KR102495580B1 - A method and a server providing image pirate detection service - Google Patents

Abstract

The present invention relates to a method for providing an image theft detection service and a server thereof. The server includes a transceiver and a processor. Therefore, the method provides a non-fungible token (NFT) image theft detection service to a user.

Description

Method and server for providing image theft detection service {A METHOD AND A SERVER PROVIDING IMAGE PIRATE DETECTION SERVICE}

The present invention relates to a technology for determining authenticity of an image.

In addition, an embodiment of the present invention relates to a method and a server for providing a user with a service for detecting a suspicious case of non-fungible token (NFT) theft and analyzing similarity between images.

With the development of the Internet and smartphone applications, the importance of copyright of digital images such as digital photos, digital images, and NFT images is increasing. Due to this, the demand for a digital image theft detection service that determines whether or not the copyright of a digital image has been stolen is also increasing day by day.

Domestic Patent Publication 10-2013-0082033 A (2013.07.18) Domestic Patent Publication 10-2019-0076419 A (2019.07.02) Domestic Patent Publication 10-2014-0112204 A (2014.09.23)

Various embodiments of the present invention provide a method and server for providing a NFT image theft determination service to a user.

According to an embodiment of the present invention, a method for a server to provide a NFT image theft determination service to a user is provided. The method includes the steps of receiving, from a user device of a user, a first image that the user wants to request for theft determination and a theft determination request for the first image, based on receiving the theft determination request, theft determination Determining a pre-set number of NFT market places for, detecting a plurality of second images related to the first image in the determined first number of NFT market places set in advance for ), determining a plurality of NFTs related to the copyright of the plurality of second images as suspected theft NFTs, and transmitting information about the plurality of NFTs to the user device, wherein the The first number of NFT marketplaces set in advance may be determined in the order of increasing number of NFT registrations in the marketplace based on the time point at which the theft determination request is received.

In one embodiment, the plurality of second images related to the first image represent a plurality of second images similar to the first image, and the plurality of second images include a predefined AI ( It may be images whose similarity with the first image derived based on artificial intelligence (AI) image similarity analysis is greater than or equal to a first threshold value.

In one embodiment, based on receiving the theft determination request for the first image, further comprising: identifying the theft determination request type information of the user, wherein the theft determination request type information includes the number of times Any one of a base theft determination request type and a pass-based theft determination request type may be indicated.

In one embodiment, the number-based theft determination request type indicates a case in which the number of theft determination requests is possible is at least one remaining, and the commuter pass-based theft determination request type is theft determination by a preset second number during one month. Any one of a requestable case, a case in which an unlimited number of theft determination can be requested for one month, a case in which a third number of theft determination can be requested in advance for one year, and a case in which theft determination can be requested indefinitely for one year can be indicated.

In one embodiment, the first number set in advance is determined to be a larger value when the theft determination request type information indicates the number-based theft determination request type, than when the pass-based theft determination request type is indicated. can

In one embodiment, the NFT marketplaces represent websites or applications for NFT transactions, and the information on the plurality of NFTs includes an ID (identification) in the NFT marketplace of an NFT publisher, a blockchain that owns the NFT. It includes at least one of an electronic wallet address or an NFT selling price indicated on an NFT marketplace, and the NFT selling price may appear based on the quantity of a specific cryptocurrency.

In one embodiment, a third image related to an NFT uploaded to an NFT marketplace other than the NFT marketplaces of the first number using a blockchain electronic wallet address that owns one NFT among the plurality of NFTs and the third image A similarity between one image is determined, the predefined AI image similarity analysis is used to determine the similarity between the first image and the third image, and the similarity between the first image and the third image is determined. If it is equal to or greater than the threshold of 2, it may be determined that the first image and the third image are similar.

In one embodiment, the second threshold may be different from the first threshold.

In one embodiment, based on receiving the theft determination request for the first image, further comprising the step of identifying the theft determination request type information of the user, wherein the theft determination request type information is based on the number of theft determination Indicates any one of a request type and a pass-based theft determination request type, wherein the number-based theft determination request type indicates a case where the number of possible theft determination requests is at least one remaining, and the commuter pass-based theft determination request type is one Cases that can request theft determination as many as the second number set in advance for one month, cases that can request theft determination for an unlimited number of cases for one month, cases that can request theft determination for the third number set in advance for one year, and unlimited theft determination requests for one year Indicates one of possible cases, and the preset first number is larger when the theft determination request type information indicates the number-based theft determination request type than when the pass-based theft determination request type is indicated. is determined to be a large value, the plurality of second images related to the first image represent a plurality of second images similar to the first image, and the plurality of second images analyze a predefined AI image similarity are images whose similarity with the first image derived based on is greater than or equal to a first threshold, the NFT marketplaces represent websites or applications for NFT transactions, and the information on the plurality of NFTs is the NFT publisher's At least one of an ID in the NFT marketplace, an address of a blockchain electronic wallet that owns the NFT, or an NFT sale request price indicated on the NFT market place, and the NFT sale request price appears based on the quantity of a specific cryptocurrency, and the plurality of Between the third image related to the NFT uploaded to the NFT marketplace excluding the first number of NFT marketplaces and the first image using the blockchain electronic wallet address that owns one of the NFTs. A similarity is determined, the predefined AI image similarity analysis is used to determine the similarity between the first image and the third image, and the similarity between the first image and the third image is equal to or greater than a second threshold. , it is determined that the first image and the third image are similar, and the second threshold may be different from the first threshold.

According to one embodiment of the present invention, a server providing a NFT image theft determination service to a user is provided. The server includes a transceiver and a processor, wherein the processor includes, from a user device of a user, a first image that the user wants to request for theft determination and a theft determination request for the first image. Controls the transceiver to receive, and based on receiving the theft determination request, determines a preset number of NFT market places for theft determination, and determines the determined first number of NFT markets. Detect a plurality of second images related to the first image in NFT marketplaces of, determine a plurality of NFTs related to the copyright of the plurality of second images as suspected theft NFTs, and determine the plurality of second images related to the plurality of second images. Controls the transceiver to transmit information on NFTs of to the user device, but the NFT marketplaces of the first number set in advance have a large number of NFTs registered in the marketplace based on the time point at which the stealing determination request is received. order can be determined.

According to various embodiments of the present invention, the server can effectively provide NFT image theft determination services to users.

Effects according to the present invention are not limited to the effects described above, and other effects not described will be clearly understood by those skilled in the art from the following description.

1 shows an example of a communication structure between a server and a user device.
2 is a diagram for explaining an example in which a blockchain transaction is performed.
3 is a diagram for explaining examples of a method of proving a blockchain transaction.
4 is a flowchart illustrating an operation of a server according to an exemplary embodiment.
5 is a flowchart illustrating a method in which a server and a user device operate based on mutual communication according to an embodiment.
6A and 6B are diagrams illustrating an example in which a server performs AI image similarity analysis.
7 is a block diagram showing the configuration of a server according to an embodiment.
8 is a block diagram showing the configuration of a processor according to an embodiment.

Since the present invention can make various changes and have various embodiments, specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. The term "and/or" includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when an element is referred to as “directly connected” or “directly connected” to another element, it should be understood that no other element exists in the middle.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in this application, they should not be interpreted in an ideal or excessively formal meaning. don't

Hereinafter, with reference to the accompanying drawings, preferred embodiments of the present invention will be described in more detail. In order to facilitate overall understanding in describing the present invention, the same reference numerals are used for the same components in the drawings, and redundant descriptions of the same components are omitted.

1 shows an example of a communication structure between a server and a user device.

In this specification, “server” is a kind of server that communicates with external devices (eg, user devices) or external servers (other than itself) through a network, and is used to operate external devices or external servers. can indicate a server for In one example, the server may be implemented using a web server program provided in various ways according to an operating system such as DOS, Windows, Linux, Unix, and Macintosh in general server hardware.

In one embodiment, the server 110 may refer to a device that provides a NFT image theft determination service to a user (or customer). For example, the server 110 may be referred to by various names such as an online image theft determination platform, a digital image theft determination platform, a digital image theft determination platform server, an NFT image theft determination server, and an NFT image theft determination platform.

Whether or not the image is stolen by the server 110 is not limited to NFT images. For example, the server 110 may determine whether a digital image or digital video other than an NFT image is stolen.

In this specification, “user device” refers to smart phones, mobile phones, smart TVs, smart watches, electronic wristwatches, set-top boxes, tablet PCs, digital cameras, camcorders, laptop computers, desktops, electronic With a variety of devices including book terminals, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMP (Portable Multimedia Players), navigations, MP3 players, wearable devices, air conditioners, microwave ovens, audio, DVD players, etc. can be implemented

In this specification, the server 110 and the user device 120 may mutually communicate through a communication network. The communication network may be, for example, a wireless communication network or a wired communication network. The wireless communication network may be, for example, a communication network based on Long Term Evolution (LTE), Radio Access Technology (RAT), New Radio (NR) RAT, WiFi, and the like.

In one example, the server 110 and the user device 120 may perform Device-to-Device (D2D) communication with each other and may perform UU communication with a base station (eg, gNB and/or eNB). can In a time division multiple access (TDMA) and frequency division multiples access (FDMA) system for performing the D2D communication or the UU communication, accurate time and frequency synchronization may be required. If time and frequency synchronization are not accurate, system performance may deteriorate due to Inter Symbol Interference (ISI) and Inter Carrier Interference (ICI). In D2D communication according to an example, for time/frequency synchronization, a synchronization signal may be used in a physical layer and a master information block (MIB) may be used in a radio link control (RLC) layer.

In the process of D2D communication, the server 110 and the user device 120 are directly synchronized with global navigation satellite systems (GNSS), or indirectly through a terminal directly synchronized with GNSS (within network coverage or outside network coverage). can be synchronized to GNSS. When GNSS is set as the synchronization source, the server 110 and the user device 120 can calculate the DFN and subframe number using Coordinated Universal Time (UTC) and a (pre)set Direct Frame Number (DFN) offset.

Alternatively, the server 110 and the user device 120 may be directly synchronized with the base station or synchronized with other terminals that are time/frequency synchronized with the base station. For example, the base station may be an eNB or gNB. For example, when the server 110 and the user device 120 are within network coverage, the server 110 and the user device 120 may receive synchronization information provided by a base station and synchronize directly with the base station. . After that, the server 110 and the user device 120 may provide synchronization information to other nearby terminals. When the base station timing is set as a synchronization criterion, the server 110 and the user device 120 use a cell associated with a corresponding frequency (if the frequency is within cell coverage), a primary cell, or a serving cell ( out of cell coverage at the frequency).

A base station (eg, a serving cell) may provide synchronization settings for a carrier used for D2D or sidelink (SL) communication. In this case, the server 110 and the user device 120 may follow the synchronization settings received from the base station. If the server 110 and the user device 120 do not detect any cell on the carrier used for the D2D or SL communication and do not receive synchronization settings from the serving cell, the server 110 and the user device 120 ) may follow a preset synchronization setting.

Alternatively, the server 110 and the user device 120 may be synchronized with other terminals that do not directly or indirectly acquire synchronization information from the base station or GNSS. Synchronization source and preference may be set in advance for the terminal. Alternatively, the synchronization source and preference may be set through a control message provided by the base station.

In one embodiment, server 110 and user device 120 may mutually communicate via network 100 (or communication network). For example, when the server 110 transmits data to the network 100, the network 100 may deliver (transmit) the data to the user device 120. Alternatively, when the user device 120 transmits data to the network 100, the network 100 may transmit (transmit) the data to the server 110.

2 to 8, based on signal exchange or communication between the server 110 and the user device 120, the server 110 provides a NFT image theft determination service to the user in detail. review with

2 is a diagram for explaining an example in which a blockchain transaction is performed.

A block chain is a collection of blocks connected one after another. Here, the block forming the chain may record/include confirmed transaction details traded for a certain period of time through the corresponding blockchain platform. In order for a block recording transaction details before confirmation to be approved, a validity judgment must be performed by network participants. An example of a validity judgment method or a consensus protocol will be described later in detail with reference to FIG. 3 .

Figure 2 shows a communication structure between participants performed within a specific blockchain platform. The first blockchain transaction participation device 210 and the second blockchain transaction participation device 220 may represent user devices of two users performing block chain transactions, and one or all devices may be a server. can For example, each of the first blockchain transaction participation device 210 and the second block chain transaction participation device 220 may be one of the server 110 or the user device 120 described above in FIG. 1 .

A blockchain platform may mean a blockchain ecosystem or a blockchain network operated based on an independent blockchain technology. There are various types of blockchain platforms, such as bitcoin and ethereum, and each blockchain platform may have different elements such as blockchain consensus protocol, interface, and block size. . The transaction method used in each blockchain platform is cryptocurrency, and the method of generating and trading cryptocurrency may vary according to the consensus protocol adopted by each blockchain platform. The consensus protocol is described in detail in FIG. to be described later. Cryptocurrency may also be referred to as virtual currency, digital asset, digital currency, and the like.

In one embodiment, cryptocurrencies may be classified into coins and tokens. Coin means a cryptocurrency that has its own mainnet and constitutes an independent ecosystem without being dependent on other platforms, and all platform coins such as Ethereum and EOS are examples. In addition, even if it is not a platform coin, an independent cryptocurrency that is not dependent on other platforms, such as Bitcoin or Ripple, can also be referred to as a coin. A token means a cryptocurrency used to achieve an individual purpose on top of another platform coin. In other words, the token does not have its own mainnet and operates based on other platforms. For example, Status Network Token (SNT) is a token that operates based on the Ethereum platform (or next-generation Ethereum platform (eg, Ethereum 2.0)).

Ethereum is a public blockchain platform created by Vitalik Buterin on July 30, 2015, and represents the name of the platform's own currency (i.e., cryptocurrency). While Bitcoin focuses on payment or transaction-related systems, that is, functions as currency, Ethereum is based on blockchain, which is a core technology. It can provide scalability so that various applications can be operated transparently. In other words, it is a platform that allows anyone to create and use analysis applications (Decentralized Applications) called dAPP as well as currency. The mainstream of Ethereum's programming language has versatility by supporting most major programming languages such as Solidity, which is a variation of JavaScript, C++, Java, Python, and Go.

NFT (Non-Fungible Token), that is, 'non-fungible token', can refer to a blockchain-based token that is unique and scarce because it is impossible to exchange and copy. Fungible cryptocurrencies such as Bitcoin mentioned above have the same value, so 1:1 exchange is possible, whereas NFTs have values and characteristics that cannot be replaced by each being given a unique recognition value. do. By applying NFT technology that puts a unique serial number on assets that can be digitized, it is possible to create (digital) assets that cannot be duplicated, that is, the only one in the world. They range from digital contents such as texts to artworks, collectibles, game items, phonemes, various products, and virtual real estate.

The plurality of nodes 230 represent a plurality of servers, a plurality of devices, and a plurality of networks involved in the consensus protocol of transactions performed on the specific blockchain platform. In one example, one of the plurality of nodes 230 may be configured based on at least one of a plurality of servers, a plurality of devices, or a plurality of networks. Alternatively, in another example, one node among the plurality of nodes 230 may mean one server, one device, or one network. In one example, the ranges of the plurality of nodes 230 may be different according to the type of consensus protocol.

In FIG. 2, it is described that the plurality of nodes 230 and the first block chain transaction participation device 210 and the second block chain transaction participation device 220 are distinguished, but this is to clearly indicate the block chain transaction participation device. In some embodiments, the plurality of nodes 230 may include the first blockchain transaction participation device 210 and the second blockchain transaction participation device 220 . The plurality of nodes 230 shown in FIG. 2, the first blockchain transaction participation device 210, and the second blockchain transaction participation device 220, through the network 100 described above in FIG. Data can be transmitted and received between them.

A method of transmitting a specific cryptocurrency used in the specific blockchain platform from the first blockchain transaction participation device 210 to the second blockchain transaction participation device 220 according to an embodiment is as follows. The address of the cryptocurrency electronic wallet owned by the first user of the first blockchain transaction participation device 210, the amount of the specific cryptocurrency to be transmitted, and the cryptocurrency electronic wallet to be transmitted (i.e. , Transaction information (or ID) including the address of the cryptocurrency electronic wallet owned by the second user of the second blockchain transaction participation device 220, the first blockchain transaction participation device 210 ) to the plurality of nodes 230, the plurality of nodes 230 may approve the transaction through a predetermined consensus protocol method. If the transaction is approved, the specified amount of cryptocurrency may be transferred from the cryptocurrency electronic wallet owned by the first user to the cryptocurrency electronic wallet owned by the second user. In other words, through the plurality of nodes 230, the specific cryptocurrency by the amount is reduced in the cryptocurrency electronic wallet owned by the first user, and in the cryptocurrency electronic wallet owned by the second user. A block recording that the specific cryptocurrency has increased by the amount can be combined with an existing block chain in the block chain platform to form a new block chain.

A smart contract refers to a digital contract method in which contract conditions are coded based on blockchain technology and the contents of the contract are fulfilled when the conditions are met. The first block chain transaction participation device 210 and the second block chain transaction participation device 220 according to an embodiment conclude a smart contract based on the specific block chain platform as follows. same. At this time, either of the first blockchain transaction participation device 210 and the second blockchain transaction participation device 220 supports a non-fungible token (NFT) trading platform such as, for example, opensea. It may be a server that When the first blockchain transaction participation device 210 requests the plurality of nodes 230 to create a smart contract account, the plurality of nodes 230 create a smart contract account can do. At this time, the second blockchain transaction participation device 220 agreeing to the contract details of the smart contract transfers the contract details and the first user of the first block chain transaction participation device 210 to the plurality of nodes 230. When transmitting transaction information (or ID) including the cryptocurrency electronic wallet address owned by and the cryptocurrency electronic wallet address owned by the second user of the second blockchain transaction participation device 220, the smart contract By being concluded, the contents of the contract can be realized/executed. For example, the NFT owned by the first user moves from the cryptocurrency electronic wallet of the first user to the cryptocurrency electronic wallet of the second user, and the predetermined cryptocurrency owned by the second user moves to the second user's cryptocurrency electronic wallet. It is possible to move from the user's cryptocurrency electronic wallet to the first user's cryptocurrency electronic wallet.

In one embodiment, the blockchain transaction between the devices participating in the blockchain transaction according to FIG. 2 may be performed in a metaverse environment. Metaverse means a virtual space platform that enables real-life social, economic, educational, cultural, and scientific and technological activities through avatars. The metaverse environment may be expressed in a 3D virtual space, but this is only an example. The metaverse environment may be expressed through a two-dimensional flat virtual space, or through a four-dimensional virtual space in which the sense of touch or smell is added.

3 is a diagram for explaining examples of a method of proving a blockchain transaction.

The consensus protocol method in which a plurality of nodes 230 constituting a blockchain platform prove a blockchain transaction is, for example, a Proof of Work (PoW) 310 and a Proof of Stake (Proof of Stake) method. PoS) 320 exists, and the types of consensus protocol methods are not limited to the above two.

In the proof-of-work method 310, a block creator (or miner, verifier, etc.) applies a nonce value and hash algorithm with random characteristics to transaction record information, which is presented in the block header of the block chain. It refers to a consensus protocol that creates a block and receives compensation by detecting a hash value that satisfies the difficulty condition. Block creators can receive, for example, cryptocurrency used in the blockchain platform as a reward. Blockchain platforms using the proof-of-work scheme 310 include, for example, Bitcoin and Ethereum. When the consensus protocol method of a specific block chain platform is the proof-of-work method 310, since the object of proving the block chain transaction within the specific block chain platform is the block creator (or miner, verifier, etc.), the plurality of Nodes 230 may mean the block generator.

The proof-of-stake method 320 refers to a consensus protocol that differentially grants authority to create a block to each node according to the amount of stake of each node in the blockchain platform at the time of consensus. The stake of each node may be proportional to the amount of cryptocurrency each node holds. Each node can receive a reward for the transaction fee generated by the blockchain platform according to the rate at which each node contributes to block creation. Blockchain platforms using the proof-of-stake method 320 include, for example, Solana, ADA, and next-generation Ethereum (eg, Ethereum 2.0). When the consensus protocol method of a specific blockchain platform is the proof-of-stake method (320), all participants or nodes holding cryptocurrency used in the blockchain platform are subject to proof of blockchain transactions within the specific blockchain platform. Therefore, the plurality of nodes 230 may mean all participants or nodes.

4 is a flowchart illustrating an operation of a server according to an exemplary embodiment.

Operations disclosed in the flowchart of FIG. 4 may be performed in conjunction with various embodiments of the present invention. In one example, the server described in FIG. 2 may correspond to the server 110 disclosed in FIG. 1 , the server 501 disclosed in FIG. 5 , or the server 700 disclosed in FIG. 7 . In one example, the operations disclosed in the flowchart of FIG. 4 may correspond to some of the (server) operations disclosed in FIGS. 1 to 3 and 5 to 7 .

In step S410, the server according to an embodiment may receive, from the user device of the user, a first image to which the user wants to determine stealing and a request for determining stealing the first image.

In one embodiment, the first image may be an NFT-linked image, a digital image, or a digital image. The NFT-linked image may refer to an image whose copyright can be verified/tracked by NFT.

In one embodiment, the theft determination request may be text information input by the user through an application or website, or HTML (hypertext markup language) generated by converting the text information, metadata, It may also refer to syntax, semantics or programming language.

In step S420, the server according to an embodiment may determine a pre-set number of NFT market places for determining theft based on receiving the theft determination request.

In one embodiment, the NFT marketplaces may represent a website or application for NFT trading. For example, the NFT marketplaces may indicate OpenX, LarryX, UpbyX, NiftyGatewayX, and the like.

In step S430, the server according to an embodiment may detect a plurality of second images related to the first image from the determined first number of NFT marketplaces set in advance.

In one embodiment, the plurality of second images related to the first image represent a plurality of second images similar to the first image, and the plurality of second images include a predefined AI ( It may be images whose similarity with the first image derived based on artificial intelligence (AI) image similarity analysis is greater than or equal to a first threshold value.

In one embodiment, a detailed description of the AI image similarity analysis defined in advance will be described later in the description of FIGS. 6 and 8 .

In another embodiment, the AI image similarity analysis defined in advance may operate on the same/similar principle as the 'find by image' function used in a search engine.

In one embodiment, the first threshold may be a real number greater than 0 and less than 1.

In step S440, the server according to an embodiment may determine a plurality of NFTs related to copyrights of the plurality of second images as NFTs suspected of being stolen.

As described above in FIG. 2, the plurality of second images, as NFT-applied digital assets, have irreplaceable values and characteristics by being given their own unique recognition values.

In step S450, the server according to an embodiment may transmit information on the plurality of NFTs to the user device.

In one embodiment, the first number of NFT marketplaces set in advance may be determined in the order of increasing number of NFT registrations in the marketplace based on the time point at which the theft determination request is received.

That is, at the time of receiving the theft determination request, A NFT Marketplace is ranked first in the number of registered NFTs (10,000), B NFT Marketplace is second in number of registered NFTs (5,000), and C NFT Marketplace is registered NFT. 3rd in number (2,000), and if the first number set in advance is 3, the 'preset first number of NFT marketplaces' are A NFT market place, B NFT market place, and C NFT market place can be determined by place.

The server according to an embodiment may identify the user's theft determination request type information based on receiving the theft determination request for the first image. Here, the theft determination request type information may indicate one of a number-based theft determination request type and a pass-based theft determination request type.

In one embodiment, the number-based theft determination request type indicates a case in which the number of theft determination requests is possible is at least one remaining, and the commuter pass-based theft determination request type is theft determination by a preset second number during one month. Any one of a requestable case, a case in which an unlimited number of theft determination can be requested for one month, a case in which a third number of theft determination can be requested in advance for one year, and a case in which theft determination can be requested indefinitely for one year can be indicated.

In one embodiment, the first number set in advance is determined to be a larger value when the theft determination request type information indicates the number-based theft determination request type, than when the pass-based theft determination request type is indicated. can

For example, when the theft determination request type information indicates the number-based theft determination request type, the previously set first number is determined to be three, and the theft determination request type information indicates the pass-based theft determination request type. When instructed, the preset first number may be determined to be five.

In one embodiment, the NFT marketplaces represent websites or applications for NFT transactions, and the information on the plurality of NFTs includes an ID (identification) in the NFT marketplace of an NFT publisher, a blockchain that owns the NFT. It includes at least one of an electronic wallet address or an NFT selling price indicated on an NFT marketplace, and the NFT selling price may appear based on the quantity of a specific cryptocurrency.

For example, the NFT sale request price may be expressed as 1 Bitcoin, 10 Ethereum, and the like. This indicates that a specific NFT is requested to be exchanged for 1 Bitcoin, 10 Ethereum, etc.

In one embodiment, a third image related to an NFT uploaded to an NFT marketplace other than the NFT marketplaces of the first number using a blockchain electronic wallet address that owns one NFT among the plurality of NFTs and the third image A similarity between one image is determined, the predefined AI image similarity analysis is used to determine the similarity between the first image and the third image, and the similarity between the first image and the third image is determined. If it is equal to or greater than the threshold of 2, it may be determined that the first image and the third image are similar.

For example, a blockchain electronic wallet address that owns an NFT uploaded to a specific NFT marketplace (an NFT marketplace that is not included in the first number of NFT marketplaces) and one NFT among the plurality of NFTs. When the owned blockchain electronic wallet address is the same, a similarity determination between the third image and the first image associated with the NFT uploaded to the specific NFT marketplace may be performed.

In one embodiment, the second threshold may be different from the first threshold.

In one example, the second threshold may be smaller than the first threshold.

In another example, the second threshold may be the same as the first threshold.

In one embodiment, the method further comprises identifying the theft determination request type information of the user based on receiving the theft determination request for the first image, wherein the theft determination request type information is based on the number of times Indicates any one of a theft determination request type and a pass-based theft determination request type, wherein the number-based theft determination request type indicates a case in which the number of possible theft determination requests is at least one remaining, and the commuter pass-based theft determination request type is , Cases in which theft determination can be requested as many as the second number set in advance for one month, cases in which theft determination can be requested for an unlimited number of cases for one month, cases in which theft determination can be requested as many as the third number set in advance for one year, and unlimited theft for one year Indicates any one of cases where the determination request is possible, and the first number set in advance indicates the theft determination request type based on the commuter pass, rather than when the theft determination request type information indicates the number-based theft determination request type. When determined as a larger value, the plurality of second images related to the first image represent a plurality of second images similar to the first image, and the plurality of second images are predefined AI images. Images having a similarity with the first image derived based on a similarity analysis are equal to or greater than a first threshold, the NFT marketplaces represent websites or applications for NFT transactions, and information on the plurality of NFTs includes NFTs. At least one of the publisher's ID in the NFT marketplace, the address of a blockchain electronic wallet that owns the NFT, or the NFT sale request price indicated on the NFT market place, the NFT sale request price appears based on the quantity of a specific cryptocurrency, and the A third image related to an NFT uploaded to an NFT marketplace excluding the NFT marketplaces of the first number using a blockchain electronic wallet address that owns one NFT among a plurality of NFTs and the first image A similarity between images is determined, the predefined AI image similarity analysis is used to determine the similarity between the first image and the third image, and the similarity between the first image and the third image is determined by a second image. If the value is equal to or greater than the threshold value, it is determined that the first image and the third image are similar, and the second threshold value may be different from the first threshold value.

5 is a flowchart illustrating a method in which a server and a user device operate based on mutual communication according to an embodiment.

In one embodiment, S510 to S550 may correspond to S410 to S450 of FIG. 4 , respectively.

In step S510, the server 501 according to an embodiment may receive, from the user device 502 of the user, a first image for which the user wants to request theft determination and a theft determination request for the first image. there is.

In step S520, the server 501 according to an embodiment may determine a preset number of NFT market places for determining theft based on receiving the theft determination request.

In step S530, the server 501 according to an embodiment may detect a plurality of second images related to the first image from the predetermined first number of NFT marketplaces.

In step S540, the server 501 according to an embodiment may determine a plurality of NFTs related to copyrights of the plurality of second images as NFTs suspected of being stolen.

In step S550, the server 501 according to an embodiment may transmit information on the plurality of NFTs to the user device.

6A and 6B are diagrams illustrating an example in which a server performs AI image similarity analysis.

Referring to STEP 1 of FIG. 6A , the server may derive characteristics of an original image and a suspected (suspected) image of theft. Deriving the characteristics here may be recognizing and confirming whether there is a change (color value) in all directions based on one pixel through object recognition through corner analysis in the image. In one example, the original image on the left side of STEP 1 may have 373 feature points, and the number of feature Tscript values used per feature point may be 128. The anti-stealth image on the right side of STEP 1 has 487 feature points, and the number of feature T-script values used per feature point may be 128.

Referring to STEP 2 of FIG. 6B, the server may calculate a similarity by comparing the original image and the stolen images. In the example of FIG. 6B , it is shown that the similarity between the original image and the stolen image is 0.93726. The similarity determination may be based on the previously set AI image similarity analysis described in FIG. 4 . In addition, if the stolen image is slightly distorted or the design of the original image is slightly distorted, it is possible to display where the stolen image is identically stolen and where it has been changed.

The server according to an embodiment may perform analysis of main similarity features of an image. That is, it is possible to indicate which characteristics of the original image were mainly used (stealed) by the stolen image, and even major similar characteristics.

According to an embodiment, the server may provide a user with a summary report including similarities, differences, and main similarities between the original image and the image to be stolen. That is, the server may transmit information on the summary report to the user device.

7 is a block diagram showing the configuration of a server according to an embodiment.

As shown in FIG. 7 , the server 700 according to an embodiment may include a database (DB) 710 , a transceiver 720 and a processor 730 . However, in some cases, all of the components shown in FIG. 7 may not be essential components of the server 700, and the server 700 may be implemented with more or fewer components than those shown in FIG. can

In the server 700 according to an embodiment, the database 710, the transceiver 720, and the processor 730 may be implemented as separate chips, or at least two or more components may be implemented through a single chip. may be

The database (DB, 710) may store data received from the transceiver 720 or the processor 730. In one embodiment, database 710 may store at least one program. In one example, the at least one program may be used when the processor 730 executes a learning model.

The transmission/reception unit 720 may be used for communication between modules in the server and/or transmission/reception of data/signals, and may perform communication with an external device. In one example, the transceiver 720 may transmit and receive data to and from an external device (eg, an external user device, an external server, etc.).

The processor 730 according to an embodiment may control overall operations of the server 700 . In one example, the processor 730 may overall control the database 710 and the transceiver 720 by executing programs stored in the database 710 of the server 700 . In one example, the processor 730 may perform some of the operations of the server 700 of FIGS. 1 to 6 by executing programs stored in a database of the server 700 .

The processor 730 according to an embodiment may control the transceiver 720 to receive a first image that the user wants to request to determine theft and a request for determining theft for the first image, from the user's user device. can

Based on receiving the theft determination request, the processor 730 according to an embodiment may determine a pre-set number of NFT market places for theft determination.

The processor 730 according to an embodiment may detect a plurality of second images related to the first image from the determined first number of NFT marketplaces set in advance.

The processor 730 according to an embodiment may determine a plurality of NFTs related to copyrights of the plurality of second images as NFTs suspected of being stolen.

The processor 730 according to an embodiment may control the transceiver 720 to transmit information on the plurality of NFTs to the user device.

In one embodiment, the first number of NFT marketplaces set in advance may be determined in the order of increasing number of NFT registrations in the marketplace based on the time point at which the theft determination request is received.

In one example, the processor 730 may execute an artificial intelligence (AI) learning model based on at least one program stored in the database 710 . Hereinafter, in FIG. 8, an example of the configuration of the processor 730 for executing the AI learning model will be described.

8 is a block diagram showing the configuration of a processor according to an embodiment.

As shown in FIG. 8 , the processor 730 according to an embodiment includes a data acquisition unit 732, a training data selection unit 734, a learning model execution unit 736, and a learning result providing unit 738. can do. However, in some cases, all of the components shown in FIG. 8 may not be essential components of the processor 730, and the processor 730 may be implemented with more or fewer components than those shown in FIG. can

A person skilled in the art will understand that the configuration of the processor 730 shown in FIG. 8 is one of modules of the processor 730 that can be used when the server 700 performs machine learning based on an AI learning model. This is just an example, and since the server 700 does not necessarily perform machine learning, some or all of the modules of the processor 730 shown in FIG. 8 may not be included in the processor 730 will be easily understood.

The data acquisition unit 732 according to an embodiment may acquire data required to determine the user's intention, provide relevant information, and recommend an alternative operation. Alternatively, the data acquisition unit 732 may acquire data necessary for learning to determine the user's intention, provide related information, and recommend an alternative motion.

In one example, the data acquisition unit 732 may acquire at least one of, for example, user voice, image information, and predetermined context information. In one example, the data acquisition unit 732 may convert the acquired data into a pre-defined format.

The learning data selection unit 734 according to an embodiment may select data necessary for learning from among data acquired by the data acquisition unit 732 . For example, the learning data selector 734 determines the user's intention, provides relevant information, and recommends an alternative operation according to a predefined criterion, among data acquired by the data acquisition unit 732, data necessary for learning. can choose Alternatively, the learning data selection unit 734 may select data according to a predefined criterion based on learning by the learning model execution unit 736 .

The learning model executor 736 according to an embodiment may learn criteria on how to determine the user's intention, how to determine related information, and how to recommend an alternative motion based on the learning data. In addition, the learning model executor 736 may learn a criterion for which learning data to use for determining the user's intention, determining related information, and recommending an alternative operation.

In addition, the learning model executor 736 may learn an AI learning model used for determining a user's intention, determining related information, and recommending an alternative operation using learning data. In this case, the AI learning model may be a pre-built model. For example, the AI learning model may be a model built in advance by receiving basic learning data (eg, sample data, etc.).

The AI learning model may be built in consideration of the application field of the learning model, the purpose of learning, or the computer performance of the device. The AI learning model may be, for example, a model based on a neural network. For example, a model such as a deep neural network (DNN), a recurrent neural network (RNN), or a bidirectional recurrent deep neural network (BRDNN) may be used as an AI learning model, but the embodiment is not limited thereto.

The learning model executor 736 according to an embodiment, when a plurality of pre-built AI learning models exist, determines an AI learning model having a high correlation between the input learning data and the basic learning data as the AI learning model to be learned. can In this case, the basic learning data may be pre-classified for each type of data, and the AI learning model may be pre-built for each type of data. For example, the basic training data is pre-classified according to various criteria such as the region where the training data was created, the time the training data was created, the size of the training data, the genre of the training data, the creator of the training data, and the type of object in the training data. may have been

The learning model execution unit 736 according to an embodiment is configured to train an AI learning model using a learning algorithm including, for example, error back-propagation or gradient descent. can

The learning model executor 736 according to an embodiment may learn an AI learning model through supervised learning using learning data as an input value, for example. In addition, the learning model executor 736 determines the user's intention, provides related information, and learns the type of data necessary for recommending an alternative operation, for example, without any guidance, to determine the user's intention, Unsupervised learning may be performed to discover criteria for providing relevant information and recommending alternative motions. Through the unsupervised learning, the learning model executor 736 may learn the AI learning model. In addition, the learning model execution unit 736, for example, through reinforcement learning using feedback on whether the result of determining the user's intention according to learning, providing relevant information, and recommending an alternative operation is correct, for example, You can train an AI learning model.

In addition, when the AI learning model is learned, the learning model executor 736 may store the learned AI learning model. In this case, the learning model execution unit 736 may store the learned AI learning model in the database 710 of the server 700 . Alternatively, the learning model execution unit 836 may store the learned AI learning model in a memory or database of a server or device connected to the server 700 through a wired or wireless network.

The learning result providing unit 738 according to an embodiment may derive or obtain a (machine) learning result based on the AI learning model learned by the learning model execution unit 736 . The learning result provider 738 may provide the (machine) learning result to the database 710 or the transceiver 720 .

The learning result provider 738 according to an embodiment derives the plurality of second images similar to the first image of FIG. 4 based on an AI learning model (or AI image similarity analysis defined in advance). can do. For example, the plurality of second images may be images whose similarity to the first image derived based on the AI learning model is greater than or equal to a first threshold.

Some embodiments may be implemented in the form of a recording medium including instructions executable by a computer, such as program modules executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer readable media may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, 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. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transport mechanism, and includes any information delivery media.

So far, the present invention has been looked at mainly with its preferred embodiments. Those skilled in the art to which the present invention pertains will understand that the present invention can be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the scope of the present invention should be construed to include various embodiments within the scope equivalent to those described in the claims without being limited to the above-described embodiments.

Claims (5)

In a server that provides NFT image theft determination services to users,
Transceiver; and a processor; Including,
The processor:
Controlling the transceiver to receive, from a user device of a user, a first image for which the user wants to request stealing determination and a stealing determination request for the first image;
Based on receiving the theft determination request, determine a pre-set number of NFT market places for theft determination, wherein the NFT marketplaces represent websites or applications for NFT transactions,
Detect (detect) a plurality of second images related to the first image in the determined first number of NFT marketplaces set in advance, but the plurality of second images are AI (Artificial Intelligence) images defined in advance Images whose similarity with the first image derived based on similarity analysis is equal to or greater than a first threshold value;
Determining a plurality of NFTs related to the copyright of the plurality of second images as suspected theft NFTs,
Controlling the transceiver to transmit information on the plurality of NFTs to the user device;
The first number of NFT marketplaces set in advance is determined in the order of the number of NFT registrations in the marketplace based on the time point at which the theft determination request is received,
the processor,
Based on receiving the theft determination request for the first image, identify the theft determination request type information of the user,
The theft determination request type information indicates: one of a number-based theft determination request type and a pass-based theft determination request type;
The number-based theft determination request type: represents a case in which the number of theft determination request possible is at least one remaining;
The commutation pass-based theft determination request types are: Cases in which theft determination can be requested by the second number set in advance for one month, cases in which theft determination can be requested unlimitedly for one month, cases in which theft determination can be requested by the third number set in advance for one year Case, or one of the cases that can be requested for identification of theft indefinitely for one year,
The first number set in advance is: determined to be a larger value when the theft determination request type information indicates the number-based theft determination request type, than when the pass-based theft determination request type is indicated,
The information on the plurality of NFTs includes: an identity (identification) of the NFT publisher in the NFT marketplace, an address of a blockchain electronic wallet that owns the NFT, and an NFT sale request price indicated on the NFT marketplace;
The NFT sale request price appears based on the quantity of a specific cryptocurrency,
The similarity between the first image and the third image related to the NFT uploaded to the NFT marketplace excluding the NFT marketplaces of the first number using the blockchain electronic wallet address that owns one NFT among the plurality of NFTs Determined based on the predefined AI image similarity analysis,
When the degree of similarity between the first image and the third image is greater than or equal to a second threshold, it is determined that the first image and the third image are similar;
The second threshold is set to be different from the first threshold, and the first threshold is set to a real number greater than 0 and less than 1, characterized in that the server. delete delete delete delete

Images