Intelligent content creation support method, computing device, and program for senior creators

Abstract

The present invention is an intelligent content creation support method that supports senior users in easily creating digital content, and may include the steps of: activating a camera of a user terminal device to acquire real-time video according to user input; overlaying a conversation script related to the real-time video onto the real-time video and outputting it; processing the real-time video to edit according to the user's editing command to generate an edited video; and uploading the generated edited video to a social network service server. Through this, the present invention enables senior users to easily create digital content through an intuitive interface and automation functions without having to acquire complex editing skills.

Description

Technology Field

[0001] The present invention relates to a technology for supporting the creation of digital content by senior users, and more specifically, to a method, device, and program that facilitates content creation by automating the processes of video shooting, script generation, editing, and uploading based on artificial intelligence. Background Technology

[0002] Existing digital content creation platforms were primarily designed for young people and professionals, which had limitations in making them difficult for senior users to access.

[0003] These platforms often require complex interfaces, multi-step settings, and detailed editing functions, posing a high barrier to entry for seniors unfamiliar with the digital environment.

[0004] In particular, video editing software and social media-based content creation tools were difficult for seniors to use intuitively due to small fonts, low-contrast UI designs, and complex menu configurations, and the various functions required in the content creation process (cut editing, adding effects, inserting subtitles, etc.) were excessively subdivided, making it burdensome for non-professionals to use.

[0005] As a result, despite having a desire to share their life experiences and expertise through digital content, many seniors are struggling to realize this in the existing digital environment.

[0006] While creating and communicating content through online platforms such as YouTube and social media plays an important role in modern society, the utilization of currently available video and content creation tools has been limited due to a lack of senior-friendly features.

[0007] Furthermore, most existing content creation platforms require professional editing skills or adopt standardized template-based production methods, making it difficult to create customized content desired by senior users.

[0008] For example, while currently widely used video editing programs offer high-level editing capabilities, they have many unnecessary features for users who want to create simple videos, resulting in a steep learning curve and poor usability.

[0009] On the other hand, relatively easy content creation tools offered low editing freedom, which limited senior creators' ability to produce content that reflected their individuality.

[0010] Furthermore, another common problem senior creators face during the content production process is the need for additional editing steps, such as subtitle generation, translation, and voice narration insertion.

[0011] General video editing tools often do not provide such features or require the use of separate paid plugins and software, resulting in additional financial burdens and learning costs for senior users.

[0012] In particular, for senior creators producing multilingual content, translation and subtitling are essential; however, handling these tasks manually is difficult, and existing automatic translation and subtitle generation functions were often difficult to use intuitively or lacked accuracy.

[0013] Ultimately, senior creators face challenges due to complex technical issues and a lack of accessibility, even though they wish to produce content; to address this, there is a need for an intelligent content creation platform that includes senior-friendly UI / UX, automated editing functions, technical support, and training systems. The problem to be solved

[0014] Therefore, the present invention aims to solve the aforementioned problem.

[0015] One of the various objectives of the present invention is to provide an intelligent content creation environment that supports senior users in easily performing the entire process of video shooting, dialogue generation, editing, and uploading without complex technical knowledge.

[0016] In addition, one of the various objectives of the present invention is to lower the entry barrier to content creation through a senior-friendly user interface and AI-based automation technology.

[0017] In addition, one of the various objectives of the present invention is to improve production efficiency and completeness by having an artificial intelligence model automatically perform editing processes such as video quality correction, subtitle generation, and scene splitting. means of solving the problem

[0018] Various embodiments for solving the problem of the present invention include an intelligent content creation support method that supports senior users in easily creating digital content, which may include the steps of: activating a camera of a user terminal device to acquire real-time video according to user input; overlaying a conversation script related to the real-time video onto the real-time video and outputting it; processing the real-time video to edit according to the user's editing command to generate an edited video; and uploading the generated edited video to a social network service server.

[0019] In addition, the outputting step can generate a dialogue script related to the real-time video using a previously trained first artificial neural network model.

[0020] In addition, the first artificial neural network model can be trained to generate the conversation script by considering situation information extracted based on image feature information within a real-time video.

[0021] In addition, the step of generating the edited video can generate the edited video by processing the real-time video using a previously trained second artificial neural network model.

[0022] In addition, the second artificial neural network model can be trained to generate an edited video by analyzing image feature information within a real-time video and performing visual quality correction and content composition processing according to the user's editing command.

[0023] In addition, when the recording of the real-time video is completed, the method may further include a step of saving the real-time video.

[0024] In addition, the uploading step may analyze multiple frames from the edited video to select a representative image, generate text corresponding to the representative image, and upload it to the social network service server together with the edited video.

[0025] Meanwhile, the present invention is a computing device that performs an intelligent content creation support method to support senior users in easily creating digital content, comprising a processor and a memory that communicates with said processor, wherein the memory stores commands that cause said processor to perform operations, and said operations may include an operation of activating a camera of a user terminal device to acquire real-time video according to user input, an operation of overlaying a conversation script related to said real-time video onto said real-time video and outputting it, an operation of processing said real-time video to edit and generate an edited video according to said user's editing command, and an operation of uploading the generated edited video to a social network service server.

[0026] In addition, the above-mentioned output operation can generate a dialogue script related to the real-time video using a pre-trained first artificial neural network model.

[0027] In addition, the operation of generating the above-mentioned edited video can generate the edited video by processing the real-time video using a previously trained second artificial neural network model.

[0028] In addition, when the recording of the real-time video is completed, the operation of saving the real-time video may be further included.

[0029] In addition, the uploading operation may analyze multiple frames from the edited video to select a representative image, generate text corresponding to the representative image, and upload it to the social network service server together with the edited video.

[0030] Meanwhile, the present invention may be implemented as a program recorded on a computer-readable recording medium having program code for executing an intelligent content creation support method, or as a computer-readable recording medium storing a program for performing an intelligent content creation support method.

[0031] Each of the features of the above-described embodiments may be implemented in combination in other embodiments, provided that such features do not contradict or are exclusive of other embodiments. Effects of the invention

[0032] According to various embodiments of the present invention, senior users can easily create digital content through an intuitive interface and automation functions without having to acquire complex editing skills.

[0033] According to various embodiments of the present invention, by providing a real-time overlay of a dialogue script automatically generated during video recording, senior users can naturally participate in the recording without memorizing lines or explanations.

[0034] According to various embodiments of the present invention, editing commands can be entered by selecting function-specific icons via touch or voice commands, allowing even seniors unfamiliar with technology to easily edit.

[0035] According to various embodiments of the present invention, an artificial intelligence model can automatically correct brightness, color, sharpness, etc., to produce visually balanced content without the need for separate equipment.

[0036] According to various embodiments of the present invention, the posting process for senior users is simplified by automatically receiving platform-specific upload specifications and automatically performing format conversion, generating representative images, inserting descriptive text, etc.

[0037] The effects of the present invention are not limited to those described above, and other unmentioned effects will be clearly recognized by a person skilled in the art from the description below. Brief explanation of the drawing

[0038] FIG. 1 is a conceptual diagram illustrating an intelligent content creation support method according to an embodiment of the present invention. FIG. 2 is a flowchart illustrating an intelligent content creation support method according to an embodiment of the present invention. FIG. 3 is an exemplary diagram illustrating the learning process of a first artificial neural network model according to one embodiment of the present invention. FIG. 4 is an example diagram showing a conversation script of a user terminal device according to one embodiment of the present invention. FIG. 5 is an exemplary diagram showing a user interface for receiving control input according to an embodiment of the present invention. FIG. 6 is an exemplary diagram illustrating the learning process of a second artificial neural network model according to an embodiment of the present invention. FIG. 7 is a timing diagram illustrating an intelligent content creation support method according to an embodiment of the present invention. FIG. 8 is an exemplary diagram showing the configuration of a computing device according to one embodiment of the present invention. Specific details for implementing the invention

[0039] Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to facilitate a comprehensive understanding of the methods, apparatuses, and / or systems described herein. However, this is merely illustrative and the present invention is not limited thereto.

[0040] In describing the embodiments of the present invention, detailed descriptions of known technologies related to the present invention are omitted if it is determined that such descriptions may unnecessarily obscure the essence of the invention. Furthermore, the terms described below are defined considering their functions in the present invention, and these definitions may vary depending on the intentions or practices of the user or operator. Therefore, their definitions should be based on the content throughout this specification.

[0041] The terms used in the detailed description are merely for describing embodiments of the invention and should not be limiting in any way. Unless explicitly stated otherwise, expressions in the singular form include the meaning of the plural form.

[0042] In this description, expressions such as “include” or “equipped” are intended to refer to certain characteristics, numbers, steps, actions, elements, parts or combinations thereof, and should not be interpreted to exclude the existence or possibility of one or more other characteristics, numbers, steps, actions, elements, parts or combinations thereof other than those described.

[0043] In addition, terms such as first, second, A, B, (a), (b), etc. may be used when describing the components of the embodiments of the present invention. These terms are used merely to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by the terms.

[0044] FIG. 1 is a conceptual diagram illustrating an intelligent content creation support method according to an embodiment of the present invention.

[0045] Referring to FIG. 1, a senior creator (10) (hereinafter referred to as a senior user) can easily create digital content, especially video content, without having to acquire complex video production tools or editing skills. This is made possible through an intelligent content creation platform that provides AI-based content creation support functions, and the platform can be implemented in the form of a web-based or application.

[0046] More specifically, senior users can access the content creation function by installing an application with an intelligent content creation platform on a user terminal device (100) or by accessing it through a web interface without installing a separate application.

[0047] At this time, the user terminal device (100) includes a smartphone, a tablet, or other mobile computing device equipped with a camera, and the main functions of the present invention can be executed integrally within the terminal.

[0048] Additionally, senior users (10) can directly film and edit content through the application, and the completed content can be automatically uploaded to a social network service (SNS) server after user verification or according to pre-set conditions.

[0049] Below, we will explain in more detail the method of supporting intelligent content creation, focusing on the user terminal device (100) to which the intelligent content creation platform is applied.

[0050] FIG. 2 is a flowchart illustrating an intelligent content creation support method according to an embodiment of the present invention.

[0051] Referring to FIG. 2, the user terminal device (100) can acquire real-time video by activating the camera of the user terminal device according to user input from a senior user (10) (S100). Here, the user input is a control input to start shooting, and may include a touch input such as pressing a shooting button within an application, or natural language-based voice commands such as "start shooting" or "take a video." Such various input methods are designed with the convenience of senior users in mind, allowing the camera to be controlled in the way the user prefers between touch or voice.

[0052] More specifically, when the user terminal device (100) detects user input, it initializes the camera according to the preset shooting environment setting value and captures the surrounding environment to obtain real-time video.

[0053] In this case, the settings include, for example, the shooting resolution, frame rate (FPS), camera orientation (front / rear), autofocus status, and whether automatic lighting correction is enabled, all of which are pre-specified by the user. These settings can be customized according to the senior user's shooting habits or environmental conditions, and once set, they are automatically applied thereafter, minimizing user intervention.

[0054] Additionally, the user terminal device (100) may include a function to automatically correct lighting brightness, color balance (white balance), contrast, etc. in real time according to the shooting environment.

[0055] For example, the user terminal device (100) can automatically achieve a color tone close to natural light by adjusting the aperture value or digitally increasing the brightness when the indoor lighting is dark, and by adjusting the color temperature when the yellow light is strong.

[0056] In addition, if the background is complex or distracting, a feature to emphasize the video subject (e.g., a person) through background blur effects or background removal algorithms can also be applied.

[0057] This automatic correction is performed by an AI-based image processing module that automatically identifies and corrects issues such as dark faces or overexposed backgrounds, enabling senior users to capture visually balanced videos without the need for separate video lighting equipment.

[0058] Next, the user terminal device (100) can output a dialogue script related to the real-time video by overlaying it on the real-time video (S200). Here, the dialogue script is text content in the form of dialogue that is automatically generated based on scenes, actions of people, background situations, etc., appearing in the real-time video, and refers to a text prompt that a senior user (10) can read or refer to while filming the video.

[0059] Specifically, the user terminal device (100) can generate a conversation script related to real-time video using a first artificial neural network model that has been trained. Here, the first artificial neural network model can generate a conversation script by considering situational information by learning various situations, behavioral patterns of people, background characteristics, etc., in advance. A multimodal deep learning model, a vision-language model, or an image captioning model may be used for this first artificial neural network model.

[0060] Hereinafter, the learning process of the first artificial neural network model will be described with reference to FIG. 3.

[0061] FIG. 3 is an exemplary diagram illustrating the learning process of a first artificial neural network model according to one embodiment of the present invention.

[0062] Referring to FIG. 3, the first artificial neural network model (1) uses image data (31) and text data (33) semantically corresponding to the image data (31) as inputs as a training dataset. At this time, the image data (31) provides visual information including the actions of a person, background, objects, scene transitions, etc., and the corresponding text data (33) may be composed of sentences that reflect situational information such as descriptions, dialogues, and question phrases suitable for the scene.

[0063] Additionally, the Vision Encoder of the first artificial neural network model (1) receives image data (31) and performs the role of extracting visual features, and this feature information can be converted into a hidden representation and transmitted to a higher-level language processing module. Next, the Text Embedder of the Language Model of the first artificial neural network model (1) embeds the input text to convert semantic information into a vector form, and the Self-Attention-based language generation model can be trained to combine the features transmitted from the Vision Encoder and the Text Embedder to output a dialogue script (35) suitable for the corresponding image scene. At this time, the first artificial neural network model (1) can be trained in a way that maximizes the semantic matching degree between the image data (31) and the corresponding text data (33).

[0064] That is, the first artificial neural network model can be trained to generate the above dialogue script by considering situational information extracted based on image feature information within the real-time video.

[0065] Additionally, the user terminal device (100) can output the generated conversation script by overlaying it together with the real-time video. Here, overlay refers to a method of visually displaying the generated text by overlaying it at a specific location on the real-time video.

[0066] Specifically, the user terminal device (100) can output a conversation script generated on the display overlaid with the real-time video so that the senior user can directly read or refer to the script while recording video. This will be explained with reference to FIG. 4.

[0067] FIG. 4 is an example diagram showing a conversation script of a user terminal device (100) according to one embodiment of the present invention.

[0068] Referring to FIG. 4, the user terminal device (100) can output a conversation script (43) overlaid on the bottom of a real-time video (41).

[0069] At this time, the display position of the script can be adjusted to the bottom, center, or top of the video screen, and can be selectively specified according to the user's preferences or visual convenience.

[0070] In addition, text size, color, font, and background transparency can be adjusted automatically or manually to suit the eyesight and preferences of senior users. For example, if the screen background is complex, a translucent background block can be automatically inserted to improve text readability.

[0071] Furthermore, the overlay output can operate similarly to teleprompter mode.

[0072] In other words, the dialogue script can be automatically scrolled on the screen or divided into sections and displayed sequentially based on the user's speech rate, sentence length, video scene transition timing, etc.

[0073] This feature enables senior users to check information and shoot content from a fixed position without having to move their eyes significantly across the screen, thereby ensuring both user immersion and shooting stability.

[0074] Additionally, the user terminal device (100) can control the output timing and content of the conversation script dynamically based on the voice speech speed of the senior user (10) and / or real-time video scene switching.

[0075] Additionally, the user terminal device (100) can output a simplified sentence structure within a conversation script or automatically adjust the vocabulary difficulty according to the senior user's (10) level of understanding.

[0076] Furthermore, a user terminal device (100) according to one embodiment of the present invention is not limited to providing static scripts, but can perform an adaptive prompting function that monitors the real-time speech performance ability of a senior user (10) and dynamically regenerates the remaining conversation script.

[0077] To this end, the user terminal device (100) analyzes the user's voice input through the microphone in real time and calculates the speech rate (WPM: Words Per Minute) and the frequency of silence intervals of the user reading the currently displayed script.

[0078] At this time, the user terminal device (100) may determine that the senior user (10) is having difficulty reading the content of the currently presented script or is under cognitive load if the calculated speech rate is lower than a preset threshold (e.g., senior average speech rate or user’s usual speech rate) or if the frequency of silent intervals in the middle of a sentence is detected to be higher than a reference value.

[0079] When such a judgment is made, the user terminal device (100) controls the first artificial neural network model to modify the content of a subsequent script that has not yet been scrolled to the screen (i.e., the user has not yet read it) in real time. Specifically, the user terminal device (100) immediately changes the complex sentence structure of the subsequent script into a simple sentence, or replaces technical terms or difficult-to-pronounce vocabulary with easy synonyms of the same meaning in real time and outputs them.

[0080] This variable script optimization technology significantly reduces the frequency of reshoots caused by senior users stumbling over their lines (NG) during filming, and has the technical effect of increasing the completion rate of video production by adjusting the difficulty of the content in real time to match the user's pace.

[0081] In addition, a user terminal device (100) according to one embodiment of the present invention measures the distance between a camera and a subject in real time and can dynamically control the visual attributes of the conversation script based on the measured distance information (Depth).

[0082] Specifically, the user terminal device (100) can measure the distance between the user's face and the camera when shooting using the front camera, and calculate the distance between the main subject and the camera in real time through a depth sensor or an image analysis algorithm when shooting using the rear camera.

[0083] At this time, if the user terminal device (100) determines that the user is moving away from the screen or that the distance from the subject is increasing, it can enlarge the font size of the conversation script in proportion to the increase in distance. At the same time, the user terminal device (100) reduces the frequency of line breaks in the text or reduces the number of words displayed per line to ensure readability so that a senior user (10) located at a distance can intuitively recognize the text.

[0084] Conversely, if it is determined that the user is getting closer to the screen or the distance from the subject is decreasing, the user terminal device (100) can control the font size of the conversation script and increase the amount of information (amount of text) displayed on one screen so that the user can check more specific content.

[0085] And, when the user terminal device (100) finishes capturing the real-time video, it can save the real-time video (S300).

[0086] Specifically, when saving a video, the user terminal device (100) can store the shooting time at the time of shooting, location information (GPS-based location information), user ID, or content subject information together in the form of metadata by mapping them.

[0087] This storage method facilitates video search and classification, allowing senior users to access previously recorded videos through automatically recommended or sorted lists without relying on memory when they want to find or edit them.

[0088] In addition, the saved video is duplicated by distinguishing between the original real-time video and the video to which subsequent editing will be applied, enabling flexible editing and utilization when senior users wish to revert to the original video or create new versions of content.

[0089] Furthermore, the user terminal device (100) can automatically analyze the entire captured video and divide and store it in units of a predetermined length (e.g., 10 seconds, 30 seconds, 1 minute, etc.).

[0090] This split-saving method is advantageous for quickly selecting specific sections of a video or for automatically extracting highlights to meet the time limits of social media platforms (e.g., TikTok, Shorts, etc.), and allows senior users to select and utilize desired sections with a simple touch, without having to manually cut the entire video.

[0091] Next, the user terminal device (100) can generate an edited video by processing a real-time video according to the user's editing command (S400).

[0092] Specifically, the user terminal device (100) receives an editing command for a real-time video from a senior user (10) and can generate an edited video by processing the real-time video using a previously trained second artificial neural network model. Here, the user's editing command refers to a post-processing request, such as applying a specific visual effect to the captured video, splitting or deleting video segments, changing the background, or inserting subtitles.

[0093] Considering the characteristics of senior users who find it difficult to directly handle complex editing software, these editing commands can be easily entered via touch-based or voice input methods using function-specific icons or intuitive UI elements. This will be explained with further reference to Fig. 5.

[0094] FIG. 5 is an exemplary diagram showing a user interface for receiving control input according to an embodiment of the present invention.

[0095] Referring to FIG. 5, the senior user (10) can simply perform the desired editing function by selecting an editing command icon (51) displayed near the saved real-time video screen. At this time, the user terminal device (100) may display a user interface for receiving control input even while recording real-time video, and the senior user (10) can input editing commands even while recording real-time video.

[0096] Each icon is provided in a visually distinct form so that the corresponding function can be intuitively recognized, and the user can input it through a touch action (53).

[0097] For example, selecting the “Brighten” icon automatically applies a lighting correction filter to the real-time video, pressing the “Change Background” icon activates AI-based background removal and virtual background switching functions, and selecting the “Automatic Subtitle Generation” icon performs speech recognition-based automatic subtitle generation and insertion functions.

[0098] In addition, if a command such as "Keep only important parts" is selected, a second artificial neural network model analyzes the entire video to automatically extract highlight sections, and the user can check and select the corresponding sections on the preview screen.

[0099] In addition, the user terminal device (100) can automatically adjust the visual elements (size, color, contrast ratio, etc.) of the interface according to the senior user's vision condition or display illumination conditions.

[0100] Additionally, the user terminal device (100) can receive input by filtering out shaking or duplicate inputs at the input location, taking into account the physical characteristics of the senior user.

[0101] In addition, a user terminal device (100) according to one embodiment of the present invention can perform an 'intelligent touch input filtering' function that detects biological tremors, which are physical characteristics of a senior user (10), such as Parkinson's disease or muscle weakness due to aging, and dynamically adjusts the touch input sensitivity accordingly.

[0102] Specifically, the user terminal device (100) monitors the minute vibration pattern of the terminal being used for video recording or editing operations in real time using a built-in gyro sensor and an accelerometer. At this time, if the detected vibration shows a preset periodic pattern (e.g., shaking in the 3-6 Hz band) or if the amplitude persists above a certain level, the user terminal device (100) determines that it is not an intentional movement but rather the user's hand tremor.

[0103] Additionally, when hand tremors are detected, the user terminal device (100) performs variable logic to immediately change the acceptance criteria of the touch interface to prevent incorrect input. First, the user terminal device (100) expands the touch effective area of ​​an icon or button displayed on the screen to be wider than its visual size. This allows the user to recognize the periphery as a valid input even if they fail to accurately touch the center of the icon due to hand tremors and instead hit the periphery, thereby increasing the success rate of operation.

[0104] Second, the user terminal device (100) lowers the input sensitivity by adjusting the temporal threshold of the touch input. For example, in a state of severe shaking, a tap action that is briefly brushed against the screen is likely to be a false input and is therefore ignored, and the device may be modified to recognize only a long press action that holds the screen for a certain period of time as a valid command.

[0105] In this way, senior users (10) can easily utilize various video editing functions with only an intuitive input method in the form of icons, without complex timeline editing or keyframe manipulation, and these editing commands are linked with a second artificial neural network model to lead to automated editing processing that takes into account visual features within the video and the user's editing purpose.

[0106] In addition, the second artificial neural network model can be trained to generate an edited video by analyzing image feature information within a real-time video and performing visual quality correction (e.g., lighting / color correction, noise removal, sharpness enhancement, shake correction, etc.) and content composition processing (e.g., scene segmentation, segment selection, visual effects, background processing, text insertion, etc.) according to the user's editing commands.

[0107] These second artificial neural network models may utilize CNN-RNN hybrid structures, GAN (Generative Adversarial Network)-based image restoration / transformation models, Attention-based Transformer models, etc., and may be a combination of multiple deep learning models configured in an ensemble form.

[0108] Hereinafter, the learning process of the second artificial neural network model will be described with reference to FIG. 6.

[0109] FIG. 6 is an exemplary diagram illustrating the learning process of a second artificial neural network model according to an embodiment of the present invention.

[0110] Referring to FIG. 6, the second artificial neural network model (2) receives a real-time video (61) stored as input and a user control command (63) corresponding to the real-time video (61) as input, and is trained to generate a video editing result suitable for the command.

[0111] The second artificial neural network model (2) can be implemented as an ensemble structure composed of multiple partial artificial neural network models (2-1, 2-2, ..., 2-n), rather than a single structure model.

[0112] These partial artificial neural network models are each specialized for specific editing functions and may consist of, for example, a partial model for improving image quality for lighting and color correction (2-1), a partial artificial neural network model for separating people for background removal and virtual background application (2-2), a partial artificial neural network model for sequence analysis for scene segmentation and segment extraction (2-3), an artificial neural network model for video transformation for applying visual effects such as style filters and transition effects (2-4), and a subtitle generation and subtitle insertion model (2-5) that recognizes audio data of the video to generate and insert automatic subtitles.

[0113] At this time, each partial artificial neural network model (2-1 to 2-5) is independently trained to perform a function suitable for the corresponding command by analyzing the visual features of the input editing command (63) and the image (61), and the second artificial neural network model (2) operates in an ensemble manner in which one or more partial artificial neural network models are combined and executed according to the editing purpose.

[0114] For example, when a user inputs the "brightness adjustment and subtitle insertion" command, the second artificial neural network model activates the lighting correction model (2-1) and the subtitle insertion model (2-5) together, and outputs the processed result as an edited video (65) in sequential or parallel.

[0115] Consequently, the second artificial neural network model of the present invention can be trained to automatically generate an edited video (65) optimized for the editing purpose selected by the senior user by receiving a stored real-time video (61) and a user editing command (63) as inputs and selecting and combining a plurality of partial artificial neural network models according to the situation.

[0116] That is, the second artificial neural network model can be trained to generate an edited video by analyzing image feature information within a real-time video and performing visual quality correction and content composition processing according to the user's editing commands.

[0117] And, the user terminal device (100) can upload the generated edited video to a social network service server (200) (S500).

[0118] Specifically, the user terminal device (100) can analyze multiple frames from an edited video, automatically select a representative image (or thumbnail) that can represent the content of the video, and generate explanatory text or recommendation text corresponding to the representative image.

[0119] In addition, the timing of the upload can be adjusted according to the choice of the senior user (10).

[0120] That is, after the senior user (10) completes editing, checks the result video and can perform an upload command by touching the "Upload" button or inputting a voice command such as "Upload video." Accordingly, the user terminal device (100) links with the social network service server (200) to automatically upload the posted content including the edited video, representative image, and description text.

[0122] Hereinafter, with reference to FIG. 7, the overall operation of the intelligent content creation support method will be described.

[0123] FIG. 7 is a timing diagram illustrating an intelligent content creation support method according to an embodiment of the present invention.

[0124] Referring to FIG. 7, a senior user (10) inputs user input for shooting to a user terminal device (100) (S1001), and the user terminal device (100) can activate the camera according to the user input to shoot real-time video (S1002). For example, the senior user can activate the camera function by touching the 'Start shooting' button displayed on the application screen or by using a voice command such as "Start shooting."

[0125] Next, the user terminal device (100) can generate a conversation script related to the real-time video and overlay the generated conversation script onto the real-time video and output it through a display to provide it to the senior user (10) (S1003).

[0126] And, the senior user (10) can create real-time video based on a conversation script (S1004). For example, the user can create video content by reading along with a set sentence while looking at a script displayed on the screen, or by naturally adding explanations in their own words while referring to it.

[0127] This method is particularly effective for senior users who have difficulty memorizing lines, enhancing content delivery while reducing the burden of filming.

[0128] Then, when the senior user (10) finishes shooting, the senior user inputs user input (S1005) for shooting into the user terminal device (10) (S1005), and the user terminal device (100) can save real-time video according to the user input (S1006). At this time, the senior user (10) can press a "shooting complete" button or input a termination command through voice commands such as "shooting finished."

[0129] For example, the video is stored in the local storage of the terminal device, and at this time, metadata such as the shooting date and time, location information, and content type may be recorded together.

[0130] Next, the senior user (10) inputs user input (S1007) for editing into the user terminal device (100) (S1007), and the user terminal device (100) can create an edited video by processing the real-time video (S1008). For example, the senior user can input an editing request by touching function icons such as "adjust brightness," "change background," or "keep only important scenes" displayed on the terminal screen, or by using voice commands such as "make the screen brighter" or "change the background to something else."

[0131] And, the senior user (10) receives an edited video from the user terminal device (100) (S1009), and can view the provided edited video and input user input for editing into the user terminal device (100) (S1010). For example, the user input may be an upload or editing instruction command such as "upload it" or "edit it again," and may also include detailed editing requests such as removing specific scenes or modifying subtitles.

[0132] Next, the user terminal device (100) can receive upload specification information from the social network service server (200) (S1011). At this time, the upload specification information may consist of the video format (MP4, MOV, etc.) required by the SNS server, resolution, capacity limit, maximum video length, thumbnail resolution, and whether authentication information is required.

[0133] And, the user terminal device (100) can convert and optimize the edited video according to the received upload specification information and upload the edited video to the social network service server (200) (S1012).

[0134] Meanwhile, the present invention can be implemented not only in the form of an application on a user terminal device (100), but also separately through a computing device (1000) configured with dedicated hardware.

[0135] Hereinafter, the configuration of a computing device (1000) for performing the intelligent content creation support method of the present invention will be described.

[0136] FIG. 8 is an exemplary diagram showing the configuration of a computing device (1000) according to one embodiment of the present invention.

[0137] Referring to FIG. 8, in some embodiments of the present invention, one or more of the modules constituting the computing device (1000) are implemented on a general-purpose computing processor and thus may include a processor (1088), input / output I / O (1082), memory (1084), interface (186) and bus (1085).

[0138] Additionally, the processor (1088), input / output device (1082), memory (1084) and / or interface (1086) may be connected to each other via a bus (1085). The bus (1085) corresponds to a path through which data travels.

[0139] Specifically, the processor (1088) may include at least one of a CPU (Central Processing Unit), MPU (Micro Processor Unit), MCU (Micro Controller Unit), GPU (Graphic Processing Unit), microprocessor, digital signal processor, microcontroller, application processor (AP), and logic elements capable of performing similar functions.

[0140] The input / output device (1082) may include at least one of a keypad, a keyboard, a touchscreen, and a display device. The memory (1084) may store data and / or programs, etc.

[0141] The interface (1086) can perform the function of transmitting data to a communication network or receiving data from a communication network. The interface (1086) may be wired or wireless. For example, the interface (1086) may include an antenna or a wired / wireless transceiver, etc. The memory (1084) is a volatile operational memory for protecting personal information, which enhances the operation of the processor (1088), and may further include high-speed DRAM and / or SRAM, etc.

[0142] Additionally, the memory (1084) stores programming and data configurations that provide the functions of some or all of the modules described herein. For example, it may include logic that enables the execution of selected aspects of the intelligent content creation support method according to the present embodiment using an artificial intelligence model.

[0143] A program or application is loaded as a set of instructions including each operation using the aforementioned artificial intelligence model stored in memory (1084), and the processor is enabled to perform each operation. For example, the operations may include an operation to activate the camera of a user terminal device to acquire real-time video according to user input, an operation to overlay a conversation script related to the real-time video onto the real-time video and output it, an operation to process the real-time video for editing according to the user's editing command to generate an edited video, an operation to upload the generated edited video to a social network service server, and an operation to save the real-time video when the recording of the real-time video is completed.

[0144] This computing device (1000) may be implemented by being integrated as a module of a user terminal device (100), or it may be implemented as an independent device including a separate display device, storage device, input device, etc., so as to be able to perform the intelligent content creation support method independently.

[0145] According to the present invention described above, senior users can easily create digital content through an intuitive interface and automation functions without having to acquire complex editing skills.

[0146] In addition, according to various embodiments of the present invention, by providing a real-time overlay of a dialogue script automatically generated during video recording, senior users can naturally participate in the recording without memorizing lines or explanations.

[0147] In addition, according to various embodiments of the present invention, editing commands can be entered by selecting function-specific icons via touch or voice commands, allowing even seniors unfamiliar with technology to easily edit.

[0148] In addition, according to various embodiments of the present invention, an artificial intelligence model can automatically correct brightness, color, sharpness, etc., to produce visually balanced content without the need for separate equipment.

[0149] In addition, according to various embodiments of the present invention, the posting process for senior users is simplified by automatically receiving platform-specific upload specifications and automatically performing format conversion, generating representative images, inserting descriptive text, etc.

[0150] Although various embodiments of the present invention have been described in detail above, those skilled in the art will understand that various modifications can be made to the above-described embodiments without departing from the scope of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined by the claims set forth below as well as equivalents thereof.

[0151] Meanwhile, the method according to the various embodiments of the present invention described above may be implemented as a program and provided to servers or devices. Accordingly, each device may connect to a server or device where the program is stored and download the program.

[0152] In addition, the method according to the various embodiments of the present invention described above may be implemented as a program and provided by being stored on various non-transitory computer-readable media. A non-transitory computer-readable medium refers to a medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short moment, such as a register, cache, or memory. Specifically, the various applications or programs described above may be provided by being stored on non-transitory computer-readable media such as CDs, DVDs, hard disks, Blu-ray discs, USBs, memory cards, ROMs, etc. Explanation of the symbols

[0153] 10: Senior users 100 : User terminal device 1000: Computing device

Claims

Claim 1 An intelligent content creation support method that supports senior users in easily creating digital content, comprising: a step of acquiring real-time video by activating a camera of a user terminal device according to user input; a step of outputting a conversation script related to the real-time video by overlaying it on the real-time video; a step of generating an edited video by processing the real-time video according to the user's editing command; and a step of uploading the generated edited video to a social network service server. Claim 2 An intelligent content creation support method according to claim 1, wherein the outputting step is characterized by generating a dialogue script related to the real-time video using a previously trained first artificial neural network model. Claim 3 An intelligent content creation support method according to claim 2, characterized in that the first artificial neural network model is pre-trained to generate the dialogue script by considering situation information extracted based on image feature information within a real-time image. Claim 4 An intelligent content production support method according to claim 1, wherein the step of generating the edited video is characterized by generating the edited video by editing the real-time video using a previously trained second artificial neural network model. Claim 5 An intelligent content production support method according to claim 4, characterized in that the second artificial neural network model is trained to generate an edited video by analyzing image feature information within a real-time video and performing visual quality correction and content composition processing according to a user's editing command. Claim 6 An intelligent content creation support method characterized by further including the step of saving the real-time video when the shooting of the real-time video is completed in claim 1. Claim 7 An intelligent content creation support method according to claim 1, wherein the uploading step involves analyzing a plurality of frames from the edited video to select a representative image, generating text corresponding to the representative image, and uploading it to the social network service server together with the edited video. Claim 8 A computing device for performing an intelligent content creation support method that supports senior users in easily creating digital content, comprising: a processor and a memory communicating with said processor, wherein the memory stores commands that cause said processor to perform operations, and said operations include: an operation of activating a camera of a user terminal device to acquire real-time video according to user input; an operation of overlaying a conversation script related to said real-time video onto said real-time video and outputting it; an operation of processing said real-time video to edit and generate an edited video according to said user's editing command; and an operation of uploading the generated edited video to a social network service server. Claim 9 A computing device according to claim 8, wherein the output operation is characterized by generating a dialogue script related to the real-time image using a previously trained first artificial neural network model. Claim 10 A computing device according to claim 9, characterized in that the first artificial neural network model is pre-trained to generate the dialogue script by considering situation information extracted based on image feature information within a real-time image. Claim 11 A computing device according to claim 8, wherein the operation of generating the edited image is characterized by generating the edited image by editing the real-time image using a previously trained second artificial neural network model. Claim 12 A computing device according to claim 11, characterized in that the second artificial neural network model is trained to generate an edited video by analyzing image feature information within a real-time video and performing visual quality correction and content composition processing according to a user's editing command. Claim 13 A computing device characterized by further including, in claim 8, an operation of saving the real-time video when the shooting of the real-time video is completed. Claim 14 A computing device according to claim 8, wherein the uploading operation involves analyzing a plurality of frames from the edited video to select a representative image, generating text corresponding to the representative image, and uploading it together with the edited video to the social network service server. Claim 15 A program recorded on a computer-readable recording medium having program code recorded thereon for executing an intelligent content production support method according to any one of claims 1 to 7. Claim 16 A computer-readable recording medium storing a program that performs an intelligent content creation support method according to any one of claims 1 to 7.

Images