KR20240018296A - System for providing non-fungible token issuing service using video stillcut - Google Patents

Abstract

A system for providing an NFT automatic creation service using video still cuts is provided, and a user terminal and video that selects at least one still cut with at least one unique identification code and acquires an NFT issued based on at least one still cut. A generating unit that generates at least one frame forming at least one still cut, an identification unit that identifies the at least one still cut by assigning at least one unique identification code, and an NFT for at least one still cut selected in the user terminal. It includes a creation service providing server that includes an issuing unit that issues an NFT, and a delivery unit that delivers the amount to the electronic wallet address of the user terminal when the user terminal pays the amount corresponding to the NFT.

Description

NFG creation service provision system using video still cuts {SYSTEM FOR PROVIDING NON-FUNGIBLE TOKEN ISSUING SERVICE USING VIDEO STILLCUT}

The present invention relates to a system for providing an NFT automatic creation service using video still cuts, and provides a platform that allows users to designate still cuts in a video and then automatically issue and trade NFTs based on the designated still cuts.

The environment for using media content is rapidly changing due to the convergence of broadcasting and communications as media technology develops. The spread of media devices has enabled active use of content centered on each user's tastes and choices, and the traditional media content industry structure, which was produced and distributed mainly by professional producers and production companies, has allowed anyone to create and share content freely and freely. It was changed to an open structure. As media technology and industry develop, the global media content market and users are entering an era of transformation, and at the center of this is the online video platform. Media service users are using new media platforms to satisfy diversified individual needs and share interpersonal connections.

At this time, a platform for creating stillcut frames from videos or trading copyrighted works as NFTs was researched and developed. In relation to this, the prior art, Korea Patent Publication No. 2009-0015323 (published on February 12, 2009) and Korea Patent Publication No. Registered Patent No. 10-2388581 (announced on April 21, 2022) requires capturing a still image that is closest to the image the user wants to capture in the continuous video, in order to create a still cut frame from a continuously displayed video. , when a still cut command signal is input, the video frame is confirmed and the confirmed video frame is stored, and when trading a copyrighted work with an NFT, deep learning is applied to the image for which the NFT has been issued to match the previously stored copyrighted work. Each configuration is disclosed to confirm whether it is a counterfeit or illegal copy by determining the degree of similarity.

However, in the former case, the concern that the still cut may be crushed when captured is only confirmed and saved through the user's manual confirmation, and in the latter case, it is checked whether the work is the true copyright holder's work through comparison with the already registered work. It is only a composition that understands the back, and is not a composition that uses still cuts. Recently, there are many fan art contents that create secondary works such as posting still cuts from movies, YouTube, music videos, etc. through blogs or social media, and writing reviews or introductions. When capturing, the fan art content is used. Because people want to capture the moment they want, it takes effort from the user to capture the moment well, and movies and dramas become more popular through marketing using these still cuts. Accordingly, research and development of a platform that allows users to create and trade NFTs by directly selecting still cuts within a video is required.

One embodiment of the present invention allows users to directly select still cuts in videos including movies, dramas, advertisements, concerts, music videos, and sports broadcasts and convert them into NFTs, at least one frame forming the video. At least one unique identification code is mapped and stored, an NFT is issued based on the still cut selected on the user terminal, and a deep learning algorithm determines whether the still cut is the same as the pre-selected still cut, and is used for promotional purposes of the video. By allowing new values to be added to the tens of thousands of still cuts that are lost once the screening or broadcast ends, additional profits can be provided to production companies and artists, and users can hold NFTs that can be converted into assets while satisfying fan sentiment. It is possible to provide a system for providing an NFT automatic creation service using video still cuts. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, one embodiment of the present invention selects at least one still cut to which at least one unique identification code is assigned and acquires an NFT issued based on the at least one still cut. a user terminal and a generating unit that generates at least one frame constituting the video as at least one still cut, an identification unit that identifies the at least one still cut by assigning at least one unique identification code, and at least one selected by the user terminal. It includes a creation service providing server that includes an issuing unit that issues NFTs for still cuts, and a delivery unit that delivers the amount to the electronic wallet address of the user terminal when paying the amount corresponding to the NFT at the user terminal.

According to any one of the means for solving the problem of the present invention described above, when a user directly selects a still cut in a video including a movie, drama, advertisement, concert, music video, or sports broadcast, it can be automatically converted into NFT. At least one unique identification code is mapped and stored to at least one frame that makes up the video, and an NFT is automatically issued based on the still cut selected on the user terminal, but the still cut is the same as the still cut preempted by the deep learning algorithm. By determining whether people are aware of the video, using it for promotional purposes, and adding new value to the tens of thousands of still cuts that are lost once the screening or broadcast ends, additional profits can be generated for production companies and artists, and users can become fans. You can hold NFTs that can be capitalized while satisfying your Sim.

Figure 1 is a diagram for explaining a system for providing an NFT automatic creation service using video still cuts according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a creation service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment in which an NFT automatic creation service using video still cuts is implemented according to an embodiment of the present invention.
Figure 5 is an operation flowchart illustrating a method of providing an NFT automatic creation service using video still cuts according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a diagram for explaining a system for providing an NFT automatic creation service using video still cuts according to an embodiment of the present invention. Referring to Figure 1, the NFT automatic creation service providing system 1 using video still cuts may include at least one user terminal 100, a creation service providing server 300, and at least one transaction terminal 400. You can. However, since the NFT automatic generation service providing system 1 using the video still cut of FIG. 1 is only an embodiment of the present invention, the present invention is not limited to the interpretation of FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one user terminal 100 may be connected to the creation service providing server 300 through the network 200. In addition, the creation service providing server 300 may be connected to at least one user terminal 100 and at least one transaction terminal 400 through the network 200. Additionally, at least one transaction terminal 400 may be connected to the creation service providing server 300 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), and Wi-Fi. , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC ( It includes, but is not limited to, Near-Field Communication (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one user terminal 100 selects a still cut in the video using a web page, app page, program, or application related to the NFT automatic creation service using video still cuts, and receives an NFT based on the selected still cut, It may be the terminal of a user purchasing an NFT. The user terminal 100 may be a terminal that sells NFTs to the transaction terminal 400 through the creation service providing server 300 or a preset exchange.

Here, at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The creation service providing server 300 may be a server that provides an NFT automatic creation service web page, app page, program, or application using video still cuts. And, the creation service providing server 300 may be a server that assigns at least one unique identification code to at least one frame in the video. In addition, the creation service providing server 300 selects at least one frame from the user terminal 100 to generate a still cut, and when requesting the issuance of an NFT based on the still cut, the server issues the NFT and receives payment. It can be. In addition, the creation service providing server 300 may be a server that records NFT transactions on the blockchain and mediates NFT transactions between the transaction terminal 400 and the user terminal 100. In addition, the creation service providing server 300 may be a server that determines whether to issue an NFT after comparing the pre-empted still cut with the same or similar still cut for which the user wishes to issue an NFT through deep learning.

Here, the creation service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one transaction terminal 400 may be a terminal that purchases NFTs using a web page, app page, program, or application related to an NFT automatic creation service using video still cuts.

Here, at least one transaction terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one transaction terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one transaction terminal 400 is, for example, a wireless communication device that ensures portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

Figure 2 is a block diagram for explaining the creation service providing server included in the system of Figure 1, and Figures 3 and 4 are implementations of an NFT automatic creation service using video still cuts according to an embodiment of the present invention. This drawing is for explaining an embodiment.

Referring to FIG. 2, the creation service providing server 300 includes a generating unit 310, an identification unit 320, an issuing unit 330, a delivery unit 340, a first-come-first-served basis provision unit 350, and a selection unit 360. ), may include a blockchain unit 370.

The creation service providing server 300 or another server (not shown) operating in conjunction with an embodiment of the present invention uses video still cuts with at least one user terminal 100 and at least one transaction terminal 400. When transmitting an NFT automatic generation service application, program, app page, web page, etc., at least one user terminal 100 and at least one transaction terminal 400 are an NFT automatic generation service application, program using a video still cut. , you can install or open app pages, web pages, etc. Additionally, a service program may be run in at least one user terminal 100 and at least one transaction terminal 400 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone).

Before explaining Figure 2, the basic concept of NFT will be explained below. Things described below are not duplicated in FIG. 2 .

When issuing an NFT for a work of art or digital art, the history of the owner of the digitally expressed work of art can be recorded on the blockchain. NFT art refers to using NFT technology to turn works into digital assets. In general, the original digital work is stored in an off-chain or distributed file system (Inter Planetary File System) outside the blockchain, and NFT contains meta information such as the name of the work, details, contract terms, and link information to access the original. Contains only data. The NFT platform refers to a secondary distribution market that sells NFT art and characters and items represented in NFT. In the case of NFT art, the object of transaction is not the digital work itself, but rather the link to the work is purchased.

Real art, which is a work of art expressed through physical media such as canvas, is valued not only for its value in artistic expression, but also for its scarcity in that the original work is only one in the world. However, because real art is a physical object, there are problems such as physical deterioration over time and limitations in distribution speed and scope. Meanwhile, works of art expressed in digital media (hereinafter referred to as digital art) have no physical deterioration and have a very high distribution potential, but are less rare than real art in that they can be copied. However, NFT art can be said to be a so-called hybrid work of art that combines the scarcity of real art and the distribution of digital art. However, there are still no established opinions or precedents among experts regarding the legal nature of NFT or NFT art, that is, what rights arise for what.

Digital data or content is free, easily replicable, and fungible. NFT uses blockchain technology to artificially create scarcity in replaceable digital information, making it a suitable form for tradability in the market. Unlike books or records that can be replaced, the trade of non-replaceable works of art is bound to be limited in the original-centered market. However, if replaceable books or records are artificially made scarce through NFTs, or if uniqueness or scarcity is given to digital artworks that can be copied infinitely, their value will inevitably rise.

In this way, because NFTs have unique digital data characteristics, NFTs enable ownership of data, or NFT owners can be seen as acquiring ownership or copyright of digital art and digital characters. Transforming offline digital files into NFTs is called minting. Anyone can mint with NFT, but if you mint someone else's copyrighted work, there may be issues with infringement of reproduction rights and transmission rights among copyright property rights. Minting tangible works or real art, such as paintings, sculptures, and prints, and turning them into NFTs can be seen as the act of copying the physical work as a digital image and transmitting it to the platform's website (Internet).

<Derivative works>

Since a digital file is a work protected by copyright law, constructing or implementing it in different dimensions (from 2D to 3D) can be viewed as an act of copying or creating a secondary work depending on whether the process is creative. there is. Additionally, if an NFT produced using another person's work constitutes a secondary work, the copyright is acquired regardless of whether or not it infringes copyright. Although it is difficult to consider providing metadata related to a work to the public as an act of transmission, linking to the work is essential for creating and selling NFTs of other people's works without permission, and the Supreme Court ruled against the act of linking. does not recognize copyright infringement (infringement of transmission rights). Of course, there is a counterargument that the original work cannot be copied within the off-chain NFT, but since minting appears to be impossible without copying the original work, infringement of reproduction rights for minting activities may occur. In addition, the act of minting tangible works such as paintings, sculptures, and prints of third parties, that is, real art, as NFTs as digital twins, the act of minting real art works as NFTs, and the act of minting by licensees of real art works. There are various ways to use NFTs, such as minting public domain work, and depending on the method of use, rights attribution and rights infringement can appear in various ways.

Copyright is a right to expression, or an intangible object, while ownership is a right to a tangible object. First of all, copyright property rights and moral rights are rights to creative expressions called works, that is, to intangible objects without a form, while real art such as paintings and sculptures are tangible objects and are subject to ownership, and their owners exist independently. . Ownership is defined in the Civil Code as the right to freely use, profit, and dispose of the property within the limits of the law (Article 206 of the Civil Code), and is protected as an absolute right that can be exercised against a third party without a contractual relationship. Considering the nature of such ownership, the Copyright Act has provisions for adjusting these rights in situations where the copyright and ownership of artistic works may conflict.

<Resale rights>

The existence of resale rights, which are not yet recognized under Korean copyright law, is also important. Artist Resale Right (also known as Artist Resale Right) is the right for artists to claim a certain percentage of the sales revenue when an artwork is resold, and is being introduced in over 80 countries, including the European Union (EU). The right to resell is an important right from the perspective of establishing a fair compensation system in the field of art creation. In Korea, it is not yet recognized as a legal right due to technical difficulties in tracking art transactions. However, since transaction tracking is possible through blockchain technology, the basis of NFT, it is technically possible to create resale rights or similar structures, which can be one of the great attractions of creating NFT art for artists.

<Rights Exhaustion Theory>

There is a need to apply the exhaustion of distribution rights applied to transactions of tangible media such as books or albums to digital assets to which NFTs are applied. The theory of exhaustion of rights is a theory that once a copyright holder sells a copyrighted work, he or she cannot claim his/her distribution rights for future distribution or distribution of the copied work. According to this theory, when a copyright holder first sells a copy of a work and receives compensation for it, the copyright holder's right to control the disposition of the copy is terminated. Through the application of this theory of exhaustion of rights, the person who first sold the copy and acquired ownership of the copy can fully exercise the copyright holder's rights to the copy. Therefore, conversely, in the case of a copyright holder, the author's right to control further sales of the copy is suspended. This is because allowing the author to control further sales would significantly limit the distribution of these copyrights.

In addition, this is to prevent the copyright holder from continuing to unfairly infringe on private property rights, such as the right to transfer and trade, even if such transfer has already occurred and ownership has already been transferred. If there are no restrictions on copyright under the exhaustion of rights theory, those who own copies of the work will not be able to display or sell the copies without the consent of the copyright holder. Through this theory of exhaustion of rights, it also serves to provide opportunities for ordinary people who do not have the means or opportunity to purchase copies of works directly from the copyright holder to purchase copies. The principle of exhaustion of rights applies when permanent control is transferred through the transmission of copies of works through traditional media, but the principle of exhaustion of rights applies to online provision of services that do not transmit or provide digital copies to users on a permanent basis. It doesn't work. However, since the uniqueness of secondary transactions and distribution of NFTs, which are digital assets, is maintained, it is necessary to acknowledge the exhaustion of digital rights.

<Responsibility and liability of NFT platform operators>

The person primarily responsible for posts that infringe copyright on the Internet is the person who posted the post. Even if the above posting was posted on an Internet posting space provided by an online service provider (hereinafter referred to as OSP) that operates an Internet portal site, and Internet users can easily find the posting through the search function, the copyright is immediately transferred to OSP for that reason alone. Tort liability for infringement cannot be assumed. If copyright infringement art is posted on an NFT art platform, it is necessary to review whether the above OSP liability and immunity legal principles can be applied to the platform. NFT trading can be said to be a transaction of metadata records that prove the work rather than a transaction of the work itself, and since it is conducted as a decentralized service, it is difficult to view it as a storage service that allows data to be stored on a server and used, but metadata NFT art content Since it is stored on the platform company's server and posted to members, it may be judged as an OSP that provides storage services in a centralized manner within this scope.

Accordingly, in one embodiment of the present invention, each user creates a still cut of the video and issues an NFT for it, so that a marketing effect can occur naturally like a trend like a meme, and each fan can create a still cut of the video. It allows you to have still cuts of your favorite celebrities, famous people, or videos you like, while also making them available as assets. This is subject to licensing through consultation and agreement with the original copyright holder of the video.

Referring to FIG. 2, the generator 310 may generate at least one frame of a video as at least one still cut. At this time, after attaching a unique identification code to at least one frame, it is also possible to attach a unique identification code of another system to a still cut made by gathering at least one frame. For example, if 1 frame is 1 still cut, it is possible to use the same unique identification code, but if 1 to N frames are gathered together to create 1 still cut, a new unique identification code system may be needed. Accordingly, the identification unit 320 can identify at least one still cut by assigning at least one unique identification code. At this time, frames selected by others may be marked with an X so that they are deactivated and not displayed. In other words, whether selection is possible can be displayed.

The issuing unit 330 may issue an NFT for at least one still cut selected by the user terminal 100. The user terminal 100 may select at least one still cut to which at least one unique identification code is assigned and obtain an NFT issued based on the at least one still cut. At this time, when uploading at least one frame, a method of converting the impact of each section into a score by analyzing the multimodal information of the video and extracting the section with the highest score can be used. This allows users to create still cuts more easily. For example, assuming it's a 2-hour movie, you don't have to watch all 2 hours to get the still cuts you want, but the system automatically selects only the most impactful parts in advance, making it easier to choose. Of course, the impactful part may not be what the user wants, but it can be used as a useful tool for users who want the impactful part.

The scores extracted from multimodal information are as follows. First, through audio analysis, unusual sounds such as high-pitched voices and sound effects are found and the sound score for each section is measured. Second, through image analysis, a close-up score is calculated based on the degree of close-up of the subject for each video section. Lastly, the voice in the sound is converted into text through speech recognition (Speech To Text), and the positive score is measured by measuring positivity through text emotion analysis. Based on the three derived scores, major sections of the video can be finally selected and summarized.

<Generation of sound source separation model for specific sound extraction>

The video contains various sounds such as background music and event sound effects. In this way, the decibel level of variously recognized unique sounds is measured and used as a sound score. In one embodiment of the present invention, only unique sounds are separated from input audio using Wave-U-Net. Wave-U-Net is an end-to-end audio source separation model that showed good performance in the audio signal separation competition.

Wave-U-Net is a model that applies the U-Net structure to the time domain and proposes the use of linear interpolation to prevent audio artifacts that occur during upsampling. In this case, audio artifacts refer to unwanted audio such as noise, buzz, and electrical noise. You can separate only the desired audio from the audio input through Wave-U-Net. When original audio is input, only unusual sounds can be separated from normal sounds by Wave-U-Net, and scores are calculated for the separated unique sounds. To calculate the sound score, singular sounds are separated into regular intervals. Then, after measuring the decibel of the audio for each section, the sound score is calculated according to the size.

<Selection of major sections>

All multimodal scores extracted through the above-described process are normalized to a value between 0 and 1 and added to calculate the final score for selecting the target section. When selecting key sections, each score can be weighted differently and added up so that sections are selected differently depending on the editor's intention and the purpose of the summary. By adjusting the weight of each score according to the editor's summary intention, it is possible to create a summary video focusing on specific multimodal information, and by providing frames that make up the impactful part of the video rather than mechanical frame extraction, ordinary users can It can help you figure out which parts were impactful even without watching the video.

The transmission unit 340 may transmit the amount corresponding to the NFT to the electronic wallet address of the user terminal 100 when the user terminal 100 pays the amount corresponding to the NFT. When uploading at least one still cut, the first-come-first-served basis provision unit 350 may provide at least one still cut that has not been preempted along with a unique identification code.

When uploading at least one still cut by mapping it to a unique identification code, the selection unit 360 can distinguish between still cuts that have been preempted and still cuts that have not been preempted using a pre-built deep learning algorithm and allow upload. . For example, if a video of a person walking one step is expressed as a frame, it can be expressed as hundreds to tens of thousands of frames, like in the animation production process. Among these, it is up to the user to choose from frames N to N+M. At this time, let us assume that the user selects a still cut called A by selecting frames N to N+M. At this time, assuming that user B has selected still cuts from frame N+M+1 to frame N+M+Z, since user B has selected frames N+M+1, the still cuts of user A who selected frame N+M and They may be similar or identical, but if there are various facial expressions or movements even at the moment, the still cuts may come out differently.

Accordingly, a unique identification code is assigned to all frames, but the similarity is determined through deep learning rather than comparing frames and still cuts using the unique identification code. Deep learning can be used to determine pixel units, and it can be used to determine whether they are similar and identical or completely different still cuts by tracking the skeleton of an object. Assuming you are capturing a scene of a celebrity dancing, what you capture at second A and what you capture at second A+1 may be similar, but they may also be very different, and depending on how you capture them, you can end up with a popular meme that is reproduced as a meme. Whether it can be, or whether it can become a bizarre photo that will be floating around the Internet for the rest of its life can arise from the difference of a moment. In summary, a still cut including N+M and a still cut including N+M+1 may be the same, but may be completely different, so deep learning, which analyzes images based on the image rather than the unique identification code described above, is used. It is required.

At this time, the previously constructed deep learning algorithm may be an algorithm that automatically edits at least one still cut in the video. For example, by automatically extracting the impactful part in a multi-modal manner and uploading it as a still cut candidate frame, or when a still cut of a new user terminal 100 is input, the still cut that has been pre-empted, that is, issued as an NFT It could be two hybrid deep learning models that check for similarity to the cut. At this time, in the latter case, it is possible to use YOLO (You Only Look Once) to compare objects by grid rather than pixel by using YOLO (You Only Look Once), which compares each object. Deep learning algorithms can also be used based on SLIC.

<SLIC Super Pixel Algorithm>

Superpixel is one of the methods frequently used in the field of image segmentation and object tracking, so it is an algorithm that divides the image using each method from the input image. The superpixel algorithm used in one embodiment of the present invention may use the Simple Linear Iterative Clustering (SLIC) algorithm. Because the SLIC algorithm performs clustering using only information within a certain area rather than using all cluster information, SLIC is known to be fast among superpixel algorithms. The SLIC algorithm is carried out in the LAB color space with color values specified by the CIE (International Commission on Illumination). It uses color and distance information between pixels and clusters to cluster all pixels in the image into k superpixels. Proceed with .

In particular, because the SLIC algorithm maintains the homogeneity of the input image and processes pixel-level operations in groups, superpixel segmentation can be performed using the SLIC algorithm to determine whether still cuts A and B still cuts are different. The deep learning model used in one embodiment of the present invention can perform classification using a deep learning model based on the Inception module, which is one of the models that achieved good results in ImageNet among CNN models specialized in image analysis. In order to effectively extract image features, the Inception module creates one module consisting of convolution and Max Pooling, and can be connected to 9 modules to form one CNN model. As a result, this model is designed to enable learning while solving the above problems by efficiently reducing the overfitting problem caused by deeply stacked networks, which is a unique problem of deep learning, and the increasing amount of computation.

When an NFT is issued, the blockchain unit 370 creates a block on the blockchain, inputs and stores the information of the NFT, and stores at least one still cut represented by the NFT in the InterPlanetary File System (IPFS). . When an NFT is issued, the blockchain unit 370 ensures that the smart contract for the NFT transaction is recorded in the blockchain, and the content resource that is the basis of the NFT can be stored in the InterPlanetary File System (IPFS). The reason is that large files cannot be uploaded to the blockchain, and even if uploaded, the gas fee is very expensive. Therefore, large files that cannot be uploaded to the blockchain are distributedly stored in IPFS and only the CID value, which is the main value where the file is stored, is uploaded to the blockchain, thereby reducing server and database operating costs and making data forgery and falsification impossible, creating a reliable decentralized app (dApp). can be implemented.

At this time, the blockchain unit 370 can use IPFS to distribute and store content resources after applying asymmetric encryption. To issue NFTs, transactions are created and transmitted to the blockchain network through a dApp (Decentralized Application) connected to Hyperledger Fabric, and after uploading content through IPFS (Inter Planet File System), a hash (hash) is used to download the content. Hash) value can be returned and passed to Hyperledger Fabric to record the content on the blockchain. At this time, the blockchain may be a private blockchain such as Hyperledger Fabric or a permissioned blockchain. Permissioned blockchains use contracts called smart contracts to process and conduct transactions. A smart contract is a program that can be developed in a programming language, and the functions that process the contract are written as functions.

In the implementation of blockchain, smart contract is one of the key concepts along with ledger. Therefore, a method is needed to support the management and optimization of smart contracts in permissioned blockchain platforms. In one embodiment of the present invention, a smart contract management method that sets priorities and sorts functions based on the execution time and importance of functions can be used as a way to effectively manage smart contracts. An embodiment of the present invention can be used to improve the performance of transaction verification and assurance stages as well as smart contract management in a permissioned blockchain platform.

In addition, one embodiment of the present invention can further utilize an automatic income settlement system. The automatic profit settlement department (not shown) can settle profits with at least one subject who participated in the production of the video. In other words, when uploading a video, a video content provider, an artist, a copyright holder, a celebrity, or a platform operator, etc. can sign a contract with the provider or artist through an electronic contract, post the video based on this, and settle the profits generated.

Hereinafter, the operation process according to the configuration of the generation service providing server of FIG. 2 described above will be described in detail using FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to FIG. 3, (a) the creation service providing server 300 assigns a unique identification code to at least one still cut corresponding to at least one frame constituting the video, and at least one selected by the user terminal 100 NFTs can be issued based on still cuts. The creation service providing server 300 may be a server that excludes pre-selected still cuts and issues NFTs using the remaining still cuts in the user terminal 100. In addition, before issuing an NFT on the user terminal 100 using a deep learning-based algorithm, it is checked whether the still cut selected on the user terminal 100 is the same or similar to the pre-selected still cut to prevent duplicate works. It may be a server being reviewed. As in (b), the creation service providing server 300 may be a server that allows the NFT of the user terminal 100 to be transferred to the transaction terminal 400, and as in (c), when the NFT is issued, it is registered in the blockchain. Therefore, it may be a server that records NFT metadata. In summary, it may be the same as Figure 4, but it is not limited to this.

Matters that are not explained regarding the method of providing an NFT automatic generation service using video still cuts of Figures 2 to 4 are the same as those previously described regarding the method of providing an NFT automatic generation service using video still cuts through Figure 1. Since it can be easily inferred from the explained contents, the description below will be omitted.

Figure 5 is a diagram showing the process of transmitting and receiving data between each component included in the NFT automatic creation service providing system using the video still cut of Figure 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to FIG. 5, the creation service providing server generates at least one frame constituting the video as at least one still cut (S5100) and identifies the at least one still cut by assigning at least one unique identification code (S5100). S5200).

In addition, the creation service providing server issues an NFT for at least one still cut selected by the user terminal (S5300), and delivers it to the electronic wallet address of the user terminal when the user terminal pays the amount corresponding to the NFT (S5400) ).

The sequence between the above-described steps (S5100 to S5400) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5400) may change, and some of the steps may be executed simultaneously or deleted.

Matters that are not explained regarding the method of providing an NFT automatic generation service using video still cuts of Figure 5 are the same as those previously described regarding the method of providing an NFT automatic generation service using video still cuts through Figures 1 to 4. Since it can be easily inferred from the explained contents, the description below will be omitted.

The method of providing an NFT automatic creation service using video still cuts according to an embodiment described in Figure 5 is also in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. It can be implemented. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing an NFT automatic creation service using a video still cut according to an embodiment of the present invention described above is an application installed by default in the terminal (this may include programs included in the platform or operating system, etc., installed by default in the terminal). It may be executed by, and may also be executed by an application (i.e. program) installed by the user directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing an NFT automatic creation service using video still cuts according to an embodiment of the present invention described above is implemented as an application (i.e., program) installed by default in the terminal or directly installed by the user, and is implemented as an application (i.e., program) installed by default in the terminal, etc. It may be recorded on a computer-readable recording medium.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (6)

A user terminal that selects at least one still cut to which at least one unique identification code is assigned and acquires an NFT issued based on the at least one still cut; and
A generator for generating at least one frame of a video into at least one still cut, an identification unit for identifying the at least one still cut by assigning at least one unique identification code, and at least one still cut selected by the user terminal. A generation service providing server including an issuing unit that issues an NFT, and a delivery unit that delivers the amount to the electronic wallet address of the user terminal when the user terminal pays the amount corresponding to the NFT;
NFT automatic creation service provision system using video still cuts including.
According to claim 1,
The creation service providing server,
When uploading the at least one still cut, a first-come-first-served basis provision unit that provides at least one still cut that has not been preempted with a unique identification code;
A system for providing an NFT automatic creation service using video still cuts, further comprising:
According to claim 1,
The creation service providing server,
When uploading the at least one still cut by mapping it with the unique identification code, a selection unit that distinguishes between still cuts that have been pre-empted and still cuts that have not been pre-empted using a pre-established deep learning algorithm and uploads them;
A system for providing an NFT automatic creation service using video still cuts, further comprising:
According to claim 2,
The previously constructed deep learning algorithm is,
A system for providing an NFT automatic creation service using video still cuts, characterized in that the algorithm automatically edits the at least one still cut in the video.
According to claim 1,
The creation service providing server,
When the NFT is issued, a blockchain unit that creates a block on the blockchain, inputs and stores the information of the NFT, and stores the at least one still cut represented by the NFT in the InterPlanetary File System (IPFS);
A system for providing an NFT automatic creation service using video still cuts, further comprising:
According to claim 1,
The creation service providing server,
an automatic profit settlement unit that settles profits with at least one subject who participated in the production of the video;
A system for providing an NFT automatic creation service using video still cuts, further comprising:

Images