KR102472427B1 - Artificial intelligence-based counterfeit screening inspection and digital certificate issuance method, device and program - Google Patents

Abstract

According to one embodiment of the present invention, disclosed are an artificial intelligence-based counterfeit screening test performed by a computing device and a method for issuing a digital certificate. The method includes the steps of: acquiring at least one product image; performing a counterfeit product screening test on the product based on the at least one product image; and issuing a digital certificate for the product, if the product is judged to be genuine. The digital certificate may include fingerprint information corresponding to the product and history information about a process of determining whether the product is genuine. Accordingly, environmental and consumer selective benefits can be enhanced through reuse of resources.

Description

Artificial intelligence-based counterfeit screening inspection and digital certificate issuance method, device and program

The present invention relates to a method, apparatus, and program for screening for counterfeit goods based on artificial intelligence and issuing digital certificates. It relates to methods, devices and programs for distributing goods.

As information and communication technology develops, a new industrial era begins with the convergence of various technologies. This is also called the fourth industrial revolution. Technologies in various fields such as big data analysis, artificial intelligence, robotics, the Internet of Things, 3D printing, and nanotechnology are mentioned as technological elements constituting the 4th Industrial Revolution.

Blockchain is also attracting attention as a major technology constituting this fourth industrial revolution. Blockchain refers to a system that stores data to be managed in a chain-type connection-based distributed data storage environment (“block”) created in a peer-to-peer manner. Due to its structural characteristics, the blockchain system cannot be arbitrarily modified by anyone, and can have the characteristics of a public transaction ledger system in which anyone can view the results of changes. As this decentralized and open structure of the blockchain draws attention, various blockchain-based distributed computing platforms such as the Bitcoin platform and the Ethereum platform are being proposed and widely used.

In relation to blockchain, Decentralized Identifier (DID) is a technology that allows identity information to be controlled by individuals rather than controlled by a central system. DID technology is used to issue digital identification cards, etc., and can be used not only for identification but also for all types of certificates guaranteed by the issuer. Specifically, the issuer issues a DID to the user, and the user can prove his identity by submitting his DID to the verifier.

In addition, a non-fungible token (NFT) is a data unit stored in a blockchain, and each data unit means a token with a unique identity. Due to these characteristics of non-fungible tokens, non-fungible tokens can function as a means of imparting uniqueness and rarity to digital assets.

Meanwhile, the size of the luxury goods market at home and abroad is gradually expanding due to the recent abundant liquidity. In particular, luxury goods demand, which was concentrated offline, is rapidly moving online due to retaliatory sentiment and increased non-face-to-face consumption due to the prolonged COVID-19.

The expansion of the size of the online luxury goods market causes a side effect of increasing suspicious cases of counterfeit goods, and there is a demand for a method for solving this problem in the related art.

Therefore, in order to solve the side effects caused by the expansion of the luxury goods market, it is necessary to study how to resolve doubts about counterfeit goods by utilizing various technologies related to the 4th industrial revolution.

It is intended to provide artificial intelligence-based counterfeit screening tests and digital certificate issuance methods, devices, and programs.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

According to one embodiment of the present invention for solving the above problems, an artificial intelligence-based counterfeit screening test performed by a computing device and a method for issuing a digital certificate are disclosed. The method includes: acquiring at least one item image; performing a counterfeit product screening test on products based on the at least one product image; and issuing a digital certificate for the product if it is determined that the product is genuine, wherein the digital certificate includes fingerprint information corresponding to the product and information about a process of determining whether the product is genuine. It may contain historical information.

The acquiring of at least one article image may include obtaining the at least one article image by controlling a plurality of cameras and a plurality of lights provided to photograph the article based on photographing information corresponding to the article. Including, the photographing information may be information in which a photographing position and a photographing method are mapped corresponding to each brand and type of an item to be inspected for counterfeit goods.

In addition, the performing of the counterfeit screening test on the product based on the at least one product image may include: determining whether the product is genuine using the at least one product image and a pretrained neural network model; Including, the pre-trained neural network model may be a model learned with training data in which genuine images and counterfeit images are each labeled.

In addition, the step of determining whether the product is genuine by using the at least one product image and the pretrained neural network model may include inputting the at least one product image into the pretrained neural network model to correspond to the genuine product class. obtaining a score value that and determining that the product is a genuine product when the score value exceeds a predetermined threshold value and determining that the product is a counterfeit product when the score value is less than or equal to the threshold value.

In addition, the step of determining whether the product is genuine by using the at least one product image and the pretrained neural network model may include inputting the at least one product image into the pretrained neural network model to correspond to the counterfeit class. obtaining a score value that and when the score value corresponding to the counterfeit product class exceeds a preset first threshold value and is less than or equal to a second threshold value greater than the first threshold value, the item is determined as a suspected counterfeit item, and the score value corresponding to the counterfeit product class When the value exceeds the second threshold value, determining the product as a counterfeit product; may include.

In addition, the method further includes transmitting a message requesting re-authentication of the product to an administrator terminal when it is determined that the product is a counterfeit product or suspected of being a counterfeit product, and through the re-authentication, the product is If it is determined that the product is genuine, a digital certificate for the product may be issued.

Also, the fingerprint information may be unique identification information for identifying the product including any one of the at least one product image and determined to be genuine.

In addition, if it is determined that the product is genuine, issuing a digital certificate for the product includes: storing the fingerprint information and whether or not the product is genuine, if it is determined that the product is genuine; Obtaining an inspection number for the product, generating a digital certificate using the inspection number, and recording the fingerprint information and whether or not the product is genuine in the digital certificate.

In addition, when it is determined that the product is genuine, the step of issuing a digital certificate for the product includes a wallet on a blockchain network, a private key, and a public key corresponding to the private key. generating a key); generating the fingerprint information and the history information; generating signature data obtained by encrypting the fingerprint information and the history information with the private key through an asymmetric key encryption algorithm; generating a transaction including the fingerprint information, the history information, and the signature data; And sending the transaction and the public key to at least one node included in the blockchain network, causing a plurality of nodes to record the transaction in a block through a consensus algorithm, wherein the digital certificate includes It may be a transaction recorded in the block of the blockchain network.

The method may further include allocating a serial number to the product if it is determined that the product is genuine; recording the serial number into the digital certificate; and recording a first hash value obtained by hashing the serial number in the product.

The method may further include receiving a first hash value recorded in the product when authenticating the product; obtaining a second hash value by hashing the serial number recorded in the digital certificate; and authenticating that the product is genuine when the first hash value and the second hash value correspond to each other.

The method may further include allocating a serial number to the product if it is determined that the product is genuine; recording the serial number into the digital certificate; hashing the serial number to obtain a first hash value; dividing the first hash value into at least two parts to obtain a first partition value and a second partition value; and recording the first division value in the article and transmitting the second division value to a user terminal.

The method may further include, when authenticating the product, receiving a first division value recorded in the article and receiving a second division value from the user terminal; obtaining a second hash value by hashing the serial number recorded in the digital certificate; and authenticating that the product is genuine when a combination value obtained by combining the first division value and the second division value corresponds to the second hash value.

The method may further include receiving a first division value recorded in the product when authenticating the product; obtaining a second hash value by hashing the serial number recorded in the digital certificate; and authenticating that the product is genuine when the first division value is included in the second hash value.

In addition, in the case of dividing the first hash value into at least two or more, the method provides information on a method of dividing the first hash value into the first division value and the second division value in the digital certificate Further comprising the step of recording; and, when authenticating the product, receiving information on the dividing method, dividing the second hash value based on the information on the dividing method, and A three-division value is obtained, and when the third division value corresponds to the first division value, it is possible to authenticate that the product is genuine.

The method may also include, when receiving an image of a product for authenticating from a user terminal or an external server, performing product authentication based on the product image; and transmitting an authentication result of the product for performing the genuine certification to the user terminal or the external server, wherein the product image includes an image captured based on photographing information corresponding to the product and the product. The hash value recorded in may include at least one of the captured images.

According to one embodiment of the present invention for solving the above problems, a memory for storing one or more instructions; and a processor that executes the one or more instructions stored in the memory, wherein the processor executes the one or more instructions, thereby performing the methods described above.

According to one embodiment of the present invention for solving the above problems, a computer program stored in a computer-readable recording medium to perform the above-described methods by being combined with a computer as hardware is disclosed.

The technical solutions obtainable in the present invention are not limited to the above-mentioned solutions, and other solutions not mentioned will become clear to those skilled in the art from the description below. You will be able to understand.

The artificial intelligence-based counterfeit screening test and digital certificate issuance method, device, and program of the present invention allow users to authenticate genuine products using a digital certificate app, and enable second-hand sales by linking the app to a second-hand trading platform. . Through this, the present invention can provide a digital authentication ecosystem from customs clearance to distribution and used transactions.

In addition, as the platform according to the disclosed embodiment is connected to the used trading platform, there is an advantage in improving environmental and consumer selective benefits through reuse of resources.

The effects obtainable in the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below. .

1 is a diagram illustrating a system according to an embodiment of the present invention.
2 is a hardware configuration diagram of a server according to another embodiment of the present invention.
3 is a diagram illustrating an AI-based counterfeit screening test and digital certificate issuance system according to an embodiment of the present invention.
4 is a diagram for explaining an example of an artificial intelligence-based counterfeit product screening test and digital certificate issuance method according to some embodiments of the present disclosure.
5 is a diagram for explaining an example of a method of issuing a digital certificate according to some embodiments of the present disclosure.
6 is a diagram for explaining an example of a method for verifying a correlation between an article and a digital certificate according to some embodiments of the present disclosure.
7 is a diagram for explaining another example of a method for verifying a correlation between an article and a digital certificate according to some embodiments of the present disclosure.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, only these embodiments are intended to complete the disclosure of the present invention, and are common in the art to which the present invention belongs. It is provided to fully inform the person skilled in the art of the scope of the invention, and the invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

The term "unit" or "module" used in the specification means a hardware component such as software, FPGA or ASIC, and "unit" or "module" performs certain roles. However, "unit" or "module" is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside in an addressable storage medium and may be configured to reproduce one or more processors. Thus, as an example, a “unit” or “module” may refer to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Functions provided within components and "units" or "modules" may be combined into smaller numbers of components and "units" or "modules" or may be combined into additional components and "units" or "modules". can be further separated.

The spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe a component's correlation with other components. Spatially relative terms should be understood as including different orientations of elements in use or operation in addition to the orientations shown in the drawings. For example, if you flip a component that is shown in a drawing, a component described as "below" or "beneath" another component will be placed "above" the other component. can Thus, the exemplary term “below” may include directions of both below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer means any kind of hardware device including at least one processor, and may be understood as encompassing a software configuration operating in a corresponding hardware device according to an embodiment. For example, a computer may be understood as including a smartphone, a tablet PC, a desktop computer, a laptop computer, and user clients and applications running on each device, but is not limited thereto.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Although each step described in this specification is described as being performed by a computer, the subject of each step is not limited thereto, and at least a part of each step may be performed in different devices according to embodiments.

1 is a diagram illustrating a system according to an embodiment of the present invention.

Referring to FIG. 1 , a system according to an embodiment of the present invention may include a server 100, a user terminal 200, and an external server 300.

Here, the system shown in FIG. 1 is according to an embodiment, and its components are not limited to the embodiment shown in FIG. 1, and may be added, changed, or deleted as necessary.

In one embodiment, the server 100 may perform an artificial intelligence-based counterfeit product screening test and digital certificate issuance method.

For example, the server 100 may be connected to the user terminal 200 through the network 400 and provide the user terminal 200 with a UI for using an artificial intelligence-based counterfeit screening test and digital certificate issuance method. It can receive commands through the UI and output analysis results for them.

In various embodiments, the server 100 may provide web or application based services. However, it is not limited thereto.

Here, the user terminal 200 may include a display on at least a portion of the user terminal 200 and may include an operating system for driving services based on applications or extension programs provided from the server 100 . For example, the user terminal 200 may be a smart phone, but is not limited thereto, and the user terminal 200 is a wireless communication device that ensures portability and mobility, and is capable of navigation, personal communication (PCS) System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), 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) terminal, smart pad (Smartpad), tablet PC (Tablet PC), and all kinds of handheld-based wireless communication devices can include

Also, here, the network 400 may refer to a connection structure capable of exchanging information between nodes such as a plurality of terminals and servers. For example, the network 400 includes a local area network (LAN), a wide area network (WAN), a world wide web (WWW), a wired and wireless data communication network, a telephone network, a wired and wireless television communication network, and the like. do.

In addition, here, the wireless data communication networks are 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi (Wi-Fi) 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, A Near-Field Communication (NFC) network, a satellite broadcasting network, an analog broadcasting network, a Digital Multimedia Broadcasting (DMB) network, and the like are included, but are not limited thereto.

In one embodiment, the external server 300 may be connected to the server 100 through the network 400, and may store and manage various information/data necessary for the server 100 to perform analysis, and the server 100 may It is possible to store and manage various types of information/data generated as (100) provides services.

In various embodiments, the external server 300 may be a storage server (eg, a database server) provided separately outside the server 100, but is not limited thereto, and the external server 300 is used to store various information and data. ) is not separately provided outside the server 100, and a database may be prepared in a separate space within the server 100 to be stored and managed in the corresponding space. Hereinafter, with reference to FIG. 2, the hardware configuration of the server 100 will be described.

2 is a hardware configuration diagram of a server according to another embodiment of the present invention.

Referring to FIG. 2, a server 100 according to another embodiment of the present invention includes one or more processors 110, a memory 120 for loading a computer program 151 executed by the processor 110, It may include a storage 150 storing a bus 130 , a communication interface 140 , and a computer program 151 . Here, in FIG. 2, only components related to the embodiment of the present invention are shown. Therefore, those skilled in the art to which the present invention pertains can know that other general-purpose components may be further included in addition to the components shown in FIG. 2 .

The processor 110 controls the overall operation of each component of the server 100. The processor 110 includes a Central Processing Unit (CPU), a Micro Processor Unit (MPU), a Micro Controller Unit (MCU), a Graphic Processing Unit (GPU), or any type of processor well known in the art of the present invention. It can be.

Also, the processor 110 may perform an operation for at least one application or program for executing a method according to embodiments of the present invention, and the server 100 may include one or more processors.

In various embodiments, the processor 110 may temporarily and/or permanently store signals (or data) processed in the processor 110 (RAM: Random Access Memory, not shown) and ROM (ROM: Read -Only Memory, not shown) may be further included. In addition, the processor 110 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.

Memory 120 stores various data, commands and/or information. Memory 120 may load computer program 151 from storage 150 to execute methods/operations according to various embodiments of the present invention. When the computer program 151 is loaded into the memory 120, the processor 110 may perform the method/operation by executing one or more instructions constituting the computer program 151. The memory 120 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

The bus 130 provides a communication function between components of the server 100 . The bus 130 may be implemented in various types of buses such as an address bus, a data bus, and a control bus.

The communication interface 140 supports wired and wireless Internet communication of the server 100 . Also, the communication interface 140 may support various communication methods other than Internet communication. To this end, the communication interface 140 may include a communication module well known in the art. In some embodiments, communication interface 140 may be omitted.

The storage 150 may non-temporarily store the computer program 151 . When performing the detailed diagnosis module proposal process through the server 100, the storage 150 may store various types of information necessary to perform analysis according to the disclosed embodiment.

The storage 150 may be a non-volatile memory such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or the like, a hard disk, a removable disk, or a device well known in the art. It may be configured to include any known type of computer-readable recording medium.

Computer program 151 may include one or more instructions that when loaded into memory 120 cause processor 110 to perform methods/operations in accordance with various embodiments of the invention. That is, the processor 110 may perform the method/operation according to various embodiments of the present disclosure by executing the one or more instructions.

In one embodiment, the computer program 151 may include one or more instructions for performing an AI-based counterfeit screening test and digital certificate issuance method.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.

Components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, such as C, C++ , Java (Java), can be implemented in a programming or scripting language such as assembler (assembler). Functional aspects may be implemented in an algorithm running on one or more processors.

Hereinafter, various embodiments according to the present invention will be described respectively.

The term 'product' used in the following description may be used interchangeably with 'article' for convenience of description.

3 is a diagram illustrating an AI-based counterfeit screening test and digital certificate issuance system according to an embodiment of the present invention.

The artificial intelligence-based counterfeit screening test and digital certificate issuance method according to the disclosed embodiment may be used to check whether a product is counterfeit during customs clearance, and to take follow-up measures according to the inspection result, but is not limited thereto.

In one embodiment, it is possible to determine whether a product is counterfeit or suspected of counterfeiting by photographing a product to inspect whether or not the product is counterfeit during customs clearance, and analyzing the captured image using an artificial intelligence-based model.

In various embodiments, a photographing device for performing photographing for inspecting counterfeit products may be used. The photographing device may be composed of a combination of lenses and filters for performing precise photographing and excluding interference due to external light reflection, etc., but is not limited thereto.

In addition, information on locations and shooting methods for each product or brand to be photographed may be provided in order to inspect counterfeit products. The inspector performs a photographing according to the provided information, and a computing device (eg, a scanning device, an edge server, or an external server, etc.) may perform a counterfeit product inspection based on the photographed image using an artificial intelligence model.

In various embodiments, there may be a plurality of pieces of information about a location and a method for capturing. For example, there may be a total of 10 photographing locations for checking whether a specific bag is authentic. In this regard, the computing device may randomly select 3 locations out of 10 locations and request photographing. Depending on the photographing result, the computing device may additionally request photographing of another location, and a method or sequence of requesting photographing is not limited thereto.

The artificial intelligence model may be a neural network-based model trained on the basis of training data in which fake images and genuine images are labeled, but is not limited thereto.

In addition, data collected in the customs clearance process according to the disclosed embodiment and data on the final validation result thereof may be collected and used for learning of the artificial intelligence model.

If it is judged to be a counterfeit by the artificial intelligence model or if a counterfeit product suspicion result is obtained that exceeds the preset standard value, the product or product image is delivered to the right holder (ie, the right holder holding the intellectual property right to the product) to determine whether it is a counterfeit product. can request The holder of the right can judge whether the product is counterfeit or not, and reply the result.

When the product is finally determined to be counterfeit by the holder of the right, follow-up measures such as accusation may be performed, and history information of the corresponding counterfeit product may be recorded.

If the product is judged to be genuine by the artificial intelligence model, or is judged or suspected to be counterfeit, but is judged to be genuine by the right holder, the computing device may issue a digital certificate for the product. In the digital certificate, a history of counterfeit screening inspection records for the corresponding product may be recorded.

Digital certificates can be created and issued in a way that cannot be forged or altered using blockchain technology (e.g., DID or NFT), but is not limited thereto.

A product confirmed as genuine and a digital certificate thereof can be delivered to a distributor, and the distributor can sell the product to consumers. When a consumer purchases a product, the distributor can deliver a digital certificate for the product to the consumer. The delivery process of digital certificates can be recorded by blockchain and stored in a way that cannot be tampered with.

The blockchain network of the present disclosure may store transactions transmitted from the server 100, the user terminal 200, the external server 300, and/or other user terminals in block form based on a predetermined consensus algorithm. Data stored in block form can be shared by a plurality of nodes constituting a blockchain network. Here, each of the server 100, user terminal 200, external server 300, and/or other user terminals may be one of a plurality of nodes constituting a blockchain network.

In an exemplary embodiment, nodes in a blockchain network may be operated by a blockchain core package according to a hierarchical structure. The hierarchical structure is: a data layer that defines the structure of data handled in the blockchain network and manages the data; performs mining that verifies block validity and creates blocks; and handles fees paid to miners during the mining process. A consensus layer in charge, an execution layer that processes and executes smart contracts, a common layer that implements and manages P2P network protocols, hash functions, digital signatures, encoding, and common storage, and an application layer that creates, processes, and manages various applications. can include

A blockchain network may include multiple nodes. In addition, at least one node included in the blockchain network may receive a transaction from the server 100, the user terminal 200, the external server 300, and/or other user terminals. In this case, each of a plurality of nodes included in the blockchain network may verify the transaction through a consensus algorithm and generate a block. Also, each of the plurality of nodes may record a transaction in the created block.

The server 100, user terminal 200, external server 300 and/or other user terminals may operate as nodes constituting a blockchain network. In this example, the server 100, the user terminal 200, the external server 300, and/or other user terminals have at least one of a wallet function, a miner function, and a storage function of full blockchain data. function can be implemented. For example, when the server 100, the user terminal 200, the external server 300, and/or other user terminals include only a wallet function, a node that performs transactions and validation (e.g., SPV (Simplified Payment Verification ) node).

The term “node” used in this disclosure refers to any form of computing, such as a server or terminal capable of exchanging data with at least one of “server”, “user terminal”, “external server” and “blockchain network”. may be a device. However, it is not limited thereto, and the node may be any device capable of mutually exchanging data between a plurality of nodes.

According to some embodiments of the present disclosure, a plurality of nodes included in a blockchain network may include a full block chain node and a lightweight node.

A full blockchain node can include all block information from the first block in the block chain to the currently newly created block. In addition, the full blockchain node collects and stores all blockchain information, and can verify the received block in order to add a new block.

A lightweight node does not have the original source of all block information, and may include only header information. In order for a lightweight node to verify a transaction, it can perform SPV (Simple Payment Verify).

For example, a lightweight node can request block information from a full blockchain node and confirm the authentication details of the transaction through the Merkle Root.

However, for convenience of description, a plurality of nodes included in a blockchain network may be described below assuming that they are full blockchain nodes.

The term “block” used in this disclosure is a unit stored in a blockchain network, and can form a blockchain as it is connected to adjacent blocks.

When the contents related to the information of the server 100, the information of the user terminal 200, the information of the external server 300, the information of the user terminals, and the information of the blockchain network are issued to the blockchain network as a transaction, the transaction becomes a block It can be included in and recorded on the blockchain network. Depending on the settings of the blockchain network, the right to read, the right to agree, and/or the right to verify data stored in a block may be determined.

A plurality of nodes included in the blockchain network may share and store generated transactions and/or smart contracts through the network. In addition, a plurality of nodes may perform a function of recording a transaction in a block when the transaction and/or smart contract verification is completed through the consensus algorithm of block chain technology.

This blockchain network can be implemented in a form included in an artificial intelligence-based counterfeit product screening and digital certificate issuance system. However, it is not limited thereto, and a blockchain network may be implemented as a separate entity.

Depending on the type of implementation, the blockchain network may include a public blockchain network in which arbitrary nodes can perform consensus operation or a private blockchain network in which only predetermined nodes can perform consensus operation.

According to some embodiments of the present disclosure, the consensus algorithm performed in the blockchain network is: Proof of Work (PoW) algorithm, Proof of Stake (PoS) algorithm, Delegated Proof of Stake (DPoS) algorithm, Practical Byzantine Fault Tolerance (PBFT) ) algorithm, DBFT (Delegated Byzantine Fault Tolerance) algorithm, RBFT (Redundant Byzantine Fault Tolerance) algorithm, Sieve algorithm, Tendermint algorithm, Paxos algorithm, Raft algorithm, PoA (Proof of Authority) algorithm, and/or PoET (Proof of Elapsed Time) Algorithms may be included.

Since transactions or tokens containing digital certificates are recorded in blocks using the consensus algorithm of blockchain technology, forgery or alteration of digital certificates related to products that have been verified as genuine can be prevented.

Meanwhile, the blockchain network structure of the present disclosure may be of a public type or a private type. In the case of a public blockchain network, since verification must be performed on all nodes to verify a transaction, there is a disadvantage that it is inefficient in terms of consensus time, transaction processing speed, and efficiency of use of computing resources. Because it is possible, there may be advantages in the transparency and integrity of the stored data. In addition, in the case of a private type (or consortium type) blockchain, since the operator is clear, there is an advantage of being efficient in terms of consensus time, transaction processing speed, and efficiency of use of computing resources, but transparency of the transaction processing process and results In terms of, there may be advantages.

The consensus algorithm in some embodiments of the present disclosure may be a private type or consortium type blockchain network in order to improve user experience through efficient utilization of computing resources and increase in transaction processing speed, but is not limited thereto. Depending on the implementation, the public type may be used as a consensus algorithm if transparency of a transaction or smart contract is to be emphasized more.

On the other hand, consumers can check the authenticity of the product by using the digital certificate. In addition, information for verifying a connection relationship between a real product and a corresponding digital certificate (ie, whether or not the digital certificate is an actual product for which a digital certificate has been issued) may be stored in the digital certificate.

For example, fingerprint information for determining the identity of a corresponding product may be stored in the digital certificate, or information for accessing the corresponding fingerprint information may be stored. For example, the fingerprint information may include, but is not limited to, an image of a product or a label attached to a product or other characteristic information for determining the identity of a corresponding product.

For another example, a seed value of a hash value for determining the identity of a corresponding product may be stored in the digital certificate, or information for accessing the corresponding seed value may be stored. For example, the user can prove the correlation between the digital certificate and the product by hashing the seed value and comparing it with the hash value recorded in the product.

A consumer can determine the identity of a product for which a digital certificate has been issued and a product owned by the consumer using the provided app, and the app can request a photograph of the product based on the fingerprint information. The user can take a picture of the product according to the request, and the app can send the information to the server to request identity determination.

The server may provide the consumer with information on whether or not the digital certificate issued for the corresponding product is correct according to the result of determining the identity.

In a non-limiting embodiment, identity verification through an app may be performed only through an image taken with a consumer's device at a specific time period. For example, it may be configured to enable identity confirmation using only images directly captured in a specific time period so that identity confirmation cannot be performed with a previously captured image. In this process, a process of generating and verifying OTP information may be accompanied, but is not limited thereto.

In various embodiments, the used transaction platform may be interlocked through an app that provides a digital certificate and provides an identity confirmation service. For example, a consumer can use an app to manage digital certificates, verify product identity (i.e., verify authenticity), and use a second-hand trading platform through the app.

When registering a product on the used trading platform through the app, the server transmits digital certificate information about the product or information that the product is a product that has been confirmed genuine and is safely managed with a digital certificate according to the disclosed embodiment. provided through the platform. Alternatively, the used trading platform may be configured to register only products whose authenticity has been confirmed with a digital certificate according to the disclosed embodiment.

As described above, the system according to the disclosed embodiment may check authenticity from the customs clearance process and issue a digital certificate. The issued digital certificate is then delivered in the transaction process and used to verify the authenticity and identity of the product. In addition, by enabling consumers to use the second-hand transaction platform via digital certificates, there is an advantage in providing integrated services that cover from customs clearance to transactions through distributors and second-hand transactions.

Hereinafter, a more detailed description related to the artificial intelligence-based counterfeit screening test and digital certificate issuance system will be described later with reference to FIGS. 4 to 7 .

4 is a diagram for explaining an example of an artificial intelligence-based counterfeit product screening test and digital certificate issuance method according to some embodiments of the present disclosure.

Referring to FIG. 4 , the processor 110 of the server 100 may acquire at least one product image (S110).

Specifically, the processor 110 of the server 100 may acquire at least one image of an item by controlling a plurality of cameras and a plurality of lights provided to photograph an item based on photographing information corresponding to the item. . Here, photographing information may be received from a product manufacturer. In addition, the photographing information may be information in which a photographing position and a photographing method are mapped corresponding to each brand and type of a product subject to the counterfeit product screening test. That is, information on a location and a shooting method for each product or brand may be provided.

The processor 110 of the server 100 may perform a counterfeit screening test on the product based on at least one product image (S120).

Specifically, the processor 110 of the server 100 may determine whether the product is genuine by using at least one product image and a pretrained neural network model. Here, the pre-trained neural network model may be a model trained with training data in which genuine images and counterfeit images are labeled.

For example, the processor 110 of the server 100 may obtain a score value corresponding to a genuine product class by inputting at least one product image to a pretrained neural network model. In addition, the processor 110 may determine that the product is genuine when the score value exceeds a predetermined threshold value. Meanwhile, the processor 110 may determine that the product is counterfeit when the score value is less than or equal to the threshold value.

For example, the processor 110 of the server 100 may determine that the product corresponding to at least one product image is genuine when the score value corresponding to the genuine class is 85 and the predetermined threshold value is 80. . Meanwhile, when the score value corresponding to the genuine class is 75 and the predetermined threshold value is 80, the processor 110 may determine that the product corresponding to at least one product image is a counterfeit product.

As another example, the processor 110 of the server 100 may obtain a score value corresponding to a counterfeit product class by inputting at least one product image to a pretrained neural network model. In addition, the processor 110 may determine the product as a suspected counterfeit product when the score value corresponding to the counterfeit product class exceeds a preset first threshold value and is equal to or less than a second threshold value greater than the first threshold value. Meanwhile, the processor 110 may determine the product as a counterfeit when the score value corresponding to the counterfeit class exceeds the second threshold.

For example, the processor 110 of the server 100, when the score corresponding to the counterfeit product class is 65, the preset first threshold value is 60, and the preset second threshold value is 70, at least one item A product corresponding to the image may be judged as a suspected counterfeit product. Meanwhile, when the score value corresponding to the counterfeit product class is 75 and the predetermined second threshold value is 70, the processor 110 may determine the product corresponding to at least one product image as a counterfeit product.

According to some embodiments of the present disclosure, when the processor 110 of the server 100 determines that the product is genuine in step S120, it may issue a digital certificate for the product (S130). Here, the digital certificate may include fingerprint information corresponding to the product and history information about a process of determining whether the product is genuine.

Finger print information of the present disclosure includes at least one product image and may be unique identification information for identifying a product determined to be genuine, but is not limited thereto.

The server 100 of the present disclosure may be connected to a blockchain network to issue a digital certificate, or may be any one of a plurality of nodes constituting the blockchain network. That is, digital certificates can be formed in the form of tokens issued by blockchain networks or linked to tokens.

In one embodiment, a digital certificate may be issued in a DID format. That is, inspection information (e.g., no suspicion of infringement of intellectual property rights) and fingerprint information can be stored for products that have been confirmed, and inspection numbers can be generated to issue digital certificates in the form of DID. After that, the digital certificate can be issued using the DID issuance information (ie, the inspection number).

As another example, the digital certificate may be created in the form of a token having uniqueness by storing a unique value, for example, a non-fungible token (NFT) or linked to a non-fungible token. However, it is not limited thereto.

In the case of NFT, once issued, it cannot be changed, but with DID, information to be included in the certificate can be added according to the situation. Accordingly, DID or NFT technology can be selected and utilized according to the purpose.

In a preferred embodiment of the present invention, the DID is easier to manage. For example, if a problem such as the Fake NFT issue occurs, using DID has the advantage of being able to discard or retrieve the DID. Through this, it is possible to control cases in which distribution of digital certificates are abused (eg, when a product matching a digital certificate is replaced with a counterfeit product and sold second-hand, or when only digital certificates are sold separately).

According to some other embodiments of the present disclosure, if the processor 110 of the server 100 determines that the product is counterfeit or suspected of being counterfeit in step S120, a message requesting re-authentication of the product is sent to the manager terminal. can transmit In addition, when it is determined that the product is genuine through re-authentication, a digital certificate for the product may be issued.

For example, an administrator who receives a message requesting re-certification may transfer the corresponding item or image of the item to the right holder (ie, the right holder holding the intellectual property right to the corresponding item) and request determination of whether the item is counterfeit or not. In addition, the administrator may send a reply to the server 100 of the result of determining whether the product is counterfeit or not from the owner of the right.

According to some additional embodiments of the present disclosure, the processor 110 of the server 100 may perform genuine product authentication based on the product image when receiving an product image for product product authentication from a user terminal or an external server. . Here, the item image may include at least one of an image captured based on photographing information corresponding to the item and an image in which a hash value recorded in the item is captured.

Specifically, the processor 1100 of the server 100 may determine whether a digital certificate for an article exists using an image captured based on photographing information corresponding to the article. and authentication of the product may be performed by proving a correlation between the product and the digital certificate using an image of a hash value recorded in the product.

Hereinafter, a description of a method for the processor 110 of the server 100 to verify the correlation between an article and a digital certificate will be described later with reference to FIGS. 6 and 7 .

When product activation is performed, the processor 110 of the server 100 may transmit an authentication result to a user terminal or an external server. Here, the user terminal or the external server may be related to the used trading platform. For example, the user terminal may be a used product seller or buyer terminal. The external server may be a used trading platform server.

That is, the server 100 of the present disclosure can provide a more accurate genuine product authentication function by verifying whether a counterfeit product has been tested (if a digital certificate exists) and proving a correlation between the product and the digital certificate.

5 is a diagram for explaining an example of a method of issuing a digital certificate according to some embodiments of the present disclosure.

5, the processor 110 of the server 100 stores inspection information (e.g., there is no suspicion of infringement of intellectual property rights) and fingerprint information when the product is certified as genuine, and issues a digital certificate in DID format. A check number can be generated for Thereafter, a digital certificate can be issued using the DID issuance information (ie, a test number) (S210). Then, the processor 110 may record inspection information (eg, fingerprint information, genuineness determination, etc.) in the digital certificate (S220).

As another example, if the product is certified as genuine, the processor 110 of the server 100 performs minting to link the fingerprint information and the token to obtain a non-fungible token (NFT) corresponding to the product. can create And, the processor 110 may record whether or not the authenticity of the product is determined in the NFT. Here, the NFT may be a digital certificate. However, it is not limited thereto, and the NFT may be configured in a form connected to a digital certificate.

The digital certificate of the present disclosure may include token identification information, product meta information, and transaction details. However, it is not limited thereto, and the digital certificate may include more information than the above-described elements according to the type of item or the token creator's request.

For example, the token identification information may include a unique identification value assigned to the token. The product meta information may include at least one of product fingerprint information, product name information, product price information, and product detailed information. The transaction history may include at least one of information about a history of token generation and information about a history of change in ownership of a token.

According to some other embodiments of issuing a digital certificate of the present disclosure, the processor 110 of the server 100 generates a wallet on a blockchain network, a private key, and a public key corresponding to the private key. (public key) can be generated. Here, each of the wallet, private key, and public key may be a wallet, private key, and public key of the server. However, it is not limited thereto, and may be a wallet, a private key, and a public key of a user terminal of an item owner.

The processor 110 of the server 100 may generate fingerprint information and history information. In addition, the processor 110 may generate signature data obtained by encrypting fingerprint information and history information with a private key through an asymmetric key encryption algorithm. Also, the processor 110 may generate a transaction including fingerprint information, history information, and signature data. In addition, the processor 110 may cause a plurality of nodes to record the transaction in a block through a consensus algorithm by transmitting the transaction and the public key to at least one node included in the blockchain network. Here, the digital certificate may be a transaction recorded in a block of a blockchain network, but is not limited thereto.

In this case, at least one node included in the blockchain network may receive a transaction and a public key from the server 100. In addition, each of a plurality of nodes included in the blockchain network may decrypt the signature data included in the transaction using the received public key. In addition, each of a plurality of nodes included in the blockchain network may recognize whether the decrypted data and the saved data match. When each of a plurality of nodes included in the blockchain network recognizes that the decrypted data and the saved data match, the transaction can be verified through a consensus algorithm and a block can be created. Also, each of the plurality of nodes may record a transaction in the created block.

That is, each of a plurality of nodes included in the blockchain network can check whether the server 100 sent the transaction using the signature data included in the transaction. In addition, each of a plurality of nodes included in the blockchain network may record the transaction in a block based on a consensus algorithm when recognizing that the server 100 has sent the transaction.

A transaction may include a transaction input value including identification information generated from a private key. In addition, the transaction may include a transaction output value including fingerprint information and history information and address information in a blockchain network in which a transaction including the finger print information and the history information will be stored.

Specifically, the transaction is a consensus algorithm when any one of a plurality of nodes included in the blockchain network extracts a specific nonce value that satisfies a predetermined specific condition, and the specific nonce value is recognized as valid in each of the plurality of nodes. It can be recognized that it has been verified through Here, the preset specific condition may be satisfied when a hash value of a block generated when information stored in a block header and a specific nonce value is converted through a hash algorithm is smaller than a difficulty value of the block. Here, the block may include fingerprint information and history information generated as the server 100 determines that the product is genuine.

Accordingly, the server 100 of the present disclosure may ensure the integrity of the digital certificate by recording the digital certificate role performance information included in the transaction on the blockchain network.

6 is a diagram for explaining an example of a method for verifying a correlation between an article and a digital certificate according to some embodiments of the present disclosure.

Referring to FIG. 6 , the processor 110 of the server 100 may assign a serial number to the product when it is determined that the product is genuine (S310). Also, the processor 110 may record the serial number in the digital certificate (S320).

Then, the processor 110 of the server 100 may record the first hash value obtained by hashing the serial number to the product (S330).

Specifically, the processor 110 of the server 100 may hash the serial number using SHA (Secure Hash Algorithm). Here, SHA may include at least one of SHA-128, SHA-256 and SHA-512, but is not limited thereto.

Meanwhile, the processor 110 of the server 100 may receive a first hash value recorded in the product when authenticating the product.

For example, the processor 110 of the server 100 receives a first hash value recorded in an article from a user terminal or a used trading platform server related to a seller or buyer of a used article, or an article image in which the first hash value is captured. can receive

When obtaining the first hash value, the processor 110 of the server 100 may obtain the second hash value by hashing the serial number recorded in the digital certificate. In addition, the processor 1100 may authenticate that the product is genuine when the first hash value and the second hash value correspond to each other.

For example, the processor 110 of the server 100 may authenticate that the product is genuine when the first hash value recorded in the product is the same as the second hash value obtained by hashing the serial number recorded in the digital certificate.

7 is a diagram for explaining another example of a method for verifying a correlation between an article and a digital certificate according to some embodiments of the present disclosure.

Referring to FIG. 7 , the processor 110 of the server 100 may assign a serial number to the product when it is determined that the product is genuine (S410). Also, the processor 110 may record the serial number in the digital certificate (S420). Also, the processor 110 may obtain a first hash value by hashing the serial number (S430). Also, the processor 110 may obtain a first split value and a second split value by dividing the first hash value into at least two (S440). Then, the processor 110 may record the first division value in the article and transmit the second division value to the user terminal (S450).

According to some embodiments of the present disclosure, when authenticating an article, the processor 110 of the server 100 receives a first division value recorded in the article and receives a second division value from the user terminal. can do.

For example, the processor 110 of the server 100 receives a first division value recorded in an article from a user terminal or a used trading platform server related to a seller or buyer of a used article, or an article image in which the first hash value is captured. can receive Also, the processor 110 may receive a second division value from a user terminal associated with a used item seller.

When receiving the first division value and the second division value, the processor 110 of the server 100 may obtain a second hash value by hashing the serial number recorded in the digital certificate. Further, the processor 110 may authenticate that the product is genuine when a combination value obtained by combining the first division value and the second division value corresponds to the second hash value.

For example, when the first partition value is 1234, the second partition value is 4567, and the second hash value is 1234567, the processor 110 of the server 100 combines the first partition value and the second partition value. It is determined that the product corresponds to (or is identical to) 12345678, which is a combination value, and the product can be authenticated as genuine.

According to some other embodiments of the present disclosure, when authenticating a product, the processor 110 of the server 100 may receive a first division value recorded in the product.

For example, the processor 110 of the server 100 receives a first division value recorded in an article from a user terminal or a used trading platform server related to a seller or buyer of a used article, or an article image in which the first hash value is captured. can receive

When receiving the first division value, the processor 110 of the server 100 may obtain a second hash value by hashing the serial number recorded in the digital certificate. And, when the first division value is included in the second hash value, the processor 110 may authenticate that the product is genuine.

For example, when the first division value is 1234 and the second hash value is 1234567, the processor 110 of the server 100 determines that the first division value is included in the second hash value and authenticates that the product is genuine. can do.

According to some additional embodiments of the present disclosure, when the processor 110 of the server 100 divides the first hash value into at least two pieces in step S440, the first hash value is first divided into the digital certificate. It is possible to record information about a method of dividing into a value and a second division value.

For example, the information on the splitting method may include information on the number corresponding to the first split value and the number corresponding to the second split value among a plurality of values constituting the first hash value. For another example, the information on the splitting method may include information on the number of digits corresponding to the first split value and the number of digits corresponding to the second split value among a plurality of values constituting the first hash value. .

In this case, when authenticating a product, the processor 110 of the server 100 may receive a first division value recorded in the article and information about a division method. Also, the processor 110 may acquire a third partition value by dividing the second hash value based on the information about the division method. Further, the processor 110 may authenticate that the product is genuine when the third division value corresponds to the first division value.

For example, if the second hash value is 12345678, the processor 110 of the server 100 is based on information about the division method (eg, the number corresponding to the first division value. Here, 4). A third division value of 1234 can be obtained as Also, the processor 110 may authenticate that the product is genuine when the third division value and the first division value are the same.

For another example, when the second hash value is 12345678, the processor 110 of the server 100 provides information on a division method (eg, digits corresponding to the first division value. Here, 1, 2,5,6), a third division value of 1256 can be obtained. Also, the processor 110 may authenticate that the product is genuine when the third division value and the first division value are the same.

Therefore, the server 100 of the present disclosure can clearly prove the correlation between the digital certificate and the product by using the hash value, which is impossible to decrypt, and perform genuine product authentication for the product based on this.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (18)

In the artificial intelligence-based counterfeit screening test and digital certificate issuance method performed by a computing device,
acquiring at least one article image;
performing a counterfeit product screening test on products based on the at least one product image; and
issuing a digital certificate for the product and allocating a serial number to the product if it is determined that the product is genuine;
recording the serial number into the digital certificate;
hashing the serial number to obtain a first hash value;
dividing the first hash value into at least two parts to obtain a first partition value and a second partition value; and
recording the first division value in the article and transmitting the second division value to a user terminal;
including,
The digital certificate,
Includes fingerprint information corresponding to the product and history information about a process of determining whether the product is genuine;
Issued in the form of a non-fungible token, linked to the non-fungible token, or issued in the form of a decentralized proof of identity;
The fingerprint information,
Including any one of the at least one article image,
Unique identification information for identifying the product determined to be genuine,
When the digital certificate is issued in the form of the non-fungible token, information contained in the digital certificate is recorded in the non-fungible token, and when the digital certificate is issued in the form of the decentralized identification, inspection of the item The digital certificate is generated using the number;
When authenticating the product, a first division value recorded in the product is received, a second division value is received from the user terminal, and the serial number recorded in the digital certificate is hashed to obtain a second division value. Obtaining a hash value, and when a combination value obtained by combining the first split value and the second split value corresponds to the second hash value, authenticating that the product is genuine;
If it is determined that the product is counterfeit or suspected to be counterfeit, a message requesting re-authentication of the product is transmitted to the manager terminal, and if the product is determined to be genuine through the re-authentication, a digital certificate for the product issuing,
Linking with a used trading platform, obtaining a request for a result of determining whether the item is genuine or not from the used trading platform, and providing a digital certificate for the item in response to the request,
AI-based counterfeit product inspection and digital certificate issuance method.
According to claim 1,
Acquiring at least one product image,
obtaining an image of the at least one item by controlling a plurality of cameras and a plurality of lights provided to photograph the item based on photographing information corresponding to the item;
including,
The shooting information,
Information in which the shooting location and shooting method are mapped in correspondence with each brand and type of the counterfeit goods subject to screening,
AI-based counterfeit product inspection and digital certificate issuance method.
According to claim 1,
The step of performing a counterfeit screening test on an article based on the at least one article image,
determining whether the product is genuine by using the at least one product image and a pretrained neural network model;
including,
The pretrained neural network model,
A model trained with training data labeled with each of the genuine image and the counterfeit image,
AI-based counterfeit product inspection and digital certificate issuance method.
According to claim 3,
The step of determining whether the product is genuine by using the at least one product image and a pretrained neural network model,
acquiring a score value corresponding to a genuine product class by inputting the at least one product image into the pretrained neural network model; and
determining that the product is a genuine product when the score value exceeds a predetermined threshold value, and determining that the product is a counterfeit product when the score value is less than or equal to the threshold value;
including,
AI-based counterfeit product inspection and digital certificate issuance method.
According to claim 3,
The step of determining whether the product is genuine by using the at least one product image and a pretrained neural network model,
acquiring a score value corresponding to a counterfeit product class by inputting the at least one product image into the pretrained neural network model; and
When the score value corresponding to the counterfeit product class exceeds a first threshold value set in advance and is less than or equal to a second threshold value greater than the first threshold value, the item is determined as a suspected counterfeit item, and the score value corresponding to the counterfeit product class is determining that the product is a counterfeit product when the second threshold value is exceeded;
including,
AI-based counterfeit product inspection and digital certificate issuance method.
delete delete According to claim 1,
If it is determined that the product is genuine, issuing a digital certificate for the product includes:
If it is determined that the product is genuine, storing the fingerprint information and whether or not the product is genuine;
obtaining an inspection number for the article;
generating a digital certificate using the check number; and
recording the fingerprint information and whether or not the product is genuine in the digital certificate;
including,
AI-based counterfeit product inspection and digital certificate issuance method.
According to claim 1,
If it is determined that the product is genuine, issuing a digital certificate for the product includes:
Generating a wallet on a blockchain network, a private key, and a public key corresponding to the private key;
generating the fingerprint information and the history information;
generating signature data obtained by encrypting the fingerprint information and the history information with the private key through an asymmetric key encryption algorithm;
generating a transaction including the fingerprint information, the history information, and the signature data; and
sending the transaction and the public key to at least one node included in the blockchain network, causing a plurality of nodes to record the transaction in a block through a consensus algorithm;
including,
The digital certificate is a transaction recorded in the block of the blockchain network,
AI-based counterfeit product inspection and digital certificate issuance method.
According to claim 1,
assigning a serial number to the product if it is determined that the product is genuine;
recording the serial number into the digital certificate; and
recording a first hash value obtained by hashing the serial number in the article;
Including more,
AI-based counterfeit product inspection and digital certificate issuance method.
According to claim 10,
receiving a first hash value recorded in the product when authenticating the product;
obtaining a second hash value by hashing the serial number recorded in the digital certificate; and
authenticating that the product is genuine when the first hash value corresponds to the second hash value;
Including more,
AI-based counterfeit product inspection and digital certificate issuance method.
delete delete According to claim 1,
receiving a first division value recorded in the product when authenticating the product;
obtaining a second hash value by hashing the serial number recorded in the digital certificate; and
authenticating that the product is genuine when the first division value is included in the second hash value;
Including more,
AI-based counterfeit product inspection and digital certificate issuance method.
15. The method of claim 14,
recording information on a method for dividing the first hash value into the first division value and the second division value in the digital certificate when the first hash value is divided into at least two;
Including more,
When authenticating the product, receiving information about the dividing method;
Obtaining a third split value by dividing the second hash value based on the information on the splitting method;
When the third division value corresponds to the first division value, authenticating that the product is genuine,
AI-based counterfeit product inspection and digital certificate issuance method.
According to claim 1,
performing genuine product authentication based on the product image when an image of a product for product authentication is received from a user terminal or an external server; and
Transmitting an authentication result of the product for performing the genuine authentication to the user terminal or the external server;
Including more,
The product image is
Including at least one of an image captured based on photographing information corresponding to the item and an image in which a hash value recorded in the item is captured.
AI-based counterfeit product inspection and digital certificate issuance method.
a memory that stores one or more instructions; and
a processor to execute the one or more instructions stored in the memory;
By executing the one or more instructions, the processor:
An apparatus that performs the method of claim 1 .
A computer program stored in a computer-readable recording medium to be combined with a computer, which is hardware, to perform the method of claim 1.

Images