system

Abstract

We provide the system. [Solution] A means for constructing a generative model that learns editing patterns based on the user's video editing history, A means of analyzing unedited video content received from a user and automatically applying editing elements, A method for automatically performing video editing according to the user's style using a generative model, A means of presenting the editing results to the user and receiving feedback, A means of improving the generative model based on the feedback received, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 an explanation of a character of the chatbot, 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] [[ID= twenty-one ]]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Video editing requires a great deal of time and effort, and it is a major burden for many creators. The conventional editing process is often performed manually, and high skills are required to adapt to the individual editing styles of users. Furthermore, when quick response is required, such as in breaking news, quick editing work is demanded, but it is difficult to achieve this with conventional methods. The present invention aims to solve these problems and provide a system that automates video editing based on the user's editing style and enables efficient content creation.

Means for Solving the Problems

[0005] This invention provides a system that automates the video editing process using a series of generative models. First, it analyzes the user's past editing history and builds a generative model that learns editing patterns. Next, it analyzes the unedited video material received from the user and applies this generative model to automatically perform editing based on the user's style. After editing, the generated video is presented to the user, and feedback is obtained. By continuously improving the generative model based on this feedback, further editing optimization is achieved. In particular, for video content including news flashes, the system is configured to enhance visual impact and speed by performing editing specific to news flashes, thereby improving the impact of the content.

[0006] A "generative model" is a machine learning algorithm that learns from a user's past editing data and automates the reproduction of specific editing patterns.

[0007] An "editing pattern" refers to a user-specific set of settings and techniques regarding the placement and timing of text overlays, music, sound effects, and other elements in video editing.

[0008] "Unedited video content" refers to raw video footage shot by a user but that has not yet undergone any editing.

[0009] "Analysis" is the process of breaking down the details of a video, such as scenes, audio, and visual elements, and extracting information according to its intended use.

[0010] "Editing elements" refer to elements such as text overlays, music, sound effects, and image effects that are inserted during video editing, and are factors that make content visually appealing.

[0011] "Feedback" refers to opinions provided by users regarding the edited results, indicating evaluations and areas for improvement, and is used to improve the system.

[0012] "Breaking news" refers to a type of content that provides viewers with urgent and timely news in a short amount of time.

[0013] "Visual effects" refer to techniques that integrate elements such as filters, transitions, and animations used within a video to enhance the visual appeal and impact of the content. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] ​​​​​In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention provides an advanced automated editing system to streamline users' video editing tasks. This system is implemented through interaction between a server, a terminal, and the user. Its embodiments are described in detail below.

[0036] First, the user provides the server with a dataset containing video projects they have edited themselves. This includes video files, editing project settings, text overlay placement, and sound effect timing. The server analyzes this dataset and builds a generative model to learn editing characteristics. This generative model extracts user-specific editing styles and patterns from the data and automates editing tasks based on them.

[0037] Next, the user uploads newly shot, unedited video content from their device to the server. The server receives the uploaded footage and performs automated editing using a trained generative model. This process analyzes scenes within the video, inserting text overlays at optimal timings and placing music and sound effects in appropriate locations. This allows complex editing tasks that were previously done manually to be completed quickly and efficiently.

[0038] Once automated editing is complete, the server sends the edited video back to the user's device. The user reviews the video and evaluates whether they are satisfied with the editing. This evaluation and feedback are sent back to the server and used to improve the generative model. By receiving feedback, the model can better reflect the user's intentions in its editing style.

[0039] For example, in the case of a user who produces cooking videos, the system can learn specific background music and text overlay styles used in past videos and automatically apply them to newly filmed videos. Furthermore, for urgent videos such as breaking news, the system can highlight important parts of the footage and perform timely editing.

[0040] In this way, the present invention provides a practical solution for efficiently producing video content while significantly reducing the effort required from the user.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects video editing data previously saved by users. This data includes edited video files, timing information for text overlays and sound effects, music clips used, and applied visual effects.

[0044] Step 2:

[0045] The server begins training a generative model using the collected data. This process involves analyzing the data to capture the features of editing patterns and feeding this information back into the model for pattern recognition. Furthermore, feature extraction and data preprocessing are performed to train the model.

[0046] Step 3:

[0047] The user uploads newly filmed, unedited video content from their device to the server. The device displays the progress until the upload is complete, performs error checks, and notifies the user when it is finished.

[0048] Step 4:

[0049] The server inputs the received video into a generative model and begins automatically applying editing elements. This process analyzes scenes within the video and, based on that analysis, automatically inserts text overlays and places music and sound effects. This makes the editing process much more efficient.

[0050] Step 5:

[0051] The server sends the edited video to the user. The user reviews the video and evaluates whether there are any problems with the editing quality or applied style. If necessary, they submit feedback via a form requesting corrections or further editing.

[0052] Step 6:

[0053] The server receives feedback from users and implements a process to improve the generative model. This allows the model to continuously learn editing patterns that match the user's intentions, thereby improving the accuracy of subsequent automated edits.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] Traditional video editing processes require considerable time and effort, and maintaining consistent quality according to the user's editing style is challenging. In particular, urgent video information requires immediate attention, demanding rapid and accurate editing capabilities. This invention aims to solve these problems by automatically learning the user's editing style and enabling rapid video editing.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for constructing a generative AI model that learns editing styles based on the user's video editing history, means for analyzing unedited video information provided by the user and automatically applying editing elements, and means for automatically performing video editing according to the user's specific style using the generative AI model. This significantly reduces the user's workload and enables efficient and high-quality video editing.

[0059] "User" refers to an entity that provides video information using a video editing system and receives the edited results.

[0060] "Video editing history" refers to the record and content of video editing performed by the user in the past.

[0061] "Editing style" refers to the unique style or pattern that a user employs in video editing.

[0062] A "generative AI model" is an artificial intelligence model that learns by analyzing a user's editing history and is used to automatically apply the user's unique editing style.

[0063] "Unedited video information" refers to video footage that has not yet been edited after filming.

[0064] "Editing elements" refer to elements added to or adjusted in video editing, such as text overlays, music, sound effects, and cut points.

[0065] "Opinions" refers to evaluations and feedback provided by users regarding the editing results.

[0066] This invention provides a system for streamlining video editing and automating user-specific editing styles. This system is implemented through a configuration including a server, terminals, and a generative AI model.

[0067] The server first receives the user's video editing history and builds a generative AI model based on that data. The generative AI model uses machine learning algorithms to learn the user's editing style and define the patterns necessary for future automated editing. The server is equipped with a high-performance processor and large memory capacity, which supports data analysis and model building.

[0068] Users upload newly recorded, unedited video footage to the server using their own devices. This requires a stable internet connection and a suitable file transfer application on the user's device. The video can be easily sent to the server via the GUI provided by the device.

[0069] The server receives the uploaded unedited video and performs analysis. This process utilizes a generative AI model, allowing the server to identify cut points and key scenes in the video and automatically apply appropriate editing elements. Specifically, it places subtitles, background music, and sound effects based on past editing styles. This significantly reduces the time-consuming manual work that users would otherwise have to do.

[0070] Once editing is complete, the server sends the results to the user's device, where the user reviews the edits. The user also provides feedback to the server regarding satisfaction levels and areas for improvement. Based on this feedback, the server continuously improves the generated AI model. This cycle allows for the creation of a model that more closely matches the user's editing style.

[0071] As a concrete example, users who produce cooking videos can train the system to learn specific background music and subtitle styles they have used in the past, and automatically apply them to new videos. An example of a prompt message in this case might be, "Please apply the subtitle style of the cooking instructions previously used to this video."

[0072] As described above, this invention reduces the effort required from users and enables efficient and consistent video editing.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] Users upload their past video editing projects to the server. This input includes video files, editing settings, text overlay placement, sound effect timing, and more. The server receives this data and performs data analysis. Specifically, it extracts editing features and prepares a dataset to understand the user's editing style. This output serves as foundational data for training a generative AI model.

[0076] Step 2:

[0077] The server uses the dataset obtained in Step 1 to build a generative AI model. Specifically, it uses a machine learning algorithm to input the user's editing patterns into the model. This calculation outputs an AI model that automates the selection of editing elements that are suitable for the user's style.

[0078] Step 3:

[0079] The user uploads newly shot, unedited footage from their device to the server. This is done by selecting the file through the GUI on the device and pressing the send button. This input becomes the basic material for automated editing in the next step.

[0080] Step 4:

[0081] The server analyzes the unedited video uploaded in step 3. It applies a generative AI model and automatically performs video editing. Specifically, the server identifies scenes within the video and places text overlays and background music in optimal positions. This utilizes the aforementioned data processing and AI model. The output is an edited video file.

[0082] Step 5:

[0083] The server sends the edited video back to the user's device. The user reviews the video and provides feedback on the edits. This user feedback is sent to the server as input. This feedback information is used to improve the generative AI model.

[0084] Step 6:

[0085] The server receives feedback and uses it to improve the generative AI model. Specifically, it adjusts the model based on the feedback information so that the next edit can be more tailored to the user's preferences. This output is the updated generative AI model.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] Traditional video editing required users to pay meticulous attention to each individual editing project and manually apply detailed editing elements, which was time-consuming and laborious. This made it difficult to efficiently produce high-quality content, and was particularly burdensome for users in situations where rapid editing was required, such as in content distribution services.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for constructing a generative model that learns editing patterns based on the user's video editing history, means for analyzing unedited video content received from the user and automatically applying editing elements, and means for automatically performing video editing according to the user's style using the generative model. This streamlines video editing work, eliminates the time and effort problems faced by the user, and enables the rapid generation of high-quality content.

[0091] A "user" is an individual or group that uses the system to create and edit video content.

[0092] "Video editing history" refers to the history of editing operations performed by the user in past editing projects.

[0093] A "generative model" is an artificial intelligence model that learns specific patterns and styles from data and automatically generates new data based on it.

[0094] "Unedited video content" refers to video data that has been newly filmed by the user and has not been edited.

[0095] "Editing elements" refer to individual editing patterns in video editing, such as text overlays, background music, sound effects, and scene transitions.

[0096] "Automated execution" means that the system autonomously completes the editing task without requiring user intervention.

[0097] This invention is a system that learns a user's unique editing style based on their past video editing history and automatically edits unedited videos using that style. First, the user provides the server with video projects they have edited so far. This includes video files, the placement of text overlays, and the timing of sound effects used. The server analyzes this data and builds a generative model to learn the characteristics of the editing.

[0098] The server creates generative AI models using machine learning frameworks such as TENSORFLOW® and PyTorch. These models automate the user's editing process by applying editing styles learned from past editing data to new videos.

[0099] The user uploads a newly filmed, unedited video from their device to the server. The server receives the uploaded video, applies a generative AI model, and performs automatic editing. After editing is complete, the server sends the edited video to the user's device.

[0100] This system allows users to skip tedious manual editing and generate high-quality videos immediately. Specifically, when a user uploads a video taken during a trip to this system, it automatically edits it based on the editing style of past travel videos, making it ready to share upon returning home. The prompt "Generate the optimal sound effects and text placement for this video project. Consider past editing data and apply editing that aligns with the theme." can be used with the generating AI model. This prompt allows the model to derive an accurate editing style.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] Users upload a dataset containing video projects they have edited to the server from their device. Inputs include video files, editing project settings, text overlay placement, and sound effect timing. The server receives this data and formats it into a format suitable for analysis.

[0104] Step 2:

[0105] The server analyzes a formatted dataset and builds a generative AI model to learn user editing patterns. The input is the analyzed editing data, and the server learns from this data to generate a model that extracts user-specific editing styles. The output is a generative AI model that reflects the user's editing patterns.

[0106] Step 3:

[0107] The user uploads newly filmed, unedited video content from their device to the server. The input is an unedited video file. The server receives the video and begins analysis using a generative AI model.

[0108] Step 4:

[0109] The server automatically edits the video by applying a generative AI model. The input for this step is a prompt based on the model's output and an unedited video file, specifically the prompt: "Generate the optimal sound effects and text placement for this video project. Consider past editing data and make edits that are in line with the theme." Following this prompt, the server analyzes the video scenes, sets appropriate text overlays, places sound effects and music, and outputs the edited video.

[0110] Step 5:

[0111] The server sends the edited video to the user's device. The user reviews the video and evaluates the editing results. The input is an automatically edited video, and the output is the user's evaluation and feedback.

[0112] Step 6:

[0113] The server further improves the generative AI model using feedback received from the user. The input is user feedback data, and the server uses this data to update the model so that it can more accurately reflect the editing style. The output is the improved generative AI model.

[0114] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0115] This invention is a system for automating video editing that takes user emotions into account. This system is implemented through the interaction of a server, a terminal, and the user.

[0116] First, the user provides the server with video editing projects they have created in the past. At this stage, the server analyzes the timing of text overlays, music, and sound effects, as well as the use of visual effects, within the video created by the user. In addition, the server uses an emotion engine to recognize and analyze emotional responses from the user's video viewing and editing history. This allows the server to build a generative model that reflects the individual emotional tone of the user's editing style, if any.

[0117] Next, the user uploads new, unedited video content from their device to the server. The server inputs this video content into a generative model and performs automatic editing according to the user's emotional preferences. In this editing process, the emotion engine works in conjunction with the generative model to optimize the emotional tone of the video by placing editing elements such as text overlays, music, sound effects, and visual effects in appropriate positions.

[0118] Once editing is complete, the server sends the edited video to the user. The user reviews the video and evaluates whether the content aligns with the intended emotional tone. The user's feedback and real-time emotional responses are collected on the device and sent to the server. The server uses this feedback to further improve both the generative model and the emotion engine, thereby improving the accuracy of future edits.

[0119] For example, when a user creates a story-driven video, the system takes into account the user's past editing patterns and the emotional tone analyzed by the emotion engine, and appropriately places music and visual effects that emphasize the emotions. This makes it possible to create a stronger emotional impact on the viewer.

[0120] As described above, the present invention enables the efficient and emotionally appealing production of video content by providing editing that takes user emotions into consideration.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] Users send their past video editing and viewing history from their device to the server. This allows the server to obtain data to analyze the user's unique editing style and emotional preferences.

[0124] Step 2:

[0125] The server analyzes received past editing data to train a generative model. This training process includes the placement of text overlays used by the user, music selection, and sound effect timing. It also utilizes an emotion engine to identify the user's emotional responses from their viewing history and captures emotional tones as data points.

[0126] Step 3:

[0127] The user uploads newly recorded video content from their device to the server. The device monitors the upload progress of the video file and notifies the user when the upload is successful.

[0128] Step 4:

[0129] The server inputs the uploaded video into the generative model and begins automatic editing. The emotion engine determines which emotional tones should be emphasized in the video based on the user's emotional preferences. It then selects appropriate text overlays, music, and sound effects to match the scene and performs overall editing.

[0130] Step 5:

[0131] The edited video is sent from the server to the user's device. The user watches the edited video and evaluates whether the edits align with the expected emotional tone.

[0132] Step 6:

[0133] Users send feedback to the server via their device after viewing, and their emotional responses are analyzed in real time by the emotion engine. The server uses this feedback to update the generative model and emotion engine, aiming to improve editing accuracy and user satisfaction in future edits.

[0134] (Example 2)

[0135] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0136] In video editing, reflecting a user's editing style and emotional elements is a time-consuming and laborious task, especially when dealing with a large amount of video footage. Furthermore, accurately visualizing the user's intended emotional tone and effectively conveying it to the viewer requires advanced knowledge. Moreover, constantly checking whether the editing results have the desired emotional impact is not practical. To address these challenges, there is a need for a more efficient automated editing process that takes into account each user's individual editing style and emotional responses.

[0137] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0138] This invention includes a server that includes means for constructing a generative model that learns individual editing styles and emotional tones based on the user's video editing history and emotional responses; means for analyzing unedited video data received from the user and automatically optimizing the placement of editing elements considering the emotional tone; and means for automatically performing video editing according to the user's editing style and emotional preferences using the generative model. As a result, video editing is performed automatically in accordance with the user's intentions and emotions, enabling the efficient production of high-quality video content.

[0139] "User video editing history" refers to a record of video editing work performed by the user in the past, as well as the patterns of that work, and is data that reflects the user's preferences and style.

[0140] "Emotional response" refers to the emotional changes and evaluations that users exhibit when watching or editing videos, and is data that indicates users' emotional preferences.

[0141] A "generative model" refers to an algorithm or computational model that learns individual editing styles and emotional tones, built based on a user's editing history and emotional responses.

[0142] "Unedited video data" refers to video material that has not yet undergone any editing and is video content that requires further processing.

[0143] "Emotional tone" refers to the emotional atmosphere or impression conveyed to the viewer through visual and auditory elements, and is an element that can be adjusted through video editing.

[0144] "Automatically optimize placement" means that editing elements are automatically placed in the optimal position according to defined criteria or algorithms.

[0145] "Real-time evaluation" refers to the immediate collection and analysis of user feedback and emotional responses during or immediately after video viewing.

[0146] "Improving the generative model and emotion recognition engine" means improving the performance of the model and engine based on the collected feedback data, thereby increasing the accuracy of future edits.

[0147] This invention is a system that enables automated video editing based on individual editing styles and emotional tones by utilizing a user's past video editing history and emotional responses. The concepts, hardware, and software necessary for carrying out the invention are described below.

[0148] First, users upload their past video editing projects to the server using their device. This allows past editing styles and patterns to be stored in a database. The device used here can be a general computer or smartphone, as long as it is capable of managing and transferring video data.

[0149] The server constructs a generative AI model based on accumulated editing history and emotional response data. Specifically, it utilizes machine learning techniques such as neural networks to design a unique generative model that reflects the user's editing preferences. At this time, it uses video analysis tools such as "FFmpeg" and "OpenCV" to analyze the editing history in detail.

[0150] When a user uploads new video content from their device, the server automatically edits it using a generative model. This editing includes automatic placement of editing elements and adjustment of emotional tone. The server utilizes the Adobe Premiere Pro API and other automated video editing scripts to apply edits that match the user's individual emotional style.

[0151] For example, if a user wants to create a video with an emotionally moving story, they can refer to past editing patterns and emotional data to optimally place music and visual effects that emphasize emotional impact. This makes it possible to create videos that have a strong emotional impact on viewers.

[0152] An example of a prompt message could be input to the generating AI model: "Consider the editing style of the emotionally moving videos the user has created in the past, and provide editing instructions to apply to the new video."

[0153] This invention allows users to efficiently edit videos in line with their emotional intentions without requiring advanced technical skills or editing knowledge. Through the collaboration between the server and the terminal, the accuracy of the model will be continuously improved based on feedback, which is expected to further enhance the performance of automatic editing.

[0154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0155] Step 1:

[0156] The user uploads previously created video editing projects from their device to the server. In this process, the device prepares the video data and sends it to the server using a file transfer protocol. The input is the video editing history, and the output is the edited project file stored on the server.

[0157] Step 2:

[0158] The server analyzes the received video editing history. This analysis includes extracting text, sound patterns, sound effect timing, and visual effect usage from the video. Tools such as "FFmpeg" and "OpenCV" are used in this process. The input is the video editing history, and the output is editing pattern data based on the analysis results.

[0159] Step 3:

[0160] The server builds a generative AI model based on the analysis results. This involves a process of training the model using machine learning algorithms to reflect the user's editing style and emotional tone. The input is editing pattern data, and the output is an individual generative model.

[0161] Step 4:

[0162] The user uploads new, unedited video content from their device to the server. The device transfers the video file to the server and prepares it for processing. The input is the new video content, and the output is the unedited video file on the server.

[0163] Step 5:

[0164] The server automatically edits new videos using a generative AI model. The editing process places text overlays, music, sound effects, and visual effects in appropriate locations within the video to create footage that matches the user's emotional preferences. This operation utilizes tools such as the Adobe Premiere Pro API. Input is an unedited video file and the generative model, while output is an edited video.

[0165] Step 6:

[0166] The server sends the edited video to the user. The user plays this video on their device and reviews its content. The input is the edited video, and the output is the user's rating and feedback.

[0167] Step 7:

[0168] The user sends feedback from their device to the server. The server analyzes the feedback and uses it to improve the model. This includes collected real-time sentiment response data. The input is user feedback and sentiment response data, and the output is the improved generative AI model.

[0169] (Application Example 2)

[0170] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0171] In modern content distribution services, a challenge is that video content must cater to viewers' emotional preferences in order to maintain their interest. Traditional video editing techniques struggle to capture the diverse emotional responses of viewers, creating a need for a system that delivers videos efficiently and emotionally compelling. Furthermore, the lack of automated editing techniques that can easily apply editing styles optimized for individual users is also a significant challenge.

[0172] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0173] This invention includes a server that includes means for constructing a generative AI model that learns editing patterns based on the user's video production history and emotional responses; means for analyzing unedited video material received from the user and automatically placing editing elements according to the emotional tone; and means for automatically performing video editing according to the user's style and emotional preferences using the generative AI model. This makes it possible to efficiently provide emotionally optimized video content.

[0174] "User" refers to an individual or legal entity that uses this system to edit video content.

[0175] "Video production history" refers to the record and content of video projects that a user has edited in the past.

[0176] "Emotional response" refers to changes in the feelings or sensations that a user or viewer exhibits in response to video content.

[0177] A "generative AI model" refers to an algorithm that learns a user's editing patterns and emotional tendencies, and then automatically edits videos based on that information.

[0178] "Editing patterns" refer to the tendencies in video editing techniques and styles that a user has used in the past.

[0179] "Unedited video footage" refers to raw video data created by a user that has not yet been edited.

[0180] "Emotional tone" refers to the emotions and atmosphere that should be conveyed to the viewer throughout the entire video.

[0181] "Editing elements" refer to components used in video editing, such as subtitles, music, sound effects, and visual effects.

[0182] To implement this invention, the following system is required: The server collects the user's video production history and emotional response data, and builds a generative AI model based on this data. Machine learning libraries using Python (e.g., TensorFlow or PyTorch) are suitable for use in this process. The server uses this model to analyze the unedited video material received from the user and automatically applies edits according to the emotional tone. Specifically, it places text overlays, music, sound effects, and visual effects in appropriate positions.

[0183] The device (e.g., PC or smartphone) provides an interface for users to upload new video footage. This interface is typically developed using JavaScript® or React and is required to be user-friendly. Users review the edited video on this device and provide feedback on whether it matches their intentions.

[0184] The server then receives this feedback and uses it to improve the generative AI model and emotion engine. Here, a database (e.g., PostgreSQL or MySQL®) is used to manage the feedback and continuously improve the machine learning model.

[0185] For example, a user might create a fun video themed around a family holiday. In this case, the system will appropriately place cheerful music and fun sound effects. It will also enhance the emotional tone by selecting bright and colorful visual effects.

[0186] Examples of prompts to input into a generative AI model include: "This video is themed around a family picnic. Please edit it in a tone that makes viewers feel happy and joyful." Implementing these specifics makes it easier to edit videos to best suit the user's emotional tendencies.

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The server collects the user's video production history and past emotional response data. This data is retrieved from a database stored on the server. Specifically, it extracts records of videos the user has edited so far and the results of emotional analysis obtained from the emotion engine.

[0190] Step 2:

[0191] The server builds a generative AI model based on the collected data. Here, a Python machine learning library (e.g., TensorFlow) is used to train a model that learns user-specific editing patterns and sentiment tendencies. In this step, data preprocessing such as normalization and label encoding is performed to ensure the model learns accurately.

[0192] Step 3:

[0193] Users upload unedited video footage to the server via their device. The device interface is designed to allow users to easily provide footage to the server by offering drag-and-drop and file selection windows.

[0194] Step 4:

[0195] The server analyzes the received video footage and automatically places editing elements based on the emotional tone. The video content is processed using a generative AI model as input, and appropriate music, sound effects, subtitles, and visual effects are selected and edited. Specifically, editing is performed using video processing libraries such as MoviePy.

[0196] Step 5:

[0197] The edited video is sent from the server to the user's device. The user reviews the edited video and evaluates whether the emotional tone and content meet their expectations. This feedback is displayed on the device in real time and can be easily provided through user interaction.

[0198] Step 6:

[0199] The server analyzes user feedback and uses it to improve the generative AI model and emotion engine. During this process, feedback data is stored in a database and incorporated into subsequent model training. This enables more accurate video editing tailored to user needs.

[0200] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0201] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0202] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0206] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0207] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0208] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0209] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0210] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0211] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0212] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0213] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0214] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0215] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0216] This invention provides an advanced automated editing system to streamline users' video editing tasks. This system is implemented through interaction between a server, a terminal, and the user. Its embodiments are described in detail below.

[0217] First, the user provides the server with a dataset containing video projects they have edited themselves. This includes video files, editing project settings, text overlay placement, and sound effect timing. The server analyzes this dataset and builds a generative model to learn editing characteristics. This generative model extracts user-specific editing styles and patterns from the data and automates editing tasks based on them.

[0218] Next, the user uploads newly shot, unedited video content from their device to the server. The server receives the uploaded footage and performs automated editing using a trained generative model. This process analyzes scenes within the video, inserting text overlays at optimal timings and placing music and sound effects in appropriate locations. This allows complex editing tasks that were previously done manually to be completed quickly and efficiently.

[0219] Once automated editing is complete, the server sends the edited video back to the user's device. The user reviews the video and evaluates whether they are satisfied with the editing. This evaluation and feedback are sent back to the server and used to improve the generative model. By receiving feedback, the model can better reflect the user's intentions in its editing style.

[0220] For example, in the case of a user who produces cooking videos, the system can learn specific background music and text overlay styles used in past videos and automatically apply them to newly filmed videos. Furthermore, for urgent videos such as breaking news, the system can highlight important parts of the footage and perform timely editing.

[0221] In this way, the present invention provides a practical solution for efficiently producing video content while significantly reducing the effort required from the user.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The server collects video editing data previously saved by users. This data includes edited video files, timing information for text overlays and sound effects, music clips used, and applied visual effects.

[0225] Step 2:

[0226] The server begins training a generative model using the collected data. This process involves analyzing the data to capture the features of editing patterns and feeding this information back into the model for pattern recognition. Furthermore, feature extraction and data preprocessing are performed to train the model.

[0227] Step 3:

[0228] The user uploads newly filmed, unedited video content from their device to the server. The device displays the progress until the upload is complete, performs error checks, and notifies the user when it is finished.

[0229] Step 4:

[0230] The server inputs the received video into a generative model and begins automatically applying editing elements. This process analyzes scenes within the video and, based on that analysis, automatically inserts text overlays and places music and sound effects. This makes the editing process much more efficient.

[0231] Step 5:

[0232] The server sends the edited video to the user. The user reviews the video and evaluates whether there are any problems with the editing quality or applied style. If necessary, they submit feedback via a form requesting corrections or further editing.

[0233] Step 6:

[0234] The server receives feedback from users and implements a process to improve the generative model. This allows the model to continuously learn editing patterns that match the user's intentions, thereby improving the accuracy of subsequent automated edits.

[0235] (Example 1)

[0236] Next, we will describe Example 1. 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."

[0237] Traditional video editing processes require considerable time and effort, and maintaining consistent quality according to the user's editing style is challenging. In particular, urgent video information requires immediate attention, demanding rapid and accurate editing capabilities. This invention aims to solve these problems by automatically learning the user's editing style and enabling rapid video editing.

[0238] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0239] In this invention, the server includes means for constructing a generative AI model that learns editing styles based on the user's video editing history, means for analyzing unedited video information provided by the user and automatically applying editing elements, and means for automatically performing video editing according to the user's specific style using the generative AI model. This significantly reduces the user's workload and enables efficient and high-quality video editing.

[0240] "User" refers to an entity that provides video information using a video editing system and receives the edited results.

[0241] "Video editing history" refers to the record and content of video editing performed by the user in the past.

[0242] "Editing style" refers to the unique style or pattern that a user employs in video editing.

[0243] A "generative AI model" is an artificial intelligence model that learns by analyzing a user's editing history and is used to automatically apply the user's unique editing style.

[0244] "Unedited video information" refers to video footage that has not yet been edited after filming.

[0245] "Editing elements" refer to elements added to or adjusted in video editing, such as text overlays, music, sound effects, and cut points.

[0246] "Opinions" refers to evaluations and feedback provided by users regarding the editing results.

[0247] This invention provides a system for streamlining video editing and automating user-specific editing styles. This system is implemented through a configuration including a server, terminals, and a generative AI model.

[0248] The server first receives the user's video editing history and builds a generative AI model based on that data. The generative AI model uses machine learning algorithms to learn the user's editing style and define the patterns necessary for future automated editing. The server is equipped with a high-performance processor and large memory capacity, which supports data analysis and model building.

[0249] Users upload newly recorded, unedited video footage to the server using their own devices. This requires a stable internet connection and a suitable file transfer application on the user's device. The video can be easily sent to the server via the GUI provided by the device.

[0250] The server receives the uploaded unedited video and performs analysis. This process utilizes a generative AI model, allowing the server to identify cut points and key scenes in the video and automatically apply appropriate editing elements. Specifically, it places subtitles, background music, and sound effects based on past editing styles. This significantly reduces the time-consuming manual work that users would otherwise have to do.

[0251] Once editing is complete, the server sends the results to the user's device, where the user reviews the edits. The user also provides feedback to the server regarding satisfaction levels and areas for improvement. Based on this feedback, the server continuously improves the generated AI model. This cycle allows for the creation of a model that more closely matches the user's editing style.

[0252] As a concrete example, users who produce cooking videos can train the system to learn specific background music and subtitle styles they have used in the past, and automatically apply them to new videos. An example of a prompt message in this case might be, "Please apply the subtitle style of the cooking instructions previously used to this video."

[0253] As described above, this invention reduces the effort required from users and enables efficient and consistent video editing.

[0254] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0255] Step 1:

[0256] Users upload their past video editing projects to the server. This input includes video files, editing settings, text overlay placement, sound effect timing, and more. The server receives this data and performs data analysis. Specifically, it extracts editing features and prepares a dataset to understand the user's editing style. This output serves as foundational data for training a generative AI model.

[0257] Step 2:

[0258] The server uses the dataset obtained in Step 1 to build a generative AI model. Specifically, it uses a machine learning algorithm to input the user's editing patterns into the model. This calculation outputs an AI model that automates the selection of editing elements that are suitable for the user's style.

[0259] Step 3:

[0260] The user uploads newly shot, unedited footage from their device to the server. This is done by selecting the file through the GUI on the device and pressing the send button. This input becomes the basic material for automated editing in the next step.

[0261] Step 4:

[0262] The server analyzes the unedited video uploaded in step 3. It applies a generative AI model and automatically performs video editing. Specifically, the server identifies scenes within the video and places text overlays and background music in optimal positions. This utilizes the aforementioned data processing and AI model. The output is an edited video file.

[0263] Step 5:

[0264] The server sends the edited video back to the user's device. The user reviews the video and provides feedback on the edits. This user feedback is sent to the server as input. This feedback information is used to improve the generative AI model.

[0265] Step 6:

[0266] The server receives feedback and uses it to improve the generative AI model. Specifically, it adjusts the model based on the feedback information so that the next edit can be more tailored to the user's preferences. This output is the updated generative AI model.

[0267] (Application Example 1)

[0268] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0269] Traditional video editing required users to pay meticulous attention to each individual editing project and manually apply detailed editing elements, which was time-consuming and laborious. This made it difficult to efficiently produce high-quality content, and was particularly burdensome for users in situations where rapid editing was required, such as in content distribution services.

[0270] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0271] In this invention, the server includes means for constructing a generative model that learns editing patterns based on the user's video editing history, means for analyzing unedited video content received from the user and automatically applying editing elements, and means for automatically performing video editing according to the user's style using the generative model. This streamlines video editing work, eliminates the time and effort problems faced by the user, and enables the rapid generation of high-quality content.

[0272] A "user" is an individual or group that uses the system to create and edit video content.

[0273] "Video editing history" refers to the history of editing operations performed by the user in past editing projects.

[0274] A "generative model" is an artificial intelligence model that learns specific patterns and styles from data and automatically generates new data based on it.

[0275] "Unedited video content" refers to video data that has been newly filmed by the user and has not been edited.

[0276] "Editing elements" refer to individual editing patterns in video editing, such as text overlays, background music, sound effects, and scene transitions.

[0277] "Automated execution" means that the system autonomously completes the editing task without requiring user intervention.

[0278] This invention is a system that learns a user's unique editing style based on their past video editing history and automatically edits unedited videos using that style. First, the user provides the server with video projects they have edited so far. This includes video files, the placement of text overlays, and the timing of sound effects used. The server analyzes this data and builds a generative model to learn the characteristics of the editing.

[0279] The server creates generative AI models using machine learning frameworks such as TensorFlow and PyTorch. These models automate the user's editing process by applying editing styles learned from past editing data to new videos.

[0280] The user uploads a newly filmed, unedited video from their device to the server. The server receives the uploaded video, applies a generative AI model, and performs automatic editing. After editing is complete, the server sends the edited video to the user's device.

[0281] With this system, the user can omit the cumbersome manual editing work and immediately generate high-quality videos. Specifically, when the user uploads a video taken at the travel destination to this system, automatic editing is performed by referring to the editing styles of past travel videos, and sharing becomes possible immediately after returning home. The prompt sentence "Generate the optimal sound effects and telop placements for this video project. Considering past editing data, add editing along the theme." can be used for the generation AI model. With this prompt, the model derives the correct editing style.

[0282] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0283] Step 1:

[0284] The user uploads a dataset including video projects that the user has edited so far from the terminal to the server. The inputs are video files, editing project settings, telop positions, sound effect timings, etc. The server receives these data and formats them into a form that is easy to analyze.

[0285] Step 2:

[0286] The server analyzes the formatted dataset and constructs a generation AI model for learning the user's editing pattern. The input is the analyzed editing data, and the server learns from this data and generates a model that extracts the user-specific editing style. The output is a generation AI model that reflects the user's editing pattern.

[0287] Step 3:

[0288] The user uploads the newly taken unedited video content from the terminal to the server. The input is the unedited video file. The server receives the video and starts analysis using the generation AI model.

[0289] Step 4:

[0290] The server automatically edits the video by applying a generative AI model. The input for this step is a prompt based on the model's output and an unedited video file, specifically the prompt: "Generate the optimal sound effects and text placement for this video project. Consider past editing data and make edits that are in line with the theme." Following this prompt, the server analyzes the video scenes, sets appropriate text overlays, places sound effects and music, and outputs the edited video.

[0291] Step 5:

[0292] The server sends the edited video to the user's device. The user reviews the video and evaluates the editing results. The input is an automatically edited video, and the output is the user's evaluation and feedback.

[0293] Step 6:

[0294] The server further improves the generative AI model using feedback received from the user. The input is user feedback data, and the server uses this data to update the model so that it can more accurately reflect the editing style. The output is the improved generative AI model.

[0295] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0296] This invention is a system for automating video editing that takes user emotions into account. This system is implemented through the interaction of a server, a terminal, and the user.

[0297] First, the user provides the server with video editing projects they have created in the past. At this stage, the server analyzes the timing of text overlays, music, and sound effects, as well as the use of visual effects, within the video created by the user. In addition, the server uses an emotion engine to recognize and analyze emotional responses from the user's video viewing and editing history. This allows the server to build a generative model that reflects the individual emotional tone of the user's editing style, if any.

[0298] Next, the user uploads new, unedited video content from their device to the server. The server inputs this video content into a generative model and performs automatic editing according to the user's emotional preferences. In this editing process, the emotion engine works in conjunction with the generative model to optimize the emotional tone of the video by placing editing elements such as text overlays, music, sound effects, and visual effects in appropriate positions.

[0299] Once editing is complete, the server sends the edited video to the user. The user reviews the video and evaluates whether the content aligns with the intended emotional tone. The user's feedback and real-time emotional responses are collected on the device and sent to the server. The server uses this feedback to further improve both the generative model and the emotion engine, thereby improving the accuracy of future edits.

[0300] For example, when a user creates a story-driven video, the system takes into account the user's past editing patterns and the emotional tone analyzed by the emotion engine, and appropriately places music and visual effects that emphasize the emotions. This makes it possible to create a stronger emotional impact on the viewer.

[0301] As described above, the present invention enables the efficient and emotionally appealing production of video content by providing editing that takes user emotions into consideration.

[0302] The following describes the processing flow.

[0303] Step 1:

[0304] The user transmits their past video editing history and viewing history from the terminal to the server. Thereby, the server obtains data for analyzing the user-specific editing style and emotional preferences.

[0305] Step 2:

[0306] The server analyzes the received past editing data and trains a generation model. This training process includes the position of the subtitles used by the user, the selection of music, the timing of sound effects, etc. Also, using an emotion engine, the user's emotional reactions are identified from the viewing history, and the emotional tone is incorporated as a data point.

[0307] Step 3:

[0308] The user uploads newly shot video content from the terminal to the server. The terminal monitors the upload progress of the video file and notifies the user that the upload has been completed successfully.

[0309] Step 4:

[0310] The server inputs the uploaded video into the generation model and starts automatic editing. The emotion engine determines what emotional tone should be emphasized in the video based on the user's emotional preferences. Then, appropriate subtitles, music, and sound effects are selected according to the scene, and overall editing is performed.

[0311] Step 5:

[0312] The edited video is transmitted from the server to the user's terminal. The user watches the edited video and evaluates whether the edited content follows the expected emotional tone.

[0313] Step 6:

[0314] Users send feedback to the server via their device after viewing, and their emotional responses are analyzed in real time by the emotion engine. The server uses this feedback to update the generative model and emotion engine, aiming to improve editing accuracy and user satisfaction in future edits.

[0315] (Example 2)

[0316] Next, we will describe Example 2. 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".

[0317] In video editing, reflecting a user's editing style and emotional elements is a time-consuming and laborious task, especially when dealing with a large amount of video footage. Furthermore, accurately visualizing the user's intended emotional tone and effectively conveying it to the viewer requires advanced knowledge. Moreover, constantly checking whether the editing results have the desired emotional impact is not practical. To address these challenges, there is a need for a more efficient automated editing process that takes into account each user's individual editing style and emotional responses.

[0318] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0319] This invention includes a server that includes means for constructing a generative model that learns individual editing styles and emotional tones based on the user's video editing history and emotional responses; means for analyzing unedited video data received from the user and automatically optimizing the placement of editing elements considering the emotional tone; and means for automatically performing video editing according to the user's editing style and emotional preferences using the generative model. As a result, video editing is performed automatically in accordance with the user's intentions and emotions, enabling the efficient production of high-quality video content.

[0320] "User video editing history" refers to a record of video editing work performed by the user in the past, as well as the patterns of that work, and is data that reflects the user's preferences and style.

[0321] "Emotional response" refers to the emotional changes and evaluations that users exhibit when watching or editing videos, and is data that indicates users' emotional preferences.

[0322] A "generative model" refers to an algorithm or computational model that learns individual editing styles and emotional tones, built based on a user's editing history and emotional responses.

[0323] "Unedited video data" refers to video material that has not yet undergone any editing and is video content that requires further processing.

[0324] "Emotional tone" refers to the emotional atmosphere or impression conveyed to the viewer through visual and auditory elements, and is an element that can be adjusted through video editing.

[0325] "Automatically optimize placement" means that editing elements are automatically placed in the optimal position according to defined criteria or algorithms.

[0326] "Real-time evaluation" refers to the immediate collection and analysis of user feedback and emotional responses during or immediately after video viewing.

[0327] "Improving the generative model and emotion recognition engine" means improving the performance of the model and engine based on the collected feedback data, thereby increasing the accuracy of future edits.

[0328] This invention is a system that enables automated video editing based on individual editing styles and emotional tones by utilizing a user's past video editing history and emotional responses. The concepts, hardware, and software necessary for carrying out the invention are described below.

[0329] First, users upload their past video editing projects to the server using their device. This allows past editing styles and patterns to be stored in a database. The device used here can be a general computer or smartphone, as long as it is capable of managing and transferring video data.

[0330] The server constructs a generative AI model based on accumulated editing history and emotional response data. Specifically, it utilizes machine learning techniques such as neural networks to design a unique generative model that reflects the user's editing preferences. At this time, it uses video analysis tools such as "FFmpeg" and "OpenCV" to analyze the editing history in detail.

[0331] When a user uploads new video content from their device, the server automatically edits it using a generative model. This editing includes automatic placement of editing elements and adjustment of emotional tone. The server utilizes the Adobe Premiere Pro API and other automated video editing scripts to apply edits that match the user's individual emotional style.

[0332] For example, if a user wants to create a video with an emotionally moving story, they can refer to past editing patterns and emotional data to optimally place music and visual effects that emphasize emotional impact. This makes it possible to create videos that have a strong emotional impact on viewers.

[0333] An example of a prompt message could be input to the generating AI model: "Consider the editing style of the emotionally moving videos the user has created in the past, and provide editing instructions to apply to the new video."

[0334] This invention allows users to efficiently edit videos in line with their emotional intentions without requiring advanced technical skills or editing knowledge. Through the collaboration between the server and the terminal, the accuracy of the model will be continuously improved based on feedback, which is expected to further enhance the performance of automatic editing.

[0335] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0336] Step 1:

[0337] The user uploads previously created video editing projects from their device to the server. In this process, the device prepares the video data and sends it to the server using a file transfer protocol. The input is the video editing history, and the output is the edited project file stored on the server.

[0338] Step 2:

[0339] The server analyzes the received video editing history. This analysis includes extracting text, sound patterns, sound effect timing, and visual effect usage from the video. Tools such as "FFmpeg" and "OpenCV" are used in this process. The input is the video editing history, and the output is editing pattern data based on the analysis results.

[0340] Step 3:

[0341] The server builds a generative AI model based on the analysis results. This involves a process of training the model using machine learning algorithms to reflect the user's editing style and emotional tone. The input is editing pattern data, and the output is an individual generative model.

[0342] Step 4:

[0343] The user uploads new, unedited video content from their device to the server. The device transfers the video file to the server and prepares it for processing. The input is the new video content, and the output is the unedited video file on the server.

[0344] Step 5:

[0345] The server automatically edits new videos using a generative AI model. The editing process places text overlays, music, sound effects, and visual effects in appropriate locations within the video to create footage that matches the user's emotional preferences. This operation utilizes tools such as the Adobe Premiere Pro API. Input is an unedited video file and the generative model, while output is an edited video.

[0346] Step 6:

[0347] The server sends the edited video to the user. The user plays this video on their device and reviews its content. The input is the edited video, and the output is the user's rating and feedback.

[0348] Step 7:

[0349] The user sends feedback from their device to the server. The server analyzes the feedback and uses it to improve the model. This includes collected real-time sentiment response data. The input is user feedback and sentiment response data, and the output is the improved generative AI model.

[0350] (Application Example 2)

[0351] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0352] In modern content distribution services, a challenge is that video content must cater to viewers' emotional preferences in order to maintain their interest. Traditional video editing techniques struggle to capture the diverse emotional responses of viewers, creating a need for a system that delivers videos efficiently and emotionally compelling. Furthermore, the lack of automated editing techniques that can easily apply editing styles optimized for individual users is also a significant challenge.

[0353] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0354] This invention includes a server that includes means for constructing a generative AI model that learns editing patterns based on the user's video production history and emotional responses; means for analyzing unedited video material received from the user and automatically placing editing elements according to the emotional tone; and means for automatically performing video editing according to the user's style and emotional preferences using the generative AI model. This makes it possible to efficiently provide emotionally optimized video content.

[0355] "User" refers to an individual or legal entity that uses this system to edit video content.

[0356] "Video production history" refers to the record and content of video projects that a user has edited in the past.

[0357] "Emotional response" refers to changes in the feelings or sensations that a user or viewer exhibits in response to video content.

[0358] A "generative AI model" refers to an algorithm that learns a user's editing patterns and emotional tendencies, and then automatically edits videos based on that information.

[0359] "Editing patterns" refer to the tendencies in video editing techniques and styles that a user has used in the past.

[0360] "Unedited video footage" refers to raw video data created by a user that has not yet been edited.

[0361] "Emotional tone" refers to the emotions and atmosphere that should be conveyed to the viewer throughout the entire video.

[0362] "Editing elements" refer to components used in video editing, such as subtitles, music, sound effects, and visual effects.

[0363] To implement this invention, the following system is required: The server collects the user's video production history and emotional response data, and builds a generative AI model based on this data. Machine learning libraries using Python (e.g., TensorFlow or PyTorch) are suitable for use in this process. The server uses this model to analyze the unedited video material received from the user and automatically applies edits according to the emotional tone. Specifically, it places text overlays, music, sound effects, and visual effects in appropriate positions.

[0364] The device (e.g., PC or smartphone) provides an interface for users to upload new video footage. This interface is typically developed using JavaScript or React and is required to be user-friendly. Users review the edited video on this device and provide feedback on whether it matches their intentions.

[0365] The server then receives this feedback and uses it to improve the generative AI model and emotion engine. Here, a database (e.g., PostgreSQL or MySQL) is used to manage the feedback and continuously improve the machine learning model.

[0366] For example, a user might create a fun video themed around a family holiday. In this case, the system will appropriately place cheerful music and fun sound effects. It will also enhance the emotional tone by selecting bright and colorful visual effects.

[0367] Examples of prompts to input into a generative AI model include: "This video is themed around a family picnic. Please edit it in a tone that makes viewers feel happy and joyful." Implementing these specifics makes it easier to edit videos to best suit the user's emotional tendencies.

[0368] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0369] Step 1:

[0370] The server collects the user's video production history and past emotional response data. This data is retrieved from a database stored on the server. Specifically, it extracts records of videos the user has edited so far and the results of emotional analysis obtained from the emotion engine.

[0371] Step 2:

[0372] The server builds a generative AI model based on the collected data. Here, a Python machine learning library (e.g., TensorFlow) is used to train a model that learns user-specific editing patterns and sentiment tendencies. In this step, data preprocessing such as normalization and label encoding is performed to ensure the model learns accurately.

[0373] Step 3:

[0374] Users upload unedited video footage to the server via their device. The device interface is designed to allow users to easily provide footage to the server by offering drag-and-drop and file selection windows.

[0375] Step 4:

[0376] The server analyzes the received video footage and automatically places editing elements based on the emotional tone. The video content is processed using a generative AI model as input, and appropriate music, sound effects, subtitles, and visual effects are selected and edited. Specifically, editing is performed using video processing libraries such as MoviePy.

[0377] Step 5:

[0378] The edited video is sent from the server to the user's device. The user reviews the edited video and evaluates whether the emotional tone and content meet their expectations. This feedback is displayed on the device in real time and can be easily provided through user interaction.

[0379] Step 6:

[0380] The server analyzes user feedback and uses it to improve the generative AI model and emotion engine. During this process, feedback data is stored in a database and incorporated into subsequent model training. This enables more accurate video editing tailored to user needs.

[0381] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0382] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0383] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0384] [Third Embodiment]

[0385] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0386] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0387] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0388] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0389] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0390] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0391] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0392] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0393] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0394] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0395] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0396] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0397] This invention provides an advanced automated editing system to streamline users' video editing tasks. This system is implemented through interaction between a server, a terminal, and the user. Its embodiments are described in detail below.

[0398] First, the user provides the server with a dataset containing video projects they have edited themselves. This includes video files, editing project settings, text overlay placement, and sound effect timing. The server analyzes this dataset and builds a generative model to learn editing characteristics. This generative model extracts user-specific editing styles and patterns from the data and automates editing tasks based on them.

[0399] Next, the user uploads newly shot, unedited video content from their device to the server. The server receives the uploaded footage and performs automated editing using a trained generative model. This process analyzes scenes within the video, inserting text overlays at optimal timings and placing music and sound effects in appropriate locations. This allows complex editing tasks that were previously done manually to be completed quickly and efficiently.

[0400] Once automated editing is complete, the server sends the edited video back to the user's device. The user reviews the video and evaluates whether they are satisfied with the editing. This evaluation and feedback are sent back to the server and used to improve the generative model. By receiving feedback, the model can better reflect the user's intentions in its editing style.

[0401] For example, in the case of a user who produces cooking videos, the system can learn specific background music and text overlay styles used in past videos and automatically apply them to newly filmed videos. Furthermore, for urgent videos such as breaking news, the system can highlight important parts of the footage and perform timely editing.

[0402] In this way, the present invention provides a practical solution for efficiently producing video content while significantly reducing the effort required from the user.

[0403] The following describes the processing flow.

[0404] Step 1:

[0405] The server collects video editing data previously saved by users. This data includes edited video files, timing information for text overlays and sound effects, music clips used, and applied visual effects.

[0406] Step 2:

[0407] The server begins training a generative model using the collected data. This process involves analyzing the data to capture the features of editing patterns and feeding this information back into the model for pattern recognition. Furthermore, feature extraction and data preprocessing are performed to train the model.

[0408] Step 3:

[0409] The user uploads newly filmed, unedited video content from their device to the server. The device displays the progress until the upload is complete, performs error checks, and notifies the user when it is finished.

[0410] Step 4:

[0411] The server inputs the received video into a generative model and begins automatically applying editing elements. This process analyzes scenes within the video and, based on that analysis, automatically inserts text overlays and places music and sound effects. This makes the editing process much more efficient.

[0412] Step 5:

[0413] The server sends the edited video to the user. The user reviews the video and evaluates whether there are any problems with the editing quality or applied style. If necessary, they submit feedback via a form requesting corrections or further editing.

[0414] Step 6:

[0415] The server receives feedback from users and implements a process to improve the generative model. This allows the model to continuously learn editing patterns that match the user's intentions, thereby improving the accuracy of subsequent automated edits.

[0416] (Example 1)

[0417] Next, we will describe Example 1. 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."

[0418] Traditional video editing processes require considerable time and effort, and maintaining consistent quality according to the user's editing style is challenging. In particular, urgent video information requires immediate attention, demanding rapid and accurate editing capabilities. This invention aims to solve these problems by automatically learning the user's editing style and enabling rapid video editing.

[0419] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0420] In this invention, the server includes means for constructing a generative AI model that learns editing styles based on the user's video editing history, means for analyzing unedited video information provided by the user and automatically applying editing elements, and means for automatically performing video editing according to the user's specific style using the generative AI model. This significantly reduces the user's workload and enables efficient and high-quality video editing.

[0421] "User" refers to an entity that provides video information using a video editing system and receives the edited results.

[0422] "Video editing history" refers to the record and content of video editing performed by the user in the past.

[0423] "Editing style" refers to the unique style or pattern that a user employs in video editing.

[0424] A "generative AI model" is an artificial intelligence model that learns by analyzing a user's editing history and is used to automatically apply the user's unique editing style.

[0425] "Unedited video information" refers to video footage that has not yet been edited after filming.

[0426] "Editing elements" refer to elements added to or adjusted in video editing, such as text overlays, music, sound effects, and cut points.

[0427] "Opinions" refers to evaluations and feedback provided by users regarding the editing results.

[0428] This invention provides a system for streamlining video editing and automating user-specific editing styles. This system is implemented through a configuration including a server, terminals, and a generative AI model.

[0429] The server first receives the user's video editing history and builds a generative AI model based on that data. The generative AI model uses machine learning algorithms to learn the user's editing style and define the patterns necessary for future automated editing. The server is equipped with a high-performance processor and large memory capacity, which supports data analysis and model building.

[0430] Users upload newly recorded, unedited video footage to the server using their own devices. This requires a stable internet connection and a suitable file transfer application on the user's device. The video can be easily sent to the server via the GUI provided by the device.

[0431] The server receives the uploaded unedited video and performs analysis. This process utilizes a generative AI model, allowing the server to identify cut points and key scenes in the video and automatically apply appropriate editing elements. Specifically, it places subtitles, background music, and sound effects based on past editing styles. This significantly reduces the time-consuming manual work that users would otherwise have to do.

[0432] Once editing is complete, the server sends the results to the user's device, where the user reviews the edits. The user also provides feedback to the server regarding satisfaction levels and areas for improvement. Based on this feedback, the server continuously improves the generated AI model. This cycle allows for the creation of a model that more closely matches the user's editing style.

[0433] As a concrete example, users who produce cooking videos can train the system to learn specific background music and subtitle styles they have used in the past, and automatically apply them to new videos. An example of a prompt message in this case might be, "Please apply the subtitle style of the cooking instructions previously used to this video."

[0434] As described above, this invention reduces the effort required from users and enables efficient and consistent video editing.

[0435] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0436] Step 1:

[0437] Users upload their past video editing projects to the server. This input includes video files, editing settings, text overlay placement, sound effect timing, and more. The server receives this data and performs data analysis. Specifically, it extracts editing features and prepares a dataset to understand the user's editing style. This output serves as foundational data for training a generative AI model.

[0438] Step 2:

[0439] The server uses the dataset obtained in Step 1 to build a generative AI model. Specifically, it uses a machine learning algorithm to input the user's editing patterns into the model. This calculation outputs an AI model that automates the selection of editing elements that are suitable for the user's style.

[0440] Step 3:

[0441] The user uploads newly shot, unedited footage from their device to the server. This is done by selecting the file through the GUI on the device and pressing the send button. This input becomes the basic material for automated editing in the next step.

[0442] Step 4:

[0443] The server analyzes the unedited video uploaded in step 3. It applies a generative AI model and automatically performs video editing. Specifically, the server identifies scenes within the video and places text overlays and background music in optimal positions. This utilizes the aforementioned data processing and AI model. The output is an edited video file.

[0444] Step 5:

[0445] The server sends the edited video back to the user's device. The user reviews the video and provides feedback on the edits. This user feedback is sent to the server as input. This feedback information is used to improve the generative AI model.

[0446] Step 6:

[0447] The server receives feedback and uses it to improve the generative AI model. Specifically, it adjusts the model based on the feedback information so that the next edit can be more tailored to the user's preferences. This output is the updated generative AI model.

[0448] (Application Example 1)

[0449] Next, we will explain Application Example 1. In the following explanation, 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."

[0450] Traditional video editing required users to pay meticulous attention to each individual editing project and manually apply detailed editing elements, which was time-consuming and laborious. This made it difficult to efficiently produce high-quality content, and was particularly burdensome for users in situations where rapid editing was required, such as in content distribution services.

[0451] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0452] In this invention, the server includes means for constructing a generative model that learns editing patterns based on the user's video editing history, means for analyzing unedited video content received from the user and automatically applying editing elements, and means for automatically performing video editing according to the user's style using the generative model. This streamlines video editing work, eliminates the time and effort problems faced by the user, and enables the rapid generation of high-quality content.

[0453] A "user" is an individual or group that uses the system to create and edit video content.

[0454] "Video editing history" refers to the history of editing operations performed by the user in past editing projects.

[0455] A "generative model" is an artificial intelligence model that learns specific patterns and styles from data and automatically generates new data based on it.

[0456] "Unedited video content" refers to video data that has been newly filmed by the user and has not been edited.

[0457] "Editing elements" refer to individual editing patterns in video editing, such as text overlays, background music, sound effects, and scene transitions.

[0458] "Automated execution" means that the system autonomously completes the editing task without requiring user intervention.

[0459] This invention is a system that learns a user's unique editing style based on their past video editing history and automatically edits unedited videos using that style. First, the user provides the server with video projects they have edited so far. This includes video files, the placement of text overlays, and the timing of sound effects used. The server analyzes this data and builds a generative model to learn the characteristics of the editing.

[0460] The server creates generative AI models using machine learning frameworks such as TensorFlow and PyTorch. These models automate the user's editing process by applying editing styles learned from past editing data to new videos.

[0461] The user uploads a newly filmed, unedited video from their device to the server. The server receives the uploaded video, applies a generative AI model, and performs automatic editing. After editing is complete, the server sends the edited video to the user's device.

[0462] This system allows users to skip tedious manual editing and generate high-quality videos immediately. Specifically, when a user uploads a video taken during a trip to this system, it automatically edits it based on the editing style of past travel videos, making it ready to share upon returning home. The prompt "Generate the optimal sound effects and text placement for this video project. Consider past editing data and apply editing that aligns with the theme." can be used with the generating AI model. This prompt allows the model to derive an accurate editing style.

[0463] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0464] Step 1:

[0465] Users upload a dataset containing video projects they have edited to the server from their device. Inputs include video files, editing project settings, text overlay placement, and sound effect timing. The server receives this data and formats it into a format suitable for analysis.

[0466] Step 2:

[0467] The server analyzes a formatted dataset and builds a generative AI model to learn user editing patterns. The input is the analyzed editing data, and the server learns from this data to generate a model that extracts user-specific editing styles. The output is a generative AI model that reflects the user's editing patterns.

[0468] Step 3:

[0469] The user uploads newly filmed, unedited video content from their device to the server. The input is an unedited video file. The server receives the video and begins analysis using a generative AI model.

[0470] Step 4:

[0471] The server automatically edits the video by applying a generative AI model. The input for this step is a prompt based on the model's output and an unedited video file, specifically the prompt: "Generate the optimal sound effects and text placement for this video project. Consider past editing data and make edits that are in line with the theme." Following this prompt, the server analyzes the video scenes, sets appropriate text overlays, places sound effects and music, and outputs the edited video.

[0472] Step 5:

[0473] The server sends the edited video to the user's device. The user reviews the video and evaluates the editing results. The input is an automatically edited video, and the output is the user's evaluation and feedback.

[0474] Step 6:

[0475] The server further improves the generative AI model using feedback received from the user. The input is user feedback data, and the server uses this data to update the model so that it can more accurately reflect the editing style. The output is the improved generative AI model.

[0476] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0477] This invention is a system for automating video editing that takes user emotions into account. This system is implemented through the interaction of a server, a terminal, and the user.

[0478] First, the user provides the server with video editing projects they have created in the past. At this stage, the server analyzes the timing of text overlays, music, and sound effects, as well as the use of visual effects, within the video created by the user. In addition, the server uses an emotion engine to recognize and analyze emotional responses from the user's video viewing and editing history. This allows the server to build a generative model that reflects the individual emotional tone of the user's editing style, if any.

[0479] Next, the user uploads new, unedited video content from their device to the server. The server inputs this video content into a generative model and performs automatic editing according to the user's emotional preferences. In this editing process, the emotion engine works in conjunction with the generative model to optimize the emotional tone of the video by placing editing elements such as text overlays, music, sound effects, and visual effects in appropriate positions.

[0480] Once editing is complete, the server sends the edited video to the user. The user reviews the video and evaluates whether the content aligns with the intended emotional tone. The user's feedback and real-time emotional responses are collected on the device and sent to the server. The server uses this feedback to further improve both the generative model and the emotion engine, thereby improving the accuracy of future edits.

[0481] For example, when a user creates a story-driven video, the system takes into account the user's past editing patterns and the emotional tone analyzed by the emotion engine, and appropriately places music and visual effects that emphasize the emotions. This makes it possible to create a stronger emotional impact on the viewer.

[0482] As described above, the present invention enables the efficient and emotionally appealing production of video content by providing editing that takes user emotions into consideration.

[0483] The following describes the processing flow.

[0484] Step 1:

[0485] Users send their past video editing and viewing history from their device to the server. This allows the server to obtain data to analyze the user's unique editing style and emotional preferences.

[0486] Step 2:

[0487] The server analyzes received past editing data to train a generative model. This training process includes the placement of text overlays used by the user, music selection, and sound effect timing. It also utilizes an emotion engine to identify the user's emotional responses from their viewing history and captures emotional tones as data points.

[0488] Step 3:

[0489] The user uploads newly recorded video content from their device to the server. The device monitors the upload progress of the video file and notifies the user when the upload is successful.

[0490] Step 4:

[0491] The server inputs the uploaded video into the generative model and begins automatic editing. The emotion engine determines which emotional tones should be emphasized in the video based on the user's emotional preferences. It then selects appropriate text overlays, music, and sound effects to match the scene and performs overall editing.

[0492] Step 5:

[0493] The edited video is sent from the server to the user's device. The user watches the edited video and evaluates whether the edits align with the expected emotional tone.

[0494] Step 6:

[0495] Users send feedback to the server via their device after viewing, and their emotional responses are analyzed in real time by the emotion engine. The server uses this feedback to update the generative model and emotion engine, aiming to improve editing accuracy and user satisfaction in future edits.

[0496] (Example 2)

[0497] Next, we will describe Example 2. 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."

[0498] In video editing, reflecting a user's editing style and emotional elements is a time-consuming and laborious task, especially when dealing with a large amount of video footage. Furthermore, accurately visualizing the user's intended emotional tone and effectively conveying it to the viewer requires advanced knowledge. Moreover, constantly checking whether the editing results have the desired emotional impact is not practical. To address these challenges, there is a need for a more efficient automated editing process that takes into account each user's individual editing style and emotional responses.

[0499] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0500] This invention includes a server that includes means for constructing a generative model that learns individual editing styles and emotional tones based on the user's video editing history and emotional responses; means for analyzing unedited video data received from the user and automatically optimizing the placement of editing elements considering the emotional tone; and means for automatically performing video editing according to the user's editing style and emotional preferences using the generative model. As a result, video editing is performed automatically in accordance with the user's intentions and emotions, enabling the efficient production of high-quality video content.

[0501] "User video editing history" refers to a record of video editing work performed by the user in the past, as well as the patterns of that work, and is data that reflects the user's preferences and style.

[0502] "Emotional response" refers to the emotional changes and evaluations that users exhibit when watching or editing videos, and is data that indicates users' emotional preferences.

[0503] A "generative model" refers to an algorithm or computational model that learns individual editing styles and emotional tones, built based on a user's editing history and emotional responses.

[0504] "Unedited video data" refers to video material that has not yet undergone any editing and is video content that requires further processing.

[0505] "Emotional tone" refers to the emotional atmosphere or impression conveyed to the viewer through visual and auditory elements, and is an element that can be adjusted through video editing.

[0506] "Automatically optimize placement" means that editing elements are automatically placed in the optimal position according to defined criteria or algorithms.

[0507] "Real-time evaluation" refers to the immediate collection and analysis of user feedback and emotional responses during or immediately after video viewing.

[0508] "Improving the generative model and emotion recognition engine" means improving the performance of the model and engine based on the collected feedback data, thereby increasing the accuracy of future edits.

[0509] This invention is a system that enables automated video editing based on individual editing styles and emotional tones by utilizing a user's past video editing history and emotional responses. The concepts, hardware, and software necessary for carrying out the invention are described below.

[0510] First, users upload their past video editing projects to the server using their device. This allows past editing styles and patterns to be stored in a database. The device used here can be a general computer or smartphone, as long as it is capable of managing and transferring video data.

[0511] The server constructs a generative AI model based on accumulated editing history and emotional response data. Specifically, it utilizes machine learning techniques such as neural networks to design a unique generative model that reflects the user's editing preferences. At this time, it uses video analysis tools such as "FFmpeg" and "OpenCV" to analyze the editing history in detail.

[0512] When a user uploads new video content from their device, the server automatically edits it using a generative model. This editing includes automatic placement of editing elements and adjustment of emotional tone. The server utilizes the Adobe Premiere Pro API and other automated video editing scripts to apply edits that match the user's individual emotional style.

[0513] For example, if a user wants to create a video with an emotionally moving story, they can refer to past editing patterns and emotional data to optimally place music and visual effects that emphasize emotional impact. This makes it possible to create videos that have a strong emotional impact on viewers.

[0514] An example of a prompt message could be input to the generating AI model: "Consider the editing style of the emotionally moving videos the user has created in the past, and provide editing instructions to apply to the new video."

[0515] This invention allows users to efficiently edit videos in line with their emotional intentions without requiring advanced technical skills or editing knowledge. Through the collaboration between the server and the terminal, the accuracy of the model will be continuously improved based on feedback, which is expected to further enhance the performance of automatic editing.

[0516] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0517] Step 1:

[0518] The user uploads previously created video editing projects from their device to the server. In this process, the device prepares the video data and sends it to the server using a file transfer protocol. The input is the video editing history, and the output is the edited project file stored on the server.

[0519] Step 2:

[0520] The server analyzes the received video editing history. This analysis includes extracting text, sound patterns, sound effect timing, and visual effect usage from the video. Tools such as "FFmpeg" and "OpenCV" are used in this process. The input is the video editing history, and the output is editing pattern data based on the analysis results.

[0521] Step 3:

[0522] The server builds a generative AI model based on the analysis results. This involves a process of training the model using machine learning algorithms to reflect the user's editing style and emotional tone. The input is editing pattern data, and the output is an individual generative model.

[0523] Step 4:

[0524] The user uploads new, unedited video content from their device to the server. The device transfers the video file to the server and prepares it for processing. The input is the new video content, and the output is the unedited video file on the server.

[0525] Step 5:

[0526] The server automatically edits new videos using a generative AI model. The editing process places text overlays, music, sound effects, and visual effects in appropriate locations within the video to create footage that matches the user's emotional preferences. This operation utilizes tools such as the Adobe Premiere Pro API. Input is an unedited video file and the generative model, while output is an edited video.

[0527] Step 6:

[0528] The server sends the edited video to the user. The user plays this video on their device and reviews its content. The input is the edited video, and the output is the user's rating and feedback.

[0529] Step 7:

[0530] The user sends feedback from their device to the server. The server analyzes the feedback and uses it to improve the model. This includes collected real-time sentiment response data. The input is user feedback and sentiment response data, and the output is the improved generative AI model.

[0531] (Application Example 2)

[0532] Next, we will explain application example 2. In the following explanation, 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."

[0533] In modern content distribution services, a challenge is that video content must cater to viewers' emotional preferences in order to maintain their interest. Traditional video editing techniques struggle to capture the diverse emotional responses of viewers, creating a need for a system that delivers videos efficiently and emotionally compelling. Furthermore, the lack of automated editing techniques that can easily apply editing styles optimized for individual users is also a significant challenge.

[0534] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0535] This invention includes a server that includes means for constructing a generative AI model that learns editing patterns based on the user's video production history and emotional responses; means for analyzing unedited video material received from the user and automatically placing editing elements according to the emotional tone; and means for automatically performing video editing according to the user's style and emotional preferences using the generative AI model. This makes it possible to efficiently provide emotionally optimized video content.

[0536] "User" refers to an individual or legal entity that uses this system to edit video content.

[0537] "Video production history" refers to the record and content of video projects that a user has edited in the past.

[0538] "Emotional response" refers to changes in the feelings or sensations that a user or viewer exhibits in response to video content.

[0539] A "generative AI model" refers to an algorithm that learns a user's editing patterns and emotional tendencies, and then automatically edits videos based on that information.

[0540] "Editing patterns" refer to the tendencies in video editing techniques and styles that a user has used in the past.

[0541] "Unedited video footage" refers to raw video data created by a user that has not yet been edited.

[0542] "Emotional tone" refers to the emotions and atmosphere that should be conveyed to the viewer throughout the entire video.

[0543] "Editing elements" refer to components used in video editing, such as subtitles, music, sound effects, and visual effects.

[0544] To implement this invention, the following system is required: The server collects the user's video production history and emotional response data, and builds a generative AI model based on this data. Machine learning libraries using Python (e.g., TensorFlow or PyTorch) are suitable for use in this process. The server uses this model to analyze the unedited video material received from the user and automatically applies edits according to the emotional tone. Specifically, it places text overlays, music, sound effects, and visual effects in appropriate positions.

[0545] The device (e.g., PC or smartphone) provides an interface for users to upload new video footage. This interface is typically developed using JavaScript or React and is required to be user-friendly. Users review the edited video on this device and provide feedback on whether it matches their intentions.

[0546] The server then receives this feedback and uses it to improve the generative AI model and emotion engine. Here, a database (e.g., PostgreSQL or MySQL) is used to manage the feedback and continuously improve the machine learning model.

[0547] For example, a user might create a fun video themed around a family holiday. In this case, the system will appropriately place cheerful music and fun sound effects. It will also enhance the emotional tone by selecting bright and colorful visual effects.

[0548] Examples of prompts to input into a generative AI model include: "This video is themed around a family picnic. Please edit it in a tone that makes viewers feel happy and joyful." Implementing these specifics makes it easier to edit videos to best suit the user's emotional tendencies.

[0549] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0550] Step 1:

[0551] The server collects the user's video production history and past emotional response data. This data is retrieved from a database stored on the server. Specifically, it extracts records of videos the user has edited so far and the results of emotional analysis obtained from the emotion engine.

[0552] Step 2:

[0553] The server builds a generative AI model based on the collected data. Here, a Python machine learning library (e.g., TensorFlow) is used to train a model that learns user-specific editing patterns and sentiment tendencies. In this step, data preprocessing such as normalization and label encoding is performed to ensure the model learns accurately.

[0554] Step 3:

[0555] Users upload unedited video footage to the server via their device. The device interface is designed to allow users to easily provide footage to the server by offering drag-and-drop and file selection windows.

[0556] Step 4:

[0557] The server analyzes the received video footage and automatically places editing elements based on the emotional tone. The video content is processed using a generative AI model as input, and appropriate music, sound effects, subtitles, and visual effects are selected and edited. Specifically, editing is performed using video processing libraries such as MoviePy.

[0558] Step 5:

[0559] The edited video is sent from the server to the user's device. The user reviews the edited video and evaluates whether the emotional tone and content meet their expectations. This feedback is displayed on the device in real time and can be easily provided through user interaction.

[0560] Step 6:

[0561] The server analyzes user feedback and uses it to improve the generative AI model and emotion engine. During this process, feedback data is stored in a database and incorporated into subsequent model training. This enables more accurate video editing tailored to user needs.

[0562] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0563] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0564] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0565] [Fourth Embodiment]

[0566] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0567] As shown in Figure 7, the 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.

[0568] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0569] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0570] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0571] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0572] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0573] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0574] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0575] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0576] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0577] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0578] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0579] This invention provides an advanced automated editing system to streamline users' video editing tasks. This system is implemented through interaction between a server, a terminal, and the user. Its embodiments are described in detail below.

[0580] First, the user provides the server with a dataset containing video projects they have edited themselves. This includes video files, editing project settings, text overlay placement, and sound effect timing. The server analyzes this dataset and builds a generative model to learn editing characteristics. This generative model extracts user-specific editing styles and patterns from the data and automates editing tasks based on them.

[0581] Next, the user uploads newly shot, unedited video content from their device to the server. The server receives the uploaded footage and performs automated editing using a trained generative model. This process analyzes scenes within the video, inserting text overlays at optimal timings and placing music and sound effects in appropriate locations. This allows complex editing tasks that were previously done manually to be completed quickly and efficiently.

[0582] Once automated editing is complete, the server sends the edited video back to the user's device. The user reviews the video and evaluates whether they are satisfied with the editing. This evaluation and feedback are sent back to the server and used to improve the generative model. By receiving feedback, the model can better reflect the user's intentions in its editing style.

[0583] For example, in the case of a user who produces cooking videos, the system can learn specific background music and text overlay styles used in past videos and automatically apply them to newly filmed videos. Furthermore, for urgent videos such as breaking news, the system can highlight important parts of the footage and perform timely editing.

[0584] In this way, the present invention provides a practical solution for efficiently producing video content while significantly reducing the effort required from the user.

[0585] The following describes the processing flow.

[0586] Step 1:

[0587] The server collects video editing data previously saved by users. This data includes edited video files, timing information for text overlays and sound effects, music clips used, and applied visual effects.

[0588] Step 2:

[0589] The server begins training a generative model using the collected data. This process involves analyzing the data to capture the features of editing patterns and feeding this information back into the model for pattern recognition. Furthermore, feature extraction and data preprocessing are performed to train the model.

[0590] Step 3:

[0591] The user uploads newly filmed, unedited video content from their device to the server. The device displays the progress until the upload is complete, performs error checks, and notifies the user when it is finished.

[0592] Step 4:

[0593] The server inputs the received video into a generative model and begins automatically applying editing elements. This process analyzes scenes within the video and, based on that analysis, automatically inserts text overlays and places music and sound effects. This makes the editing process much more efficient.

[0594] Step 5:

[0595] The server sends the edited video to the user. The user reviews the video and evaluates whether there are any problems with the editing quality or applied style. If necessary, they submit feedback via a form requesting corrections or further editing.

[0596] Step 6:

[0597] The server receives feedback from users and implements a process to improve the generative model. This allows the model to continuously learn editing patterns that match the user's intentions, thereby improving the accuracy of subsequent automated edits.

[0598] (Example 1)

[0599] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0600] Traditional video editing processes require considerable time and effort, and maintaining consistent quality according to the user's editing style is challenging. In particular, urgent video information requires immediate attention, demanding rapid and accurate editing capabilities. This invention aims to solve these problems by automatically learning the user's editing style and enabling rapid video editing.

[0601] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0602] In this invention, the server includes means for constructing a generative AI model that learns editing styles based on the user's video editing history, means for analyzing unedited video information provided by the user and automatically applying editing elements, and means for automatically performing video editing according to the user's specific style using the generative AI model. This significantly reduces the user's workload and enables efficient and high-quality video editing.

[0603] "User" refers to an entity that provides video information using a video editing system and receives the edited results.

[0604] "Video editing history" refers to the record and content of video editing performed by the user in the past.

[0605] "Editing style" refers to the unique style or pattern that a user employs in video editing.

[0606] A "generative AI model" is an artificial intelligence model that learns by analyzing a user's editing history and is used to automatically apply the user's unique editing style.

[0607] "Unedited video information" refers to video footage that has not yet been edited after filming.

[0608] "Editing elements" refer to elements added to or adjusted in video editing, such as text overlays, music, sound effects, and cut points.

[0609] "Opinions" refers to evaluations and feedback provided by users regarding the editing results.

[0610] This invention provides a system for streamlining video editing and automating user-specific editing styles. This system is implemented through a configuration including a server, terminals, and a generative AI model.

[0611] The server first receives the user's video editing history and builds a generative AI model based on that data. The generative AI model uses machine learning algorithms to learn the user's editing style and define the patterns necessary for future automated editing. The server is equipped with a high-performance processor and large memory capacity, which supports data analysis and model building.

[0612] Users upload newly recorded, unedited video footage to the server using their own devices. This requires a stable internet connection and a suitable file transfer application on the user's device. The video can be easily sent to the server via the GUI provided by the device.

[0613] The server receives the uploaded unedited video and performs analysis. This process utilizes a generative AI model, allowing the server to identify cut points and key scenes in the video and automatically apply appropriate editing elements. Specifically, it places subtitles, background music, and sound effects based on past editing styles. This significantly reduces the time-consuming manual work that users would otherwise have to do.

[0614] Once editing is complete, the server sends the results to the user's device, where the user reviews the edits. The user also provides feedback to the server regarding satisfaction levels and areas for improvement. Based on this feedback, the server continuously improves the generated AI model. This cycle allows for the creation of a model that more closely matches the user's editing style.

[0615] As a concrete example, users who produce cooking videos can train the system to learn specific background music and subtitle styles they have used in the past, and automatically apply them to new videos. An example of a prompt message in this case might be, "Please apply the subtitle style of the cooking instructions previously used to this video."

[0616] As described above, this invention reduces the effort required from users and enables efficient and consistent video editing.

[0617] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0618] Step 1:

[0619] Users upload their past video editing projects to the server. This input includes video files, editing settings, text overlay placement, sound effect timing, and more. The server receives this data and performs data analysis. Specifically, it extracts editing features and prepares a dataset to understand the user's editing style. This output serves as foundational data for training a generative AI model.

[0620] Step 2:

[0621] The server uses the dataset obtained in Step 1 to build a generative AI model. Specifically, it uses a machine learning algorithm to input the user's editing patterns into the model. This calculation outputs an AI model that automates the selection of editing elements that are suitable for the user's style.

[0622] Step 3:

[0623] The user uploads newly shot, unedited footage from their device to the server. This is done by selecting the file through the GUI on the device and pressing the send button. This input becomes the basic material for automated editing in the next step.

[0624] Step 4:

[0625] The server analyzes the unedited video uploaded in step 3. It applies a generative AI model and automatically performs video editing. Specifically, the server identifies scenes within the video and places text overlays and background music in optimal positions. This utilizes the aforementioned data processing and AI model. The output is an edited video file.

[0626] Step 5:

[0627] The server sends the edited video back to the user's device. The user reviews the video and provides feedback on the edits. This user feedback is sent to the server as input. This feedback information is used to improve the generative AI model.

[0628] Step 6:

[0629] The server receives feedback and uses it to improve the generative AI model. Specifically, it adjusts the model based on the feedback information so that the next edit can be more tailored to the user's preferences. This output is the updated generative AI model.

[0630] (Application Example 1)

[0631] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0632] Traditional video editing required users to pay meticulous attention to each individual editing project and manually apply detailed editing elements, which was time-consuming and laborious. This made it difficult to efficiently produce high-quality content, and was particularly burdensome for users in situations where rapid editing was required, such as in content distribution services.

[0633] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0634] In this invention, the server includes means for constructing a generative model that learns editing patterns based on the user's video editing history, means for analyzing unedited video content received from the user and automatically applying editing elements, and means for automatically performing video editing according to the user's style using the generative model. This streamlines video editing work, eliminates the time and effort problems faced by the user, and enables the rapid generation of high-quality content.

[0635] A "user" is an individual or group that uses the system to create and edit video content.

[0636] "Video editing history" refers to the history of editing operations performed by the user in past editing projects.

[0637] A "generative model" is an artificial intelligence model that learns specific patterns and styles from data and automatically generates new data based on it.

[0638] "Unedited video content" refers to video data that has been newly filmed by the user and has not been edited.

[0639] "Editing elements" refer to individual editing patterns in video editing, such as text overlays, background music, sound effects, and scene transitions.

[0640] "Automated execution" means that the system autonomously completes the editing task without requiring user intervention.

[0641] This invention is a system that learns a user's unique editing style based on their past video editing history and automatically edits unedited videos using that style. First, the user provides the server with video projects they have edited so far. This includes video files, the placement of text overlays, and the timing of sound effects used. The server analyzes this data and builds a generative model to learn the characteristics of the editing.

[0642] The server creates generative AI models using machine learning frameworks such as TensorFlow and PyTorch. These models automate the user's editing process by applying editing styles learned from past editing data to new videos.

[0643] The user uploads a newly filmed, unedited video from their device to the server. The server receives the uploaded video, applies a generative AI model, and performs automatic editing. After editing is complete, the server sends the edited video to the user's device.

[0644] This system allows users to skip tedious manual editing and generate high-quality videos immediately. Specifically, when a user uploads a video taken during a trip to this system, it automatically edits it based on the editing style of past travel videos, making it ready to share upon returning home. The prompt "Generate the optimal sound effects and text placement for this video project. Consider past editing data and apply editing that aligns with the theme." can be used with the generating AI model. This prompt allows the model to derive an accurate editing style.

[0645] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0646] Step 1:

[0647] Users upload a dataset containing video projects they have edited to the server from their device. Inputs include video files, editing project settings, text overlay placement, and sound effect timing. The server receives this data and formats it into a format suitable for analysis.

[0648] Step 2:

[0649] The server analyzes a formatted dataset and builds a generative AI model to learn user editing patterns. The input is the analyzed editing data, and the server learns from this data to generate a model that extracts user-specific editing styles. The output is a generative AI model that reflects the user's editing patterns.

[0650] Step 3:

[0651] The user uploads newly filmed, unedited video content from their device to the server. The input is an unedited video file. The server receives the video and begins analysis using a generative AI model.

[0652] Step 4:

[0653] The server automatically edits the video by applying a generative AI model. The input for this step is a prompt based on the model's output and an unedited video file, specifically the prompt: "Generate the optimal sound effects and text placement for this video project. Consider past editing data and make edits that are in line with the theme." Following this prompt, the server analyzes the video scenes, sets appropriate text overlays, places sound effects and music, and outputs the edited video.

[0654] Step 5:

[0655] The server sends the edited video to the user's device. The user reviews the video and evaluates the editing results. The input is an automatically edited video, and the output is the user's evaluation and feedback.

[0656] Step 6:

[0657] The server further improves the generative AI model using feedback received from the user. The input is user feedback data, and the server uses this data to update the model so that it can more accurately reflect the editing style. The output is the improved generative AI model.

[0658] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0659] This invention is a system for automating video editing that takes user emotions into account. This system is implemented through the interaction of a server, a terminal, and the user.

[0660] First, the user provides the server with video editing projects they have created in the past. At this stage, the server analyzes the timing of text overlays, music, and sound effects, as well as the use of visual effects, within the video created by the user. In addition, the server uses an emotion engine to recognize and analyze emotional responses from the user's video viewing and editing history. This allows the server to build a generative model that reflects the individual emotional tone of the user's editing style, if any.

[0661] Next, the user uploads new, unedited video content from their device to the server. The server inputs this video content into a generative model and performs automatic editing according to the user's emotional preferences. In this editing process, the emotion engine works in conjunction with the generative model to optimize the emotional tone of the video by placing editing elements such as text overlays, music, sound effects, and visual effects in appropriate positions.

[0662] Once editing is complete, the server sends the edited video to the user. The user reviews the video and evaluates whether the content aligns with the intended emotional tone. The user's feedback and real-time emotional responses are collected on the device and sent to the server. The server uses this feedback to further improve both the generative model and the emotion engine, thereby improving the accuracy of future edits.

[0663] For example, when a user creates a story-driven video, the system takes into account the user's past editing patterns and the emotional tone analyzed by the emotion engine, and appropriately places music and visual effects that emphasize the emotions. This makes it possible to create a stronger emotional impact on the viewer.

[0664] As described above, the present invention enables the efficient and emotionally appealing production of video content by providing editing that takes user emotions into consideration.

[0665] The following describes the processing flow.

[0666] Step 1:

[0667] Users send their past video editing and viewing history from their device to the server. This allows the server to obtain data to analyze the user's unique editing style and emotional preferences.

[0668] Step 2:

[0669] The server analyzes received past editing data to train a generative model. This training process includes the placement of text overlays used by the user, music selection, and sound effect timing. It also utilizes an emotion engine to identify the user's emotional responses from their viewing history and captures emotional tones as data points.

[0670] Step 3:

[0671] The user uploads newly recorded video content from their device to the server. The device monitors the upload progress of the video file and notifies the user when the upload is successful.

[0672] Step 4:

[0673] The server inputs the uploaded video into the generative model and begins automatic editing. The emotion engine determines which emotional tones should be emphasized in the video based on the user's emotional preferences. It then selects appropriate text overlays, music, and sound effects to match the scene and performs overall editing.

[0674] Step 5:

[0675] The edited video is sent from the server to the user's device. The user watches the edited video and evaluates whether the edits align with the expected emotional tone.

[0676] Step 6:

[0677] Users send feedback to the server via their device after viewing, and their emotional responses are analyzed in real time by the emotion engine. The server uses this feedback to update the generative model and emotion engine, aiming to improve editing accuracy and user satisfaction in future edits.

[0678] (Example 2)

[0679] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0680] In video editing, reflecting a user's editing style and emotional elements is a time-consuming and laborious task, especially when dealing with a large amount of video footage. Furthermore, accurately visualizing the user's intended emotional tone and effectively conveying it to the viewer requires advanced knowledge. Moreover, constantly checking whether the editing results have the desired emotional impact is not practical. To address these challenges, there is a need for a more efficient automated editing process that takes into account each user's individual editing style and emotional responses.

[0681] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0682] This invention includes a server that includes means for constructing a generative model that learns individual editing styles and emotional tones based on the user's video editing history and emotional responses; means for analyzing unedited video data received from the user and automatically optimizing the placement of editing elements considering the emotional tone; and means for automatically performing video editing according to the user's editing style and emotional preferences using the generative model. As a result, video editing is performed automatically in accordance with the user's intentions and emotions, enabling the efficient production of high-quality video content.

[0683] "User video editing history" refers to a record of video editing work performed by the user in the past, as well as the patterns of that work, and is data that reflects the user's preferences and style.

[0684] "Emotional response" refers to the emotional changes and evaluations that users exhibit when watching or editing videos, and is data that indicates users' emotional preferences.

[0685] A "generative model" refers to an algorithm or computational model that learns individual editing styles and emotional tones, built based on a user's editing history and emotional responses.

[0686] "Unedited video data" refers to video material that has not yet undergone any editing and is video content that requires further processing.

[0687] "Emotional tone" refers to the emotional atmosphere or impression conveyed to the viewer through visual and auditory elements, and is an element that can be adjusted through video editing.

[0688] "Automatically optimize placement" means that editing elements are automatically placed in the optimal position according to defined criteria or algorithms.

[0689] "Real-time evaluation" refers to the immediate collection and analysis of user feedback and emotional responses during or immediately after video viewing.

[0690] "Improving the generative model and emotion recognition engine" means improving the performance of the model and engine based on the collected feedback data, thereby increasing the accuracy of future edits.

[0691] This invention is a system that enables automated video editing based on individual editing styles and emotional tones by utilizing a user's past video editing history and emotional responses. The concepts, hardware, and software necessary for carrying out the invention are described below.

[0692] First, users upload their past video editing projects to the server using their device. This allows past editing styles and patterns to be stored in a database. The device used here can be a general computer or smartphone, as long as it is capable of managing and transferring video data.

[0693] The server constructs a generative AI model based on accumulated editing history and emotional response data. Specifically, it utilizes machine learning techniques such as neural networks to design a unique generative model that reflects the user's editing preferences. At this time, it uses video analysis tools such as "FFmpeg" and "OpenCV" to analyze the editing history in detail.

[0694] When a user uploads new video content from their device, the server automatically edits it using a generative model. This editing includes automatic placement of editing elements and adjustment of emotional tone. The server utilizes the Adobe Premiere Pro API and other automated video editing scripts to apply edits that match the user's individual emotional style.

[0695] For example, if a user wants to create a video with an emotionally moving story, they can refer to past editing patterns and emotional data to optimally place music and visual effects that emphasize emotional impact. This makes it possible to create videos that have a strong emotional impact on viewers.

[0696] An example of a prompt message could be input to the generating AI model: "Consider the editing style of the emotionally moving videos the user has created in the past, and provide editing instructions to apply to the new video."

[0697] This invention allows users to efficiently edit videos in line with their emotional intentions without requiring advanced technical skills or editing knowledge. Through the collaboration between the server and the terminal, the accuracy of the model will be continuously improved based on feedback, which is expected to further enhance the performance of automatic editing.

[0698] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0699] Step 1:

[0700] The user uploads previously created video editing projects from their device to the server. In this process, the device prepares the video data and sends it to the server using a file transfer protocol. The input is the video editing history, and the output is the edited project file stored on the server.

[0701] Step 2:

[0702] The server analyzes the received video editing history. This analysis includes extracting text, sound patterns, sound effect timing, and visual effect usage from the video. Tools such as "FFmpeg" and "OpenCV" are used in this process. The input is the video editing history, and the output is editing pattern data based on the analysis results.

[0703] Step 3:

[0704] The server builds a generative AI model based on the analysis results. This involves a process of training the model using machine learning algorithms to reflect the user's editing style and emotional tone. The input is editing pattern data, and the output is an individual generative model.

[0705] Step 4:

[0706] The user uploads new, unedited video content from their device to the server. The device transfers the video file to the server and prepares it for processing. The input is the new video content, and the output is the unedited video file on the server.

[0707] Step 5:

[0708] The server automatically edits new videos using a generative AI model. The editing process places text overlays, music, sound effects, and visual effects in appropriate locations within the video to create footage that matches the user's emotional preferences. This operation utilizes tools such as the Adobe Premiere Pro API. Input is an unedited video file and the generative model, while output is an edited video.

[0709] Step 6:

[0710] The server sends the edited video to the user. The user plays this video on their device and reviews its content. The input is the edited video, and the output is the user's rating and feedback.

[0711] Step 7:

[0712] The user sends feedback from their device to the server. The server analyzes the feedback and uses it to improve the model. This includes collected real-time sentiment response data. The input is user feedback and sentiment response data, and the output is the improved generative AI model.

[0713] (Application Example 2)

[0714] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0715] In modern content distribution services, a challenge is that video content must cater to viewers' emotional preferences in order to maintain their interest. Traditional video editing techniques struggle to capture the diverse emotional responses of viewers, creating a need for a system that delivers videos efficiently and emotionally compelling. Furthermore, the lack of automated editing techniques that can easily apply editing styles optimized for individual users is also a significant challenge.

[0716] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0717] This invention includes a server that includes means for constructing a generative AI model that learns editing patterns based on the user's video production history and emotional responses; means for analyzing unedited video material received from the user and automatically placing editing elements according to the emotional tone; and means for automatically performing video editing according to the user's style and emotional preferences using the generative AI model. This makes it possible to efficiently provide emotionally optimized video content.

[0718] "User" refers to an individual or legal entity that uses this system to edit video content.

[0719] "Video production history" refers to the record and content of video projects that a user has edited in the past.

[0720] "Emotional response" refers to changes in the feelings or sensations that a user or viewer exhibits in response to video content.

[0721] A "generative AI model" refers to an algorithm that learns a user's editing patterns and emotional tendencies, and then automatically edits videos based on that information.

[0722] "Editing patterns" refer to the tendencies in video editing techniques and styles that a user has used in the past.

[0723] "Unedited video footage" refers to raw video data created by a user that has not yet been edited.

[0724] "Emotional tone" refers to the emotions and atmosphere that should be conveyed to the viewer throughout the entire video.

[0725] "Editing elements" refer to components used in video editing, such as subtitles, music, sound effects, and visual effects.

[0726] To implement this invention, the following system is required: The server collects the user's video production history and emotional response data, and builds a generative AI model based on this data. Machine learning libraries using Python (e.g., TensorFlow or PyTorch) are suitable for use in this process. The server uses this model to analyze the unedited video material received from the user and automatically applies edits according to the emotional tone. Specifically, it places text overlays, music, sound effects, and visual effects in appropriate positions.

[0727] The device (e.g., PC or smartphone) provides an interface for users to upload new video footage. This interface is typically developed using JavaScript or React and is required to be user-friendly. Users review the edited video on this device and provide feedback on whether it matches their intentions.

[0728] The server then receives this feedback and uses it to improve the generative AI model and emotion engine. Here, a database (e.g., PostgreSQL or MySQL) is used to manage the feedback and continuously improve the machine learning model.

[0729] For example, a user might create a fun video themed around a family holiday. In this case, the system will appropriately place cheerful music and fun sound effects. It will also enhance the emotional tone by selecting bright and colorful visual effects.

[0730] Examples of prompts to input into a generative AI model include: "This video is themed around a family picnic. Please edit it in a tone that makes viewers feel happy and joyful." Implementing these specifics makes it easier to edit videos to best suit the user's emotional tendencies.

[0731] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0732] Step 1:

[0733] The server collects the user's video production history and past emotional response data. This data is retrieved from a database stored on the server. Specifically, it extracts records of videos the user has edited so far and the results of emotional analysis obtained from the emotion engine.

[0734] Step 2:

[0735] The server builds a generative AI model based on the collected data. Here, a Python machine learning library (e.g., TensorFlow) is used to train a model that learns user-specific editing patterns and sentiment tendencies. In this step, data preprocessing such as normalization and label encoding is performed to ensure the model learns accurately.

[0736] Step 3:

[0737] Users upload unedited video footage to the server via their device. The device interface is designed to allow users to easily provide footage to the server by offering drag-and-drop and file selection windows.

[0738] Step 4:

[0739] The server analyzes the received video footage and automatically places editing elements based on the emotional tone. The video content is processed using a generative AI model as input, and appropriate music, sound effects, subtitles, and visual effects are selected and edited. Specifically, editing is performed using video processing libraries such as MoviePy.

[0740] Step 5:

[0741] The edited video is sent from the server to the user's device. The user reviews the edited video and evaluates whether the emotional tone and content meet their expectations. This feedback is displayed on the device in real time and can be easily provided through user interaction.

[0742] Step 6:

[0743] The server analyzes user feedback and uses it to improve the generative AI model and emotion engine. During this process, feedback data is stored in a database and incorporated into subsequent model training. This enables more accurate video editing tailored to user needs.

[0744] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0745] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0746] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0747] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0748] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0749] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0750] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0751] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0752] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0753] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0754] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0755] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0756] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0757] 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.

[0758] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0759] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0760] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0761] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0762] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0763] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0764] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0765] The following is further disclosed regarding the embodiments described above.

[0766] (Claim 1)

[0767] A means for constructing a generative model that learns editing patterns based on the user's video editing history,

[0768] A means of analyzing unedited video content received from a user and automatically applying editing elements,

[0769] A method for automatically performing video editing according to the user's style using a generative model,

[0770] A means of presenting the editing results to the user and receiving feedback,

[0771] A means of improving the generative model based on the feedback received,

[0772] A system that includes this.

[0773] (Claim 2)

[0774] Based on learned editing patterns, the system automates the placement of text overlays, music, and sound effects.

[0775] The system according to claim 1.

[0776] (Claim 3)

[0777] When video content includes a news flash format, applying news flash-specific editing techniques can enhance the urgency and visual impact of the footage.

[0778] The system according to claim 1.

[0779] "Example 1"

[0780] (Claim 1)

[0781] A means for constructing a generative AI model that learns editing styles based on the user's video editing history,

[0782] A means for analyzing unedited video information provided by users and automatically applying editing elements,

[0783] A method for automatically performing video editing according to the user's specific style using a generative AI model,

[0784] A means of presenting the editing results to users and receiving their feedback,

[0785] A means of improving the generative AI model based on the feedback received,

[0786] A means that allows users to provide data via an interface and verify the edited content,

[0787] A system that includes this.

[0788] (Claim 2)

[0789] Based on learned editing patterns, the placement of subtitles, music, and sound effects is automated, improving efficiency.

[0790] The system according to claim 1.

[0791] (Claim 3)

[0792] When video information includes breaking news format, applying editing techniques specific to breaking news enhances the urgency and visual impact of the footage.

[0793] The system according to claim 1.

[0794] "Application Example 1"

[0795] (Claim 1)

[0796] A means for constructing a generative model that learns editing patterns based on the user's video editing history,

[0797] A means of analyzing unedited video content received from a user and automatically applying editing elements,

[0798] A method for automatically performing video editing according to the user's style using a generative model,

[0799] A means of providing automatically edited video to users via communication functions,

[0800] A means of receiving confirmation and evaluation from users and collecting feedback on the editing results,

[0801] Based on the feedback received, we will improve the generative model and enhance the accuracy of the editing style.

[0802] A system that includes this.

[0803] (Claim 2)

[0804] Based on learned editing patterns, the system automates the insertion of background music, placement of subtitles, and addition of sound effects according to the theme and situation.

[0805] The system according to claim 1.

[0806] (Claim 3)

[0807] When video content includes footage of events or tourism, highlighting elements that match the editing style and enhancing the visual appeal will improve the video's appeal.

[0808] The system according to claim 1.

[0809] "Example 2 of combining an emotion engine"

[0810] (Claim 1)

[0811] A means for constructing a generative model that learns individual editing styles and emotional tones based on a user's video editing history and emotional responses,

[0812] A method for analyzing unedited video data received from users and automatically optimizing the placement of editing elements while considering the emotional tone,

[0813] A method for automatically performing video editing according to the user's editing style and emotional preferences using a generative model,

[0814] A means for sending the editing results to the user and collecting real-time evaluation and sentiment response data,

[0815] A means of improving the generative model and emotion recognition engine based on the received feedback and emotion response data,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] Based on learned editing styles and emotional tones, the placement of visual text, sounds, and audio effects is automated to enhance emotional impact.

[0819] The system according to claim 1.

[0820] (Claim 3)

[0821] When video data includes informational news formats, adding a unique style and emotional tone enhances the immediacy and emotional impact of the footage.

[0822] The system according to claim 1.

[0823] "Application example 2 when combining with an emotional engine"

[0824] (Claim 1)

[0825] A means for constructing a generative AI model that learns editing patterns based on the user's video production history and emotional reactions,

[0826] A method for analyzing unedited video footage received from users and automatically placing editing elements according to the emotional tone,

[0827] A method for automatically performing video editing according to the user's style and emotional preferences using a generative AI model,

[0828] A means of presenting the edited results to the user and collecting emotional reactions as feedback,

[0829] A means of improving the generative AI model and sentiment analysis engine based on the feedback received,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] Automate the placement of subtitles, music, and sound effects based on learned editing patterns and emotional tones.

[0833] The system according to claim 1.

[0834] (Claim 3)

[0835] When video footage contains information dissemination methods, editing tailored to the specific information presented can enhance the urgency and emotional impact of the video.

[0836] The system according to claim 1. [Explanation of Symbols]

[0837] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for constructing a generative model that learns editing patterns based on the user's video editing history, A means of analyzing unedited video content received from a user and automatically applying editing elements, A method for automatically performing video editing according to the user's style using a generative model, A means of presenting the editing results to the user and receiving feedback, A means of improving the generative model based on the feedback received, A system that includes this.

2. Based on learned editing patterns, the system automates the placement of text overlays, music, and sound effects. The system according to claim 1.

3. When video content includes a news flash format, applying news flash-specific editing techniques can enhance the urgency and visual impact of the footage. The system according to claim 1.

Images