone application. The entered data is converted into JSON format.

[1114] Input: Target information (e.g., age, gender, occupation), product description (e.g., product features, benefits)

[1115] Output: JSON format data (e.g., {"target_info": "Woman in her 30s, working mother", "product_desc": "Skin-friendly organic cosmetics"})

[1116] Step 2:

[1117] The device sends JSON format data to the server.

[1118] Input: JSON format data

[1119] Output: Data sent to the server

[1120] Step 3:

[1121] The server converts the received data into a prompt sentence to be passed to the AI ​​model. The prompt sentence is in text format based on the target information and product description.

[1122] Input: JSON format data

[1123] Output: Prompt text (e.g., "Target information: women in their 30s, working mothers, product description: organic cosmetics that are gentle on the skin. Please generate the optimal ad proposal by referring to past ad examples.")

[1124] Step 4:

[1125] The server uses OpenAI's API to input the prompt text into the AI ​​model and generate advertising proposals.

[1126] Input: prompt statement

[1127] Output: Generated ad ideas (e.g. text of multiple ad ideas)

[1128] Step 5:

[1129] The server returns the generated advertising proposals to the smartphone application.

[1130] Input: Generated ad ideas

[1131] Output: Data for the user interface

[1132] Step 6:

[1133] The device displays ad suggestions in the form of cards on the user interface, and the user can select and approve the best one from multiple ad suggestions.

[1134] Input: Data for the user interface

[1135] Output: ID of the ad proposal that the user accepted

[1136] Step 7:

[1137] The server automatically generates presentation materials and audio narration based on the ID of the approved advertising proposal.

[1138] Input: Approved ad proposal ID

[1139] Output: Presentation materials, audio narration

[1140] Step 8:

[1141] The server generates a presentation video based on the presentation materials and audio narration, and the generated presentation video is saved in cloud storage.

[1142] Input: Presentation materials, voice narration

[1143] Output: Presentation video

[1144] Step 9:

[1145] A preview link for the presentation video will be provided to the user, who can then review the video and approve it if there are no issues with the content.

[1146] Input: Preview link of presentation video

[1147] Output: Acknowledgement from the user

[1148] Step 10:

[1149] The server will automatically upload the approved presentation video to the designated web platform.

[1150] Input: Approval from the user

[1151] Output: Presentation video uploaded to the web platform

[1152] 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.

[1153] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the advertising proposals, which are then automatically uploaded to the web. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and collect, analyze, and reflect emotional data when selecting advertising proposals.

[1154] Main processes and their operations

[1155] A means of inputting target information and product descriptions

[1156] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form and press the send button.

[1157] example)

[1158] Target information: Women in their 30s, working mothers

[1159] Product description: Skin-friendly organic cosmetics

[1160] Means for sending target information and product description to the server

[1161] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[1162] Means for generating advertisement proposals by the server

[1163] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[1164] A means of recognizing user emotions with an emotion engine

[1165] Device: The generated ad ideas are displayed in the form of cards on the user interface. At the same time, an emotion engine is activated to collect emotional data from facial expressions, tone of voice, etc. while the user is viewing the ad ideas.

[1166] example)

[1167] Advertisement idea 1: Elegant design using natural materials

[1168] Advertisement idea 2: Skin care that is gentle on mothers raising children

[1169] Analyzing sentiment data and adjusting advertising proposals

[1170] Server: Analyzes the emotional data collected by the emotion engine and evaluates the effectiveness of advertising proposals. It has the ability to automatically adjust parts of advertising proposals (visuals and catchphrases) based on user emotions.

[1171] A means of selecting and approving advertising proposals

[1172] User: Select the best ad from the displayed suggestions. After selecting, click the approve button. At this point, a final analysis of the sentiment data is also performed.

[1173] A means of automatically generating presentation materials and narration

[1174] Server: Calls up the "natural language processing tool" and automatically generates presentation materials based on the selected advertising proposal and emotional data. The materials include target information, product descriptions, advertising visuals, and selling points in slide format. Next, an audio narration is automatically generated and incorporated into the presentation materials.

[1175] example)

[1176] Slide 1: Target Information and Product Description

[1177] Slide 2: Generated ad visual

[1178] Slide 3: Key selling points

[1179] A means to provide users with presentation videos and automatically upload them to the web

[1180] Server: Temporarily saves the generated presentation video and provides the user with a confirmation link or preview. Notifies the user of this link.

[1181] Final approval and upload of presentation video

[1182] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[1183] Terminal: Notifies the server of the user's final approval.

[1184] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[1185] This allows users to efficiently carry out a series of tasks, from generating advertising proposals incorporating emotion data to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[1186] The processing flow will be explained below.

[1187] Specific processing steps of the function

[1188] Step 1:

[1189] User: Enter target information and product description. Enter the required information in the dedicated input form (e.g., female in her 30s, skin-friendly organic cosmetics) and press the send button.

[1190] example)

[1191] Target information: Women in their 30s, working mothers

[1192] Product description: Skin-friendly organic cosmetics

[1193] Step 2:

[1194] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[1195] Step 3:

[1196] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[1197] Step 4:

[1198] Server: The generated multiple advertising proposals (e.g., elegant designs using natural materials, skin care products that are gentle on mothers raising children) are sent again to the device in JSON format.

[1199] Step 5:

[1200] Terminal: The received ad proposal is displayed in the form of a card on the user interface. At the same time, an emotion engine is activated to collect emotional data in real time from facial expressions, tone of voice, etc. while the user is viewing the ad proposal.

[1201] Step 6:

[1202] User: Expresses their feelings about the displayed ad suggestions and selects the most suitable one.

[1203] Step 7:

[1204] Emotion Engine: While the user is viewing the ad proposal, emotional data is collected from facial expressions, voice, mouse movements, etc. The collected data is temporarily stored.

[1205] Step 8:

[1206] Server: Analyzes the emotion data collected by the emotion engine and evaluates the effectiveness of the ad suggestions until the user makes a selection. If necessary, it resends optimized ad suggestions to the device.

[1207] Step 9:

[1208] User: Review the optimized ad proposals and approve the final ad proposal.

[1209] Step 10:

[1210] Terminal: After receiving the user's approval, the data of the selected advertisement proposal is sent back to the server.

[1211] Step 11:

[1212] Server: Calls the "presentation material generation tool" and "voice narration generation tool" and automatically generates presentation materials and narration based on the selected advertising proposal and emotion data.

[1213] example)

[1214] Slide 1: Target Information and Product Description

[1215] Slide 2: Generated ad visual

[1216] Slide 3: Key selling points

[1217] Step 12:

[1218] Server: Incorporates narration into presentation materials, completes the presentation video, and temporarily saves the completed presentation video.

[1219] Step 13:

[1220] Server: Provide the user with a confirmation link or preview of the completed presentation video. Notify the user of this link.

[1221] Step 14:

[1222] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[1223] Step 15:

[1224] Terminal: Notifies the server of the user's final approval.

[1225] Step 16:

[1226] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[1227] This series of processes allows users to efficiently complete tasks from generating advertising proposals incorporating emotional data to creating presentations and finally uploading them to the web.

[1228] Example 2

[1229] 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."

[1230] Conventional ad generation systems have had issues with incorporating user emotional data to evaluate the effectiveness of ads, and with insufficient feedback to optimize the accuracy and effectiveness of ads. Furthermore, there is a lack of an efficient way to automatically create presentation materials and videos based on the generated ad ideas and automatically upload them to a network.

[1231] 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.

[1232] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to a computer connected to a network, means for the computer to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for collecting user emotion data and evaluating the effectiveness of the advertising proposals, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, and means for providing the generated presentation video to the user and automatically uploading it to the network. This makes it possible to generate advertising proposals that reflect the user's emotions, and further makes it possible to efficiently create presentation materials and presentation videos based on the advertising proposals and share them seamlessly on the network.

[1233] "Target information" refers to attribute data such as age, gender, and occupation of specific advertising targets.

[1234] "Product description" refers to detailed information about the product being advertised, such as its features and benefits.

[1235] A "networked computer" refers to a computing device that is capable of communicating over a network, such as the Internet.

[1236] "Advertising Proposal" refers to an advertising idea or plan generated based on target information and product description.

[1237] "Emotion data" refers to data related to emotions collected from the user's facial expressions, tone of voice, etc.

[1238] "Presentation materials" refers to slide-format materials created to explain the contents of an advertising proposal.

[1239] "Natural language processing tools" refers to artificial intelligence techniques used to analyze, generate, and transform text data.

[1240] "Presentation video" refers to a video presentation created by incorporating audio narration into presentation materials.

[1241] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the advertising proposals, which are then automatically uploaded to the web. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and collect, analyze, and reflect emotional data when selecting advertising proposals.

[1242] The user first enters target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into a dedicated input form, and then presses the submit button. At this time, appropriate validation is performed for each field in the input form. As a specific example, the target is working mothers in their 30s, and the product description is entered as "skin-friendly organic cosmetics."

[1243] The terminal packages the information entered by the user in JSON format and sends it to the server as an HTTP request. The JSON data is generated by a JavaScript function. For example, you can generate a prompt like this:

[1244] "Please create an ad idea for organic cosmetics that are gentle on the skin and target working mothers in their 30s. Please refer to past success stories."

[1245] The server analyzes the received target information and product description and calls up a generative AI model (e.g., OpenAI GPT-3) installed on it. The AI ​​model has learned from past advertising case data and generates advertising ideas that are likely to resonate with the target based on the input data.

[1246] The generated ad suggestions are sent to the device and displayed in the form of cards on the user interface. At the same time, the device activates an emotion engine (e.g., Microsoft Azure Cognitive Services) to collect emotional data through facial expressions and tone of voice while the user is viewing the ad suggestions. Specific examples of generated ad suggestions include:

[1247] Advertisement idea 1: Elegant design using natural materials

[1248] Advertisement idea 2: Skin care that is gentle on mothers raising children

[1249] The server analyzes the emotional data sent from the device and evaluates the effectiveness of the proposed ad. This analysis uses collected emotional data (e.g., frequency of smiling, tone of voice). If necessary, elements of the proposed ad, such as visuals and catchy copy, are adjusted.

[1250] The user selects the best one from the multiple ad ideas provided and clicks the approval button. The selected ad idea and the final emotion data are sent to the server, and the system proceeds to the next step.

[1251] The server calls a natural language processing tool (e.g., OpenAI GPT-3) based on the selected advertising proposal and emotion data to automatically generate presentation materials. The materials are composed of slides and include target information, product descriptions, advertising visuals, and selling points. A voice synthesis engine (e.g., Amazon Polly) is also used to generate narration voices, which are incorporated into the presentation materials. For example, the following slides are generated:

[1252] Slide 1: Target Information and Product Description

[1253] Slide 2: Generated ad visual

[1254] Slide 3: Key selling points

[1255] The server temporarily saves the generated presentation video and provides a confirmation link or preview to the user. If the user checks the link or preview and determines that the content is OK, they click the final approval button.

[1256] Once final approval is given, the device notifies the server, which then automatically uploads the approved presentation video to a designated web platform (e.g., YouTube, Vimeo). If the upload is successful, the URL is sent back to the user's device.

[1257] This allows users to efficiently create advertisement proposals, create presentations, and finally upload them to the web. The system of the present invention is expected to speed up advertisement design, improve efficiency, and improve the quality of advertisement design.

[1258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1259] Step 1:

[1260] The user enters target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into the input form and presses the submit button. The input data is for target information to be "women in their 30s, working mothers" and for product description to be "skin-friendly organic cosmetics." The input data is formatted as a JSON-formatted object.

[1261] Input: Target information, product description

[1262] Output: JSON format object (target information and product description)

[1263] Step 2:

[1264] The device packages the target information and product description entered by the user and sends it to a computer (server) connected to the network using an HTTP POST request, generating JSON format data using JavaScript.

[1265] Input: JSON formatted object

[1266] Output: HTTP POST request

[1267] Step 3:

[1268] The server analyzes the HTTP POST request received from the device and obtains target information and product description in JSON format. It then invokes a generative AI model (e.g., OpenAI GPT-3) to generate a prompt based on past advertising case data. The generated prompt is then input into the AI ​​model to generate advertising proposals.

[1269] Input: Target information and product description in JSON format

[1270] Output: Generated ad ideas

[1271] Step 4:

[1272] The device displays the generated ad suggestions received from the server in the form of cards on the user interface. At the same time, it launches an emotion engine (e.g., Microsoft Azure Cognitive Services) to collect facial expressions and tone of voice while the user is viewing the ad suggestions. The collected emotion data is temporarily stored in a local database.

[1273] Input: Generated ad ideas

[1274] Output: Display on the user interface, collected emotion data

[1275] Step 5:

[1276] The server analyzes the emotional data sent from the device and evaluates the effectiveness of the proposed advertisements. Specifically, it automatically adjusts the visuals and catchy copy of the proposed advertisements based on emotional data such as the frequency of smiling and tone of voice.

[1277] Input: Emotion data

[1278] Output: Adjusted ad proposals

[1279] Step 6:

[1280] The user selects the best ad from the multiple ad ideas displayed and clicks the approval button. The selected ad idea and the final emotion data are sent to the server for final analysis.

[1281] Input: Multiple ad ideas

[1282] Output: Selected ad ideas and final sentiment data

[1283] Step 7:

[1284] The server calls a natural language processing tool (e.g., OpenAI GPT-3) based on the selected advertising proposal and emotion data to automatically generate presentation materials. These materials are in the form of slides and include target information, product descriptions, advertising visuals, and selling points. Narration is also generated using a speech synthesis engine (e.g., Amazon Polly) and incorporated into the presentation materials.

[1285] Input: Selected ad idea, emotion data

[1286] Output: Generated presentation materials and narration audio

[1287] Step 8:

[1288] The server temporarily saves the generated presentation video and provides the user with a confirmation link or preview. The user checks the link or preview and confirms that there are no problems with the content. If there are no problems, the user clicks the final approval button.

[1289] Input: Generated presentation video

[1290] Output: Confirmation link or preview

[1291] Step 9:

[1292] The device notifies the server that the user has given final approval. The server then automatically uploads the approved presentation video to a designated web platform (e.g., YouTube, Vimeo). If the upload is successful, the URL is sent back to the device.

[1293] Input: Final approval information

[1294] Output: URL on the web platform

[1295] (Application example 2)

[1296] 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."

[1297] Conventional ad generation systems have difficulty reflecting user emotional data when generating ad proposals, making it difficult to provide optimal ad proposals for the target audience. Furthermore, there is no way to evaluate and adjust the effectiveness of generated ad proposals in real time, meaning users are unable to obtain sufficient information when selecting the optimal ad proposal. Furthermore, the process from creating ad proposals to generating presentation materials and uploading them to the web is cumbersome, making it necessary to perform the process efficiently.

[1298] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the information processing device, means for the information processing device to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for the user to select and approve the advertising proposals, means for collecting user emotion data while the generated advertising proposals are displayed, means for the information processing device to analyze the collected emotion data and adjust the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, and means for providing the generated presentation video to the user and automatically uploading it to the Web. This makes it possible to generate effective advertising proposals based on user emotion data, evaluate and adjust the advertising proposals in real time, and improve the efficiency of the entire process.

[1299] "Target information" refers to information about the person who is the target of the advertisement, specifically data such as age, gender, and occupation.

[1300] "Product description" is information that describes the features and benefits of the advertised product.

[1301] "Information processing device" refers to a computer or server that receives input data and processes and analyzes it.

[1302] "Past advertising cases" refers to data about previous advertising campaigns and their results.

[1303] An "advertising proposal" is an advertising idea or design created to effectively appeal to a target audience.

[1304] "Emotional data" refers to data relating to the user's psychological reactions collected from facial expressions, tone of voice, and the like.

[1305] "Presentation materials" are materials used to explain advertising proposals and are provided in slide or document format.

[1306] "Audio" refers to the narration and explanatory audio added to presentation materials.

[1307] The "generated presentation video" is video content that is automatically generated based on the advertising proposal.

[1308] "Automatic uploading to the web" is the process of automatically uploading the generated presentation video to a designated platform on the Internet.

[1309] MODE FOR CARRYING OUT THE INVENTION

[1310] To implement this invention, an advertising planner application using a smartphone is constructed. The program of this system and its processing are explained below.

[1311] Hardware and software used

[1312] Hardware

[1313] Smartphone (iOS or Android)

[1314] software

[1315] Frontend: React Native, Expo

[1316] Backend: Node.js, Express

[1317] Database: MongoDB

[1318] AI model: Python (TensorFlow, PyTorch)

[1319] Emotion engine: OpenCV, DLIB

[1320] Natural Language Processing: GPT-4 API (OpenAI)

[1321] System processing flow

[1322] 1. Enter target information and product description:

[1323] Users enter target information (age, gender, occupation) and product description (product features, benefits) into the smartphone app's input form. This data is sent in JSON format to a back-end information processing device.

[1324] 2. Generate advertising ideas:

[1325] The information processing device calls the generative AI model (GPT-4) and generates optimal advertising proposals based on past advertising case data. At this time, the information processing device refers to the advertising case data stored in the database.

[1326] 3. Launching the emotion engine and collecting emotion data:

[1327] The app displays advertising ideas in the form of cards on the user interface. At the same time, it uses the smartphone's camera and microphone to collect the user's emotional data (facial expressions, tone of voice). It uses OpenCV and DLIB to recognize facial expressions, and this data is sent to an information processing device in real time.

[1328] 4. Analyze sentiment data and adjust advertising proposals:

[1329] The information processing device analyzes the collected emotional data, evaluates the effectiveness of the ad proposal, and, if necessary, automatically adjusts parts of the ad proposal (visuals and catchphrases) using a generative AI model.

[1330] 5. Automatic generation of presentation materials and narration:

[1331] Based on the selected advertising proposal, the information processing device generates presentation materials and narration using natural language processing tools (GPT-4 API).

[1332] 6. Providing a video of your presentation and uploading it to the web:

[1333] The generated presentation video is temporarily saved and a confirmation link is provided to the user. After the user gives their final approval, the presentation video is automatically uploaded to the designated web platform and the user is notified of the URL upon successful upload.

[1334] Examples of concrete examples and prompts

[1335] Specific examples

[1336] Target information: Women in their 30s, working mothers

[1337] Product description: Skin-friendly organic cosmetics

[1338] Prompt Sentence Examples

[1339] Target Information:

[1340] Age: 30s

[1341] Gender: Female

[1342] Occupation: Working mom

[1343] Product Description:

[1344] Product name: Organic cosmetics

[1345] Feature: Gentle on the skin

[1346] Advantages: Made from natural materials

[1347] Based on this target information and product description, please refer to similar past advertising examples and generate an ad proposal that will appeal to your target. The ad proposal should include visual suggestions and a catchy copy.

[1348] In this way, by implementing the present invention, users can generate effective advertising proposals based on emotional data, evaluate and adjust the advertising proposals in real time, and streamline the entire process.

[1349] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1350] Step 1:

[1351] Input and output: The user enters target information (age, gender, occupation) and product description (product features, benefits) into the smartphone app form and presses the submit button. The entered data is sent to the backend server in JSON format.

[1352] Operation: The terminal triggers a click event on the send button, packages the target information and product description in JSON format, and sends the data to the server using an HTTP POST request.

[1353] Step 2:

[1354] Input and output: Based on the target information and product description received by the server, the generative AI model (GPT-4) is called and the optimal advertising proposal is generated using past advertising case data. The output is the generated advertising proposal.

[1355] How it works: The server parses the received data and constructs a prompt. It then calls the GPT-4 API and generates ad suggestions using this prompt as input. These ad suggestions are stored in a database and ready to be sent to the frontend.

[1356] Step 3:

[1357] Input and output: The generated ad proposals are sent to the terminal and displayed in the form of cards on the app interface. The output is the displayed ad proposals.

[1358] Operation: The server sends the generated ad proposals in JSON format to the device. The device analyzes the received data and displays the ad proposals in a card format on the user interface.

[1359] Step 4:

[1360] Input and Output: When a user views an ad, emotional data is collected using a camera and microphone. The input is the user's facial expression and tone of voice, and the output is the collected emotional data.

[1361] How it works: The device displays ad suggestions and activates the smartphone's camera and microphone, then analyzes the user's facial expressions and tone of voice using OpenCV and DLIB. The collected emotional data is sent to the server in real time.

[1362] Step 5:

[1363] Input and output: The server analyzes the collected emotional data and evaluates and adjusts the effectiveness of advertising proposals. The input is the emotional data, and the output is the adjusted advertising proposals.

[1364] How it works: The server analyzes the collected emotion data and evaluates the ad suggestions. If necessary, it calls the generative AI model again to generate adjusted ad suggestions. These adjusted ad suggestions are then presented to the user again.

[1365] Step 6:

[1366] Input and Output: The user selects and approves the best ad suggestion. The input is the user's selection, and the output is the selected ad suggestion.

[1367] Operation: The terminal records the user's selection and sends the selected ad proposal data to the server, which receives the selection data and prepares to process the information again.

[1368] Step 7:

[1369] Input and output: The server automatically generates presentation materials and audio based on the selected advertising proposal. The input is the selected advertising proposal, and the output is the generated presentation materials and audio.

[1370] How it works: Based on the selected ad proposal, the server uses natural language processing tools (GPT-4 API) to generate presentation materials. The materials include target information, product descriptions, ad visuals, and selling points in slide format. Next, audio narration is automatically generated and incorporated into the video format.

[1371] Step 8:

[1372] Input and Output: The generated presentation video is temporarily saved and a confirmation link is provided to the user. The input is the generated presentation video, and the output is the confirmation link.

[1373] How it works: The server saves the generated presentation video and sends the user a preview link before finalizing it. The user clicks the link to check the content and approve or modify it.

[1374] Step 9:

[1375] Input and Output: After the user gives their final approval, the server will automatically upload the generated presentation video to the designated web platform. The input is the user's approval, and the output is the URL of the uploaded video.

[1376] How it works: After the user gives their final approval, the server will automatically upload the presentation video to the designated web platform. If the upload is successful, the URL will be sent to the user.

[1377] 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.

[1378] 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.

[1379] 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.

[1380] [Fourth embodiment]

[1381] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1382] 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.

[1383] 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).

[1384] 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.

[1385] 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.

[1386] 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).

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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."

[1394] This invention is a system that inputs and transmits target information and product descriptions, automatically generates optimal advertising proposals by referencing past advertising examples, generates presentation materials and presentation videos based on those advertising proposals, and finally automatically uploads them to the web. The specific process flow and each means are explained below.

[1395] Main processes and their operations

[1396] A means of inputting target information and product descriptions

[1397] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form.

[1398] example)

[1399] Target information: Women in their 30s, working mothers

[1400] Product description: Skin-friendly organic cosmetics

[1401] Means for sending target information and product description to the server

[1402] Terminal: Sends the entered target information and product description to the server. The data format is typically JSON.

[1403] Means for generating advertisement proposals by the server

[1404] Server: Based on the received target information and product description, the server generates optimal advertising proposals using an AI model trained from a database of past advertising cases. Ad proposals are created from multiple different perspectives, and each proposal includes visuals, catchphrases, etc.

[1405] example)

[1406] Advertisement idea 1: Elegant design using natural materials

[1407] Advertisement idea 2: Skin care that is gentle on mothers raising children

[1408] A means of displaying generated ad ideas

[1409] Terminal: Ad proposals received from the server are displayed on the user interface in card format, etc. Each ad proposal is laid out to make it easy to visually compare them.

[1410] A means of selecting and approving advertising proposals

[1411] User: Select the best ad from multiple options and approve it with a click or tap.

[1412] A means of automatically generating presentation materials and narration

[1413] Server: Using a "natural language processing tool" (for example, the API of a general office suite), the server automatically generates presentation materials based on the selected advertising proposal. The materials include product descriptions, target information, selling points, and advertising visuals. Next, an audio narration is automatically generated and incorporated into the presentation materials.

[1414] example)

[1415] Slide 1: Target Information and Product Description

[1416] Slide 2: Generated ad visual

[1417] Slide 3: Key selling points

[1418] A means to provide users with presentation videos and automatically upload them to the web

[1419] Server: The server temporarily stores the generated presentation video and provides a link or preview for the user to review. After the user has reviewed the content, they can click the approval button and the video will be automatically uploaded to the designated web platform.

[1420] This allows users to efficiently carry out a series of tasks, from generating advertising proposals to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[1421] The processing flow will be explained below.

[1422] Step 1:

[1423] User: Enter target information and product description. Enter the required information in the dedicated input form and press the send button.

[1424] example)

[1425] Target information: Women in their 30s, working mothers

[1426] Product description: Skin-friendly organic cosmetics

[1427] Step 2:

[1428] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[1429] Step 3:

[1430] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[1431] Step 4:

[1432] Server: The generated multiple advertising proposals (e.g., elegant designs using natural materials, skin care products that are gentle on mothers raising children) are sent again to the device in JSON format.

[1433] Step 5:

[1434] Device: The received ad ideas are displayed in the form of cards on the user interface. Each ad idea is visually easy to understand and easy to compare.

[1435] Step 6:

[1436] User: Select the best one from the displayed ad suggestions, then click the approve button.

[1437] Step 7:

[1438] Terminal: Sends data on the advertisements selected and approved by the user to the server.

[1439] Step 8:

[1440] Server: Calls the "presentation material generation tool" and automatically generates presentation materials based on the selected advertising proposal. The materials include target information, product descriptions, advertising visuals, and selling points in slide format.

[1441] Step 9:

[1442] Server: Uses the "audio narration generation tool" to generate audio narration corresponding to the presentation materials. The generated audio file is incorporated into the presentation materials to complete the presentation video.

[1443] Step 10:

[1444] Server: Temporarily saves the completed presentation video and provides the user with a confirmation link or preview. This link is notified to the user.

[1445] Step 11:

[1446] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[1447] Step 12:

[1448] Terminal: Notifies the server of the user's final approval.

[1449] Step 13:

[1450] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[1451] Example 1

[1452] 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."

[1453] The traditional advertising creation process required a lot of manual work, which was time-consuming and labor-intensive. It was also difficult to predict the effectiveness of advertising proposals, making it difficult to quickly create advertisements that effectively appeal to the target audience. To solve these problems, a system was needed that could automatically generate advertising proposals and automatically create presentation materials and presentation videos based on those proposals.

[1454] 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.

[1455] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the server, means for the server to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, means for providing the generated presentation video to the user and automatically uploading it to the Web, means for displaying multiple advertising proposals in a card format for easy visual comparison, and means for automatically generating audio narration and incorporating it into the presentation materials.This streamlines the process from generating advertising proposals to creating presentation videos and uploading them to the Web, making it possible to quickly create advertisements that effectively appeal to the target.

[1456] The "means for inputting target information" is an interface that allows users to input information about a specific target demographic (e.g., age, gender, occupation, etc.).

[1457] The "means for inputting product description" is an interface that allows a user to input the features and benefits of a particular product.

[1458] The "means for transmitting target information and product description to the server" is a mechanism for transmitting the target information and product description entered by the user to the server.

[1459] "A means for the server to learn from past advertising examples and generate advertising proposals that are likely to resonate with the target" refers to a function in which the server uses an AI model based on past advertising data to generate optimal advertising proposals.

[1460] A "means for displaying generated ad suggestions" is a mechanism for displaying the server-generated ad suggestions in a user interface.

[1461] The "means for user to select and approve advertising proposals" is an interface that allows the user to select the most suitable one from multiple advertising proposals and confirm the selection.

[1462] The "means for automatically generating presentation materials and audio based on the approved advertising proposal" is a function for automatically generating presentation materials and audio narration based on the selected advertising proposal.

[1463] "Means for providing the generated presentation video to the user and automatically uploading it to the web" refers to a function that provides the created presentation video in a form that the user can check, and automatically uploads it to the web after approval.

[1464] The "means for displaying multiple advertising proposals in a card format for easy visual comparison" is an interface that displays the generated advertising proposals in a card format, allowing the user to intuitively compare them.

[1465] A "means for automatically generating audio narration and incorporating it into presentation materials" is an automated process that converts specified text into audio and integrates the audio into presentation materials.

[1466] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the proposals, which are then automatically uploaded to the web. This system is primarily composed of three main components: the user, the terminal, and the server.

[1467] A means of inputting target information and product descriptions

[1468] Users enter target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into a dedicated input form. The input form is provided by a web application or a dedicated desktop application.

[1469] Example: A user fills in a form with "Female, 30s, working mom" and then "Skin-friendly organic cosmetics."

[1470] Means for sending target information and product description to the server

[1471] The device sends the entered target information and product description to the server. The data format is generally JSON. By pressing the send button, the data is sent to the server as an HTTP POST request.

[1472] Means for generating advertisement proposals by the server

[1473] The server generates optimal ad proposals based on the received target information and product description using a generative AI model (e.g., GPT-4) trained from a database of past advertising cases. Ad proposals are created from multiple different perspectives, and each proposal includes visuals, catchphrases, etc.

[1474] Example prompt sentence:

[1475] "Generate an ad proposal that appeals to working mothers in their 30s. The product description is about organic cosmetics that are gentle on the skin."

[1476] A means of displaying generated ad ideas

[1477] The terminal displays the ad proposals received from the server in a card format on the user interface, with each proposal laid out in a way that makes it easy to visually compare them.

[1478] A means of selecting and approving advertising proposals

[1479] The user selects and approves the best ad from multiple ad proposals by tapping or clicking on the ad proposal card and finally pressing the "Approve" button.

[1480] A means of automatically generating presentation materials and narration

[1481] The server automatically generates presentation materials based on the selected advertising proposal. Using natural language processing tools (e.g., Microsoft Office API or Google Docs API), the materials include product descriptions, target information, selling points, advertising visuals, etc. Additionally, audio narration is automatically generated and incorporated into the presentation materials.

[1482] Example: The server forms a prompt sentence and instructs the natural language processing tool, "Generate presentation materials based on the selected advertising proposal. The materials should include product descriptions, target information, selling points, and advertising visuals."

[1483] Provision of presentation videos and automatic uploading to the web

[1484] The server temporarily saves the generated presentation video and provides a link or preview for the user to review. Once the user confirms the content and finally presses the "Approve" button, the video is automatically uploaded to the designated web platform (e.g., YouTube, Vimeo).

[1485] This allows users to efficiently carry out a series of tasks, from generating advertising proposals to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[1486] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1487] Step 1:

[1488] Enter target information and product description

[1489] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form.

[1490] Specific actions: Access the web application or dedicated desktop application, enter target information such as "Woman in her 30s, working mother," and then enter the product description as "Skin-friendly organic cosmetics."

[1491] Input and Output: Target information and product description are input and this is output as a dataset for processing in the next step.

[1492] Step 2:

[1493] Sending target information and product descriptions

[1494] Terminal: Sends the entered target information and product description to the server.

[1495] Specific operation: When you click the send button, the device will send the target information and product description in JSON format to the server. The data will be sent as an HTTP POST request.

[1496] Input and Output: User input data is taken into the terminal, structured in JSON format, and sent to the server.

[1497] Step 3:

[1498] Server-generated advertising proposals

[1499] Server: Based on the received target information and product description, the optimal advertising proposal is generated using a generative AI model (e.g., GPT-4) trained from a database of past advertising cases.

[1500] Specific operation: The server creates a prompt sentence and sends it to the AI ​​model: "Please generate an ad proposal that appeals to working mothers in their 30s. The product description is organic cosmetics that are gentle on the skin." The AI ​​model generates multiple optimal ad proposals from each prompt and outputs ad proposals including visuals and catchphrases.

[1501] Input and output: The server creates a prompt based on the target information and product description received, and inputs it into the generative AI model. The generated ad proposals are output as a dataset to be displayed in the next step.

[1502] Step 4:

[1503] View generated ad ideas

[1504] Terminal: Displays the advertising proposals received from the server in the form of cards on the user interface.

[1505] What it does: Ad ideas are displayed on the screen as cards, laid out for easy visual comparison. Hovering over each card will pop up more information.

[1506] Input and Output: Receives ad proposal data from the server and displays it in a card-style UI, allowing users to visually compare ad proposals.

[1507] Step 5:

[1508] Selection and Approval of Ad Proposals

[1509] User: Selects and approves the best ad from multiple options.

[1510] Specific actions: Click on the ad card to select it, and finally click the "Approve" button.

[1511] Input and Output: The user selects one of the displayed advertisement proposals, and the selected advertisement proposal is sent to the server.

[1512] Step 6:

[1513] Automatic generation of presentation materials and narration

[1514] Server: Automatically generates presentation materials based on the selected advertising proposal. Using natural language processing tools (e.g., Microsoft Office API or Google Docs API), the materials include product descriptions, target information, selling points, advertising visuals, etc. Additionally, automatically generates voice narration and incorporates it into the presentation materials.

[1515] Specific operation: The server creates a prompt sentence and commands the natural language processing tool, "Generate presentation materials based on the selected advertising proposal. The materials should include product descriptions, target information, selling points, and advertising visuals." The generated materials are then integrated with the narration to create a presentation video.

[1516] Input and Output: The system takes the user's selected advertising proposal as input, generates presentation materials and audio narration based on it, and outputs the final presentation video.

[1517] Step 7:

[1518] Providing presentation videos and automatically uploading them to the web

[1519] Server: The server temporarily stores the generated presentation video and provides a link or preview for the user to review. Once the user confirms the content and finally presses the "Approve" button, the video is automatically uploaded to the designated web platform (e.g., YouTube, Vimeo).

[1520] Specific operation: A link to the generated presentation video is generated and provided to the user. The user clicks the link to view a preview of the video. When the user clicks the "Approve" button, the video is uploaded to the specified web platform.

[1521] Input and Output: We treat the generated presentation video as input and provide it to the user, who will upload it to the web platform after confirmation.

[1522] (Application example 1)

[1523] 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."

[1524] In the advertising industry, it is important to quickly generate optimal advertising proposals for each target audience and create effective presentation materials and videos. However, many companies rely on manual work that requires time and effort, and there is a need for greater efficiency. Furthermore, with previous systems, it was difficult for marketers to easily use smartphone apps to create and upload advertising proposals. Therefore, there is a need for an efficient system that can solve these issues.

[1525] 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.

[1526] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the server in JSON format, means for using an AI model to learn from past advertising cases and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals in card format, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, means for providing the generated presentation video to the user and automatically uploading it to the Web, and means for functioning as a smartphone application for marketers. This enables marketers to efficiently input target information and product descriptions, generate optimal advertising proposals using the AI ​​model, and quickly create presentation materials and presentation videos and upload them to the Web.

[1527] "Target information" refers to information about consumers targeted by advertising (e.g., age, gender, occupation, etc.).

[1528] "Product description" is information that indicates the features and benefits of the advertised product.

[1529] A "server" is a computer system that receives and processes data.

[1530] "JSON format" is a data description language that structures and expresses data in text format.

[1531] An "AI model" is an artificial intelligence algorithm that learns from past data and makes predictions and generates new data.

[1532] An "advertising proposal" is a proposal that includes an advertising design and catchy slogan that will appeal to the target audience.

[1533] The "card format" is a rectangular display format for displaying information in a visually easy-to-understand manner.

[1534] "Presentation materials" are slide-format documents summarizing the contents of an advertising proposal.

[1535] "Audio" refers to a narration audio accompanying the presentation materials to explain the contents.

[1536] A "presentation video" is a video presentation that incorporates audio narration.

[1537] A "smartphone application" is software that runs on a smartphone and provides specific functions or services.

[1538] A "web platform" is a system or site that provides services over the Internet.

[1539] MODE FOR CARRYING OUT THE INVENTION

[1540] The present invention provides a system that enables marketing personnel to efficiently generate advertising proposals and create presentation materials and presentation videos. The device configuration and processing procedure are described below in detail.

[1541] System Configuration

[1542] Hardware:

[1543] Smartphone

[1544] server

[1545] Cloud Storage

[1546] software:

[1547] Python

[1548] Flask

[1549] OpenAI API

[1550] Database (e.g. MongoDB)

[1551] User interface frameworks (e.g., React Native)

[1552] Data entry and submission

[1553] Users use a dedicated smartphone application to input target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits). The input data is converted into JSON format and sent to the server.

[1554] Generate advertising proposals

[1555] The server generates ad suggestions using OpenAI's AI model based on the target information and product description it receives. Specifically, it passes data in the following text format as a prompt to the AI ​​model.

[1556] Example prompt sentence:

[1557] Target information: Women in their 30s, working mothers. Product description: Organic cosmetics that are gentle on the skin. Please refer to past advertising examples to generate optimal advertising proposals.

[1558] View and approve ad proposals

[1559] The generated ad proposals are displayed in the form of cards on the user interface of the smartphone application, and the user can select the best one from multiple proposals and approve it with a tap or click.

[1560] Presentation and video generation

[1561] Based on the advertising proposal approved by the user, the server automatically generates presentation materials and audio narration. The presentation materials include product descriptions, target information, selling points, advertising visuals, etc. Next, the server generates audio narration and incorporates it into the presentation materials to create a presentation video.

[1562] Providing and uploading videos

[1563] The generated presentation video is temporarily stored in cloud storage, where users can preview it or view it via a link. If there are no problems with the content, the presentation video will be automatically uploaded to the designated web platform with the user's approval.

[1564] This allows marketers to efficiently and quickly input target information and product descriptions, use AI models to generate optimal advertising ideas, and quickly create presentation materials and videos, which can then be uploaded to the web.

[1565] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1566] Step 1:

[1567] The user enters target information and product description into the smartphone application. The entered data is converted into JSON format.

[1568] Input: Target information (e.g., age, gender, occupation), product description (e.g., product features, benefits)

[1569] Output: JSON format data (e.g., {"target_info": "Woman in her 30s, working mother", "product_desc": "Skin-friendly organic cosmetics"})

[1570] Step 2:

[1571] The device sends JSON format data to the server.

[1572] Input: JSON format data

[1573] Output: Data sent to the server

[1574] Step 3:

[1575] The server converts the received data into a prompt sentence to be passed to the AI ​​model. The prompt sentence is in text format based on the target information and product description.

[1576] Input: JSON format data

[1577] Output: Prompt text (e.g., "Target information: women in their 30s, working mothers, product description: organic cosmetics that are gentle on the skin. Please generate the optimal ad proposal by referring to past ad examples.")

[1578] Step 4:

[1579] The server uses OpenAI's API to input the prompt text into the AI ​​model and generate advertising proposals.

[1580] Input: prompt statement

[1581] Output: Generated ad ideas (e.g. text of multiple ad ideas)

[1582] Step 5:

[1583] The server returns the generated advertising proposals to the smartphone application.

[1584] Input: Generated ad ideas

[1585] Output: Data for the user interface

[1586] Step 6:

[1587] The device displays ad suggestions in the form of cards on the user interface, and the user can select and approve the best one from multiple ad suggestions.

[1588] Input: Data for the user interface

[1589] Output: ID of the ad proposal that the user accepted

[1590] Step 7:

[1591] The server automatically generates presentation materials and audio narration based on the ID of the approved advertising proposal.

[1592] Input: Approved ad proposal ID

[1593] Output: Presentation materials, audio narration

[1594] Step 8:

[1595] The server generates a presentation video based on the presentation materials and audio narration, and the generated presentation video is saved in cloud storage.

[1596] Input: Presentation materials, voice narration

[1597] Output: Presentation video

[1598] Step 9:

[1599] A preview link for the presentation video will be provided to the user, who can then review the video and approve it if there are no issues with the content.

[1600] Input: Preview link of presentation video

[1601] Output: Acknowledgement from the user

[1602] Step 10:

[1603] The server will automatically upload the approved presentation video to the designated web platform.

[1604] Input: Approval from the user

[1605] Output: Presentation video uploaded to the web platform

[1606] 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.

[1607] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the advertising proposals, which are then automatically uploaded to the web. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and collect, analyze, and reflect emotional data when selecting advertising proposals.

[1608] Main processes and their operations

[1609] A means of inputting target information and product descriptions

[1610] User: Enter target information (e.g., age, gender, occupation) and product description (e.g., product features, benefits) into a dedicated input form and press the send button.

[1611] example)

[1612] Target information: Women in their 30s, working mothers

[1613] Product description: Skin-friendly organic cosmetics

[1614] Means for sending target information and product description to the server

[1615] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[1616] Means for generating advertisement proposals by the server

[1617] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[1618] A means of recognizing user emotions with an emotion engine

[1619] Device: The generated ad ideas are displayed in the form of cards on the user interface. At the same time, an emotion engine is activated to collect emotional data from facial expressions, tone of voice, etc. while the user is viewing the ad ideas.

[1620] example)

[1621] Advertisement idea 1: Elegant design using natural materials

[1622] Advertisement idea 2: Skin care that is gentle on mothers raising children

[1623] Analyzing sentiment data and adjusting advertising proposals

[1624] Server: Analyzes the emotional data collected by the emotion engine and evaluates the effectiveness of advertising proposals. It has the ability to automatically adjust parts of advertising proposals (visuals and catchphrases) based on user emotions.

[1625] A means of selecting and approving advertising proposals

[1626] User: Select the best ad from the displayed suggestions. After selecting, click the approve button. At this point, a final analysis of the sentiment data is also performed.

[1627] A means of automatically generating presentation materials and narration

[1628] Server: Calls up the "natural language processing tool" and automatically generates presentation materials based on the selected advertising proposal and emotional data. The materials include target information, product descriptions, advertising visuals, and selling points in slide format. Next, an audio narration is automatically generated and incorporated into the presentation materials.

[1629] example)

[1630] Slide 1: Target Information and Product Description

[1631] Slide 2: Generated ad visual

[1632] Slide 3: Key selling points

[1633] A means to provide users with presentation videos and automatically upload them to the web

[1634] Server: Temporarily saves the generated presentation video and provides the user with a confirmation link or preview. Notifies the user of this link.

[1635] Final approval and upload of presentation video

[1636] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[1637] Terminal: Notifies the server of the user's final approval.

[1638] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[1639] This allows users to efficiently carry out a series of tasks, from generating advertising proposals incorporating emotion data to creating presentations and finally uploading them to the web. By using the system of this invention, it is expected that advertising design will become faster, more efficient, and of higher quality.

[1640] The processing flow will be explained below.

[1641] Specific processing steps of the function

[1642] Step 1:

[1643] User: Enter target information and product description. Enter the required information in the dedicated input form (e.g., female in her 30s, skin-friendly organic cosmetics) and press the send button.

[1644] example)

[1645] Target information: Women in their 30s, working mothers

[1646] Product description: Skin-friendly organic cosmetics

[1647] Step 2:

[1648] Terminal: Sends the entered target information and product description to the server. This data is packaged in JSON format and sent to the server using an HTTP request.

[1649] Step 3:

[1650] Server: Calls the AI ​​model based on the received target information and product description. The AI ​​model learns from past advertising case data and generates advertising ideas that are likely to resonate with the target.

[1651] Step 4:

[1652] Server: The generated multiple advertising proposals (e.g., elegant designs using natural materials, skin care products that are gentle on mothers raising children) are sent again to the device in JSON format.

[1653] Step 5:

[1654] Terminal: The received ad proposal is displayed in the form of a card on the user interface. At the same time, an emotion engine is activated to collect emotional data in real time from facial expressions, tone of voice, etc. while the user is viewing the ad proposal.

[1655] Step 6:

[1656] User: Expresses their feelings about the displayed ad suggestions and selects the most suitable one.

[1657] Step 7:

[1658] Emotion Engine: While the user is viewing the ad proposal, emotional data is collected from facial expressions, voice, mouse movements, etc. The collected data is temporarily stored.

[1659] Step 8:

[1660] Server: Analyzes the emotion data collected by the emotion engine and evaluates the effectiveness of the ad suggestions until the user makes a selection. If necessary, it resends optimized ad suggestions to the device.

[1661] Step 9:

[1662] User: Review the optimized ad proposals and approve the final ad proposal.

[1663] Step 10:

[1664] Terminal: After receiving the user's approval, the data of the selected advertisement proposal is sent back to the server.

[1665] Step 11:

[1666] Server: Calls the "presentation material generation tool" and "voice narration generation tool" and automatically generates presentation materials and narration based on the selected advertising proposal and emotion data.

[1667] example)

[1668] Slide 1: Target Information and Product Description

[1669] Slide 2: Generated ad visual

[1670] Slide 3: Key selling points

[1671] Step 12:

[1672] Server: Incorporates narration into presentation materials, completes the presentation video, and temporarily saves the completed presentation video.

[1673] Step 13:

[1674] Server: Provide the user with a confirmation link or preview of the completed presentation video. Notify the user of this link.

[1675] Step 14:

[1676] User: Checks the provided link or preview to make sure there are no issues with the content, and if there are no issues, presses the final approval button.

[1677] Step 15:

[1678] Terminal: Notifies the server of the user's final approval.

[1679] Step 16:

[1680] Server: Automatically uploads the approved presentation video to the designated web platform. If the upload is successful, the URL is sent back to the device.

[1681] This series of processes allows users to efficiently complete tasks from generating advertising proposals incorporating emotional data to creating presentations and finally uploading them to the web.

[1682] Example 2

[1683] 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."

[1684] Conventional ad generation systems have had issues with incorporating user emotional data to evaluate the effectiveness of ads, and with insufficient feedback to optimize the accuracy and effectiveness of ads. Furthermore, there is a lack of an efficient way to automatically create presentation materials and videos based on the generated ad ideas and automatically upload them to a network.

[1685] 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.

[1686] In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to a computer connected to a network, means for the computer to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for collecting user emotion data and evaluating the effectiveness of the advertising proposals, means for the user to select and approve the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, and means for providing the generated presentation video to the user and automatically uploading it to the network. This makes it possible to generate advertising proposals that reflect the user's emotions, and further makes it possible to efficiently create presentation materials and presentation videos based on the advertising proposals and share them seamlessly on the network.

[1687] "Target information" refers to attribute data such as age, gender, and occupation of specific advertising targets.

[1688] "Product description" refers to detailed information about the product being advertised, such as its features and benefits.

[1689] A "networked computer" refers to a computing device that is capable of communicating over a network, such as the Internet.

[1690] "Advertising Proposal" refers to an advertising idea or plan generated based on target information and product description.

[1691] "Emotion data" refers to data related to emotions collected from the user's facial expressions, tone of voice, etc.

[1692] "Presentation materials" refers to slide-format materials created to explain the contents of an advertising proposal.

[1693] "Natural language processing tools" refers to artificial intelligence techniques used to analyze, generate, and transform text data.

[1694] "Presentation video" refers to a video presentation created by incorporating audio narration into presentation materials.

[1695] This system automatically generates optimal advertising proposals by inputting and transmitting target information and product descriptions, referring to past advertising examples, and then generates presentation materials and videos based on the advertising proposals, which are then automatically uploaded to the web. Furthermore, by combining it with an emotion engine, it has the ability to recognize user emotions and collect, analyze, and reflect emotional data when selecting advertising proposals.

[1696] The user first enters target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into a dedicated input form, and then presses the submit button. At this time, appropriate validation is performed for each field in the input form. As a specific example, the target is working mothers in their 30s, and the product description is entered as "skin-friendly organic cosmetics."

[1697] The terminal packages the information entered by the user in JSON format and sends it to the server as an HTTP request. The JSON data is generated by a JavaScript function. For example, you can generate a prompt like this:

[1698] "Please create an ad idea for organic cosmetics that are gentle on the skin and target working mothers in their 30s. Please refer to past success stories."

[1699] The server analyzes the received target information and product description and calls up a generative AI model (e.g., OpenAI GPT-3) installed on it. The AI ​​model has learned from past advertising case data and generates advertising ideas that are likely to resonate with the target based on the input data.

[1700] The generated ad suggestions are sent to the device and displayed in the form of cards on the user interface. At the same time, the device activates an emotion engine (e.g., Microsoft Azure Cognitive Services) to collect emotional data through facial expressions and tone of voice while the user is viewing the ad suggestions. Specific examples of generated ad suggestions include:

[1701] Advertisement idea 1: Elegant design using natural materials

[1702] Advertisement idea 2: Skin care that is gentle on mothers raising children

[1703] The server analyzes the emotional data sent from the device and evaluates the effectiveness of the proposed ad. This analysis uses collected emotional data (e.g., frequency of smiling, tone of voice). If necessary, elements of the proposed ad, such as visuals and catchy copy, are adjusted.

[1704] The user selects the best one from the multiple ad ideas provided and clicks the approval button. The selected ad idea and the final emotion data are sent to the server, and the system proceeds to the next step.

[1705] The server calls a natural language processing tool (e.g., OpenAI GPT-3) based on the selected advertising proposal and emotion data to automatically generate presentation materials. The materials are composed of slides and include target information, product descriptions, advertising visuals, and selling points. A voice synthesis engine (e.g., Amazon Polly) is also used to generate narration voices, which are incorporated into the presentation materials. For example, the following slides are generated:

[1706] Slide 1: Target Information and Product Description

[1707] Slide 2: Generated ad visual

[1708] Slide 3: Key selling points

[1709] The server temporarily saves the generated presentation video and provides a confirmation link or preview to the user. If the user checks the link or preview and determines that the content is OK, they click the final approval button.

[1710] Once final approval is given, the device notifies the server, which then automatically uploads the approved presentation video to a designated web platform (e.g., YouTube, Vimeo). If the upload is successful, the URL is sent back to the user's device.

[1711] This allows users to efficiently create advertisement proposals, create presentations, and finally upload them to the web. The system of the present invention is expected to speed up advertisement design, improve efficiency, and improve the quality of advertisement design.

[1712] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1713] Step 1:

[1714] The user enters target information (e.g., age, gender, occupation) and product description (e.g., product features and benefits) into the input form and presses the submit button. The input data is for target information to be "women in their 30s, working mothers" and for product description to be "skin-friendly organic cosmetics." The input data is formatted as a JSON-formatted object.

[1715] Input: Target information, product description

[1716] Output: JSON format object (target information and product description)

[1717] Step 2:

[1718] The device packages the target information and product description entered by the user and sends it to a computer (server) connected to the network using an HTTP POST request, generating JSON format data using JavaScript.

[1719] Input: JSON formatted object

[1720] Output: HTTP POST request

[1721] Step 3:

[1722] The server analyzes the HTTP POST request received from the device and obtains target information and product description in JSON format. It then invokes a generative AI model (e.g., OpenAI GPT-3) to generate a prompt based on past advertising case data. The generated prompt is then input into the AI ​​model to generate advertising proposals.

[1723] Input: Target information and product description in JSON format

[1724] Output: Generated ad ideas

[1725] Step 4:

[1726] The device displays the generated ad suggestions received from the server in the form of cards on the user interface. At the same time, it launches an emotion engine (e.g., Microsoft Azure Cognitive Services) to collect facial expressions and tone of voice while the user is viewing the ad suggestions. The collected emotion data is temporarily stored in a local database.

[1727] Input: Generated ad ideas

[1728] Output: Display on the user interface, collected emotion data

[1729] Step 5:

[1730] The server analyzes the emotional data sent from the device and evaluates the effectiveness of the proposed advertisements. Specifically, it automatically adjusts the visuals and catchy copy of the proposed advertisements based on emotional data such as the frequency of smiling and tone of voice.

[1731] Input: Emotion data

[1732] Output: Adjusted ad proposals

[1733] Step 6:

[1734] The user selects the best ad from the multiple ad ideas displayed and clicks the approval button. The selected ad idea and the final emotion data are sent to the server for final analysis.

[1735] Input: Multiple ad ideas

[1736] Output: Selected ad ideas and final sentiment data

[1737] Step 7:

[1738] The server calls a natural language processing tool (e.g., OpenAI GPT-3) based on the selected advertising proposal and emotion data to automatically generate presentation materials. These materials are in the form of slides and include target information, product descriptions, advertising visuals, and selling points. Narration is also generated using a speech synthesis engine (e.g., Amazon Polly) and incorporated into the presentation materials.

[1739] Input: Selected ad idea, emotion data

[1740] Output: Generated presentation materials and narration audio

[1741] Step 8:

[1742] The server temporarily saves the generated presentation video and provides the user with a confirmation link or preview. The user checks the link or preview and confirms that there are no problems with the content. If there are no problems, the user clicks the final approval button.

[1743] Input: Generated presentation video

[1744] Output: Confirmation link or preview

[1745] Step 9:

[1746] The device notifies the server that the user has given final approval. The server then automatically uploads the approved presentation video to a designated web platform (e.g., YouTube, Vimeo). If the upload is successful, the URL is sent back to the device.

[1747] Input: Final approval information

[1748] Output: URL on the web platform

[1749] (Application example 2)

[1750] 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."

[1751] Conventional ad generation systems have difficulty reflecting user emotional data when generating ad proposals, making it difficult to provide optimal ad proposals for the target audience. Furthermore, there is no way to evaluate and adjust the effectiveness of generated ad proposals in real time, meaning users are unable to obtain sufficient information when selecting the optimal ad proposal. Furthermore, the process from creating ad proposals to generating presentation materials and uploading them to the web is cumbersome, making it necessary to perform the process efficiently.

[1752] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting target information, means for inputting product descriptions, means for transmitting the input target information and product descriptions to the information processing device, means for the information processing device to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target, means for displaying the generated advertising proposals, means for the user to select and approve the advertising proposals, means for collecting user emotion data while the generated advertising proposals are displayed, means for the information processing device to analyze the collected emotion data and adjust the advertising proposals, means for automatically generating presentation materials and audio based on the approved advertising proposals, and means for providing the generated presentation video to the user and automatically uploading it to the Web. This makes it possible to generate effective advertising proposals based on user emotion data, evaluate and adjust the advertising proposals in real time, and improve the efficiency of the entire process.

[1753] "Target information" refers to information about the person who is the target of the advertisement, specifically data such as age, gender, and occupation.

[1754] "Product description" is information that describes the features and benefits of the advertised product.

[1755] "Information processing device" refers to a computer or server that receives input data and processes and analyzes it.

[1756] "Past advertising cases" refers to data about previous advertising campaigns and their results.

[1757] An "advertising proposal" is an advertising idea or design created to effectively appeal to a target audience.

[1758] "Emotional data" refers to data relating to the user's psychological reactions collected from facial expressions, tone of voice, and the like.

[1759] "Presentation materials" are materials used to explain advertising proposals and are provided in slide or document format.

[1760] "Audio" refers to the narration and explanatory audio added to presentation materials.

[1761] The "generated presentation video" is video content that is automatically generated based on the advertising proposal.

[1762] "Automatic uploading to the web" is the process of automatically uploading the generated presentation video to a designated platform on the Internet.

[1763] MODE FOR CARRYING OUT THE INVENTION

[1764] To implement this invention, an advertising planner application using a smartphone is constructed. The program of this system and its processing are explained below.

[1765] Hardware and software used

[1766] Hardware

[1767] Smartphone (iOS or Android)

[1768] software

[1769] Frontend: React Native, Expo

[1770] Backend: Node.js, Express

[1771] Database: MongoDB

[1772] AI model: Python (TensorFlow, PyTorch)

[1773] Emotion engine: OpenCV, DLIB

[1774] Natural Language Processing: GPT-4 API (OpenAI)

[1775] System processing flow

[1776] 1. Enter target information and product description:

[1777] Users enter target information (age, gender, occupation) and product description (product features, benefits) into the smartphone app's input form. This data is sent in JSON format to a back-end information processing device.

[1778] 2. Generate advertising ideas:

[1779] The information processing device calls the generative AI model (GPT-4) and generates optimal advertising proposals based on past advertising case data. At this time, the information processing device refers to the advertising case data stored in the database.

[1780] 3. Launching the emotion engine and collecting emotion data:

[1781] The app displays advertising ideas in the form of cards on the user interface. At the same time, it uses the smartphone's camera and microphone to collect the user's emotional data (facial expressions, tone of voice). It uses OpenCV and DLIB to recognize facial expressions, and this data is sent to an information processing device in real time.

[1782] 4. Analyze sentiment data and adjust advertising proposals:

[1783] The information processing device analyzes the collected emotional data, evaluates the effectiveness of the ad proposal, and, if necessary, automatically adjusts parts of the ad proposal (visuals and catchphrases) using a generative AI model.

[1784] 5. Automatic generation of presentation materials and narration:

[1785] Based on the selected advertising proposal, the information processing device generates presentation materials and narration using natural language processing tools (GPT-4 API).

[1786] 6. Providing a video of your presentation and uploading it to the web:

[1787] The generated presentation video is temporarily saved and a confirmation link is provided to the user. After the user gives their final approval, the presentation video is automatically uploaded to the designated web platform and the user is notified of the URL upon successful upload.

[1788] Examples of concrete examples and prompts

[1789] Specific examples

[1790] Target information: Women in their 30s, working mothers

[1791] Product description: Skin-friendly organic cosmetics

[1792] Prompt Sentence Examples

[1793] Target Information:

[1794] Age: 30s

[1795] Gender: Female

[1796] Occupation: Working mom

[1797] Product Description:

[1798] Product name: Organic cosmetics

[1799] Feature: Gentle on the skin

[1800] Advantages: Made from natural materials

[1801] Based on this target information and product description, please refer to similar past advertising examples and generate an ad proposal that will appeal to your target. The ad proposal should include visual suggestions and a catchy copy.

[1802] In this way, by implementing the present invention, users can generate effective advertising proposals based on emotional data, evaluate and adjust the advertising proposals in real time, and streamline the entire process.

[1803] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1804] Step 1:

[1805] Input and output: The user enters target information (age, gender, occupation) and product description (product features, benefits) into the smartphone app form and presses the submit button. The entered data is sent to the backend server in JSON format.

[1806] Operation: The terminal triggers a click event on the send button, packages the target information and product description in JSON format, and sends the data to the server using an HTTP POST request.

[1807] Step 2:

[1808] Input and output: Based on the target information and product description received by the server, the generative AI model (GPT-4) is called and the optimal advertising proposal is generated using past advertising case data. The output is the generated advertising proposal.

[1809] How it works: The server parses the received data and constructs a prompt. It then calls the GPT-4 API and generates ad suggestions using this prompt as input. These ad suggestions are stored in a database and ready to be sent to the frontend.

[1810] Step 3:

[1811] Input and output: The generated ad proposals are sent to the terminal and displayed in the form of cards on the app interface. The output is the displayed ad proposals.

[1812] Operation: The server sends the generated ad proposals in JSON format to the device. The device analyzes the received data and displays the ad proposals in a card format on the user interface.

[1813] Step 4:

[1814] Input and Output: When a user views an ad, emotional data is collected using a camera and microphone. The input is the user's facial expression and tone of voice, and the output is the collected emotional data.

[1815] How it works: The device displays ad suggestions and activates the smartphone's camera and microphone, then analyzes the user's facial expressions and tone of voice using OpenCV and DLIB. The collected emotional data is sent to the server in real time.

[1816] Step 5:

[1817] Input and output: The server analyzes the collected emotional data and evaluates and adjusts the effectiveness of advertising proposals. The input is the emotional data, and the output is the adjusted advertising proposals.

[1818] How it works: The server analyzes the collected emotion data and evaluates the ad suggestions. If necessary, it calls the generative AI model again to generate adjusted ad suggestions. These adjusted ad suggestions are then presented to the user again.

[1819] Step 6:

[1820] Input and Output: The user selects and approves the best ad suggestion. The input is the user's selection, and the output is the selected ad suggestion.

[1821] Operation: The terminal records the user's selection and sends the selected ad proposal data to the server, which receives the selection data and prepares to process the information again.

[1822] Step 7:

[1823] Input and output: The server automatically generates presentation materials and audio based on the selected advertising proposal. The input is the selected advertising proposal, and the output is the generated presentation materials and audio.

[1824] How it works: Based on the selected ad proposal, the server uses natural language processing tools (GPT-4 API) to generate presentation materials. The materials include target information, product descriptions, ad visuals, and selling points in slide format. Next, audio narration is automatically generated and incorporated into the video format.

[1825] Step 8:

[1826] Input and Output: The generated presentation video is temporarily saved and a confirmation link is provided to the user. The input is the generated presentation video, and the output is the confirmation link.

[1827] How it works: The server saves the generated presentation video and sends the user a preview link before finalizing it. The user clicks the link to check the content and approve or modify it.

[1828] Step 9:

[1829] Input and Output: After the user gives their final approval, the server will automatically upload the generated presentation video to the designated web platform. The input is the user's approval, and the output is the URL of the uploaded video.

[1830] How it works: After the user gives their final approval, the server will automatically upload the presentation video to the designated web platform. If the upload is successful, the URL will be sent to the user.

[1831] 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.

[1832] 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.

[1833] 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.

[1834] 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.

[1835] 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.

[1836] 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.

[1837] 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).

[1838] 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.

[1839] 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."

[1840] 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.

[1841] 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).

[1842] 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.

[1843] 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.

[1844] 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.

[1845] 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.

[1846] 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.

[1847] 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.

[1848] 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.

[1849] 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.

[1850] 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.

[1851] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1852] The following is further disclosed regarding the above embodiment.

[1853] (Claim 1)

[1854] a means for inputting target information;

[1855] a means for inputting a product description;

[1856] means for transmitting the input target information and product description to a server;

[1857] A means for the server to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target;

[1858] means for displaying the generated advertising proposals;

[1859] a means for a user to select and approve proposed advertisements;

[1860] a means for automatically generating presentation materials and audio based on the approved advertising proposal;

[1861] The system provides the generated presentation video to the user and has a means for automatically uploading it to the Web.

[1862] (Claim 2)

[1863] 10. The system of claim 1, wherein the generated advertising proposals are displayed in a card format.

[1864] (Claim 3)

[1865] The system according to claim 1, wherein a natural language processing tool is used to create presentation materials.

[1866] "Example 1"

[1867] (Claim 1)

[1868] a means for inputting target information;

[1869] a means for inputting a product description;

[1870] means for transmitting the input target information and product description to a server;

[1871] A means for the server to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target;

[1872] means for displaying the generated advertising proposals;

[1873] a means for a user to select and approve proposed advertisements;

[1874] a means for automatically generating presentation materials and audio based on the approved advertising proposal;

[1875] A means for providing the generated presentation video to the user and automatically uploading it to the web;

[1876] A way to display multiple advertising ideas in a card format for easy visual comparison,

[1877] A system that includes a means for automatically generating audio narration and incorporating it into presentation materials.

[1878] (Claim 2)

[1879] 10. The system of claim 1, wherein the generated advertising proposals are displayed in a card format.

[1880] (Claim 3)

[1881] The system according to claim 1, wherein a natural language processing tool is used to create presentation materials.

[1882] "Application Example 1"

[1883] (Claim 1)

[1884] a means for inputting target information;

[1885] a means for inputting a product description;

[1886] means for transmitting the input target information and product description to a server;

[1887] A means for the server to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target;

[1888] means for displaying the generated advertising proposals;

[1889] a means for a user to select and approve proposed advertisements;

[1890] a means for automatically generating presentation materials and audio based on the approved advertising proposal;

[1891] A means for providing the generated presentation video to the user and automatically uploading it to the web;

[1892] A means to function as a smartphone application for marketers,

[1893] A means for transmitting target information and product description in JSON format to a server;

[1894] A system including means for generating advertising suggestions using an AI model.

[1895] (Claim 2)

[1896] 10. The system of claim 1, wherein the generated advertising proposals are displayed in a card format.

[1897] (Claim 3)

[1898] The system according to claim 1, wherein a natural language processing tool is used to create presentation materials.

[1899] "Example 2: Combining Emotion Engines"

[1900] (Claim 1)

[1901] a means for inputting target information;

[1902] a means for inputting a product description;

[1903] means for transmitting the input target information and product description to a computer connected to a network;

[1904] A means for the computer to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target;

[1905] means for displaying the generated advertising proposals;

[1906] a means for collecting user sentiment data and evaluating the effectiveness of advertising proposals;

[1907] a means for a user to select and approve proposed advertisements;

[1908] a means for automatically generating presentation materials and audio based on the approved advertising proposal;

[1909] The system includes a means for providing the generated presentation video to the user and automatically uploading it to a network.

[1910] (Claim 2)

[1911] 10. The system of claim 1, wherein the generated advertising proposals are displayed in a card format.

[1912] (Claim 3)

[1913] The system according to claim 1, wherein a natural language processing tool is used to create presentation materials.

[1914] "Application example 2 when combining emotion engines"

[1915] (Claim 1)

[1916] a means for inputting target information;

[1917] a means for inputting a product description;

[1918] means for transmitting the input target information and product description to an information processing device;

[1919] means for the information processing device to learn from past advertising examples and generate advertising proposals that are likely to appeal to targets;

[1920] means for displaying the generated advertising proposals;

[1921] a means for a user to select and approve proposed advertisements;

[1922] means for collecting user emotion data while displaying the generated advertisement proposal;

[1923] means for the information processing device to analyze the collected emotion data and adjust the advertising proposal;

[1924] a means for automatically generating presentation materials and audio based on the approved advertising proposal;

[1925] The system provides the generated presentation video to the user and has a means for automatically uploading it to the Web.

[1926] (Claim 2)

[1927] 10. The system of claim 1, wherein the generated advertising proposals are displayed in a card format.

[1928] (Claim 3)

[1929] The system according to claim 1, wherein a natural language processing tool is used to create presentation materials. [Explanation of symbols]

[1930] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for inputting target information; a means for inputting a product description; means for transmitting the input target information and product description to a server; A means for the server to learn from past advertising examples and generate advertising proposals that are likely to appeal to the target; means for displaying the generated advertising proposals; a means for a user to select and approve proposed advertisements; a means for automatically generating presentation materials and audio based on the approved advertising proposal; The system also has a means for providing the generated presentation video to the user and automatically uploading it to the Web.

2. The system according to claim 1, wherein the generated advertising proposals are displayed in a card format.

3. The system according to claim 1, wherein a natural language processing tool is used to create presentation materials.

Images