System

Abstract

A system is provided.SOLUTION: A system comprising means for collecting and storing data, means for training a generative AI model using a machine-learning algorithm, means for accepting a request to generate a CM through an input interface, means for automatically generating a scenario of the CM using the generative AI model, means for integrating selected material to generate the CM, means for providing a preview of the generated CM, means for receiving feedback and generating the CM again using the generative AI, means for publishing the generated CM to a designated platform and collecting views and engagement data.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] Conventional commercial production methods have had problems with high costs and long production times. Furthermore, viewers tend to passively watch commercials as "commercials that are just shown to them," limiting the effectiveness of advertising. A particular issue is the inability to effectively reach young people. Furthermore, while there is a demand for quickly producing unique and topical commercials, it has been difficult to achieve this with existing methods. [Means for solving the problem]

[0005] The present invention is a system that includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for accepting commercial generation requests through an input interface, means for automatically generating commercial scenarios using the generative AI model, means for generating commercials by integrating selected materials, means for providing previews of the generated commercials, means for receiving feedback and again using the generative AI to generate commercials that reflect the modifications, and means for publishing the generated commercials on a specified platform and collecting view counts and engagement data. This allows commercials to be generated quickly and at minimal cost, realizing commercials that viewers actively "come to see." Furthermore, the ability to receive feedback and modify commercials based on that feedback enables flexible and effective advertising.

[0006] "Data" refers to information and materials, especially images, text, video clips, music, etc., used in the production of a commercial.

[0007] "Means" refers to a method, device, process, etc. used to achieve a particular purpose.

[0008] A "server" refers to a computer system that provides services to other computers over a network.

[0009] A "machine learning algorithm" is a computer algorithm that learns patterns and rules from data and makes predictions and classifications based on the results of that learning.

[0010] A "generative AI model" is a model trained using generative AI technology that has the ability to automatically generate new content based on input data.

[0011] "Input interface" refers to the devices and software that allow a user to input data and instructions into a system.

[0012] "CM Generation Request" means a request containing information and instructions for generating a CM based on specified requirements.

[0013] A "scenario" refers to a script or storyboard that describes the content of a commercial or video work.

[0014] "Materials" refers to various content elements used in the production of commercials, such as images, videos, music, text, etc.

[0015] "Preview" refers to a temporary display or playback of content to allow you to check it before final release.

[0016] "Feedback" refers to evaluations and requests for corrections provided by users regarding content generated by the system.

[0017] "Platform" refers to services and systems for distributing and publishing content such as commercials, such as internet sites and social media.

[0018] "Engagement data" is data that shows how users interact with content, including the number of views, shares, and comments. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention is an innovative commercial production system that uses generative AI technology, and is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and users who provide feedback, etc.

[0041] The system operates as follows.

[0042] First, the user provides the data required for commercial production, including product images, text descriptions, music and video clips to be used in the promotion, etc. This data is collected on the server and stored in a database in an appropriate format.

[0043] The server then uses machine learning algorithms to train a generative AI model based on the stored data. Data preprocessing includes adjusting the size of image data and removing noise from audio data. The trained generative AI model can then learn various viewer preferences and commercial generation patterns, allowing it to generate unique scenarios.

[0044] The device then accepts a request to create a commercial through an interface, where the user inputs specific requirements such as target audience, theme, key message, etc. The input request is then sent to the server.

[0045] Based on the received request, the server automatically generates a scenario using a generative AI model. Based on the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from a database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0046] The generated initial version of the commercial is provided as a preview on the device. The user checks this preview and sends any necessary corrections as feedback to the server. The server analyzes the feedback and extracts corrections. The generative AI model is run again to reflect the extracted corrections, and the final version of the commercial is generated.

[0047] The final commercial is published on the platform of your choice by the server, which then collects real-time engagement data, such as the number of views, shares, and comments, to help inform future commercial production.

[0048] By using this system, unique commercials can be automatically generated quickly and at low cost, resulting in "captivating commercials" that viewers will want to watch. In addition, since the system can be flexibly revised based on feedback, it is possible to maximize advertising effectiveness.

[0049] Specific examples

[0050] Let's say a company wants to promote a new product and requests the production of a commercial through this system.

[0051] Users (marketers) provide details of new products and promotional materials to the system, and this data is collected and stored by the server.

[0052] Marketers then use the interface to input their requests for new commercials, specifying that the target audience is young and the theme is adventurous and fun.

[0053] The server receives these requirements and uses a generative AI model to create a scenario. Based on the scenario, relevant materials are selected from a database and an initial version of the commercial is automatically generated.

[0054] The generated initial version of the commercial is displayed as a preview on the device, and the marketing staff can check it. If they feel that any part of the scenario needs to be revised, they can provide specific feedback on the revisions to the server.

[0055] The server analyzes the feedback and generates the final ad incorporating the changes. Once the final ad is complete, it is published on the designated platform, where viewer numbers and engagement data are collected in real time.

[0056] In this way, companies can create and release highly effective commercials quickly and with minimal effort.

[0057] The processing flow will be explained below.

[0058] Step 1:

[0059] Users provide the data needed to create a new commercial, including product images, text descriptions, music, video clips, and other promotional materials, which are uploaded through a dedicated interface.

[0060] Step 2:

[0061] The server receives the provided data, converts it to the appropriate format, and stores it in a database: for example, images are converted to the appropriate resolution, and text is formatted into a standard format.

[0062] Step 3:

[0063] The server performs data preprocessing based on the stored data, including resizing and color correction of image data and noise reduction of audio data.

[0064] Step 4:

[0065] The server uses the preprocessed data to train a generative AI model using machine learning algorithms, which study past commercial data and viewer preferences to identify new patterns.

[0066] Step 5:

[0067] The terminal (company marketing staff) inputs a request for commercial production through a dedicated interface. The request includes the target audience, theme, main message, etc. This request is then sent to the server.

[0068] Step 6:

[0069] The server runs the generative AI model based on the received request and automatically generates a commercial script, including a storyboard and narration script.

[0070] Step 7:

[0071] Based on the generated scenario, the server selects appropriate materials (images, video clips, music, etc.) from a database and integrates them to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0072] Step 8:

[0073] The server provides the generated initial version of the commercial as a preview to the device, and the user (company representative) can check the preview through the device interface.

[0074] Step 9:

[0075] The user views the generated initial version of the commercial, inputs any necessary modifications, and sends the feedback to the server, which may include corrections to the scenario or the addition of new material.

[0076] Step 10:

[0077] The server analyzes the feedback and lists the extracted corrections. Based on this list, the generative AI model is run again to generate the final commercial that reflects the corrections.

[0078] Step 11:

[0079] The server re-encodes the final commercial and prepares it for publication on the designated platform (YouTube, social media, etc.). After publication, view counts and engagement data (number of shares, number of comments, etc.) are collected in real time.

[0080] Step 12:

[0081] The server analyzes the collected engagement data and evaluates the effectiveness of the advertisement, which will be used to generate future commercials.

[0082] Example 1

[0083] 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."

[0084] The traditional commercial production process is time-consuming and costly, and it is difficult to adjust the quality of the content and tailor it to viewer preferences. Furthermore, the selection of materials and the creation of scripts are done manually, which is inefficient and can result in insufficient advertising effectiveness. Given these circumstances, there is a demand for a system that can quickly and automatically generate high-quality commercials and flexibly make revisions based on feedback.

[0085] 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.

[0086] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial that reflects corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, means for preprocessing data necessary for commercial production, and means for analyzing the provided feedback and extracting corrections. This makes it possible to quickly and efficiently generate high-quality commercials and adjust content to suit viewer preferences.

[0087] "Means for collecting and storing data" means a combination of hardware and software for receiving user-provided data such as images, audio, text, and video, and storing it in an appropriate database.

[0088] A "means for training a generative AI model using a machine learning algorithm" is a component of a system that runs a machine learning algorithm using collected data to train a generative AI model.

[0089] "Means for accepting commercial creation requests through an input interface" refers to an interface that allows users to input commercial creation requirements (target audience, theme, main message, etc.) to the system, and a mechanism for transmitting that input to the server.

[0090] A "means for automatically generating a commercial scenario using a generative AI model" is a component of a system that uses a trained generative AI model to automatically create a commercial scenario based on collected data and user requests.

[0091] The "means of integrating selected materials to generate a commercial" refers to a combination of editing software and hardware that selects appropriate images, audio, video, and other materials from a database in accordance with the generated scenario, and integrates them to create a single commercial.

[0092] The "means for providing a preview of the generated commercial" refers to an interface and a mechanism for playing back the video so that the user can check the generated commercial.

[0093] The "means of receiving feedback and using a generation AI to generate a commercial that reflects the corrections" refers to a generation AI and its control system that analyzes the feedback provided by the user and regenerates a new commercial that reflects the corrections.

[0094] "Means of publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to a system component that uploads the completed commercial to a public platform such as YouTube or social media, and collects viewing data and user engagement data in real time.

[0095] "Means for preprocessing data required for commercial production" refers to a system component that performs preprocessing such as resizing and noise removal to prepare collected image, audio, and text data in a form optimal for training and generation.

[0096] The "means for analyzing the provided feedback and extracting corrections" is a system component that analyzes the feedback from the user using a technique such as text analysis and automatically extracts the necessary corrections.

[0097] This invention is an innovative commercial production system that uses generative AI technology, and is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and a user who provides feedback, etc. This system operates as follows.

[0098] First, the user provides the data required for commercial production, including product images, text descriptions, music and video clips to be used in the promotion, etc. This data is collected on the server and stored in a database in an appropriate format.

[0099] The server then uses machine learning algorithms to train a generative AI model based on the stored data. Specific software used includes Python and TensorFlow. Data preprocessing includes adjusting the size of image data and removing noise from audio data. Once trained, the generative AI model can learn various viewer preferences and commercial generation patterns, allowing it to generate unique scenarios.

[0100] The device then accepts a request to create a commercial through an interface, where the user inputs specific requirements such as target audience, theme, key message, etc. The input request is then sent to the server.

[0101] Based on the received request, the server automatically generates a scenario using a generative AI model. Based on the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from a database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario. The specific hardware used in this process includes a server equipped with a high-performance GPU.

[0102] The generated initial version of the commercial is provided as a preview on the device. The user checks this preview and sends any necessary corrections as feedback to the server. The server analyzes the feedback and extracts corrections. The generative AI model is run again to reflect the extracted corrections, and the final version of the commercial is generated.

[0103] The final commercial is published on the platform of your choice by the server, which then collects real-time engagement data, such as the number of views, shares, and comments, to help inform future commercial production.

[0104] Specific examples

[0105] Let's say a company wants to promote a new product and requests the production of a commercial through this system.

[0106] Users (marketers) provide details of new products and promotional materials to the system, and this data is collected and stored by the server.

[0107] Marketers then use the interface to input their requests for new commercials, specifying, for example, that the target audience is people in their 20s and that the theme is energetic and active.

[0108] The server receives these requirements and uses a generative AI model to create a scenario. Based on the scenario, relevant materials are selected from a database and an initial version of the commercial is automatically generated.

[0109] The generated initial version of the commercial is displayed as a preview on the device, and the marketing staff can check it. If they feel that any part of the scenario needs to be revised, they can provide specific feedback on the revisions to the server.

[0110] The server analyzes the feedback and generates the final ad incorporating the changes. Once the final ad is complete, it is published on the designated platform, where viewer numbers and engagement data are collected in real time.

[0111] In this way, companies can quickly create and publish highly effective commercials with minimal effort, and the entire process is powered by generative AI models and advanced data processing techniques.

[0112] Prompt Sentence Examples

[0113] "Use this system to create a promotional commercial for a new product. The target audience should be in their early 20s, and the theme should be energetic and active. The provided materials include high-resolution images of the product, a description, and a lively, up-tempo song as background music."

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] The user provides the data necessary to create a commercial. Using the device interface, the user uploads high-resolution images of the product, descriptions, music and video clips to be used in the promotion, etc. The inputs include image files, audio files, text files, and video files. This data is sent to the server via the device.

[0117] Step 2:

[0118] The server stores the received data in a database in an appropriate format. Before storing, it performs preprocessing on the data. This includes resizing images and removing noise from audio data. The input is the data in various formats provided in step 1, and the output is the preprocessed data. The server performs these processes using Python and OpenCV.

[0119] Step 3:

[0120] The server uses machine learning algorithms to train a generative AI model based on the stored data. For example, it uses Python and TensorFlow to build and train the model. The input is the preprocessed data and existing training data, and the output is the trained generative AI model.

[0121] Step 4:

[0122] The terminal accepts a request from the user to create a commercial through the interface. The user inputs specific requirements such as target audience, theme, key message, etc. The input is the request information entered by the user through the terminal interface, which is then sent to the server.

[0123] Step 5:

[0124] The server automatically generates a commercial scenario using a generative AI model based on the received commercial generation request. The input is the user's request information and a trained generative AI model, and the output is the generated commercial scenario. The server runs the generative AI model and creates a scenario using a Python script.

[0125] Step 6:

[0126] The server selects appropriate materials from the database based on the generated scenario and integrates them to generate the initial version of the commercial. The materials are integrated using editing software. The input is the generated scenario and materials in the database, and the output is the initial version of the commercial.

[0127] Step 7:

[0128] The terminal provides the generated initial version of the commercial as a preview to the user, who then reviews it and provides feedback on the content. The input is the initial version of the commercial, and the output is the user's feedback. The user uses the interface to fill out and submit a feedback form.

[0129] Step 8:

[0130] The server analyzes the user feedback and extracts corrections, for example, by using text analysis techniques to understand the content of the feedback and list the corrections. The input is the user feedback and the output is the list of corrections.

[0131] Step 9:

[0132] Based on the corrections, the server uses the generative AI model again to generate the final commercial that reflects the corrections. The input is the list of corrections and the commercial material before the corrections, and the output is the final commercial. The generative AI model is run again to integrate the material and create the final version.

[0133] Step 10:

[0134] The final commercial is published by the server on a designated platform, such as YouTube or social media. After publication, the server collects engagement data in real time, including the number of views, shares, and comments. The input is the final commercial and information about the platform on which it was published, and the output is engagement data.

[0135] Prompt Sentence Examples

[0136] "Use this system to create a promotional commercial for a new product. The target audience should be in their early 20s, and the theme should be energetic and active. The provided materials include high-resolution images of the product, a description, and a lively, up-tempo song as background music."

[0137] (Application example 1)

[0138] 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."

[0139] The traditional advertising video production process was time-consuming and costly, and the revision process to incorporate feedback was particularly tedious. It was also difficult to centrally preview advertising videos and collect performance data after release. This made it difficult to respond quickly to maximize advertising effectiveness.

[0140] 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.

[0141] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving an advertisement generation request through an input interface, means for automatically generating an advertisement video scenario using the generative AI model, means for generating an advertisement video by integrating selected materials, means for providing a preview of the generated advertisement video, means for receiving feedback and again using the generative AI to generate an advertisement video reflecting modifications, means for publishing the generated advertisement video on a specified digital platform and collecting view counts and engagement data, and means for providing an application that operates on terminals including smartphones, thereby enabling the generation, modification, publication, and performance monitoring of advertisement videos quickly and efficiently.

[0142] "Means for collecting and storing data" refers to the system elements that collect material data such as images, videos, and music provided by users and store them in a database on the server.

[0143] "Means for training a generative AI model using a machine learning algorithm" refers to the element of using the collected and pre-processed data to train an AI model specialized in generating advertisements using a machine learning algorithm.

[0144] "Means for accepting advertising generation requests through an input interface" refers to a system element that provides an interface for users to input request information (e.g., target demographic and theme) required to generate an advertising video and transmits that information to a server.

[0145] "Means for automatically generating an advertising video scenario using a generative AI model" refers to an element of a system that automatically generates an advertising video scenario based on input request information using a trained generative AI model.

[0146] "Means for integrating selected materials to generate an advertising video" refers to an element of the system that selects optimal images, videos, music, and other materials from a database based on the generated scenario and integrates them to generate an advertising video.

[0147] "Means for providing a preview of the generated advertising video" refers to an element of the system that provides the generated advertising video to a terminal as a preview that can be viewed by a user.

[0148] "Means for receiving feedback and using a generative AI model to generate an advertising video that reflects the corrections" refers to the system elements that receive feedback information from users, analyze it to extract corrections, and use a generative AI model to generate an advertising video that reflects the corrections.

[0149] "Means for publishing the generated advertising video on designated digital platforms and collecting view and engagement data" refers to the system elements that publish the final advertising video on designated platforms (e.g., social media, websites) and subsequently collect engagement data such as the number of views, shares, and comments in real time.

[0150] "Means for providing an application that runs on a device, including a smartphone" means an element of a system that provides a user with a software application that runs on a smartphone or other device and that assists the user in the process of creating, editing, and publishing advertising videos through that application.

[0151] To implement this invention, a means for collecting and storing data is first required. This means collects material data such as images, videos, and music provided by users and stores them in a database on the server. This allows for centralized management of the materials needed to generate advertising videos.

[0152] Next, a means is needed to train the generative AI model using machine learning algorithms. The server uses the collected and preprocessed data to train an AI model specialized for ad generation. This is done using programming languages ​​and frameworks such as Python and TensorFlow. Specifically, preprocessing is performed, such as resizing image data and removing noise from audio data.

[0153] A user can use an input interface to receive an advertisement generation request. This interface can be implemented as a web browser or a smartphone application, and allows the user to input request information such as target audience, theme, etc. The input information is sent to the server and used to generate the advertisement video.

[0154] The server automatically generates an advertising video scenario using the generative AI model. An appropriate scenario is generated based on the request information entered by the user. For example, if a user enters the prompt, "Please generate an advertising scenario with an adventurous and fun theme for young people. Our new product is a waterproof smartwatch," the generative AI model will generate a corresponding scenario.

[0155] The server then synthesizes the selected materials to generate the advertising video. Based on the generated scenario, the server selects the most suitable images, video clips, and music from the database and synthesizes them to generate the advertising video. This process uses a video editing library such as MoviePy.

[0156] The generated advertising video can be previewed by the user. A preview function is implemented on the device, allowing the user to watch the generated advertising video and check its content. If the user needs to make any corrections, they can send them to the server as feedback.

[0157] The server receives the feedback, analyzes it, and extracts corrections. It then uses the generative AI model again to generate an advertising video that reflects the corrections. This process results in the creation of an optimal advertising video that meets the user's needs.

[0158] Finally, the generated advertising video is published on the designated digital platform. The server collects the number of views and engagement data of the published advertising video in real time, which can be used to evaluate the effectiveness of the advertising video and to help with future production.

[0159] As a concrete example, this system can be used when a company wants to promote a new product. A marketer provides the system with detailed information about the new product and promotional materials, inputting that the target audience is young people and the theme is adventurous and fun. The server that receives this request uses a generative AI model to generate a scenario and integrates the materials to automatically generate an initial advertising video. The generated advertising video can be previewed and any necessary corrections can be provided as feedback. The final advertising video is then generated and published on the specified platform.

[0160] This allows for the quick and efficient creation, modification, publishing and performance monitoring of advertising videos.

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] Users upload raw data, such as images, videos, and music, required to generate advertising videos to a server via their terminals. The server collects, organizes, and stores this data in a database. The input data is the raw data provided by the users, and the output data is the organized raw data stored in the database.

[0164] Step 2:

[0165] The server preprocesses the stored material data in the database. Specifically, it adjusts the size of image data and removes noise from audio data. The input data is the material data in the database, and the output data is clean data that has undergone preprocessing.

[0166] Step 3:

[0167] The server uses a machine learning algorithm to train the generative AI model, using preprocessed raw data in the process: the input data is the preprocessed raw data, and the output data is the trained generative AI model.

[0168] Step 4:

[0169] A user sends an advertisement generation request from the terminal to the server through the input interface. The input request includes details such as target audience, theme, main message, etc. The input data is the user's request information, and the output data is the request sent to the server.

[0170] Step 5:

[0171] The server automatically generates an advertising video scenario using a generative AI model based on the received request information. The input data is the user request information and the trained generative AI model, and the output data is the generated scenario. Specifically, the generative AI constructs a scenario based on the prompt sentence.

[0172] Step 6:

[0173] The server selects appropriate materials (images, video clips, music, etc.) from the database based on the generated scenario and integrates them to generate an advertising video. The input data is the generated scenario and the material data in the database, and the output data is the generated advertising video. Specifically, the server uses the MoviePy library to combine the materials and generate the video.

[0174] Step 7:

[0175] The terminal provides a preview of the generated advertising video to the user, and the user checks the preview and sends feedback to the server through a feedback interface, where the input data is the generated advertising video and the output data is the user's feedback.

[0176] Step 8:

[0177] The server analyzes the feedback from the user and extracts the corrections. The input data is the user feedback, and the output data is the list of corrections.

[0178] Step 9:

[0179] The server then runs the generative AI model again based on the extracted corrections to generate an advertising video that reflects the corrections. The input data is the list of corrections and the trained generative AI model, and the output data is the corrected advertising video.

[0180] Step 10:

[0181] The server publishes the generated final advertising video on a specified digital platform (e.g., social media, website), and collects subsequent view counts and engagement data (number of shares, comments, etc.) in real time. The input data is the final advertising video, and the output data is the engagement data collected in real time.

[0182] 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.

[0183] This invention is an innovative commercial production system that uses generative AI technology and combines it with an emotion engine that recognizes user emotions to generate more personalized advertisements. This system is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and users who provide feedback, etc.

[0184] System Overview

[0185] The system operates as follows.

[0186] The user provides the data required for commercial production, including promotional materials such as product images, text descriptions, music, video clips, etc. This data is collected on the server and stored in a database in an appropriate format.

[0187] The server then performs data preprocessing on the stored data, including resizing and color correction of image data and noise reduction of audio data. The preprocessed data is then used to train a generative AI model using machine learning algorithms. The trained generative AI model can then learn various viewer preferences and commercial generation patterns.

[0188] The terminal accepts commercial creation requests through an interface, which allows users to input specific requirements such as target audience, theme, key message, etc. These requests are then sent to the server.

[0189] The server runs the generative AI model based on the received request and automatically generates a commercial scenario. From the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from the database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0190] The generated initial version of the commercial is provided as a preview on the device. The user (company representative) checks the preview and sends any necessary revisions as feedback to the server. At this time, the emotion engine recognizes the user's emotions from their facial expressions and voice, and reflects the results in the feedback analysis.

[0191] The server analyzes the feedback and regenerates the commercial based on the extracted corrections and recognized emotional information. Once the final version is generated, it is published on the designated platform and viewer numbers and engagement data are collected.

[0192] Program processing details

[0193] First, the user provides the data needed to create a new commercial. This data is uploaded through a dedicated interface. The server then receives the data, converts it into a format, and stores it in a database.

[0194] The data stored in the database is pre-processed and then used to train a generative AI model using machine learning algorithms, including data on past commercial successes and viewer preferences.

[0195] Users input their requests for new commercials through an interface, specifying details of the target audience, themes, key messages, etc. The requests are sent to a server, where a generative AI model generates a commercial script based on the requests.

[0196] Based on the generated scenario, related material is selected from a database and a commercial is generated. At this time, an emotion engine recognizes emotions from the user's facial expressions and voice, and based on this information, material selection and script revisions are made.

[0197] An initial version of the commercial is generated and provided as a preview on the device. The user views the preview and provides feedback. The user's emotions, as recognized by the emotion engine, are also used as feedback.

[0198] The server analyzes the feedback and emotional information, again using the AI ​​to make corrections and generate the final commercial. The final commercial is then published on the designated platform, and view counts and engagement data are collected. This engagement data will also be used to generate future commercials.

[0199] Specific examples

[0200] Suppose a company wants to create a commercial to promote its new product "X." The user (the company's marketing manager) provides details about the new product, its target market, and the theme. This data is collected on the server.

[0201] Marketers then use the interface to input specific requests, such as target audience ages 18 to 25 and a theme that is adventurous.

[0202] The server uses a generative AI model to generate an adventurous scenario, selects the necessary materials from a database, and generates an initial commercial. During this process, an emotion engine recognizes the emotions of the user (marketer) and reflects this information in the selection of materials and scenario generation.

[0203] The generated initial version of the commercial is displayed as a preview on the device. The marketer reviews the commercial and, if they feel that any changes are necessary to the scenario or materials, they can submit feedback along with emotional information. The server analyzes the feedback, generates the final version of the commercial, and publishes it.

[0204] The present invention thus implemented can generate commercials that reflect the user's emotions by integrating an emotion engine, thereby providing content that viewers can more easily relate to.

[0205] The processing flow will be explained below.

[0206] Step 1:

[0207] Through a dedicated interface, users provide the data needed to create a new commercial, including promotional materials such as product images, text descriptions, music, and video clips.

[0208] Step 2:

[0209] The server receives the provided data, converts it into an appropriate format, and stores it in a database: for example, image data is converted to an appropriate resolution, and text is formatted into a standard format.

[0210] Step 3:

[0211] The server preprocesses the stored data, including adjusting the size and color of the image data and removing noise from the audio data.

[0212] Step 4:

[0213] The server uses the pre-processed data to train a generative AI model using machine learning algorithms, including past commercial data and viewer preference data.

[0214] Step 5:

[0215] The terminal (a company's marketing staff) inputs a request for commercial production through a dedicated interface. The request includes the target audience, theme, and main message. This request is then sent to the server.

[0216] Step 6:

[0217] The server runs the generative AI model based on the received request and automatically generates a commercial script, including a storyboard and narration script.

[0218] Step 7:

[0219] Based on the generated scenario, the server selects appropriate materials (images, video clips, music, etc.) from a database and integrates them to generate the initial version of the commercial.

[0220] Step 8:

[0221] The server uses an emotion engine to recognize the user's emotions in real time. The emotion engine analyzes the user's emotions from their facial expressions and voice, and incorporates that information as feedback.

[0222] Step 9:

[0223] The server provides the generated initial version of the commercial as a preview to the terminal, and the user can check the preview and input any necessary corrections as feedback through the terminal interface.

[0224] Step 10:

[0225] The server lists corrections based on the received feedback and the analysis results of the emotion engine, and then uses the generative AI model again to generate the final commercial that reflects the corrections.

[0226] Step 11:

[0227] The server prepares the final commercial for publication on the designated platform (YouTube, social media, etc.) After publication, view counts and engagement data (number of shares, number of comments, etc.) are collected in real time.

[0228] Step 12:

[0229] The server analyzes the collected engagement data and evaluates the effectiveness of the advertisement, which will be used to generate future commercials.

[0230] Example 2

[0231] 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."

[0232] Conventional commercial production systems have limited technology for generating advertisements that take viewer preferences into account, making it difficult to automatically generate personalized commercials that reflect user emotions. Furthermore, it is difficult to efficiently generate revised commercials that reflect appropriate feedback, resulting in the challenge of not being able to maximize the impact on viewers.

[0233] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial reflecting the corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, and means for recognizing user emotions and reflecting the emotional information in the feedback. This enables the automatic generation of personalized commercials that reflect the user's emotions, maximizing their impact on viewers.

[0234] "Data collection and storage means" means a device or system that receives user-provided promotional materials such as images, text, music, and video clips, converts them into an appropriate format, and stores them in a database.

[0235] A "means for training a generative AI model using a machine learning algorithm" is an apparatus and technology for carrying out the process of training a generative AI model using preprocessed data.

[0236] "Means for accepting commercial generation requests through an input interface" refers to a device or system that provides an interface for users to input commercial requests (e.g., target audience, theme, message, etc.) and receives the input information.

[0237] "Means for automatically generating a commercial scenario using a generative AI model" refers to devices and technologies for automatically creating a commercial scenario using a generative AI model based on a user request.

[0238] "Means for integrating selected materials to generate a commercial" refers to devices and technologies for selecting appropriate materials (images, music, video clips) from a database based on the generated scenario and integrating them to create a commercial.

[0239] The "means for providing a preview of the generated commercial" is a device or system that provides a preview function that allows a user to visually check the generated commercial.

[0240] "Means for receiving feedback and regenerating a commercial that reflects the corrections using a generative AI" refers to devices and technologies for receiving feedback from users and regenerating and correcting a commercial using a generative AI model based on that feedback.

[0241] "Means for publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to the devices and technologies for uploading the final commercial to a designated online platform and collecting subsequent view counts and viewer engagement data.

[0242] "Means for recognizing the user's emotions and reflecting that emotional information in feedback" refers to a device and technology for recognizing the user's emotions from their facial expressions and voice, and reflecting that emotional information in the analysis of the modification requirements.

[0243] MODE FOR CARRYING OUT THE INVENTION

[0244] This invention is an innovative commercial production system that combines generative AI technology with an emotion engine that recognizes user emotions. An embodiment of this system will be described in detail below.

[0245] System Configuration

[0246] This system operates in collaboration with a server with multiple functions, a terminal with an interface, and a user who provides feedback, etc. The main hardware and software include the following:

[0247] Hardware: High-performance servers, user devices (PCs, tablets, smartphones, etc.)

[0248] Software: OpenCV (image processing library), Librosa (audio processing library), machine learning frameworks (TensorFlow, PyTorch, etc.)

[0249] Program processing overview

[0250] First, the user provides the data needed to create a commercial, including product images, text, music, and video clips, through the device interface. The device receives this data and sends it to the server, which then converts it into an appropriate format and stores it in a database.

[0251] The server then preprocesses the stored data. Specifically, it uses OpenCV to resize and color correct the image data, and Librosa to remove noise from the audio data. The preprocessed data is then used to train a generative AI model using a machine learning framework (TensorFlow or PyTorch). Training utilizes data on past successful commercials and viewer preference data.

[0252] Through the interface, the user enters a request to create a new commercial, including specific requirements such as target audience, theme, key message, etc. This request is then sent from the device to the server.

[0253] The server uses a generative AI model to generate a commercial scenario based on the request, and then selects appropriate materials (images, video clips, music) from a database based on the generated scenario, and combines them to generate the initial commercial.

[0254] The generated initial commercial is provided as a preview on the device for the user to review. If there are any corrections that need to be made, the user can enter feedback and send it to the server via the device. At this time, the emotion engine recognizes the user's emotions from their facial expressions and voice, and the results are reflected in the feedback.

[0255] The server analyzes the feedback and sentiment information, then uses the generative AI model to revise and regenerate the commercial. Once the final version of the commercial is generated, it is published on the designated platform and view counts and engagement data are collected. This collected data is used to generate future commercials.

[0256] Specific examples

[0257] For example, a company wants to create a commercial to promote its new product "X." The user (the company's marketer) provides data about the new product's details, target market, and theme. This data is collected by the server. The marketer then uses the device interface to enter a specific request: for example, the target audience is 18-25 years old, and the theme is adventurous. The request is sent to the server.

[0258] The server uses a generative AI model to generate an adventurous scenario, selects the necessary materials from a database, and generates an initial version of the commercial. At this time, an emotion engine recognizes the user's (marketer's) emotions and reflects that information in the selection of materials and scenario generation. The generated initial version of the commercial is displayed as a preview on the device.

[0259] If the marketing person views the preview and feels that any part of the script or material needs to be revised, they send that feedback to the server, which analyzes the feedback, generates the final commercial, and publishes it.

[0260] An example prompt is:

[0261] Create a commercial promoting your new product "X". The target audience is 18-25 years old and the theme is adventurous. Use the following promotional materials: product images, text description, music, and video clips.

[0262] The above is a specific embodiment of the present invention. This system makes it possible to automatically generate personalized commercials that reflect the user's emotions.

[0263] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0264] Step 1:

[0265] The user provides the data required for commercial production. This data includes promotional materials such as product images, text descriptions, music, and video clips. The data is input into the terminal through an input interface. The terminal transmits this input data to the server. As output, the data is received by the server.

[0266] Step 2:

[0267] The server collects the received data, converts it into the appropriate format, and stores it in the database. For example, image files are converted into JPEG or PNG format, and text files are stored in UTF-8 format. As an output, each data is stored in the database.

[0268] Step 3:

[0269] The server preprocesses the data stored in the database. Specifically, it uses OpenCV to resize and color correct the image data, and Librosa to denoise the audio data. It takes the data in the database as input and produces preprocessed data as output.

[0270] Step 4:

[0271] The server uses the preprocessed data to train a generative AI model. Using a machine learning framework (TensorFlow or PyTorch), the model learns from past success stories and viewer preference data. The preprocessed data is used as input, and a trained generative AI model is obtained as output.

[0272] Step 5:

[0273] The user inputs a new commercial generation request through the input interface. The request includes the target audience, theme, main message, etc. The terminal receives the input request and sends it to the server. The server receives the request data as output.

[0274] Step 6:

[0275] The server uses a generative AI model to generate a commercial scenario based on the received request. It inputs the prompt sentence into the generative AI model and outputs an appropriate scenario. It then selects appropriate materials from a database based on the scenario and integrates them to generate an initial version of the commercial. Using the request data and the trained generative AI model as input, the initial version of the commercial is obtained as output.

[0276] Step 7:

[0277] The terminal provides the generated initial version of the CM to the user as a preview. The user checks the preview and inputs any necessary corrections as feedback. The terminal then sends the feedback to the server, displaying the initial version of the CM as input and sending the feedback data as output to the server.

[0278] Step 8:

[0279] The server receives and analyzes feedback from users. It uses an emotion engine to recognize emotions from the user's facial expressions and voice, and reflects the results in the feedback. Feedback data and emotional information are taken as input, and a list of corrections is output.

[0280] Step 9:

[0281] The server then re-runs the generative AI model based on the analysis results to correct and regenerate the commercial. Using the list of corrections and the generative AI model as input, the final commercial is generated as output.

[0282] Step 10:

[0283] The server publishes the final commercial to the specified platform. It then collects the number of views and engagement data for the published commercial. The final commercial is uploaded to the platform as input, and engagement data is collected as output. This data is used to generate future commercials.

[0284] (Application example 2)

[0285] 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."

[0286] Conventional commercial production systems have difficulty generating personalized advertisements that reflect user emotions, making it difficult to gain viewer empathy. Furthermore, it is difficult to quickly generate effective commercials tailored to the target audience and theme. Furthermore, the development of smartphone-based commercial production applications has not progressed. For these reasons, there is a need for a means for corporate marketing personnel to easily create high-quality commercials and deliver effective messages to their target audiences.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0288] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial reflecting the corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, means for analyzing the feedback using an emotion engine that recognizes user emotions and reflecting it in the generation of the commercial, and means for providing an application to be installed on a smartphone and for producing commercials. This makes it possible to generate personalized advertisements that reflect user emotions in a short amount of time and easily produce high-quality commercials using a smartphone.

[0289] "Means for collecting and storing data" refers to the mechanism by which promotional materials and information provided by users are collected and stored in a database in an appropriate format.

[0290] "Means for training a generative AI model using machine learning algorithms" refers to a mechanism for training a generative AI model using machine learning based on collected data.

[0291] "Means for accepting commercial generation requests through an input interface" refers to a mechanism for providing an interface that allows users to input commercial generation requirements such as target audience and theme, and for receiving those requests.

[0292] "Means for automatically generating commercial scenarios using a generative AI model" refers to a system that uses a trained AI model to automatically generate commercial scenarios based on user requests.

[0293] The "means of integrating selected materials to generate a commercial" refers to a mechanism that selects appropriate materials from a database based on the generated scenario, integrates them, and generates a commercial.

[0294] The "means for providing a preview of the generated commercial" is a mechanism for providing a preview function that allows users to check the initial version of the commercial.

[0295] "Means of receiving feedback and using generative AI to generate a commercial that reflects the corrections" refers to a system that receives feedback from users, makes corrections using a generative AI model based on that feedback, and then generates a commercial again.

[0296] "Means of publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to a system in which the final commercial is published on various platforms and its view counts and engagement data are collected.

[0297] "Means of analyzing feedback using an emotion engine that recognizes the user's emotions and reflecting it in the generation of commercials" refers to a system that recognizes emotions from the user's facial expressions and voice, and uses this emotional information in feedback analysis to reflect it in the generation of commercials.

[0298] "Means of providing an application that can be installed on a smartphone and used to produce commercials" refers to a system in which an application that can be installed on a smartphone is provided and commercials are produced through that application.

[0299] This invention is a system comprising: means for collecting and storing data; means for training a generative AI model using a machine learning algorithm; means for accepting a commercial generation request; means for automatically generating a commercial scenario using the generative AI model; means for generating a commercial by integrating selected materials; means for providing a preview of the generated commercial; means for receiving feedback and again using the generative AI to generate a commercial that reflects the corrections; means for publishing the generated commercial on a specified platform and collecting view counts and engagement data; means for analyzing feedback using an emotion engine that recognizes user emotions and reflecting the feedback in the generation of the commercial; and means for providing an application to be installed on a smartphone for producing commercials.

[0300] Specifically, the server collects promotional materials and information provided by users and stores them in a database in an appropriate format. The server then uses machine learning to train a generative AI model based on the collected data. OpenAI's GPT-4 is one example of a generative AI model. Next, the server accepts commercial generation requirements, such as target audience and theme, through an input interface. Based on these requirements, the generative AI model automatically generates a commercial scenario.

[0301] Based on the generated scenario, the server selects and integrates appropriate materials from a database to generate a commercial. The generated commercial is then provided as a preview on a smartphone application. When the user checks this preview and enters feedback, the emotion engine recognizes emotions from the user's facial expressions and voice and sends that information to the server.

[0302] Based on the feedback and sentiment information, the server uses the generative AI model again to generate a commercial that reflects the modifications. The final commercial is published on the designated platform, and the server collects the number of views and engagement data, which can be used to generate future commercials.

[0303] The hardware used includes a smartphone (iOS or Android), a server, and a suitable database (e.g., MongoDB).The software used is React Native for the front end, Node.js and Express for the back end, OpenCV for image data processing, FFmpeg for audio data processing, and the Affectiva SDK as an emotion engine.

[0304] For example, if a company wants to create a commercial for new product "X," the user (the company's marketing staff) provides details of the new product, the target market, and the theme using a smartphone application. The target audience is input as "18-25 years old," the theme as "active lifestyle," and the main message as "make your everyday life active." The generative AI model generates a scenario based on this information, and the emotion engine analyzes the user's reactions to generate a more refined commercial.

[0305] Example prompt sentence:

[0306] You want to advertise a new pair of sports shoes. The target audience is young people aged 18-25, and the theme is active lifestyle. You want to include the message "Be active every day."

[0307] We want to promote organic juice. The target audience is 25-35 years old, and the theme is health and nature. We want to convey the message that "organic juice is good for your body."

[0308] In this way, by integrating an emotion engine, this system generates personalized commercials that reflect the user's emotions, providing content that viewers can more easily relate to.

[0309] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0310] Step 1:

[0311] The server collects promotional materials (images, text, music, etc.) provided by users through a dedicated interface. This data is converted into an appropriate format and stored in a database. It receives the materials uploaded by the user as input and outputs the materials stored in the database.

[0312] Step 2:

[0313] The server preprocesses the data stored in the database. Specifically, it uses OpenCV to resize and color correct the image data, and FFmpeg to remove noise from the audio data. The preprocessed data is output as training data for the next stage.

[0314] Step 3:

[0315] The server trains a generative AI model using the preprocessed data. GPT-4 is used as the generative AI model, and machine learning algorithms are applied based on past commercial data and viewer preference data. The trained generative AI model is output.

[0316] Step 4:

[0317] The user inputs the target audience, theme, main message, and other requirements for a new commercial through the input interface of the smartphone application. The input requirements are sent to the server. The output is the time until the input request is accepted by the server.

[0318] Step 5:

[0319] The server runs the GPT-4 generative AI model based on the received user request to generate a CM scenario. The input request is applied to the AI ​​model, and an automatically generated scenario is output.

[0320] Step 6:

[0321] The server selects appropriate materials from a database based on the generated scenario, integrates them, and generates an initial version of the commercial. The input scenario is applied to the AI ​​model, and the initial version of the commercial is output.

[0322] Step 7:

[0323] The terminal provides the generated initial version of the CM to the user as a preview. The user checks the preview and inputs any necessary corrections. The input feedback is sent to the server. The preview and feedback are output.

[0324] Step 8:

[0325] The server runs the generation AI again based on the feedback sent by the user, and recreates the commercial reflecting the corrections. At this time, the emotion engine (Affectiva SDK) recognizes emotions from the user's facial expressions and voice, and this is also taken into account in the feedback. The corrected feedback and emotional information are input, and the final commercial is output.

[0326] Step 9:

[0327] The server publishes the final commercial on various platforms (such as social media and video sharing sites) and collects view counts and engagement data. This data is used to generate future commercials. The published commercial and collected data are output.

[0328] 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.

[0329] 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.

[0330] 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.

[0331] [Second embodiment]

[0332] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0333] 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.

[0334] 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).

[0335] 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.

[0336] 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.

[0337] 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).

[0338] 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.

[0339] 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.

[0340] 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.

[0341] 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.

[0342] 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.

[0343] 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."

[0344] This invention is an innovative commercial production system that uses generative AI technology, and is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and users who provide feedback, etc.

[0345] The system operates as follows.

[0346] First, the user provides the data required for commercial production, including product images, text descriptions, music and video clips to be used in the promotion, etc. This data is collected on the server and stored in a database in an appropriate format.

[0347] The server then uses machine learning algorithms to train a generative AI model based on the stored data. Data preprocessing includes adjusting the size of image data and removing noise from audio data. The trained generative AI model can then learn various viewer preferences and commercial generation patterns, allowing it to generate unique scenarios.

[0348] The device then accepts a request to create a commercial through an interface, where the user inputs specific requirements such as target audience, theme, key message, etc. The input request is then sent to the server.

[0349] Based on the received request, the server automatically generates a scenario using a generative AI model. Based on the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from a database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0350] The generated initial version of the commercial is provided as a preview on the device. The user checks this preview and sends any necessary corrections as feedback to the server. The server analyzes the feedback and extracts corrections. The generative AI model is run again to reflect the extracted corrections, and the final version of the commercial is generated.

[0351] The final commercial is published on the platform of your choice by the server, which then collects real-time engagement data, such as the number of views, shares, and comments, to help inform future commercial production.

[0352] By using this system, unique commercials can be automatically generated quickly and at low cost, resulting in "captivating commercials" that viewers will want to watch. In addition, since the system can be flexibly revised based on feedback, it is possible to maximize advertising effectiveness.

[0353] Specific examples

[0354] Let's say a company wants to promote a new product and requests the production of a commercial through this system.

[0355] Users (marketers) provide details of new products and promotional materials to the system, and this data is collected and stored by the server.

[0356] Marketers then use the interface to input their requests for new commercials, specifying that the target audience is young and the theme is adventurous and fun.

[0357] The server receives these requirements and uses a generative AI model to create a scenario. Based on the scenario, relevant materials are selected from a database and an initial version of the commercial is automatically generated.

[0358] The generated initial version of the commercial is displayed as a preview on the device, and the marketing staff can check it. If they feel that any part of the scenario needs to be revised, they can provide specific feedback on the revisions to the server.

[0359] The server analyzes the feedback and generates the final ad incorporating the changes. Once the final ad is complete, it is published on the designated platform, where viewer numbers and engagement data are collected in real time.

[0360] In this way, companies can create and release highly effective commercials quickly and with minimal effort.

[0361] The processing flow will be explained below.

[0362] Step 1:

[0363] Users provide the data needed to create a new commercial, including product images, text descriptions, music, video clips, and other promotional materials, which are uploaded through a dedicated interface.

[0364] Step 2:

[0365] The server receives the provided data, converts it to the appropriate format, and stores it in a database: for example, images are converted to the appropriate resolution, and text is formatted into a standard format.

[0366] Step 3:

[0367] The server performs data preprocessing based on the stored data, including resizing and color correction of image data and noise reduction of audio data.

[0368] Step 4:

[0369] The server uses the preprocessed data to train a generative AI model using machine learning algorithms, which study past commercial data and viewer preferences to identify new patterns.

[0370] Step 5:

[0371] The terminal (company marketing staff) inputs a request for commercial production through a dedicated interface. The request includes the target audience, theme, main message, etc. This request is then sent to the server.

[0372] Step 6:

[0373] The server runs the generative AI model based on the received request and automatically generates a commercial script, including a storyboard and narration script.

[0374] Step 7:

[0375] Based on the generated scenario, the server selects appropriate materials (images, video clips, music, etc.) from a database and integrates them to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0376] Step 8:

[0377] The server provides the generated initial version of the commercial as a preview to the device, and the user (company representative) can check the preview through the device interface.

[0378] Step 9:

[0379] The user views the generated initial version of the commercial, inputs any necessary modifications, and sends the feedback to the server, which may include corrections to the scenario or the addition of new material.

[0380] Step 10:

[0381] The server analyzes the feedback and lists the extracted corrections. Based on this list, the generative AI model is run again to generate the final commercial that reflects the corrections.

[0382] Step 11:

[0383] The server re-encodes the final commercial and prepares it for publication on the designated platform (YouTube, social media, etc.). After publication, view counts and engagement data (number of shares, number of comments, etc.) are collected in real time.

[0384] Step 12:

[0385] The server analyzes the collected engagement data and evaluates the effectiveness of the advertisement, which will be used to generate future commercials.

[0386] Example 1

[0387] 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."

[0388] The traditional commercial production process is time-consuming and costly, and it is difficult to adjust the quality of the content and tailor it to viewer preferences. Furthermore, the selection of materials and the creation of scripts are done manually, which is inefficient and can result in insufficient advertising effectiveness. Given these circumstances, there is a demand for a system that can quickly and automatically generate high-quality commercials and flexibly make revisions based on feedback.

[0389] 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.

[0390] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial that reflects corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, means for preprocessing data necessary for commercial production, and means for analyzing the provided feedback and extracting corrections. This makes it possible to quickly and efficiently generate high-quality commercials and adjust content to suit viewer preferences.

[0391] "Means for collecting and storing data" means a combination of hardware and software for receiving user-provided data such as images, audio, text, and video, and storing it in an appropriate database.

[0392] A "means for training a generative AI model using a machine learning algorithm" is a component of a system that runs a machine learning algorithm using collected data to train a generative AI model.

[0393] "Means for accepting commercial creation requests through an input interface" refers to an interface that allows users to input commercial creation requirements (target audience, theme, main message, etc.) to the system, and a mechanism for transmitting that input to the server.

[0394] A "means for automatically generating a commercial scenario using a generative AI model" is a component of a system that uses a trained generative AI model to automatically create a commercial scenario based on collected data and user requests.

[0395] The "means of integrating selected materials to generate a commercial" refers to a combination of editing software and hardware that selects appropriate images, audio, video, and other materials from a database in accordance with the generated scenario, and integrates them to create a single commercial.

[0396] The "means for providing a preview of the generated commercial" refers to an interface and a mechanism for playing back the video so that the user can check the generated commercial.

[0397] The "means of receiving feedback and using a generation AI to generate a commercial that reflects the corrections" refers to a generation AI and its control system that analyzes the feedback provided by the user and regenerates a new commercial that reflects the corrections.

[0398] "Means of publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to a system component that uploads the completed commercial to a public platform such as YouTube or social media, and collects viewing data and user engagement data in real time.

[0399] "Means for preprocessing data required for commercial production" refers to a system component that performs preprocessing such as resizing and noise removal to prepare collected image, audio, and text data in a form optimal for training and generation.

[0400] The "means for analyzing the provided feedback and extracting corrections" is a system component that analyzes the feedback from the user using a technique such as text analysis and automatically extracts the necessary corrections.

[0401] This invention is an innovative commercial production system that uses generative AI technology, and is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and a user who provides feedback, etc. This system operates as follows.

[0402] First, the user provides the data required for commercial production, including product images, text descriptions, music and video clips to be used in the promotion, etc. This data is collected on the server and stored in a database in an appropriate format.

[0403] The server then uses machine learning algorithms to train a generative AI model based on the stored data. Specific software used includes Python and TensorFlow. Data preprocessing includes adjusting the size of image data and removing noise from audio data. Once trained, the generative AI model can learn various viewer preferences and commercial generation patterns, allowing it to generate unique scenarios.

[0404] The device then accepts a request to create a commercial through an interface, where the user inputs specific requirements such as target audience, theme, key message, etc. The input request is then sent to the server.

[0405] Based on the received request, the server automatically generates a scenario using a generative AI model. Based on the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from a database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario. The specific hardware used in this process includes a server equipped with a high-performance GPU.

[0406] The generated initial version of the commercial is provided as a preview on the device. The user checks this preview and sends any necessary corrections as feedback to the server. The server analyzes the feedback and extracts corrections. The generative AI model is run again to reflect the extracted corrections, and the final version of the commercial is generated.

[0407] The final commercial is published on the platform of your choice by the server, which then collects real-time engagement data, such as the number of views, shares, and comments, to help inform future commercial production.

[0408] Specific examples

[0409] Let's say a company wants to promote a new product and requests the production of a commercial through this system.

[0410] Users (marketers) provide details of new products and promotional materials to the system, and this data is collected and stored by the server.

[0411] Marketers then use the interface to input their requests for new commercials, specifying, for example, that the target audience is people in their 20s and that the theme is energetic and active.

[0412] The server receives these requirements and uses a generative AI model to create a scenario. Based on the scenario, relevant materials are selected from a database and an initial version of the commercial is automatically generated.

[0413] The generated initial version of the commercial is displayed as a preview on the device, and the marketing staff can check it. If they feel that any part of the scenario needs to be revised, they can provide specific feedback on the revisions to the server.

[0414] The server analyzes the feedback and generates the final ad incorporating the changes. Once the final ad is complete, it is published on the designated platform, where viewer numbers and engagement data are collected in real time.

[0415] In this way, companies can quickly create and publish highly effective commercials with minimal effort, and the entire process is powered by generative AI models and advanced data processing techniques.

[0416] Prompt Sentence Examples

[0417] "Use this system to create a promotional commercial for a new product. The target audience should be in their early 20s, and the theme should be energetic and active. The provided materials include high-resolution images of the product, a description, and a lively, up-tempo song as background music."

[0418] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0419] Step 1:

[0420] The user provides the data necessary to create a commercial. Using the device interface, the user uploads high-resolution images of the product, descriptions, music and video clips to be used in the promotion, etc. The inputs include image files, audio files, text files, and video files. This data is sent to the server via the device.

[0421] Step 2:

[0422] The server stores the received data in a database in an appropriate format. Before storing, it performs preprocessing on the data. This includes resizing images and removing noise from audio data. The input is the data in various formats provided in step 1, and the output is the preprocessed data. The server performs these processes using Python and OpenCV.

[0423] Step 3:

[0424] The server uses machine learning algorithms to train a generative AI model based on the stored data. For example, it uses Python and TensorFlow to build and train the model. The input is the preprocessed data and existing training data, and the output is the trained generative AI model.

[0425] Step 4:

[0426] The terminal accepts a request from the user to create a commercial through the interface. The user inputs specific requirements such as target audience, theme, key message, etc. The input is the request information entered by the user through the terminal interface, which is then sent to the server.

[0427] Step 5:

[0428] The server automatically generates a commercial scenario using a generative AI model based on the received commercial generation request. The input is the user's request information and a trained generative AI model, and the output is the generated commercial scenario. The server runs the generative AI model and creates a scenario using a Python script.

[0429] Step 6:

[0430] The server selects appropriate materials from the database based on the generated scenario and integrates them to generate the initial version of the commercial. The materials are integrated using editing software. The input is the generated scenario and materials in the database, and the output is the initial version of the commercial.

[0431] Step 7:

[0432] The terminal provides the generated initial version of the commercial as a preview to the user, who then reviews it and provides feedback on the content. The input is the initial version of the commercial, and the output is the user's feedback. The user uses the interface to fill out and submit a feedback form.

[0433] Step 8:

[0434] The server analyzes the user feedback and extracts corrections, for example, by using text analysis techniques to understand the content of the feedback and list the corrections. The input is the user feedback and the output is the list of corrections.

[0435] Step 9:

[0436] Based on the corrections, the server uses the generative AI model again to generate the final commercial that reflects the corrections. The input is the list of corrections and the commercial material before the corrections, and the output is the final commercial. The generative AI model is run again to integrate the material and create the final version.

[0437] Step 10:

[0438] The final commercial is published by the server on a designated platform, such as YouTube or social media. After publication, the server collects engagement data in real time, including the number of views, shares, and comments. The input is the final commercial and information about the platform on which it was published, and the output is engagement data.

[0439] Prompt Sentence Examples

[0440] "Use this system to create a promotional commercial for a new product. The target audience should be in their early 20s, and the theme should be energetic and active. The provided materials include high-resolution images of the product, a description, and a lively, up-tempo song as background music."

[0441] (Application example 1)

[0442] 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."

[0443] The traditional advertising video production process was time-consuming and costly, and the revision process to incorporate feedback was particularly tedious. It was also difficult to centrally preview advertising videos and collect performance data after release. This made it difficult to respond quickly to maximize advertising effectiveness.

[0444] 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.

[0445] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving an advertisement generation request through an input interface, means for automatically generating an advertisement video scenario using the generative AI model, means for generating an advertisement video by integrating selected materials, means for providing a preview of the generated advertisement video, means for receiving feedback and again using the generative AI to generate an advertisement video reflecting modifications, means for publishing the generated advertisement video on a specified digital platform and collecting view counts and engagement data, and means for providing an application that operates on terminals including smartphones, thereby enabling the generation, modification, publication, and performance monitoring of advertisement videos quickly and efficiently.

[0446] "Means for collecting and storing data" refers to the system elements that collect material data such as images, videos, and music provided by users and store them in a database on the server.

[0447] "Means for training a generative AI model using a machine learning algorithm" refers to the element of using the collected and pre-processed data to train an AI model specialized in generating advertisements using a machine learning algorithm.

[0448] "Means for accepting advertising generation requests through an input interface" refers to a system element that provides an interface for users to input request information (e.g., target demographic and theme) required to generate an advertising video and transmits that information to a server.

[0449] "Means for automatically generating an advertising video scenario using a generative AI model" refers to an element of a system that automatically generates an advertising video scenario based on input request information using a trained generative AI model.

[0450] "Means for integrating selected materials to generate an advertising video" refers to an element of the system that selects optimal images, videos, music, and other materials from a database based on the generated scenario and integrates them to generate an advertising video.

[0451] "Means for providing a preview of the generated advertising video" refers to an element of the system that provides the generated advertising video to a terminal as a preview that can be viewed by a user.

[0452] "Means for receiving feedback and using a generative AI model to generate an advertising video that reflects the corrections" refers to the system elements that receive feedback information from users, analyze it to extract corrections, and use a generative AI model to generate an advertising video that reflects the corrections.

[0453] "Means for publishing the generated advertising video on designated digital platforms and collecting view and engagement data" refers to the system elements that publish the final advertising video on designated platforms (e.g., social media, websites) and subsequently collect engagement data such as the number of views, shares, and comments in real time.

[0454] "Means for providing an application that runs on a device, including a smartphone" means an element of a system that provides a user with a software application that runs on a smartphone or other device and that assists the user in the process of creating, editing, and publishing advertising videos through that application.

[0455] To implement this invention, a means for collecting and storing data is first required. This means collects material data such as images, videos, and music provided by users and stores them in a database on the server. This allows for centralized management of the materials needed to generate advertising videos.

[0456] Next, a means is needed to train the generative AI model using machine learning algorithms. The server uses the collected and preprocessed data to train an AI model specialized for ad generation. This is done using programming languages ​​and frameworks such as Python and TensorFlow. Specifically, preprocessing is performed, such as resizing image data and removing noise from audio data.

[0457] A user can use an input interface to receive an advertisement generation request. This interface can be implemented as a web browser or a smartphone application, and allows the user to input request information such as target audience, theme, etc. The input information is sent to the server and used to generate the advertisement video.

[0458] The server automatically generates an advertising video scenario using the generative AI model. An appropriate scenario is generated based on the request information entered by the user. For example, if a user enters the prompt, "Please generate an advertising scenario with an adventurous and fun theme for young people. Our new product is a waterproof smartwatch," the generative AI model will generate a corresponding scenario.

[0459] The server then synthesizes the selected materials to generate the advertising video. Based on the generated scenario, the server selects the most suitable images, video clips, and music from the database and synthesizes them to generate the advertising video. This process uses a video editing library such as MoviePy.

[0460] The generated advertising video can be previewed by the user. The preview function is implemented on the device, allowing the user to watch the generated advertising video and check its content. If the user needs to make any corrections, they can send them to the server as feedback.

[0461] The server receives the feedback, analyzes it, and extracts corrections. It then uses the generative AI model again to generate an advertising video that reflects the corrections. This process results in the creation of an optimal advertising video that meets the user's needs.

[0462] Finally, the generated advertising video is published on the designated digital platform. The server collects the number of views and engagement data of the published advertising video in real time, which can be used to evaluate the effectiveness of the advertising video and to help with future production.

[0463] As a concrete example, this system can be used when a company wants to promote a new product. A marketer provides the system with detailed information about the new product and promotional materials, inputting that the target audience is young people and the theme is adventurous and fun. The server that receives this request uses a generative AI model to generate a scenario and integrates the materials to automatically generate an initial advertising video. The generated advertising video can be previewed and any necessary corrections can be provided as feedback. The final advertising video is then generated and published on the specified platform.

[0464] This allows for the quick and efficient creation, modification, publishing and performance monitoring of advertising videos.

[0465] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0466] Step 1:

[0467] Users upload raw data, such as images, videos, and music, required to generate advertising videos to a server via their terminals. The server collects, organizes, and stores this data in a database. The input data is the raw data provided by the users, and the output data is the organized raw data stored in the database.

[0468] Step 2:

[0469] The server preprocesses the stored material data in the database. Specifically, it adjusts the size of image data and removes noise from audio data. The input data is the material data in the database, and the output data is clean data that has undergone preprocessing.

[0470] Step 3:

[0471] The server uses a machine learning algorithm to train the generative AI model, using preprocessed raw data in the process: the input data is the preprocessed raw data, and the output data is the trained generative AI model.

[0472] Step 4:

[0473] A user sends an advertisement generation request from the terminal to the server through the input interface. The input request includes details such as target audience, theme, main message, etc. The input data is the user's request information, and the output data is the request sent to the server.

[0474] Step 5:

[0475] The server automatically generates an advertising video scenario using a generative AI model based on the received request information. The input data is the user request information and the trained generative AI model, and the output data is the generated scenario. Specifically, the generative AI constructs a scenario based on the prompt sentence.

[0476] Step 6:

[0477] The server selects appropriate materials (images, video clips, music, etc.) from the database based on the generated scenario and integrates them to generate an advertising video. The input data is the generated scenario and the material data in the database, and the output data is the generated advertising video. Specifically, the server uses the MoviePy library to combine the materials and generate the video.

[0478] Step 7:

[0479] The terminal provides a preview of the generated advertising video to the user, and the user checks the preview and sends feedback to the server through a feedback interface, where the input data is the generated advertising video and the output data is the user's feedback.

[0480] Step 8:

[0481] The server analyzes the feedback from the user and extracts the corrections. The input data is the user feedback, and the output data is the list of corrections.

[0482] Step 9:

[0483] The server then runs the generative AI model again based on the extracted corrections to generate an advertising video that reflects the corrections. The input data is the list of corrections and the trained generative AI model, and the output data is the corrected advertising video.

[0484] Step 10:

[0485] The server publishes the generated final advertising video on a specified digital platform (e.g., social media, website), and collects subsequent view counts and engagement data (number of shares, comments, etc.) in real time. The input data is the final advertising video, and the output data is the engagement data collected in real time.

[0486] 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.

[0487] This invention is an innovative commercial production system that uses generative AI technology and combines it with an emotion engine that recognizes user emotions to generate more personalized advertisements. This system is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and users who provide feedback, etc.

[0488] System Overview

[0489] The system operates as follows.

[0490] The user provides the data required for commercial production, including promotional materials such as product images, text descriptions, music, video clips, etc. This data is collected on the server and stored in a database in an appropriate format.

[0491] The server then performs data preprocessing on the stored data, including resizing and color correction of image data and noise reduction of audio data. The preprocessed data is then used to train a generative AI model using machine learning algorithms. The trained generative AI model can then learn various viewer preferences and commercial generation patterns.

[0492] The terminal accepts commercial creation requests through an interface, which allows users to input specific requirements such as target audience, theme, key message, etc. These requests are then sent to the server.

[0493] The server runs the generative AI model based on the received request and automatically generates a commercial scenario. From the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from the database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0494] The generated initial version of the commercial is provided as a preview on the device. The user (company representative) checks the preview and sends any necessary revisions as feedback to the server. At this time, the emotion engine recognizes the user's emotions from their facial expressions and voice, and reflects the results in the feedback analysis.

[0495] The server analyzes the feedback and regenerates the commercial based on the extracted corrections and recognized emotional information. Once the final version is generated, it is published on the designated platform and viewer numbers and engagement data are collected.

[0496] Program processing details

[0497] First, the user provides the data needed to create a new commercial. This data is uploaded through a dedicated interface. The server then receives the data, converts it into a format, and stores it in a database.

[0498] The data stored in the database is pre-processed and then used to train a generative AI model using machine learning algorithms, including data on past commercial successes and viewer preferences.

[0499] Users input their requests for new commercials through an interface, specifying details of the target audience, themes, key messages, etc. The requests are sent to a server, where a generative AI model generates a commercial script based on the requests.

[0500] Based on the generated scenario, related material is selected from a database and a commercial is generated. At this time, an emotion engine recognizes emotions from the user's facial expressions and voice, and based on this information, material selection and script revisions are made.

[0501] An initial version of the commercial is generated and provided as a preview on the device. The user views the preview and provides feedback. The user's emotions, as recognized by the emotion engine, are also used as feedback.

[0502] The server analyzes the feedback and emotional information, again using the AI ​​to make corrections and generate the final commercial. The final commercial is then published on the designated platform, and view counts and engagement data are collected. This engagement data will also be used to generate future commercials.

[0503] Specific examples

[0504] Suppose a company wants to create a commercial to promote its new product "X." The user (the company's marketing manager) provides details about the new product, its target market, and the theme. This data is collected on the server.

[0505] Marketers then use the interface to input specific requests, such as target audience ages 18 to 25 and a theme that is adventurous.

[0506] The server uses a generative AI model to generate an adventurous scenario, selects the necessary materials from a database, and generates an initial commercial. During this process, an emotion engine recognizes the emotions of the user (marketer) and reflects this information in the selection of materials and scenario generation.

[0507] The generated initial version of the commercial is displayed as a preview on the device. The marketer reviews the commercial and, if they feel that any changes are necessary to the scenario or materials, they can submit feedback along with emotional information. The server analyzes the feedback, generates the final version of the commercial, and publishes it.

[0508] The present invention thus implemented can generate commercials that reflect the user's emotions by integrating an emotion engine, thereby providing content that viewers can more easily relate to.

[0509] The processing flow will be explained below.

[0510] Step 1:

[0511] Through a dedicated interface, users provide the data needed to create a new commercial, including promotional materials such as product images, text descriptions, music, and video clips.

[0512] Step 2:

[0513] The server receives the provided data, converts it into an appropriate format, and stores it in a database: for example, image data is converted to an appropriate resolution, and text is formatted into a standard format.

[0514] Step 3:

[0515] The server preprocesses the stored data, including adjusting the size and color of the image data and removing noise from the audio data.

[0516] Step 4:

[0517] The server uses the pre-processed data to train a generative AI model using machine learning algorithms, including past commercial data and viewer preference data.

[0518] Step 5:

[0519] The terminal (a company's marketing staff) inputs a request for commercial production through a dedicated interface. The request includes the target audience, theme, and main message. This request is then sent to the server.

[0520] Step 6:

[0521] The server runs the generative AI model based on the received request and automatically generates a commercial script, including a storyboard and narration script.

[0522] Step 7:

[0523] Based on the generated scenario, the server selects appropriate materials (images, video clips, music, etc.) from a database and integrates them to generate the initial version of the commercial.

[0524] Step 8:

[0525] The server uses an emotion engine to recognize the user's emotions in real time. The emotion engine analyzes the user's emotions from their facial expressions and voice, and incorporates that information as feedback.

[0526] Step 9:

[0527] The server provides the generated initial version of the commercial as a preview to the terminal, and the user can check the preview and input any necessary corrections as feedback through the terminal interface.

[0528] Step 10:

[0529] The server lists corrections based on the received feedback and the analysis results of the emotion engine, and then uses the generative AI model again to generate the final commercial that reflects the corrections.

[0530] Step 11:

[0531] The server prepares the final commercial for publication on the designated platform (YouTube, social media, etc.) After publication, view counts and engagement data (number of shares, number of comments, etc.) are collected in real time.

[0532] Step 12:

[0533] The server analyzes the collected engagement data and evaluates the effectiveness of the advertisement, which will be used to generate future commercials.

[0534] Example 2

[0535] 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."

[0536] Conventional commercial production systems have limited technology for generating advertisements that take viewer preferences into account, making it difficult to automatically generate personalized commercials that reflect user emotions. Furthermore, it is difficult to efficiently generate revised commercials that reflect appropriate feedback, resulting in the challenge of not being able to maximize the impact on viewers.

[0537] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial reflecting the corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, and means for recognizing user emotions and reflecting the emotional information in the feedback. This enables the automatic generation of personalized commercials that reflect the user's emotions, maximizing their impact on viewers.

[0538] "Data collection and storage means" means a device or system that receives user-provided promotional materials such as images, text, music, and video clips, converts them into an appropriate format, and stores them in a database.

[0539] A "means for training a generative AI model using a machine learning algorithm" is an apparatus and technology for carrying out the process of training a generative AI model using preprocessed data.

[0540] "Means for accepting commercial generation requests through an input interface" refers to a device or system that provides an interface for users to input commercial requests (e.g., target audience, theme, message, etc.) and receives the input information.

[0541] "Means for automatically generating a commercial scenario using a generative AI model" refers to devices and technologies for automatically creating a commercial scenario using a generative AI model based on a user request.

[0542] "Means for integrating selected materials to generate a commercial" refers to devices and technologies for selecting appropriate materials (images, music, video clips) from a database based on the generated scenario and integrating them to create a commercial.

[0543] The "means for providing a preview of the generated commercial" is a device or system that provides a preview function that allows a user to visually check the generated commercial.

[0544] "Means for receiving feedback and regenerating a commercial that reflects the corrections using a generative AI" refers to devices and technologies for receiving feedback from users and regenerating and correcting a commercial using a generative AI model based on that feedback.

[0545] "Means for publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to the devices and technologies for uploading the final commercial to a designated online platform and collecting subsequent view counts and viewer engagement data.

[0546] "Means for recognizing the user's emotions and reflecting that emotional information in feedback" refers to a device and technology for recognizing the user's emotions from their facial expressions and voice, and reflecting that emotional information in the analysis of the modification requirements.

[0547] MODE FOR CARRYING OUT THE INVENTION

[0548] This invention is an innovative commercial production system that combines generative AI technology with an emotion engine that recognizes user emotions. An embodiment of this system will be described in detail below.

[0549] System Configuration

[0550] This system operates in collaboration with a server with multiple functions, a terminal with an interface, and a user who provides feedback, etc. The main hardware and software include the following:

[0551] Hardware: High-performance servers, user devices (PCs, tablets, smartphones, etc.)

[0552] Software: OpenCV (image processing library), Librosa (audio processing library), machine learning frameworks (TensorFlow, PyTorch, etc.)

[0553] Program processing overview

[0554] First, the user provides the data needed to create a commercial, including product images, text, music, and video clips, through the device interface. The device receives this data and sends it to the server, which then converts it into an appropriate format and stores it in a database.

[0555] The server then preprocesses the stored data. Specifically, it uses OpenCV to resize and color correct the image data, and Librosa to remove noise from the audio data. The preprocessed data is then used to train a generative AI model using a machine learning framework (TensorFlow or PyTorch). Training utilizes data on past successful commercials and viewer preference data.

[0556] Through the interface, the user enters a request to create a new commercial, including specific requirements such as target audience, theme, key message, etc. This request is then sent from the device to the server.

[0557] The server uses a generative AI model to generate a commercial scenario based on the request, and then selects appropriate materials (images, video clips, music) from a database based on the generated scenario, and combines them to generate the initial commercial.

[0558] The generated initial commercial is provided as a preview on the device for the user to review. If there are any corrections that need to be made, the user can enter feedback and send it to the server via the device. At this time, the emotion engine recognizes the user's emotions from their facial expressions and voice, and the results are reflected in the feedback.

[0559] The server analyzes the feedback and sentiment information, then uses the generative AI model to revise and regenerate the commercial. Once the final version of the commercial is generated, it is published on the designated platform and view counts and engagement data are collected. This collected data is used to generate future commercials.

[0560] Specific examples

[0561] For example, a company wants to create a commercial to promote its new product "X." The user (the company's marketer) provides data about the new product's details, target market, and theme. This data is collected by the server. The marketer then uses the device interface to enter a specific request: for example, the target audience is 18-25 years old, and the theme is adventurous. The request is sent to the server.

[0562] The server uses a generative AI model to generate an adventurous scenario, selects the necessary materials from a database, and generates an initial version of the commercial. At this time, an emotion engine recognizes the user's (marketer's) emotions and reflects that information in the selection of materials and scenario generation. The generated initial version of the commercial is displayed as a preview on the device.

[0563] If the marketing person views the preview and feels that any part of the script or material needs to be revised, they send that feedback to the server, which analyzes the feedback, generates the final commercial, and publishes it.

[0564] An example prompt is:

[0565] Create a commercial promoting your new product "X". The target audience is 18-25 years old and the theme is adventurous. Use the following promotional materials: product images, text description, music, and video clips.

[0566] The above is a specific embodiment of the present invention. This system makes it possible to automatically generate personalized commercials that reflect the user's emotions.

[0567] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0568] Step 1:

[0569] The user provides the data required for commercial production. This data includes promotional materials such as product images, text descriptions, music, and video clips. The data is input into the terminal through an input interface. The terminal transmits this input data to the server. As output, the data is received by the server.

[0570] Step 2:

[0571] The server collects the received data, converts it into the appropriate format, and stores it in the database. For example, image files are converted into JPEG or PNG format, and text files are stored in UTF-8 format. As an output, each data is stored in the database.

[0572] Step 3:

[0573] The server preprocesses the data stored in the database. Specifically, it uses OpenCV to resize and color correct the image data, and Librosa to denoise the audio data. It takes the data in the database as input and produces preprocessed data as output.

[0574] Step 4:

[0575] The server uses the preprocessed data to train a generative AI model. Using a machine learning framework (TensorFlow or PyTorch), the model learns from past success stories and viewer preference data. The preprocessed data is used as input, and a trained generative AI model is obtained as output.

[0576] Step 5:

[0577] The user inputs a new commercial generation request through the input interface. The request includes the target audience, theme, main message, etc. The terminal receives the input request and sends it to the server. The server receives the request data as output.

[0578] Step 6:

[0579] The server uses a generative AI model to generate a commercial scenario based on the received request. It inputs the prompt sentence into the generative AI model and outputs an appropriate scenario. It then selects appropriate materials from a database based on the scenario and integrates them to generate an initial version of the commercial. Using the request data and the trained generative AI model as input, the initial version of the commercial is obtained as output.

[0580] Step 7:

[0581] The terminal provides the generated initial version of the CM to the user as a preview. The user checks the preview and inputs any necessary corrections as feedback. The terminal then sends the feedback to the server, displaying the initial version of the CM as input and sending the feedback data as output to the server.

[0582] Step 8:

[0583] The server receives and analyzes feedback from users. It uses an emotion engine to recognize emotions from the user's facial expressions and voice, and reflects the results in the feedback. Feedback data and emotional information are taken as input, and a list of corrections is output.

[0584] Step 9:

[0585] The server then re-runs the generative AI model based on the analysis results to correct and regenerate the commercial. Using the list of corrections and the generative AI model as input, the final commercial is generated as output.

[0586] Step 10:

[0587] The server publishes the final commercial to the specified platform. It then collects the number of views and engagement data for the published commercial. The final commercial is uploaded to the platform as input, and engagement data is collected as output. This data is used to generate future commercials.

[0588] (Application example 2)

[0589] 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."

[0590] Conventional commercial production systems have difficulty generating personalized advertisements that reflect user emotions, making it difficult to gain viewer empathy. Furthermore, it is difficult to quickly generate effective commercials tailored to the target audience and theme. Furthermore, the development of smartphone-based commercial production applications has not progressed. For these reasons, there is a need for a means for corporate marketing personnel to easily create high-quality commercials and deliver effective messages to their target audiences.

[0591] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0592] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial reflecting the corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, means for analyzing the feedback using an emotion engine that recognizes user emotions and reflecting it in the generation of the commercial, and means for providing an application to be installed on a smartphone and for producing commercials. This makes it possible to generate personalized advertisements that reflect user emotions in a short amount of time and easily produce high-quality commercials using a smartphone.

[0593] "Means for collecting and storing data" refers to the mechanism by which promotional materials and information provided by users are collected and stored in a database in an appropriate format.

[0594] "Means for training a generative AI model using machine learning algorithms" refers to a mechanism for training a generative AI model using machine learning based on collected data.

[0595] "Means for accepting commercial generation requests through an input interface" refers to a mechanism for providing an interface that allows users to input commercial generation requirements such as target audience and theme, and for receiving those requests.

[0596] "Means for automatically generating commercial scenarios using a generative AI model" refers to a system that uses a trained AI model to automatically generate commercial scenarios based on user requests.

[0597] The "means of integrating selected materials to generate a commercial" refers to a mechanism that selects appropriate materials from a database based on the generated scenario, integrates them, and generates a commercial.

[0598] The "means for providing a preview of the generated commercial" is a mechanism for providing a preview function that allows users to check the initial version of the commercial.

[0599] "Means of receiving feedback and using generative AI to generate a commercial that reflects the corrections" refers to a system that receives feedback from users, makes corrections using a generative AI model based on that feedback, and then generates a commercial again.

[0600] "Means of publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to a system in which the final commercial is published on various platforms and its view counts and engagement data are collected.

[0601] "Means of analyzing feedback using an emotion engine that recognizes the user's emotions and reflecting it in the generation of commercials" refers to a system that recognizes emotions from the user's facial expressions and voice, and uses this emotional information in feedback analysis to reflect it in the generation of commercials.

[0602] "Means of providing an application that can be installed on a smartphone and used to produce commercials" refers to a system in which an application that can be installed on a smartphone is provided and commercials are produced through that application.

[0603] This invention is a system comprising: means for collecting and storing data; means for training a generative AI model using a machine learning algorithm; means for accepting a commercial generation request; means for automatically generating a commercial scenario using the generative AI model; means for generating a commercial by integrating selected materials; means for providing a preview of the generated commercial; means for receiving feedback and again using the generative AI to generate a commercial that reflects the corrections; means for publishing the generated commercial on a specified platform and collecting view counts and engagement data; means for analyzing feedback using an emotion engine that recognizes user emotions and reflecting the feedback in the generation of the commercial; and means for providing an application to be installed on a smartphone for producing commercials.

[0604] Specifically, the server collects promotional materials and information provided by users and stores them in a database in an appropriate format. The server then uses machine learning to train a generative AI model based on the collected data. OpenAI's GPT-4 is one example of a generative AI model. Next, the server accepts commercial generation requirements, such as target audience and theme, through an input interface. Based on these requirements, the generative AI model automatically generates a commercial scenario.

[0605] Based on the generated scenario, the server selects and integrates appropriate materials from a database to generate a commercial. The generated commercial is then provided as a preview on a smartphone application. When the user checks this preview and enters feedback, the emotion engine recognizes emotions from the user's facial expressions and voice and sends that information to the server.

[0606] Based on the feedback and sentiment information, the server uses the generative AI model again to generate a commercial that reflects the modifications. The final commercial is published on the designated platform, and the server collects the number of views and engagement data, which can be used to generate future commercials.

[0607] The hardware used includes a smartphone (iOS or Android), a server, and a suitable database (e.g., MongoDB).The software used is React Native for the front end, Node.js and Express for the back end, OpenCV for image data processing, FFmpeg for audio data processing, and the Affectiva SDK as an emotion engine.

[0608] For example, if a company wants to create a commercial for new product "X," the user (the company's marketing staff) provides details of the new product, the target market, and the theme using a smartphone application. The target audience is input as "18-25 years old," the theme as "active lifestyle," and the main message as "make your everyday life active." The generative AI model generates a scenario based on this information, and the emotion engine analyzes the user's reactions to generate a more refined commercial.

[0609] Example prompt sentence:

[0610] You want to advertise a new pair of sports shoes. The target audience is young people aged 18-25, and the theme is active lifestyle. You want to include the message "Be active every day."

[0611] We want to promote organic juice. The target audience is 25-35 years old, and the theme is health and nature. We want to convey the message that "organic juice is good for your body."

[0612] In this way, by integrating an emotion engine, this system generates personalized commercials that reflect the user's emotions, providing content that viewers can more easily relate to.

[0613] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0614] Step 1:

[0615] The server collects promotional materials (images, text, music, etc.) provided by users through a dedicated interface. This data is converted into an appropriate format and stored in a database. It receives the materials uploaded by the user as input and outputs the materials stored in the database.

[0616] Step 2:

[0617] The server preprocesses the data stored in the database. Specifically, it uses OpenCV to resize and color correct the image data, and FFmpeg to remove noise from the audio data. The preprocessed data is output as training data for the next stage.

[0618] Step 3:

[0619] The server trains a generative AI model using the preprocessed data. GPT-4 is used as the generative AI model, and machine learning algorithms are applied based on past commercial data and viewer preference data. The trained generative AI model is output.

[0620] Step 4:

[0621] The user inputs the target audience, theme, main message, and other requirements for a new commercial through the input interface of the smartphone application. The input requirements are sent to the server. The output is the time until the input request is accepted by the server.

[0622] Step 5:

[0623] The server runs the GPT-4 generative AI model based on the received user request to generate a CM scenario. The input request is applied to the AI ​​model, and an automatically generated scenario is output.

[0624] Step 6:

[0625] The server selects appropriate materials from a database based on the generated scenario, integrates them, and generates an initial version of the commercial. The input scenario is applied to the AI ​​model, and the initial version of the commercial is output.

[0626] Step 7:

[0627] The terminal provides the generated initial version of the CM to the user as a preview. The user checks the preview and inputs any necessary corrections. The input feedback is sent to the server. The preview and feedback are output.

[0628] Step 8:

[0629] The server runs the generation AI again based on the feedback sent by the user, and recreates the commercial reflecting the corrections. At this time, the emotion engine (Affectiva SDK) recognizes emotions from the user's facial expressions and voice, and this is also taken into account in the feedback. The corrected feedback and emotional information are input, and the final commercial is output.

[0630] Step 9:

[0631] The server publishes the final commercial on various platforms (such as social media and video sharing sites) and collects view counts and engagement data. This data is used to generate future commercials. The published commercial and collected data are output.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] [Third embodiment]

[0636] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0637] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0638] 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).

[0639] 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.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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."

[0648] This invention is an innovative commercial production system that uses generative AI technology, and is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and users who provide feedback, etc.

[0649] The system operates as follows.

[0650] First, the user provides the data required for commercial production, including product images, text descriptions, music and video clips to be used in the promotion, etc. This data is collected on the server and stored in a database in an appropriate format.

[0651] The server then uses machine learning algorithms to train a generative AI model based on the stored data. Data preprocessing includes adjusting the size of image data and removing noise from audio data. The trained generative AI model can then learn various viewer preferences and commercial generation patterns, allowing it to generate unique scenarios.

[0652] The device then accepts a request to create a commercial through an interface, where the user inputs specific requirements such as target audience, theme, key message, etc. The input request is then sent to the server.

[0653] Based on the received request, the server automatically generates a scenario using a generative AI model. Based on the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from a database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0654] The generated initial version of the commercial is provided as a preview on the device. The user checks this preview and sends any necessary corrections as feedback to the server. The server analyzes the feedback and extracts corrections. The generative AI model is run again to reflect the extracted corrections, and the final version of the commercial is generated.

[0655] The final commercial is published on the platform of your choice by the server, which then collects real-time engagement data, such as the number of views, shares, and comments, to help inform future commercial production.

[0656] By using this system, unique commercials can be automatically generated quickly and at low cost, resulting in "captivating commercials" that viewers will want to watch. In addition, since the system can be flexibly revised based on feedback, it is possible to maximize advertising effectiveness.

[0657] Specific examples

[0658] Let's say a company wants to promote a new product and requests the production of a commercial through this system.

[0659] Users (marketers) provide details of new products and promotional materials to the system, and this data is collected and stored by the server.

[0660] Marketers then use the interface to input their requests for new commercials, specifying that the target audience is young and the theme is adventurous and fun.

[0661] The server receives these requirements and uses a generative AI model to create a scenario. Based on the scenario, relevant materials are selected from a database and an initial version of the commercial is automatically generated.

[0662] The generated initial version of the commercial is displayed as a preview on the device, and the marketing staff can check it. If they feel that any part of the scenario needs to be revised, they can provide specific feedback on the revisions to the server.

[0663] The server analyzes the feedback and generates the final ad incorporating the changes. Once the final ad is complete, it is published on the designated platform, where viewer numbers and engagement data are collected in real time.

[0664] In this way, companies can create and release highly effective commercials quickly and with minimal effort.

[0665] The processing flow will be explained below.

[0666] Step 1:

[0667] Users provide the data needed to create a new commercial, including product images, text descriptions, music, video clips, and other promotional materials, which are uploaded through a dedicated interface.

[0668] Step 2:

[0669] The server receives the provided data, converts it to the appropriate format, and stores it in a database: for example, images are converted to the appropriate resolution, and text is formatted into a standard format.

[0670] Step 3:

[0671] The server performs data preprocessing based on the stored data, including resizing and color correction of image data and noise reduction of audio data.

[0672] Step 4:

[0673] The server uses the preprocessed data to train a generative AI model using machine learning algorithms, which study past commercial data and viewer preferences to identify new patterns.

[0674] Step 5:

[0675] The terminal (company marketing staff) inputs a request for commercial production through a dedicated interface. The request includes the target audience, theme, main message, etc. This request is then sent to the server.

[0676] Step 6:

[0677] The server runs the generative AI model based on the received request and automatically generates a commercial script, including a storyboard and narration script.

[0678] Step 7:

[0679] Based on the generated scenario, the server selects appropriate materials (images, video clips, music, etc.) from a database and integrates them to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0680] Step 8:

[0681] The server provides the generated initial version of the commercial as a preview to the device, and the user (company representative) can check the preview through the device interface.

[0682] Step 9:

[0683] The user views the generated initial version of the commercial, inputs any necessary modifications, and sends the feedback to the server, which may include corrections to the scenario or the addition of new material.

[0684] Step 10:

[0685] The server analyzes the feedback and lists the extracted corrections. Based on this list, the generative AI model is run again to generate the final commercial that reflects the corrections.

[0686] Step 11:

[0687] The server re-encodes the final commercial and prepares it for publication on the designated platform (YouTube, social media, etc.). After publication, view counts and engagement data (number of shares, number of comments, etc.) are collected in real time.

[0688] Step 12:

[0689] The server analyzes the collected engagement data and evaluates the effectiveness of the advertisement, which will be used to generate future commercials.

[0690] Example 1

[0691] 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."

[0692] The traditional commercial production process is time-consuming and costly, and it is difficult to adjust the quality of the content and tailor it to viewer preferences. Furthermore, the selection of materials and the creation of scripts are done manually, which is inefficient and can result in insufficient advertising effectiveness. Given these circumstances, there is a demand for a system that can quickly and automatically generate high-quality commercials and flexibly make revisions based on feedback.

[0693] 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.

[0694] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial that reflects corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, means for preprocessing data necessary for commercial production, and means for analyzing the provided feedback and extracting corrections. This makes it possible to quickly and efficiently generate high-quality commercials and adjust content to suit viewer preferences.

[0695] "Means for collecting and storing data" means a combination of hardware and software for receiving user-provided data such as images, audio, text, and video, and storing it in an appropriate database.

[0696] A "means for training a generative AI model using a machine learning algorithm" is a component of a system that runs a machine learning algorithm using collected data to train a generative AI model.

[0697] "Means for accepting commercial creation requests through an input interface" refers to an interface that allows users to input commercial creation requirements (target audience, theme, main message, etc.) to the system, and a mechanism for transmitting that input to the server.

[0698] A "means for automatically generating a commercial scenario using a generative AI model" is a component of a system that uses a trained generative AI model to automatically create a commercial scenario based on collected data and user requests.

[0699] The "means of integrating selected materials to generate a commercial" refers to a combination of editing software and hardware that selects appropriate images, audio, video, and other materials from a database in accordance with the generated scenario, and integrates them to create a single commercial.

[0700] The "means for providing a preview of the generated commercial" refers to an interface and a mechanism for playing back the video so that the user can check the generated commercial.

[0701] The "means of receiving feedback and using a generation AI to generate a commercial that reflects the corrections" refers to a generation AI and its control system that analyzes the feedback provided by the user and regenerates a new commercial that reflects the corrections.

[0702] "Means of publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to a system component that uploads the completed commercial to a public platform such as YouTube or social media, and collects viewing data and user engagement data in real time.

[0703] "Means for preprocessing data required for commercial production" refers to a system component that performs preprocessing such as resizing and noise removal to prepare collected image, audio, and text data in a form optimal for training and generation.

[0704] The "means for analyzing the provided feedback and extracting corrections" is a system component that analyzes the feedback from the user using a technique such as text analysis and automatically extracts the necessary corrections.

[0705] This invention is an innovative commercial production system that uses generative AI technology, and is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and a user who provides feedback, etc. This system operates as follows.

[0706] First, the user provides the data required for commercial production, including product images, text descriptions, music and video clips to be used in the promotion, etc. This data is collected on the server and stored in a database in an appropriate format.

[0707] The server then uses machine learning algorithms to train a generative AI model based on the stored data. Specific software used includes Python and TensorFlow. Data preprocessing includes adjusting the size of image data and removing noise from audio data. Once trained, the generative AI model can learn various viewer preferences and commercial generation patterns, allowing it to generate unique scenarios.

[0708] The device then accepts a request to create a commercial through an interface, where the user inputs specific requirements such as target audience, theme, key message, etc. The input request is then sent to the server.

[0709] Based on the received request, the server automatically generates a scenario using a generative AI model. Based on the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from a database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario. The specific hardware used in this process includes a server equipped with a high-performance GPU.

[0710] The generated initial version of the commercial is provided as a preview on the device. The user checks this preview and sends any necessary corrections as feedback to the server. The server analyzes the feedback and extracts corrections. The generative AI model is run again to reflect the extracted corrections, and the final version of the commercial is generated.

[0711] The final commercial is published on the platform of your choice by the server, which then collects real-time engagement data, such as the number of views, shares, and comments, to help inform future commercial production.

[0712] Specific examples

[0713] Let's say a company wants to promote a new product and requests the production of a commercial through this system.

[0714] Users (marketers) provide details of new products and promotional materials to the system, and this data is collected and stored by the server.

[0715] Marketers then use the interface to input their requests for new commercials, specifying, for example, that the target audience is people in their 20s and that the theme is energetic and active.

[0716] The server receives these requirements and uses a generative AI model to create a scenario. Based on the scenario, relevant materials are selected from a database and an initial version of the commercial is automatically generated.

[0717] The generated initial version of the commercial is displayed as a preview on the device, and the marketing staff can check it. If they feel that any part of the scenario needs to be revised, they can provide specific feedback on the revisions to the server.

[0718] The server analyzes the feedback and generates the final ad incorporating the changes. Once the final ad is complete, it is published on the designated platform, where viewer numbers and engagement data are collected in real time.

[0719] In this way, companies can quickly create and publish highly effective commercials with minimal effort, and the entire process is powered by generative AI models and advanced data processing techniques.

[0720] Prompt Sentence Examples

[0721] "Use this system to create a promotional commercial for a new product. The target audience should be in their early 20s, and the theme should be energetic and active. The provided materials include high-resolution images of the product, a description, and a lively, up-tempo song as background music."

[0722] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0723] Step 1:

[0724] The user provides the data necessary to create a commercial. Using the device interface, the user uploads high-resolution images of the product, descriptions, music and video clips to be used in the promotion, etc. The inputs include image files, audio files, text files, and video files. This data is sent to the server via the device.

[0725] Step 2:

[0726] The server stores the received data in a database in an appropriate format. Before storing, it performs preprocessing on the data. This includes resizing images and removing noise from audio data. The input is the data in various formats provided in step 1, and the output is the preprocessed data. The server performs these processes using Python and OpenCV.

[0727] Step 3:

[0728] The server uses machine learning algorithms to train a generative AI model based on the stored data. For example, it uses Python and TensorFlow to build and train the model. The input is the preprocessed data and existing training data, and the output is the trained generative AI model.

[0729] Step 4:

[0730] The terminal accepts a request from the user to create a commercial through the interface. The user inputs specific requirements such as target audience, theme, key message, etc. The input is the request information entered by the user through the terminal interface, which is then sent to the server.

[0731] Step 5:

[0732] The server automatically generates a commercial scenario using a generative AI model based on the received commercial generation request. The input is the user's request information and a trained generative AI model, and the output is the generated commercial scenario. The server runs the generative AI model and creates a scenario using a Python script.

[0733] Step 6:

[0734] The server selects appropriate materials from the database based on the generated scenario and integrates them to generate the initial version of the commercial. The materials are integrated using editing software. The input is the generated scenario and materials in the database, and the output is the initial version of the commercial.

[0735] Step 7:

[0736] The terminal provides the generated initial version of the commercial as a preview to the user, who then reviews it and provides feedback on the content. The input is the initial version of the commercial, and the output is the user's feedback. The user uses the interface to fill out and submit a feedback form.

[0737] Step 8:

[0738] The server analyzes the user feedback and extracts corrections, for example, by using text analysis techniques to understand the content of the feedback and list the corrections. The input is the user feedback and the output is the list of corrections.

[0739] Step 9:

[0740] Based on the corrections, the server uses the generative AI model again to generate the final commercial that reflects the corrections. The input is the list of corrections and the commercial material before the corrections, and the output is the final commercial. The generative AI model is run again to integrate the material and create the final version.

[0741] Step 10:

[0742] The final commercial is published by the server on a designated platform, such as YouTube or social media. After publication, the server collects engagement data in real time, including the number of views, shares, and comments. The input is the final commercial and information about the platform on which it was published, and the output is engagement data.

[0743] Prompt Sentence Examples

[0744] "Use this system to create a promotional commercial for a new product. The target audience should be in their early 20s, and the theme should be energetic and active. The provided materials include high-resolution images of the product, a description, and a lively, up-tempo song as background music."

[0745] (Application example 1)

[0746] 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."

[0747] The traditional advertising video production process was time-consuming and costly, and the revision process to incorporate feedback was particularly tedious. It was also difficult to centrally preview advertising videos and collect performance data after release. This made it difficult to respond quickly to maximize advertising effectiveness.

[0748] 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.

[0749] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving an advertisement generation request through an input interface, means for automatically generating an advertisement video scenario using the generative AI model, means for generating an advertisement video by integrating selected materials, means for providing a preview of the generated advertisement video, means for receiving feedback and again using the generative AI to generate an advertisement video reflecting modifications, means for publishing the generated advertisement video on a specified digital platform and collecting view counts and engagement data, and means for providing an application that operates on terminals including smartphones, thereby enabling the generation, modification, publication, and performance monitoring of advertisement videos quickly and efficiently.

[0750] "Means for collecting and storing data" refers to the system elements that collect material data such as images, videos, and music provided by users and store them in a database on the server.

[0751] "Means for training a generative AI model using a machine learning algorithm" refers to the element of using the collected and pre-processed data to train an AI model specialized in generating advertisements using a machine learning algorithm.

[0752] "Means for accepting advertising generation requests through an input interface" refers to a system element that provides an interface for users to input request information (e.g., target demographic and theme) required to generate an advertising video and transmits that information to a server.

[0753] "Means for automatically generating an advertising video scenario using a generative AI model" refers to an element of a system that automatically generates an advertising video scenario based on input request information using a trained generative AI model.

[0754] "Means for integrating selected materials to generate an advertising video" refers to an element of the system that selects optimal images, videos, music, and other materials from a database based on the generated scenario and integrates them to generate an advertising video.

[0755] "Means for providing a preview of the generated advertising video" refers to an element of the system that provides the generated advertising video to a terminal as a preview that can be viewed by a user.

[0756] "Means for receiving feedback and using a generative AI model to generate an advertising video that reflects the corrections" refers to the system elements that receive feedback information from users, analyze it to extract corrections, and use a generative AI model to generate an advertising video that reflects the corrections.

[0757] "Means for publishing the generated advertising video on designated digital platforms and collecting view and engagement data" refers to the system elements that publish the final advertising video on designated platforms (e.g., social media, websites) and subsequently collect engagement data such as the number of views, shares, and comments in real time.

[0758] "Means for providing an application that runs on a device, including a smartphone" means an element of a system that provides a user with a software application that runs on a smartphone or other device and that assists the user in the process of creating, editing, and publishing advertising videos through that application.

[0759] To implement this invention, a means for collecting and storing data is first required. This means collects material data such as images, videos, and music provided by users and stores them in a database on the server. This allows for centralized management of the materials needed to generate advertising videos.

[0760] Next, a means is needed to train the generative AI model using machine learning algorithms. The server uses the collected and preprocessed data to train an AI model specialized for ad generation. This is done using programming languages ​​and frameworks such as Python and TensorFlow. Specifically, preprocessing is performed, such as resizing image data and removing noise from audio data.

[0761] A user can use an input interface to receive an advertisement generation request. This interface can be implemented as a web browser or a smartphone application, and allows the user to input request information such as target audience, theme, etc. The input information is sent to the server and used to generate the advertisement video.

[0762] The server automatically generates an advertising video scenario using the generative AI model. An appropriate scenario is generated based on the request information entered by the user. For example, if a user enters the prompt, "Please generate an advertising scenario with an adventurous and fun theme for young people. Our new product is a waterproof smartwatch," the generative AI model will generate a corresponding scenario.

[0763] The server then synthesizes the selected materials to generate the advertising video. Based on the generated scenario, the server selects the most suitable images, video clips, and music from the database and synthesizes them to generate the advertising video. This process uses a video editing library such as MoviePy.

[0764] The generated advertising video can be previewed by the user. The preview function is implemented on the device, allowing the user to watch the generated advertising video and check its content. If the user needs to make any corrections, they can send them to the server as feedback.

[0765] The server receives the feedback, analyzes it, and extracts corrections. It then uses the generative AI model again to generate an advertising video that reflects the corrections. This process results in the creation of an optimal advertising video that meets the user's needs.

[0766] Finally, the generated advertising video is published on the designated digital platform. The server collects the number of views and engagement data of the published advertising video in real time, which can be used to evaluate the effectiveness of the advertising video and to help with future production.

[0767] As a concrete example, this system can be used when a company wants to promote a new product. A marketer provides the system with detailed information about the new product and promotional materials, inputting that the target audience is young people and the theme is adventurous and fun. The server that receives this request uses a generative AI model to generate a scenario and integrates the materials to automatically generate an initial advertising video. The generated advertising video can be previewed and any necessary corrections can be provided as feedback. The final advertising video is then generated and published on the specified platform.

[0768] This allows for the quick and efficient creation, modification, publishing and performance monitoring of advertising videos.

[0769] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0770] Step 1:

[0771] Users upload raw data, such as images, videos, and music, required to generate advertising videos to a server via their terminals. The server collects, organizes, and stores this data in a database. The input data is the raw data provided by the users, and the output data is the organized raw data stored in the database.

[0772] Step 2:

[0773] The server preprocesses the stored material data in the database. Specifically, it adjusts the size of image data and removes noise from audio data. The input data is the material data in the database, and the output data is clean data that has undergone preprocessing.

[0774] Step 3:

[0775] The server uses a machine learning algorithm to train the generative AI model, using preprocessed raw data in the process: the input data is the preprocessed raw data, and the output data is the trained generative AI model.

[0776] Step 4:

[0777] A user sends an advertisement generation request from the terminal to the server through the input interface. The input request includes details such as target audience, theme, main message, etc. The input data is the user's request information, and the output data is the request sent to the server.

[0778] Step 5:

[0779] The server automatically generates an advertising video scenario using a generative AI model based on the received request information. The input data is the user request information and the trained generative AI model, and the output data is the generated scenario. Specifically, the generative AI constructs a scenario based on the prompt sentence.

[0780] Step 6:

[0781] The server selects appropriate materials (images, video clips, music, etc.) from the database based on the generated scenario and integrates them to generate an advertising video. The input data is the generated scenario and the material data in the database, and the output data is the generated advertising video. Specifically, the server uses the MoviePy library to combine the materials and generate the video.

[0782] Step 7:

[0783] The terminal provides a preview of the generated advertising video to the user, and the user checks the preview and sends feedback to the server through a feedback interface, where the input data is the generated advertising video and the output data is the user's feedback.

[0784] Step 8:

[0785] The server analyzes the feedback from the user and extracts the corrections. The input data is the user feedback, and the output data is the list of corrections.

[0786] Step 9:

[0787] The server then runs the generative AI model again based on the extracted corrections to generate an advertising video that reflects the corrections. The input data is the list of corrections and the trained generative AI model, and the output data is the corrected advertising video.

[0788] Step 10:

[0789] The server publishes the generated final advertising video on a specified digital platform (e.g., social media, website), and collects subsequent view counts and engagement data (number of shares, comments, etc.) in real time. The input data is the final advertising video, and the output data is the engagement data collected in real time.

[0790] 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.

[0791] This invention is an innovative commercial production system that uses generative AI technology and combines it with an emotion engine that recognizes user emotions to generate more personalized advertisements. This system is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and users who provide feedback, etc.

[0792] System Overview

[0793] The system operates as follows.

[0794] The user provides the data required for commercial production, including promotional materials such as product images, text descriptions, music, video clips, etc. This data is collected on the server and stored in a database in an appropriate format.

[0795] The server then performs data preprocessing on the stored data, including resizing and color correction of image data and noise reduction of audio data. The preprocessed data is then used to train a generative AI model using machine learning algorithms. The trained generative AI model can then learn various viewer preferences and commercial generation patterns.

[0796] The terminal accepts commercial creation requests through an interface, which allows users to input specific requirements such as target audience, theme, key message, etc. These requests are then sent to the server.

[0797] The server runs the generative AI model based on the received request and automatically generates a commercial scenario. From the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from the database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0798] The generated initial version of the commercial is provided as a preview on the device. The user (company representative) checks the preview and sends any necessary revisions as feedback to the server. At this time, the emotion engine recognizes the user's emotions from their facial expressions and voice, and reflects the results in the feedback analysis.

[0799] The server analyzes the feedback and regenerates the commercial based on the extracted corrections and recognized emotional information. Once the final version is generated, it is published on the designated platform and viewer numbers and engagement data are collected.

[0800] Program processing details

[0801] First, the user provides the data needed to create a new commercial. This data is uploaded through a dedicated interface. The server then receives the data, converts it into a format, and stores it in a database.

[0802] The data stored in the database is pre-processed and then used to train a generative AI model using machine learning algorithms, including data on past commercial successes and viewer preferences.

[0803] Users input their requests for new commercials through an interface, specifying details of the target audience, themes, key messages, etc. The requests are sent to a server, where a generative AI model generates a commercial script based on the requests.

[0804] Based on the generated scenario, related material is selected from a database and a commercial is generated. At this time, an emotion engine recognizes emotions from the user's facial expressions and voice, and based on this information, material selection and script revisions are made.

[0805] An initial version of the commercial is generated and provided as a preview on the device. The user views the preview and provides feedback. The user's emotions, as recognized by the emotion engine, are also used as feedback.

[0806] The server analyzes the feedback and emotional information, again using the AI ​​to make corrections and generate the final commercial. The final commercial is then published on the designated platform, and view counts and engagement data are collected. This engagement data will also be used to generate future commercials.

[0807] Specific examples

[0808] Suppose a company wants to create a commercial to promote its new product "X." The user (the company's marketing manager) provides details about the new product, its target market, and the theme. This data is collected on the server.

[0809] Marketers then use the interface to input specific requests, such as target audience ages 18 to 25 and a theme that is adventurous.

[0810] The server uses a generative AI model to generate an adventurous scenario, selects the necessary materials from a database, and generates an initial commercial. During this process, an emotion engine recognizes the emotions of the user (marketer) and reflects this information in the selection of materials and scenario generation.

[0811] The generated initial version of the commercial is displayed as a preview on the device. The marketer reviews the commercial and, if they feel that any changes are necessary to the scenario or materials, they can submit feedback along with emotional information. The server analyzes the feedback, generates the final version of the commercial, and publishes it.

[0812] The present invention thus implemented can generate commercials that reflect the user's emotions by integrating an emotion engine, thereby providing content that viewers can more easily relate to.

[0813] The processing flow will be explained below.

[0814] Step 1:

[0815] Through a dedicated interface, users provide the data needed to create a new commercial, including promotional materials such as product images, text descriptions, music, and video clips.

[0816] Step 2:

[0817] The server receives the provided data, converts it into an appropriate format, and stores it in a database: for example, image data is converted to an appropriate resolution, and text is formatted into a standard format.

[0818] Step 3:

[0819] The server preprocesses the stored data, including adjusting the size and color of the image data and removing noise from the audio data.

[0820] Step 4:

[0821] The server uses the pre-processed data to train a generative AI model using machine learning algorithms, including past commercial data and viewer preference data.

[0822] Step 5:

[0823] The terminal (a company's marketing staff) inputs a request for commercial production through a dedicated interface. The request includes the target audience, theme, and main message. This request is then sent to the server.

[0824] Step 6:

[0825] The server runs the generative AI model based on the received request and automatically generates a commercial script, including a storyboard and narration script.

[0826] Step 7:

[0827] Based on the generated scenario, the server selects appropriate materials (images, video clips, music, etc.) from a database and integrates them to generate the initial version of the commercial.

[0828] Step 8:

[0829] The server uses an emotion engine to recognize the user's emotions in real time. The emotion engine analyzes the user's emotions from their facial expressions and voice, and incorporates that information as feedback.

[0830] Step 9:

[0831] The server provides the generated initial version of the commercial as a preview to the terminal, and the user can check the preview and input any necessary corrections as feedback through the terminal interface.

[0832] Step 10:

[0833] The server lists corrections based on the received feedback and the analysis results of the emotion engine, and then uses the generative AI model again to generate the final commercial that reflects the corrections.

[0834] Step 11:

[0835] The server prepares the final commercial for publication on the designated platform (YouTube, social media, etc.) After publication, view counts and engagement data (number of shares, number of comments, etc.) are collected in real time.

[0836] Step 12:

[0837] The server analyzes the collected engagement data and evaluates the effectiveness of the advertisement, which will be used to generate future commercials.

[0838] Example 2

[0839] 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."

[0840] Conventional commercial production systems have limited technology for generating advertisements that take viewer preferences into account, making it difficult to automatically generate personalized commercials that reflect user emotions. Furthermore, it is difficult to efficiently generate revised commercials that reflect appropriate feedback, resulting in the challenge of not being able to maximize the impact on viewers.

[0841] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial reflecting the corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, and means for recognizing user emotions and reflecting the emotional information in the feedback. This enables the automatic generation of personalized commercials that reflect the user's emotions, maximizing their impact on viewers.

[0842] "Data collection and storage means" means a device or system that receives user-provided promotional materials such as images, text, music, and video clips, converts them into an appropriate format, and stores them in a database.

[0843] A "means for training a generative AI model using a machine learning algorithm" is an apparatus and technology for carrying out the process of training a generative AI model using preprocessed data.

[0844] "Means for accepting commercial generation requests through an input interface" refers to a device or system that provides an interface for users to input commercial requests (e.g., target audience, theme, message, etc.) and receives the input information.

[0845] "Means for automatically generating a commercial scenario using a generative AI model" refers to devices and technologies for automatically creating a commercial scenario using a generative AI model based on a user request.

[0846] "Means for integrating selected materials to generate a commercial" refers to devices and technologies for selecting appropriate materials (images, music, video clips) from a database based on the generated scenario and integrating them to create a commercial.

[0847] The "means for providing a preview of the generated commercial" is a device or system that provides a preview function that allows a user to visually check the generated commercial.

[0848] "Means for receiving feedback and regenerating a commercial that reflects the corrections using a generative AI" refers to devices and technologies for receiving feedback from users and regenerating and correcting a commercial using a generative AI model based on that feedback.

[0849] "Means for publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to the devices and technologies for uploading the final commercial to a designated online platform and collecting subsequent view counts and viewer engagement data.

[0850] "Means for recognizing the user's emotions and reflecting that emotional information in feedback" refers to a device and technology for recognizing the user's emotions from their facial expressions and voice, and reflecting that emotional information in the analysis of the modification requirements.

[0851] MODE FOR CARRYING OUT THE INVENTION

[0852] This invention is an innovative commercial production system that combines generative AI technology with an emotion engine that recognizes user emotions. An embodiment of this system will be described in detail below.

[0853] System Configuration

[0854] This system operates in collaboration with a server with multiple functions, a terminal with an interface, and a user who provides feedback, etc. The main hardware and software include the following:

[0855] Hardware: High-performance servers, user devices (PCs, tablets, smartphones, etc.)

[0856] Software: OpenCV (image processing library), Librosa (audio processing library), machine learning frameworks (TensorFlow, PyTorch, etc.)

[0857] Program processing overview

[0858] First, the user provides the data needed to create a commercial, including product images, text, music, and video clips, through the device interface. The device receives this data and sends it to the server, which then converts it into an appropriate format and stores it in a database.

[0859] The server then preprocesses the stored data. Specifically, it uses OpenCV to resize and color correct the image data, and Librosa to remove noise from the audio data. The preprocessed data is then used to train a generative AI model using a machine learning framework (TensorFlow or PyTorch). Training utilizes data on past successful commercials and viewer preference data.

[0860] Through the interface, the user enters a request to create a new commercial, including specific requirements such as target audience, theme, key message, etc. This request is then sent from the device to the server.

[0861] The server uses a generative AI model to generate a commercial scenario based on the request, and then selects appropriate materials (images, video clips, music) from a database based on the generated scenario, and combines them to generate the initial commercial.

[0862] The generated initial commercial is provided as a preview on the device for the user to review. If there are any corrections that need to be made, the user can enter feedback and send it to the server via the device. At this time, the emotion engine recognizes the user's emotions from their facial expressions and voice, and the results are reflected in the feedback.

[0863] The server analyzes the feedback and sentiment information, then uses the generative AI model to revise and regenerate the commercial. Once the final version of the commercial is generated, it is published on the designated platform and view counts and engagement data are collected. This collected data is used to generate future commercials.

[0864] Specific examples

[0865] For example, a company wants to create a commercial to promote its new product "X." The user (the company's marketer) provides data about the new product's details, target market, and theme. This data is collected by the server. The marketer then uses the device interface to enter a specific request: for example, the target audience is 18-25 years old, and the theme is adventurous. The request is sent to the server.

[0866] The server uses a generative AI model to generate an adventurous scenario, selects the necessary materials from a database, and generates an initial version of the commercial. At this time, an emotion engine recognizes the user's (marketer's) emotions and reflects that information in the selection of materials and scenario generation. The generated initial version of the commercial is displayed as a preview on the device.

[0867] If the marketing person views the preview and feels that any part of the script or material needs to be revised, they send that feedback to the server, which analyzes the feedback, generates the final commercial, and publishes it.

[0868] An example prompt is:

[0869] Create a commercial promoting your new product "X". The target audience is 18-25 years old and the theme is adventurous. Use the following promotional materials: product images, text description, music, and video clips.

[0870] The above is a specific embodiment of the present invention. This system makes it possible to automatically generate personalized commercials that reflect the user's emotions.

[0871] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0872] Step 1:

[0873] The user provides the data required for commercial production. This data includes promotional materials such as product images, text descriptions, music, and video clips. The data is input into the terminal through an input interface. The terminal transmits this input data to the server. As output, the data is received by the server.

[0874] Step 2:

[0875] The server collects the received data, converts it into the appropriate format, and stores it in the database. For example, image files are converted into JPEG or PNG format, and text files are stored in UTF-8 format. As an output, each data is stored in the database.

[0876] Step 3:

[0877] The server preprocesses the data stored in the database. Specifically, it uses OpenCV to resize and color correct the image data, and Librosa to denoise the audio data. It takes the data in the database as input and produces preprocessed data as output.

[0878] Step 4:

[0879] The server uses the preprocessed data to train a generative AI model. Using a machine learning framework (TensorFlow or PyTorch), the model learns from past success stories and viewer preference data. The preprocessed data is used as input, and a trained generative AI model is obtained as output.

[0880] Step 5:

[0881] The user inputs a new commercial generation request through the input interface. The request includes the target audience, theme, main message, etc. The terminal receives the input request and sends it to the server. The server receives the request data as output.

[0882] Step 6:

[0883] The server uses a generative AI model to generate a commercial scenario based on the received request. It inputs the prompt sentence into the generative AI model and outputs an appropriate scenario. It then selects appropriate materials from a database based on the scenario and integrates them to generate an initial version of the commercial. Using the request data and the trained generative AI model as input, the initial version of the commercial is obtained as output.

[0884] Step 7:

[0885] The terminal provides the generated initial version of the CM to the user as a preview. The user checks the preview and inputs any necessary corrections as feedback. The terminal then sends the feedback to the server, displaying the initial version of the CM as input and sending the feedback data as output to the server.

[0886] Step 8:

[0887] The server receives and analyzes feedback from users. It uses an emotion engine to recognize emotions from the user's facial expressions and voice, and reflects the results in the feedback. Feedback data and emotional information are taken as input, and a list of corrections is output.

[0888] Step 9:

[0889] The server then re-runs the generative AI model based on the analysis results to correct and regenerate the commercial. Using the list of corrections and the generative AI model as input, the final commercial is generated as output.

[0890] Step 10:

[0891] The server publishes the final commercial to the specified platform. It then collects the number of views and engagement data for the published commercial. The final commercial is uploaded to the platform as input, and engagement data is collected as output. This data is used to generate future commercials.

[0892] (Application example 2)

[0893] 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."

[0894] Conventional commercial production systems have difficulty generating personalized advertisements that reflect user emotions, making it difficult to gain viewer empathy. Furthermore, it is difficult to quickly generate effective commercials tailored to the target audience and theme. Furthermore, the development of smartphone-based commercial production applications has not progressed. For these reasons, there is a need for a means for corporate marketing personnel to easily create high-quality commercials and deliver effective messages to their target audiences.

[0895] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0896] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial reflecting the corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, means for analyzing the feedback using an emotion engine that recognizes user emotions and reflecting it in the generation of the commercial, and means for providing an application to be installed on a smartphone and for producing commercials. This makes it possible to generate personalized advertisements that reflect user emotions in a short amount of time and easily produce high-quality commercials using a smartphone.

[0897] "Means for collecting and storing data" refers to the mechanism by which promotional materials and information provided by users are collected and stored in a database in an appropriate format.

[0898] "Means for training a generative AI model using machine learning algorithms" refers to a mechanism for training a generative AI model using machine learning based on collected data.

[0899] "Means for accepting commercial generation requests through an input interface" refers to a mechanism for providing an interface that allows users to input commercial generation requirements such as target audience and theme, and for receiving those requests.

[0900] "Means for automatically generating commercial scenarios using a generative AI model" refers to a system that uses a trained AI model to automatically generate commercial scenarios based on user requests.

[0901] The "means of integrating selected materials to generate a commercial" refers to a mechanism that selects appropriate materials from a database based on the generated scenario, integrates them, and generates a commercial.

[0902] The "means for providing a preview of the generated commercial" is a mechanism for providing a preview function that allows users to check the initial version of the commercial.

[0903] "Means of receiving feedback and using generative AI to generate a commercial that reflects the corrections" refers to a system that receives feedback from users, makes corrections using a generative AI model based on that feedback, and then generates a commercial again.

[0904] "Means of publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to a system in which the final commercial is published on various platforms and its view counts and engagement data are collected.

[0905] "Means of analyzing feedback using an emotion engine that recognizes the user's emotions and reflecting it in the generation of commercials" refers to a system that recognizes emotions from the user's facial expressions and voice, and uses this emotional information in feedback analysis to reflect it in the generation of commercials.

[0906] "Means of providing an application that can be installed on a smartphone and used to produce commercials" refers to a system in which an application that can be installed on a smartphone is provided and commercials are produced through that application.

[0907] This invention is a system comprising: means for collecting and storing data; means for training a generative AI model using a machine learning algorithm; means for accepting a commercial generation request; means for automatically generating a commercial scenario using the generative AI model; means for generating a commercial by integrating selected materials; means for providing a preview of the generated commercial; means for receiving feedback and again using the generative AI to generate a commercial that reflects the corrections; means for publishing the generated commercial on a specified platform and collecting view counts and engagement data; means for analyzing feedback using an emotion engine that recognizes user emotions and reflecting the feedback in the generation of the commercial; and means for providing an application to be installed on a smartphone for producing commercials.

[0908] Specifically, the server collects promotional materials and information provided by users and stores them in a database in an appropriate format. The server then uses machine learning to train a generative AI model based on the collected data. OpenAI's GPT-4 is one example of a generative AI model. Next, the server accepts commercial generation requirements, such as target audience and theme, through an input interface. Based on these requirements, the generative AI model automatically generates a commercial scenario.

[0909] Based on the generated scenario, the server selects and integrates appropriate materials from a database to generate a commercial. The generated commercial is then provided as a preview on a smartphone application. When the user checks this preview and enters feedback, the emotion engine recognizes emotions from the user's facial expressions and voice and sends that information to the server.

[0910] Based on the feedback and sentiment information, the server uses the generative AI model again to generate a commercial that reflects the modifications. The final commercial is published on the designated platform, and the server collects the number of views and engagement data, which can be used to generate future commercials.

[0911] The hardware used includes a smartphone (iOS or Android), a server, and a suitable database (e.g., MongoDB).The software used is React Native for the front end, Node.js and Express for the back end, OpenCV for image data processing, FFmpeg for audio data processing, and the Affectiva SDK as an emotion engine.

[0912] For example, if a company wants to create a commercial for new product "X," the user (the company's marketing staff) provides details of the new product, the target market, and the theme using a smartphone application. The target audience is input as "18-25 years old," the theme as "active lifestyle," and the main message as "make your everyday life active." The generative AI model generates a scenario based on this information, and the emotion engine analyzes the user's reactions to generate a more refined commercial.

[0913] Example prompt sentence:

[0914] You want to advertise a new pair of sports shoes. The target audience is young people aged 18-25, and the theme is active lifestyle. You want to include the message "Be active every day."

[0915] We want to promote organic juice. The target audience is 25-35 years old, and the theme is health and nature. We want to convey the message that "organic juice is good for your body."

[0916] In this way, by integrating an emotion engine, this system generates personalized commercials that reflect the user's emotions, providing content that viewers can more easily relate to.

[0917] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0918] Step 1:

[0919] The server collects promotional materials (images, text, music, etc.) provided by users through a dedicated interface. This data is converted into an appropriate format and stored in a database. It receives the materials uploaded by the user as input and outputs the materials stored in the database.

[0920] Step 2:

[0921] The server preprocesses the data stored in the database. Specifically, it uses OpenCV to resize and color correct the image data, and FFmpeg to remove noise from the audio data. The preprocessed data is output as training data for the next stage.

[0922] Step 3:

[0923] The server trains a generative AI model using the preprocessed data. GPT-4 is used as the generative AI model, and machine learning algorithms are applied based on past commercial data and viewer preference data. The trained generative AI model is output.

[0924] Step 4:

[0925] The user inputs the target audience, theme, main message, and other requirements for a new commercial through the input interface of the smartphone application. The input requirements are sent to the server. The output is the time until the input request is accepted by the server.

[0926] Step 5:

[0927] The server runs the GPT-4 generative AI model based on the received user request to generate a CM scenario. The input request is applied to the AI ​​model, and an automatically generated scenario is output.

[0928] Step 6:

[0929] The server selects appropriate materials from a database based on the generated scenario, integrates them, and generates an initial version of the commercial. The input scenario is applied to the AI ​​model, and the initial version of the commercial is output.

[0930] Step 7:

[0931] The terminal provides the generated initial version of the CM to the user as a preview. The user checks the preview and inputs any necessary corrections. The input feedback is sent to the server. The preview and feedback are output.

[0932] Step 8:

[0933] The server runs the generation AI again based on the feedback sent by the user, and recreates the commercial reflecting the corrections. At this time, the emotion engine (Affectiva SDK) recognizes emotions from the user's facial expressions and voice, and this is also taken into account in the feedback. The corrected feedback and emotional information are input, and the final commercial is output.

[0934] Step 9:

[0935] The server publishes the final commercial on various platforms (such as social media and video sharing sites) and collects view counts and engagement data. This data is used to generate future commercials. The published commercial and collected data are output.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] [Fourth embodiment]

[0940] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0941] 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.

[0942] 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).

[0943] 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.

[0944] 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.

[0945] 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).

[0946] 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.

[0947] 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.

[0948] 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.

[0949] 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.

[0950] 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.

[0951] 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.

[0952] 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."

[0953] This invention is an innovative commercial production system that uses generative AI technology, and is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and users who provide feedback, etc.

[0954] The system operates as follows.

[0955] First, the user provides the data required for commercial production, including product images, text descriptions, music and video clips to be used in the promotion, etc. This data is collected on the server and stored in a database in an appropriate format.

[0956] The server then uses machine learning algorithms to train a generative AI model based on the stored data. Data preprocessing includes adjusting the size of image data and removing noise from audio data. The trained generative AI model can then learn various viewer preferences and commercial generation patterns, allowing it to generate unique scenarios.

[0957] The device then accepts a request to create a commercial through an interface, where the user inputs specific requirements such as target audience, theme, key message, etc. The input request is then sent to the server.

[0958] Based on the received request, the server automatically generates a scenario using a generative AI model. Based on the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from a database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0959] The generated initial version of the commercial is provided as a preview on the device. The user checks this preview and sends any necessary corrections as feedback to the server. The server analyzes the feedback and extracts corrections. The generative AI model is run again to reflect the extracted corrections, and the final version of the commercial is generated.

[0960] The final commercial is published on the platform of your choice by the server, which then collects real-time engagement data, such as the number of views, shares, and comments, to help inform future commercial production.

[0961] By using this system, unique commercials can be automatically generated quickly and at low cost, resulting in "captivating commercials" that viewers will want to watch. In addition, since the system can be flexibly revised based on feedback, it is possible to maximize advertising effectiveness.

[0962] Specific examples

[0963] Let's say a company wants to promote a new product and requests the production of a commercial through this system.

[0964] Users (marketers) provide details of new products and promotional materials to the system, and this data is collected and stored by the server.

[0965] Marketers then use the interface to input their requests for new commercials, specifying that the target audience is young and the theme is adventurous and fun.

[0966] The server receives these requirements and uses a generative AI model to create a scenario. Based on the scenario, relevant materials are selected from a database and an initial version of the commercial is automatically generated.

[0967] The generated initial version of the commercial is displayed as a preview on the device, and the marketing staff can check it. If they feel that any part of the scenario needs to be revised, they can provide specific feedback on the revisions to the server.

[0968] The server analyzes the feedback and generates the final ad incorporating the changes. Once the final ad is complete, it is published on the designated platform, where viewer numbers and engagement data are collected in real time.

[0969] In this way, companies can create and release highly effective commercials quickly and with minimal effort.

[0970] The processing flow will be explained below.

[0971] Step 1:

[0972] Users provide the data needed to create a new commercial, including product images, text descriptions, music, video clips, and other promotional materials, which are uploaded through a dedicated interface.

[0973] Step 2:

[0974] The server receives the provided data, converts it to the appropriate format, and stores it in a database: for example, images are converted to the appropriate resolution, and text is formatted into a standard format.

[0975] Step 3:

[0976] The server performs data preprocessing based on the stored data, including resizing and color correction of image data and noise reduction of audio data.

[0977] Step 4:

[0978] The server uses the preprocessed data to train a generative AI model using machine learning algorithms, which study past commercial data and viewer preferences to identify new patterns.

[0979] Step 5:

[0980] The terminal (company marketing staff) inputs a request for commercial production through a dedicated interface. The request includes the target audience, theme, main message, etc. This request is then sent to the server.

[0981] Step 6:

[0982] The server runs the generative AI model based on the received request and automatically generates a commercial script, including a storyboard and narration script.

[0983] Step 7:

[0984] Based on the generated scenario, the server selects appropriate materials (images, video clips, music, etc.) from a database and integrates them to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[0985] Step 8:

[0986] The server provides the generated initial version of the commercial as a preview to the device, and the user (company representative) can check the preview through the device interface.

[0987] Step 9:

[0988] The user views the generated initial version of the commercial, inputs any necessary modifications, and sends the feedback to the server, which may include corrections to the scenario or the addition of new material.

[0989] Step 10:

[0990] The server analyzes the feedback and lists the extracted corrections. Based on this list, the generative AI model is run again to generate the final commercial that reflects the corrections.

[0991] Step 11:

[0992] The server re-encodes the final commercial and prepares it for publication on the designated platform (YouTube, social media, etc.). After publication, view counts and engagement data (number of shares, number of comments, etc.) are collected in real time.

[0993] Step 12:

[0994] The server analyzes the collected engagement data and evaluates the effectiveness of the advertisement, which will be used to generate future commercials.

[0995] Example 1

[0996] 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."

[0997] The traditional commercial production process is time-consuming and costly, and it is difficult to adjust the quality of the content and tailor it to viewer preferences. Furthermore, the selection of materials and the creation of scripts are done manually, which is inefficient and can result in insufficient advertising effectiveness. Given these circumstances, there is a demand for a system that can quickly and automatically generate high-quality commercials and flexibly make revisions based on feedback.

[0998] 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.

[0999] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial that reflects corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, means for preprocessing data necessary for commercial production, and means for analyzing the provided feedback and extracting corrections. This makes it possible to quickly and efficiently generate high-quality commercials and adjust content to suit viewer preferences.

[1000] "Means for collecting and storing data" means a combination of hardware and software for receiving user-provided data such as images, audio, text, and video, and storing it in an appropriate database.

[1001] A "means for training a generative AI model using a machine learning algorithm" is a component of a system that runs a machine learning algorithm using collected data to train a generative AI model.

[1002] "Means for accepting commercial creation requests through an input interface" refers to an interface that allows users to input commercial creation requirements (target audience, theme, main message, etc.) to the system, and a mechanism for transmitting that input to the server.

[1003] A "means for automatically generating a commercial scenario using a generative AI model" is a component of a system that uses a trained generative AI model to automatically create a commercial scenario based on collected data and user requests.

[1004] The "means of integrating selected materials to generate a commercial" refers to a combination of editing software and hardware that selects appropriate images, audio, video, and other materials from a database in accordance with the generated scenario, and integrates them to create a single commercial.

[1005] The "means for providing a preview of the generated commercial" refers to an interface and a mechanism for playing back the video so that the user can check the generated commercial.

[1006] The "means of receiving feedback and using a generation AI to generate a commercial that reflects the corrections" refers to a generation AI and its control system that analyzes the feedback provided by the user and regenerates a new commercial that reflects the corrections.

[1007] "Means of publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to a system component that uploads the completed commercial to a public platform such as YouTube or social media, and collects viewing data and user engagement data in real time.

[1008] "Means for preprocessing data required for commercial production" refers to a system component that performs preprocessing such as resizing and noise removal to prepare collected image, audio, and text data in a form optimal for training and generation.

[1009] The "means for analyzing the provided feedback and extracting corrections" is a system component that analyzes the feedback from the user using a technique such as text analysis and automatically extracts the necessary corrections.

[1010] This invention is an innovative commercial production system that uses generative AI technology, and is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and a user who provides feedback, etc. This system operates as follows.

[1011] First, the user provides the data required for commercial production, including product images, text descriptions, music and video clips to be used in the promotion, etc. This data is collected on the server and stored in a database in an appropriate format.

[1012] The server then uses machine learning algorithms to train a generative AI model based on the stored data. Specific software used includes Python and TensorFlow. Data preprocessing includes adjusting the size of image data and removing noise from audio data. Once trained, the generative AI model can learn various viewer preferences and commercial generation patterns, allowing it to generate unique scenarios.

[1013] The device then accepts a request to create a commercial through an interface, where the user inputs specific requirements such as target audience, theme, key message, etc. The input request is then sent to the server.

[1014] Based on the received request, the server automatically generates a scenario using a generative AI model. Based on the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from a database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario. The specific hardware used in this process includes a server equipped with a high-performance GPU.

[1015] The generated initial version of the commercial is provided as a preview on the device. The user checks this preview and sends any necessary corrections as feedback to the server. The server analyzes the feedback and extracts corrections. The generative AI model is run again to reflect the extracted corrections, and the final version of the commercial is generated.

[1016] The final commercial is published on the platform of your choice by the server, which then collects real-time engagement data, such as the number of views, shares, and comments, to help inform future commercial production.

[1017] Specific examples

[1018] Let's say a company wants to promote a new product and requests the production of a commercial through this system.

[1019] Users (marketers) provide details of new products and promotional materials to the system, and this data is collected and stored by the server.

[1020] Marketers then use the interface to input their requests for new commercials, specifying, for example, that the target audience is people in their 20s and that the theme is energetic and active.

[1021] The server receives these requirements and uses a generative AI model to create a scenario. Based on the scenario, relevant materials are selected from a database and an initial version of the commercial is automatically generated.

[1022] The generated initial version of the commercial is displayed as a preview on the device, and the marketing staff can check it. If they feel that any part of the scenario needs to be revised, they can provide specific feedback on the revisions to the server.

[1023] The server analyzes the feedback and generates the final ad incorporating the changes. Once the final ad is complete, it is published on the designated platform, where viewer numbers and engagement data are collected in real time.

[1024] In this way, companies can quickly create and publish highly effective commercials with minimal effort, and the entire process is powered by generative AI models and advanced data processing techniques.

[1025] Prompt Sentence Examples

[1026] "Use this system to create a promotional commercial for a new product. The target audience should be in their early 20s, and the theme should be energetic and active. The provided materials include high-resolution images of the product, a description, and a lively, up-tempo song as background music."

[1027] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1028] Step 1:

[1029] The user provides the data necessary to create a commercial. Using the device interface, the user uploads high-resolution images of the product, descriptions, music and video clips to be used in the promotion, etc. The inputs include image files, audio files, text files, and video files. This data is sent to the server via the device.

[1030] Step 2:

[1031] The server stores the received data in a database in an appropriate format. Before storing, it performs preprocessing on the data. This includes resizing images and removing noise from audio data. The input is the data in various formats provided in step 1, and the output is the preprocessed data. The server performs these processes using Python and OpenCV.

[1032] Step 3:

[1033] The server uses machine learning algorithms to train a generative AI model based on the stored data. For example, it uses Python and TensorFlow to build and train the model. The input is the preprocessed data and existing training data, and the output is the trained generative AI model.

[1034] Step 4:

[1035] The terminal accepts a request from the user to create a commercial through the interface. The user inputs specific requirements such as target audience, theme, key message, etc. The input is the request information entered by the user through the terminal interface, which is then sent to the server.

[1036] Step 5:

[1037] The server automatically generates a commercial scenario using a generative AI model based on the received commercial generation request. The input is the user's request information and a trained generative AI model, and the output is the generated commercial scenario. The server runs the generative AI model and creates a scenario using a Python script.

[1038] Step 6:

[1039] The server selects appropriate materials from the database based on the generated scenario and integrates them to generate the initial version of the commercial. The materials are integrated using editing software. The input is the generated scenario and materials in the database, and the output is the initial version of the commercial.

[1040] Step 7:

[1041] The terminal provides the generated initial version of the commercial as a preview to the user, who then reviews it and provides feedback on the content. The input is the initial version of the commercial, and the output is the user's feedback. The user uses the interface to fill out and submit a feedback form.

[1042] Step 8:

[1043] The server analyzes the user feedback and extracts corrections, for example, by using text analysis techniques to understand the content of the feedback and list the corrections. The input is the user feedback and the output is the list of corrections.

[1044] Step 9:

[1045] Based on the corrections, the server uses the generative AI model again to generate the final commercial that reflects the corrections. The input is the list of corrections and the commercial material before the corrections, and the output is the final commercial. The generative AI model is run again to integrate the material and create the final version.

[1046] Step 10:

[1047] The final commercial is published by the server on a designated platform, such as YouTube or social media. After publication, the server collects engagement data in real time, including the number of views, shares, and comments. The input is the final commercial and information about the platform on which it was published, and the output is engagement data.

[1048] Prompt Sentence Examples

[1049] "Use this system to create a promotional commercial for a new product. The target audience should be in their early 20s, and the theme should be energetic and active. The provided materials include high-resolution images of the product, a description, and a lively, up-tempo song as background music."

[1050] (Application example 1)

[1051] 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."

[1052] The traditional advertising video production process was time-consuming and costly, and the revision process to incorporate feedback was particularly tedious. It was also difficult to centrally preview advertising videos and collect performance data after release. This made it difficult to respond quickly to maximize advertising effectiveness.

[1053] 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.

[1054] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving an advertisement generation request through an input interface, means for automatically generating an advertisement video scenario using the generative AI model, means for generating an advertisement video by integrating selected materials, means for providing a preview of the generated advertisement video, means for receiving feedback and again using the generative AI to generate an advertisement video reflecting modifications, means for publishing the generated advertisement video on a specified digital platform and collecting view counts and engagement data, and means for providing an application that operates on terminals including smartphones, thereby enabling the generation, modification, publication, and performance monitoring of advertisement videos quickly and efficiently.

[1055] "Means for collecting and storing data" refers to the system elements that collect material data such as images, videos, and music provided by users and store them in a database on the server.

[1056] "Means for training a generative AI model using a machine learning algorithm" refers to the element of using the collected and pre-processed data to train an AI model specialized in generating advertisements using a machine learning algorithm.

[1057] "Means for accepting advertising generation requests through an input interface" refers to a system element that provides an interface for users to input request information (e.g., target demographic and theme) required to generate an advertising video and transmits that information to a server.

[1058] "Means for automatically generating an advertising video scenario using a generative AI model" refers to an element of a system that automatically generates an advertising video scenario based on input request information using a trained generative AI model.

[1059] "Means for integrating selected materials to generate an advertising video" refers to an element of the system that selects optimal images, videos, music, and other materials from a database based on the generated scenario and integrates them to generate an advertising video.

[1060] "Means for providing a preview of the generated advertising video" refers to an element of the system that provides the generated advertising video to a terminal as a preview that can be viewed by a user.

[1061] "Means for receiving feedback and using a generative AI model to generate an advertising video that reflects the corrections" refers to the system elements that receive feedback information from users, analyze it to extract corrections, and use a generative AI model to generate an advertising video that reflects the corrections.

[1062] "Means for publishing the generated advertising video on designated digital platforms and collecting view and engagement data" refers to the system elements that publish the final advertising video on designated platforms (e.g., social media, websites) and subsequently collect engagement data such as the number of views, shares, and comments in real time.

[1063] "Means for providing an application that runs on a device, including a smartphone" means an element of a system that provides a user with a software application that runs on a smartphone or other device and that assists the user in the process of creating, editing, and publishing advertising videos through that application.

[1064] To implement this invention, a means for collecting and storing data is first required. This means collects material data such as images, videos, and music provided by users and stores them in a database on the server. This allows for centralized management of the materials needed to generate advertising videos.

[1065] Next, a means is needed to train the generative AI model using machine learning algorithms. The server uses the collected and preprocessed data to train an AI model specialized for ad generation. This is done using programming languages ​​and frameworks such as Python and TensorFlow. Specifically, preprocessing is performed, such as resizing image data and removing noise from audio data.

[1066] A user can use an input interface to receive an advertisement generation request. This interface can be implemented as a web browser or a smartphone application, and allows the user to input request information such as target audience, theme, etc. The input information is sent to the server and used to generate the advertisement video.

[1067] The server automatically generates an advertising video scenario using the generative AI model. An appropriate scenario is generated based on the request information entered by the user. For example, if a user enters the prompt, "Please generate an advertising scenario with an adventurous and fun theme for young people. Our new product is a waterproof smartwatch," the generative AI model will generate a corresponding scenario.

[1068] The server then synthesizes the selected materials to generate the advertising video. Based on the generated scenario, the server selects the most suitable images, video clips, and music from the database and synthesizes them to generate the advertising video. This process uses a video editing library such as MoviePy.

[1069] The generated advertising video can be previewed by the user. The preview function is implemented on the device, allowing the user to watch the generated advertising video and check its content. If the user needs to make any corrections, they can send them to the server as feedback.

[1070] The server receives the feedback, analyzes it, and extracts corrections. It then uses the generative AI model again to generate an advertising video that reflects the corrections. This process results in the creation of an optimal advertising video that meets the user's needs.

[1071] Finally, the generated advertising video is published on the designated digital platform. The server collects the number of views and engagement data of the published advertising video in real time, which can be used to evaluate the effectiveness of the advertising video and to help with future production.

[1072] As a concrete example, this system can be used when a company wants to promote a new product. A marketer provides the system with detailed information about the new product and promotional materials, inputting that the target audience is young people and the theme is adventurous and fun. The server that receives this request uses a generative AI model to generate a scenario and integrates the materials to automatically generate an initial advertising video. The generated advertising video can be previewed and any necessary corrections can be provided as feedback. The final advertising video is then generated and published on the specified platform.

[1073] This allows for the quick and efficient creation, modification, publishing and performance monitoring of advertising videos.

[1074] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1075] Step 1:

[1076] Users upload raw data, such as images, videos, and music, required to generate advertising videos to a server via their terminals. The server collects, organizes, and stores this data in a database. The input data is the raw data provided by the users, and the output data is the organized raw data stored in the database.

[1077] Step 2:

[1078] The server preprocesses the stored material data in the database. Specifically, it adjusts the size of image data and removes noise from audio data. The input data is the material data in the database, and the output data is clean data that has undergone preprocessing.

[1079] Step 3:

[1080] The server uses a machine learning algorithm to train the generative AI model, using preprocessed raw data in the process: the input data is the preprocessed raw data, and the output data is the trained generative AI model.

[1081] Step 4:

[1082] A user sends an advertisement generation request from the terminal to the server through the input interface. The input request includes details such as target audience, theme, main message, etc. The input data is the user's request information, and the output data is the request sent to the server.

[1083] Step 5:

[1084] The server automatically generates an advertising video scenario using a generative AI model based on the received request information. The input data is the user request information and the trained generative AI model, and the output data is the generated scenario. Specifically, the generative AI constructs a scenario based on the prompt sentence.

[1085] Step 6:

[1086] The server selects appropriate materials (images, video clips, music, etc.) from the database based on the generated scenario and integrates them to generate an advertising video. The input data is the generated scenario and the material data in the database, and the output data is the generated advertising video. Specifically, the server uses the MoviePy library to combine the materials and generate the video.

[1087] Step 7:

[1088] The terminal provides a preview of the generated advertising video to the user, and the user checks the preview and sends feedback to the server through a feedback interface, where the input data is the generated advertising video and the output data is the user's feedback.

[1089] Step 8:

[1090] The server analyzes the feedback from the user and extracts the corrections. The input data is the user feedback, and the output data is the list of corrections.

[1091] Step 9:

[1092] The server then runs the generative AI model again based on the extracted corrections to generate an advertising video that reflects the corrections. The input data is the list of corrections and the trained generative AI model, and the output data is the corrected advertising video.

[1093] Step 10:

[1094] The server publishes the generated final advertising video on a specified digital platform (e.g., social media, website), and collects subsequent view counts and engagement data (number of shares, comments, etc.) in real time. The input data is the final advertising video, and the output data is the engagement data collected in real time.

[1095] 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.

[1096] This invention is an innovative commercial production system that uses generative AI technology and combines it with an emotion engine that recognizes user emotions to generate more personalized advertisements. This system is implemented through the cooperation of a server with multiple functions, a terminal with an interface, and users who provide feedback, etc.

[1097] System Overview

[1098] The system operates as follows.

[1099] The user provides the data required for commercial production, including promotional materials such as product images, text descriptions, music, video clips, etc. This data is collected on the server and stored in a database in an appropriate format.

[1100] The server then performs data preprocessing on the stored data, including resizing and color correction of image data and noise reduction of audio data. The preprocessed data is then used to train a generative AI model using machine learning algorithms. The trained generative AI model can then learn various viewer preferences and commercial generation patterns.

[1101] The terminal accepts commercial creation requests through an interface, which allows users to input specific requirements such as target audience, theme, key message, etc. These requests are then sent to the server.

[1102] The server runs the generative AI model based on the received request and automatically generates a commercial scenario. From the generated scenario, appropriate materials (images, video clips, music, etc.) are selected from the database and integrated to generate the initial version of the commercial. Narration is also automatically generated based on the scenario.

[1103] The generated initial version of the commercial is provided as a preview on the device. The user (company representative) checks the preview and sends any necessary revisions as feedback to the server. At this time, the emotion engine recognizes the user's emotions from their facial expressions and voice, and reflects the results in the feedback analysis.

[1104] The server analyzes the feedback and regenerates the commercial based on the extracted corrections and recognized emotional information. Once the final version is generated, it is published on the designated platform and viewer numbers and engagement data are collected.

[1105] Program processing details

[1106] First, the user provides the data needed to create a new commercial. This data is uploaded through a dedicated interface. The server then receives the data, converts it into a format, and stores it in a database.

[1107] The data stored in the database is pre-processed and then used to train a generative AI model using machine learning algorithms, including data on past commercial successes and viewer preferences.

[1108] Users input their requests for new commercials through an interface, specifying details of the target audience, themes, key messages, etc. The requests are sent to a server, where a generative AI model generates a commercial script based on the requests.

[1109] Based on the generated scenario, related material is selected from a database and a commercial is generated. At this time, an emotion engine recognizes emotions from the user's facial expressions and voice, and based on this information, material selection and script revisions are made.

[1110] An initial version of the commercial is generated and provided as a preview on the device. The user views the preview and provides feedback. The user's emotions, as recognized by the emotion engine, are also used as feedback.

[1111] The server analyzes the feedback and emotional information, again using the AI ​​to make corrections and generate the final commercial. The final commercial is then published on the designated platform, and view counts and engagement data are collected. This engagement data will also be used to generate future commercials.

[1112] Specific examples

[1113] Suppose a company wants to create a commercial to promote its new product "X." The user (the company's marketing manager) provides details about the new product, its target market, and the theme. This data is collected on the server.

[1114] Marketers then use the interface to input specific requests, such as target audience ages 18 to 25 and a theme that is adventurous.

[1115] The server uses a generative AI model to generate an adventurous scenario, selects the necessary materials from a database, and generates an initial commercial. During this process, an emotion engine recognizes the emotions of the user (marketer) and reflects this information in the selection of materials and scenario generation.

[1116] The generated initial version of the commercial is displayed as a preview on the device. The marketer reviews the commercial and, if they feel that any changes are necessary to the scenario or materials, they can submit feedback along with emotional information. The server analyzes the feedback, generates the final version of the commercial, and publishes it.

[1117] The present invention thus implemented can generate commercials that reflect the user's emotions by integrating an emotion engine, thereby providing content that viewers can more easily relate to.

[1118] The processing flow will be explained below.

[1119] Step 1:

[1120] Through a dedicated interface, users provide the data needed to create a new commercial, including promotional materials such as product images, text descriptions, music, and video clips.

[1121] Step 2:

[1122] The server receives the provided data, converts it into an appropriate format, and stores it in a database: for example, image data is converted to an appropriate resolution, and text is formatted into a standard format.

[1123] Step 3:

[1124] The server preprocesses the stored data, including adjusting the size and color of the image data and removing noise from the audio data.

[1125] Step 4:

[1126] The server uses the pre-processed data to train a generative AI model using machine learning algorithms, including past commercial data and viewer preference data.

[1127] Step 5:

[1128] The terminal (a company's marketing staff) inputs a request for commercial production through a dedicated interface. The request includes the target audience, theme, and main message. This request is then sent to the server.

[1129] Step 6:

[1130] The server runs the generative AI model based on the received request and automatically generates a commercial script, including a storyboard and narration script.

[1131] Step 7:

[1132] Based on the generated scenario, the server selects appropriate materials (images, video clips, music, etc.) from a database and integrates them to generate the initial version of the commercial.

[1133] Step 8:

[1134] The server uses an emotion engine to recognize the user's emotions in real time. The emotion engine analyzes the user's emotions from their facial expressions and voice, and incorporates that information as feedback.

[1135] Step 9:

[1136] The server provides the generated initial version of the commercial as a preview to the terminal, and the user can check the preview and input any necessary corrections as feedback through the terminal interface.

[1137] Step 10:

[1138] The server lists corrections based on the received feedback and the analysis results of the emotion engine, and then uses the generative AI model again to generate the final commercial that reflects the corrections.

[1139] Step 11:

[1140] The server prepares the final commercial for publication on the designated platform (YouTube, social media, etc.) After publication, view counts and engagement data (number of shares, number of comments, etc.) are collected in real time.

[1141] Step 12:

[1142] The server analyzes the collected engagement data and evaluates the effectiveness of the advertisement, which will be used to generate future commercials.

[1143] Example 2

[1144] 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."

[1145] Conventional commercial production systems have limited technology for generating advertisements that take viewer preferences into account, making it difficult to automatically generate personalized commercials that reflect user emotions. Furthermore, it is difficult to efficiently generate revised commercials that reflect appropriate feedback, resulting in the challenge of not being able to maximize the impact on viewers.

[1146] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial reflecting the corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, and means for recognizing user emotions and reflecting the emotional information in the feedback. This enables the automatic generation of personalized commercials that reflect the user's emotions, maximizing their impact on viewers.

[1147] "Data collection and storage means" means a device or system that receives user-provided promotional materials such as images, text, music, and video clips, converts them into an appropriate format, and stores them in a database.

[1148] A "means for training a generative AI model using a machine learning algorithm" is an apparatus and technology for carrying out the process of training a generative AI model using preprocessed data.

[1149] "Means for accepting commercial generation requests through an input interface" refers to a device or system that provides an interface for users to input commercial requests (e.g., target audience, theme, message, etc.) and receives the input information.

[1150] "Means for automatically generating a commercial scenario using a generative AI model" refers to devices and technologies for automatically creating a commercial scenario using a generative AI model based on a user request.

[1151] "Means for integrating selected materials to generate a commercial" refers to devices and technologies for selecting appropriate materials (images, music, video clips) from a database based on the generated scenario and integrating them to create a commercial.

[1152] The "means for providing a preview of the generated commercial" is a device or system that provides a preview function that allows a user to visually check the generated commercial.

[1153] "Means for receiving feedback and regenerating a commercial that reflects the corrections using a generative AI" refers to devices and technologies for receiving feedback from users and regenerating and correcting a commercial using a generative AI model based on that feedback.

[1154] "Means for publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to the devices and technologies for uploading the final commercial to a designated online platform and collecting subsequent view counts and viewer engagement data.

[1155] "Means for recognizing the user's emotions and reflecting that emotional information in feedback" refers to a device and technology for recognizing the user's emotions from their facial expressions and voice, and reflecting that emotional information in the analysis of the modification requirements.

[1156] MODE FOR CARRYING OUT THE INVENTION

[1157] This invention is an innovative commercial production system that combines generative AI technology with an emotion engine that recognizes user emotions. An embodiment of this system will be described in detail below.

[1158] System Configuration

[1159] This system operates in collaboration with a server with multiple functions, a terminal with an interface, and a user who provides feedback, etc. The main hardware and software include the following:

[1160] Hardware: High-performance servers, user devices (PCs, tablets, smartphones, etc.)

[1161] Software: OpenCV (image processing library), Librosa (audio processing library), machine learning frameworks (TensorFlow, PyTorch, etc.)

[1162] Program processing overview

[1163] First, the user provides the data needed to create a commercial, including product images, text, music, and video clips, through the device interface. The device receives this data and sends it to the server, which then converts it into an appropriate format and stores it in a database.

[1164] The server then preprocesses the stored data. Specifically, it uses OpenCV to resize and color correct the image data, and Librosa to remove noise from the audio data. The preprocessed data is then used to train a generative AI model using a machine learning framework (TensorFlow or PyTorch). Training utilizes data on past successful commercials and viewer preference data.

[1165] Through the interface, the user enters a request to create a new commercial, including specific requirements such as target audience, theme, key message, etc. This request is then sent from the device to the server.

[1166] The server uses a generative AI model to generate a commercial scenario based on the request, and then selects appropriate materials (images, video clips, music) from a database based on the generated scenario, and combines them to generate the initial commercial.

[1167] The generated initial commercial is provided as a preview on the device for the user to review. If there are any corrections that need to be made, the user can enter feedback and send it to the server via the device. At this time, the emotion engine recognizes the user's emotions from their facial expressions and voice, and the results are reflected in the feedback.

[1168] The server analyzes the feedback and sentiment information, then uses the generative AI model to revise and regenerate the commercial. Once the final version of the commercial is generated, it is published on the designated platform and view counts and engagement data are collected. This collected data is used to generate future commercials.

[1169] Specific examples

[1170] For example, a company wants to create a commercial to promote its new product "X." The user (the company's marketer) provides data about the new product's details, target market, and theme. This data is collected by the server. The marketer then uses the device interface to enter a specific request: for example, the target audience is 18-25 years old, and the theme is adventurous. The request is sent to the server.

[1171] The server uses a generative AI model to generate an adventurous scenario, selects the necessary materials from a database, and generates an initial version of the commercial. At this time, an emotion engine recognizes the emotions of the user (marketer) and reflects that information in the selection of materials and scenario generation. The generated initial version of the commercial is displayed as a preview on the device.

[1172] If the marketing person views the preview and feels that any part of the script or material needs to be revised, they send that feedback to the server, which analyzes the feedback, generates the final commercial, and publishes it.

[1173] An example prompt is:

[1174] Create a commercial promoting your new product "X". The target audience is 18-25 years old and the theme is adventurous. Use the following promotional materials: product images, text description, music, and video clips.

[1175] The above is a specific embodiment of the present invention. This system makes it possible to automatically generate personalized commercials that reflect the user's emotions.

[1176] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1177] Step 1:

[1178] The user provides the data required for commercial production. This data includes promotional materials such as product images, text descriptions, music, and video clips. The data is input into the terminal through an input interface. The terminal transmits this input data to the server. As output, the data is received by the server.

[1179] Step 2:

[1180] The server collects the received data, converts it into the appropriate format, and stores it in the database. For example, image files are converted into JPEG or PNG format, and text files are stored in UTF-8 format. As an output, each data is stored in the database.

[1181] Step 3:

[1182] The server preprocesses the data stored in the database. Specifically, it uses OpenCV to resize and color correct the image data, and Librosa to denoise the audio data. It takes the data in the database as input and produces preprocessed data as output.

[1183] Step 4:

[1184] The server uses the preprocessed data to train a generative AI model. Using a machine learning framework (TensorFlow or PyTorch), the model learns from past success stories and viewer preference data. The preprocessed data is used as input, and a trained generative AI model is obtained as output.

[1185] Step 5:

[1186] The user inputs a new commercial generation request through the input interface. The request includes the target audience, theme, main message, etc. The terminal receives the input request and sends it to the server. The server receives the request data as output.

[1187] Step 6:

[1188] The server uses a generative AI model to generate a commercial scenario based on the received request. It inputs the prompt sentence into the generative AI model and outputs an appropriate scenario. It then selects appropriate materials from a database based on the scenario and integrates them to generate an initial version of the commercial. Using the request data and the trained generative AI model as input, the initial version of the commercial is obtained as output.

[1189] Step 7:

[1190] The terminal provides the generated initial version of the CM to the user as a preview. The user checks the preview and inputs any necessary corrections as feedback. The terminal then sends the feedback to the server, displaying the initial version of the CM as input and sending the feedback data as output to the server.

[1191] Step 8:

[1192] The server receives and analyzes feedback from users. It uses an emotion engine to recognize emotions from the user's facial expressions and voice, and reflects the results in the feedback. Feedback data and emotional information are taken as input, and a list of corrections is output.

[1193] Step 9:

[1194] The server then re-runs the generative AI model based on the analysis results to correct and regenerate the commercial. Using the list of corrections and the generative AI model as input, the final commercial is generated as output.

[1195] Step 10:

[1196] The server publishes the final commercial to the specified platform. It then collects the number of views and engagement data for the published commercial. The final commercial is uploaded to the platform as input, and engagement data is collected as output. This data is used to generate future commercials.

[1197] (Application example 2)

[1198] 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."

[1199] Conventional commercial production systems have difficulty generating personalized advertisements that reflect user emotions, making it difficult to gain viewer empathy. Furthermore, it is difficult to quickly generate effective commercials tailored to the target audience and theme. Furthermore, the development of smartphone-based commercial production applications has not progressed. For these reasons, there is a need for a means for corporate marketing personnel to easily create high-quality commercials and deliver effective messages to their target audiences.

[1200] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1201] In this invention, the server includes means for collecting and storing data, means for training a generative AI model using a machine learning algorithm, means for receiving a commercial generation request through an input interface, means for automatically generating a commercial scenario using the generative AI model, means for generating a commercial by integrating selected materials, means for providing a preview of the generated commercial, means for receiving feedback and again using the generative AI to generate a commercial reflecting the corrections, means for publishing the generated commercial on a specified platform and collecting view counts and engagement data, means for analyzing the feedback using an emotion engine that recognizes user emotions and reflecting it in the generation of the commercial, and means for providing an application to be installed on a smartphone and for producing commercials. This makes it possible to generate personalized advertisements that reflect user emotions in a short amount of time and easily produce high-quality commercials using a smartphone.

[1202] "Means for collecting and storing data" refers to the mechanism by which promotional materials and information provided by users are collected and stored in a database in an appropriate format.

[1203] "Means for training a generative AI model using machine learning algorithms" refers to a mechanism for training a generative AI model using machine learning based on collected data.

[1204] "Means for accepting commercial generation requests through an input interface" refers to a mechanism for providing an interface that allows users to input commercial generation requirements such as target audience and theme, and for receiving those requests.

[1205] "Means for automatically generating commercial scenarios using a generative AI model" refers to a system that uses a trained AI model to automatically generate commercial scenarios based on user requests.

[1206] The "means of integrating selected materials to generate a commercial" refers to a mechanism that selects appropriate materials from a database based on the generated scenario, integrates them, and generates a commercial.

[1207] The "means for providing a preview of the generated commercial" is a mechanism for providing a preview function that allows users to check the initial version of the commercial.

[1208] "Means of receiving feedback and using generative AI to generate a commercial that reflects the corrections" refers to a system that receives feedback from users, makes corrections using a generative AI model based on that feedback, and then generates a commercial again.

[1209] "Means of publishing the generated commercial on a designated platform and collecting view counts and engagement data" refers to a system in which the final commercial is published on various platforms and its view counts and engagement data are collected.

[1210] "Means of analyzing feedback using an emotion engine that recognizes the user's emotions and reflecting it in the generation of commercials" refers to a system that recognizes emotions from the user's facial expressions and voice, and uses this emotional information in feedback analysis to reflect it in the generation of commercials.

[1211] "Means of providing an application that can be installed on a smartphone and used to produce commercials" refers to a system in which an application that can be installed on a smartphone is provided and commercials are produced through that application.

[1212] This invention is a system comprising: means for collecting and storing data; means for training a generative AI model using a machine learning algorithm; means for accepting a commercial generation request; means for automatically generating a commercial scenario using the generative AI model; means for generating a commercial by integrating selected materials; means for providing a preview of the generated commercial; means for receiving feedback and again using the generative AI to generate a commercial that reflects the corrections; means for publishing the generated commercial on a specified platform and collecting view counts and engagement data; means for analyzing feedback using an emotion engine that recognizes user emotions and reflecting the feedback in the generation of the commercial; and means for providing an application to be installed on a smartphone for producing commercials.

[1213] Specifically, the server collects promotional materials and information provided by users and stores them in a database in an appropriate format. The server then uses machine learning to train a generative AI model based on the collected data. OpenAI's GPT-4 is one example of a generative AI model. Next, the server accepts commercial generation requirements, such as target audience and theme, through an input interface. Based on these requirements, the generative AI model automatically generates a commercial scenario.

[1214] Based on the generated scenario, the server selects and integrates appropriate materials from a database to generate a commercial. The generated commercial is then provided as a preview on a smartphone application. When the user checks this preview and enters feedback, the emotion engine recognizes emotions from the user's facial expressions and voice and sends that information to the server.

[1215] Based on the feedback and sentiment information, the server uses the generative AI model again to generate a commercial that reflects the modifications. The final commercial is published on the designated platform, and the server collects the number of views and engagement data, which can be used to generate future commercials.

[1216] The hardware used includes a smartphone (iOS or Android), a server, and a suitable database (e.g., MongoDB).The software used is React Native for the front end, Node.js and Express for the back end, OpenCV for image data processing, FFmpeg for audio data processing, and the Affectiva SDK as an emotion engine.

[1217] For example, if a company wants to create a commercial for new product "X," the user (the company's marketing staff) provides details of the new product, the target market, and the theme using a smartphone application. The target audience is input as "18-25 years old," the theme as "active lifestyle," and the main message as "make your everyday life active." The generative AI model generates a scenario based on this information, and the emotion engine analyzes the user's reactions to generate a more refined commercial.

[1218] Example prompt sentence:

[1219] You want to advertise a new pair of sports shoes. The target audience is young people aged 18-25, and the theme is active lifestyle. You want to include the message "Be active every day."

[1220] We want to promote organic juice. The target audience is 25-35 years old, and the theme is health and nature. We want to convey the message that "organic juice is good for your body."

[1221] In this way, by integrating an emotion engine, this system generates personalized commercials that reflect the user's emotions, providing content that viewers can more easily relate to.

[1222] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1223] Step 1:

[1224] The server collects promotional materials (images, text, music, etc.) provided by users through a dedicated interface. This data is converted into an appropriate format and stored in a database. It receives the materials uploaded by the user as input and outputs the materials stored in the database.

[1225] Step 2:

[1226] The server preprocesses the data stored in the database. Specifically, it uses OpenCV to resize and color correct the image data, and FFmpeg to remove noise from the audio data. The preprocessed data is output as training data for the next stage.

[1227] Step 3:

[1228] The server trains a generative AI model using the preprocessed data. GPT-4 is used as the generative AI model, and machine learning algorithms are applied based on past commercial data and viewer preference data. The trained generative AI model is output.

[1229] Step 4:

[1230] The user inputs the target audience, theme, main message, and other requirements for a new commercial through the input interface of the smartphone application. The input requirements are sent to the server. The output is the time until the input request is accepted by the server.

[1231] Step 5:

[1232] The server runs the GPT-4 generative AI model based on the received user request to generate a CM scenario. The input request is applied to the AI ​​model, and an automatically generated scenario is output.

[1233] Step 6:

[1234] The server selects appropriate materials from a database based on the generated scenario, integrates them, and generates an initial version of the commercial. The input scenario is applied to the AI ​​model, and the initial version of the commercial is output.

[1235] Step 7:

[1236] The terminal provides the generated initial version of the CM to the user as a preview. The user checks the preview and inputs any necessary corrections. The input feedback is sent to the server. The preview and feedback are output.

[1237] Step 8:

[1238] The server runs the generation AI again based on the feedback sent by the user, and recreates the commercial reflecting the corrections. At this time, the emotion engine (Affectiva SDK) recognizes emotions from the user's facial expressions and voice, and this is also taken into account in the feedback. The corrected feedback and emotional information are input, and the final commercial is output.

[1239] Step 9:

[1240] The server publishes the final commercial on various platforms (such as social media and video sharing sites) and collects view counts and engagement data. This data is used to generate future commercials. The published commercial and collected data are output.

[1241] 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.

[1242] 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.

[1243] 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.

[1244] 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.

[1245] 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.

[1246] 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.

[1247] 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).

[1248] 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.

[1249] 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."

[1250] 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.

[1251] 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).

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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.

[1256] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] 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.

[1262] The following is further disclosed regarding the above embodiment.

[1263] (Claim 1)

[1264] means for collecting and storing data;

[1265] a means for training a generative AI model using a machine learning algorithm;

[1266] means for receiving a CM generation request through an input interface;

[1267] A means for automatically generating a commercial scenario using a generative AI model;

[1268] means for integrating the selected materials to generate a commercial;

[1269] means for providing a preview of the generated commercial;

[1270] A means to receive feedback and generate a commercial that reflects the corrections using the generation AI again,

[1271] A means to publish the generated commercial on a designated platform and collect view counts and engagement data,

[1272] A system including:

[1273] (Claim 2)

[1274] 10. The system of claim 1, further comprising means for pre-processing the collected data.

[1275] (Claim 3)

[1276] 10. The system of claim 1, further comprising means for analyzing the feedback and listing corrections.

[1277] "Example 1"

[1278] (Claim 1)

[1279] means for collecting and storing data;

[1280] a means for training a generative AI model using a machine learning algorithm;

[1281] means for receiving a CM generation request through an input interface;

[1282] A means for automatically generating a commercial scenario using a generative AI model;

[1283] means for integrating the selected materials to generate a commercial;

[1284] means for providing a preview of the generated commercial;

[1285] A means to receive feedback and generate a commercial that reflects the corrections using the generation AI again,

[1286] A means to publish the generated commercial on a designated platform and collect view counts and engagement data,

[1287] A means of preprocessing the data required for commercial production,

[1288] A means for analyzing the provided feedback and extracting corrections;

[1289] A system including:

[1290] (Claim 2)

[1291] The system of claim 1, further comprising means for preprocessing data required for commercial production to improve the accuracy of the generative AI model.

[1292] (Claim 3)

[1293] 10. The system of claim 1, further comprising means for reviewing a preview of the generated commercial and providing feedback through the interface.

[1294] "Application Example 1"

[1295] (Claim 1)

[1296] means for collecting and storing data;

[1297] a means for training a generative AI model using a machine learning algorithm;

[1298] means for accepting an ad generation request via an input interface;

[1299] A means for automatically generating a scenario for an advertising video using a generative AI model;

[1300] means for integrating the selected materials to generate an advertising video;

[1301] means for providing a preview of the generated advertising video;

[1302] A means to receive feedback and generate advertising videos that reflect the corrections using the generation AI again;

[1303] A means for publishing the generated advertising video on a designated digital platform and collecting view counts and engagement data;

[1304] A means for providing an application that operates on a terminal including a smartphone;

[1305] A system including:

[1306] (Claim 2)

[1307] 10. The system of claim 1, further comprising means for pre-processing the collected data.

[1308] (Claim 3)

[1309] 10. The system of claim 1, further comprising means for analyzing the feedback and listing corrections.

[1310] "Example 2: Combining Emotion Engines"

[1311] (Claim 1)

[1312] means for collecting and storing data;

[1313] a means for training a generative AI model using a machine learning algorithm;

[1314] means for receiving a CM generation request through an input interface;

[1315] A means for automatically generating a commercial scenario using a generative AI model;

[1316] means for integrating the selected materials to generate a commercial;

[1317] means for providing a preview of the generated commercial;

[1318] A means to receive feedback and generate a commercial that reflects the corrections using the generation AI again,

[1319] A means to publish the generated commercial on a designated platform and collect view counts and engagement data,

[1320] a means for recognizing a user's emotion and reflecting the emotion information in feedback;

[1321] A system including:

[1322] (Claim 2)

[1323] 10. The system of claim 1, further comprising means for pre-processing the collected data.

[1324] (Claim 3)

[1325] 10. The system of claim 1, further comprising means for analyzing the feedback and listing corrections.

[1326] "Application example 2 when combining emotion engines"

[1327] (Claim 1)

[1328] means for collecting and storing data;

[1329] a means for trainin...

Claims

1. means for collecting and storing data; a means for training a generative AI model using a machine learning algorithm; means for receiving a CM generation request through an input interface; A means for automatically generating a commercial scenario using a generative AI model; means for integrating the selected materials to generate a commercial; means for providing a preview of the generated commercial; A means to receive feedback and generate a commercial that reflects the corrections using the generation AI again, A means to publish the generated commercial on a designated platform and collect view counts and engagement data, A system including:

2. 10. The system of claim 1, further comprising means for pre-processing the collected data.

3. The system of claim 1 further comprising means for analyzing the feedback and listing corrections.

Images