NFT classification device

Abstract

An NFT classification device according to the present invention comprises: an acquisition unit that acquires a first feature amount indicating a characteristic relating to each of a plurality of digital objects which are respectively associated with a plurality of NFTs; a first determination unit that determines a second feature amount indicating a relationship between each of the plurality of NFTs and at least one wallet in which each of the plurality of NFTs is stored; and a classification unit that classifies the plurality of NFTs on the basis of the first feature amount and the second feature amount.

Description

NFT classification device

[0001] The present invention relates to an NFT classifier.

[0002] Conventionally, NFTs (Non-Fungible Tokens) have been used to provide uniqueness to digital objects in real or virtual spaces, such as trading cards, digital art, and game items, and to prove the ownership of the digital objects.

[0003] For example, Patent Document 1 discloses an information processing device that manages real-space objects linked to NFTs and certifies their owners.

[0004] Japanese Patent Application Laid-Open No. 2023-136248

[0005] For example, in NFT art, which is digital art that utilizes NFT technology, multiple digital objects that are one-to-one associated with multiple NFTs and share common properties may be treated as a single NFT collection. However, using conventional technology, it has been cumbersome and time-consuming to categorize the multiple digital objects into one or more NFT collections.

[0006] The present disclosure aims to provide an NFT classification device that can classify multiple digital objects that are one-to-one associated with multiple NFTs into one or more NFT collections more easily than when using conventional technology.

[0007] The NFT classification device according to the present disclosure includes a first determination and acquisition unit that determines and acquires a first feature value indicating a characteristic of a digital object for each of a plurality of digital objects that are associated one-to-one with a plurality of NFTs; a 21st determination unit that determines a second feature value indicating a relationship between each of the plurality of NFTs and one or more wallets in which each of the plurality of NFTs has been stored; and a classification unit that classifies the plurality of NFTs based on the first feature value and the second feature value.

[0008] According to the present disclosure, multiple digital objects that are one-to-one associated with multiple NFTs can be easily classified into one or more NFT collections compared to the prior art.

[0009] A diagram showing an example of an NFT collection. A diagram showing an example of an NFT collection. A diagram showing an example of the overall configuration of an NFT classification system 1. An example of data included in block BL. A block diagram showing an example of the configuration of an account management device 30. A block diagram showing an example of the configuration of an object management device 40. A block diagram showing an example of the configuration of a terminal device 50. A block diagram showing an example of the configuration of an NFT classification device 10. A diagram showing an example of a graph G. A diagram showing an example of a vector space VS. A flowchart showing the operation of the NFT classification device 10.

[0010] 1: First Embodiment 1-1: Description of NFT Collection FIGS. 1 and 2 are diagrams illustrating an example of an NFT collection CL. The NFT collection CL1 illustrated in FIG. 1 includes NFT art NA11 to NFT art NA16. Each of NFT art NA11 to NFT art NA16 is a digital object DO. More specifically, each of NFT art NA11 to NFT art NA16 is a digital image. Furthermore, NFT art NA11 to NFT art NA16 are associated one-to-one with multiple different NFTs. Information regarding transactions and ownership of each of the NFT art NA11 to NFT art NA16 is generated and managed using technology using the blockchain BC described below. Furthermore, by being associated with an NFT, the originality and uniqueness of each of the NFT art NA11 to NFT art NA16 as a work of art is guaranteed. Furthermore, the owner of each of the multiple NFTs associated one-to-one with multiple NFT art NA11 to NFT art NA16 is proven by the NFT to be the owner of the NFT art NA corresponding to the NFT. In other words, the NFT is data indicating the owner of NFT art NA11 to NFT art NA16 on the blockchain BC described below.

[0011] 1, NFT art NA11 to NFT art NA16 each have an image of the same penguin in a different pose. Because NFT art NA11 to NFT art NA16 each have an image of the same penguin, these six images are treated as one NFT collection CL1.

[0012] 2 includes NFT art NA21 to NFT art NA24. Each of NFT art NA21 to NFT art NA24 has an image of part of the same penguin. Arranging the images included in NFT art NA21 to NFT art NA24 creates an image of a single penguin, and therefore NFT art NA21 to NFT art NA24 are treated as a single NFT collection CL2.

[0013] For example, when recommending NFT Art NAs to a collector of NFT Art NAs on an NFT Collection CL basis, it may be necessary to classify multiple NFT Art NAs into one or more NFT Collection CLs. However, in conventional technologies, classifying multiple NFT Art NAs into one or more NFT Collection CLs requires cumbersome work. In particular, the more multiple NFT Art NAs there are, the more cumbersome the work becomes. The NFT classification device 10 according to the present disclosure can classify multiple NFT Art NAs, each associated one-to-one with multiple NFTs, into one or more NFT Collection CLs more easily than conventional technologies.

[0014] For the sake of simplicity, the above description deals with an example in which an NFT collection CL includes multiple NFT art pieces NA. However, the NFT collection CL according to this embodiment may also include digital objects DO associated with NFTs other than multiple NFT art pieces NA. Examples of the digital objects DO include still images, videos, music, text, games, and characters. However, the digital objects DO are not limited to these. The NFT classification device 10 according to the present disclosure can more easily classify multiple digital objects DO associated one-to-one with multiple NFTs into one or more NFT collections CL compared to conventional techniques.

[0015] 1-2: Configuration of First Embodiment 1-2-1: Overall Configuration Figure 3 is a diagram showing an example of the overall configuration of an NFT classification system 1 according to this embodiment. The NFT classification system 1 includes an NFT classification device 10, an NFT management system 20, an account management device 30, an object management device 40, and terminal devices 50[1] to 50[4]. The NFT classification device 10, the NFT management system 20, the account management device 30, the object management device 40, and the terminal devices 50[1] to 50[4] are connected to each other via a communication network NET so that they can communicate with each other.

[0016] Terminal devices 50[1] to 50[4] correspond one-to-one to users U[1] to U[4]. Each of users U[1] to U[4] uses a terminal device 50[1] to 50[4]. As an example, user U[1] is the author who creates a digital object DO associated with an NFT by using terminal device 50[1]. As another example, user U[2] is the first purchaser who purchases the digital object DO created by user U[1] from user U[1] by using terminal device 50[2]. As another example, user U[3] is the second purchaser who purchases the digital object DO from user U[2], the first purchaser, by using terminal device 50[3]. As another example, user U[4] is the viewer who views the digital object DO by using terminal device 50[4], for example, via a browser.

[0017] Each of the terminal devices 50[1] to 50[4] may be a PC (Personal Computer), a smartphone, or a tablet.

[0018] In the example shown in FIG. 3, the NFT classification system 1 includes four terminal devices 50[1] to 50[4]. However, the fact that the NFT classification system 1 includes four terminal devices 50 is merely an example. The NFT classification system 1 may include any number of terminal devices 50. Similarly, the fact that the users U who use the terminal devices 50 are four, users U[1] to U[4], is merely an example. The terminal device 50 may be used by any number of users U. Accordingly, the number of authors, purchasers, and viewers who use the terminal devices 50 may also be any number.

[0019] As described above, the NFT classifier 10 classifies a plurality of digital objects DO associated one-to-one with a plurality of NFTs into one or more NFT collections CL. Details of the NFT classifier 10 will be described later with reference to FIGS. 8 to 11.

[0020] The NFT management system 20 is a system that manages multiple NFTs associated with multiple digital objects DO. Data related to the multiple NFTs is managed on a blockchain BC provided in the NFT management system 20. As an example, the blockchain BC records an NFT identifier, information about the NFT owner, and a token uniform resource identifier (URI) indicating the location of the NFT metadata. As an example, the NFT metadata includes data indicating the name of the digital object DO associated with the NFT, a description of the digital object DO, and a uniform resource locator (URL) indicating the location of the digital object DO.

[0021] For example, in response to a request for NFT issuance from user U[1] who created a digital object DO, the NFT management system 20 issues an NFT linked to the digital object DO. In this case, user U[1] is recorded in the blockchain BC as the owner of the NFT at the time of issuance. Furthermore, in response to a request from user U[2] to purchase the digital object DO, the NFT management system 20 transfers the NFT linked to the digital object DO from user U[1] to user U[2]. In this case, user U[2] is recorded in the blockchain BC as the owner of the NFT at the time of NFT transfer. Furthermore, in response to a request from user U[2] to sell the digital object DO and a request from user U[3] to purchase the digital object DO, the NFT management system 20 transfers the NFT linked to the digital object DO from user U[2] to user U[3]. In this case, user U[3] is recorded in the blockchain BC as the owner of the NFT at the time of NFT transfer.

[0022] In a blockchain (BC), the same records are synchronized among multiple nodes on the network. Specifically, the multiple nodes compile NFT transaction data into a format called a block (BL) and store the block (BL) in a chronological order.

[0023] FIG. 4 shows an example of data contained in a block BL. The block BL includes a hash value BH of the previous block BL, a nonce value NV, transaction data TD, and state data SD. The transaction data TD indicates a record of all transactions conducted during the period corresponding to the block BL. As described below, the NFT classification device 10 acquires history data HD from the NFT management system 20, which indicates in which of one or more wallets WL each of multiple NFTs has been stored. The history data HD is generated by the NFT management system 20 based on all transaction data TD contained in the blockchain BC. The state data SD indicates the latest status of all accounts managed in the blockchain BC. As described below, the accounts are managed by the account management device 30. The nonce value NV is a parameter for generating a hash value BH from the block BL. Once the nonce value NV is determined, the block BL is hashed, and the hash value BH is inherited by the immediately following block BL.

[0024] A plurality of blocks BL are connected in chronological order by the hash value BH of the immediately preceding block BL and the nonce value NV contained in each block BL.

[0025] In Figure 3, the account management device 30 issues and manages accounts used for transactions using the blockchain BC. As described above, user U[1], the author, user U[2], the first purchaser, and user U[3], the second purchaser, are recorded in the blockchain BC as owners of NFTs at different times. Therefore, users U[1] to U[3] must have accounts in order to be recorded in the blockchain BC as holders of NFTs. The account management device 30 issues and manages accounts for users U[1] to U[3].

[0026] The object management device 40 manages multiple digital objects DO, including a digital object DO[1] created by user U[1]. User U[1] uploads the digital object DO[1] created by user U[1] using terminal device 50[1] to the object management device 40 via the communication network NET. At least one of user U[2], the first purchaser, and user U[3], the second purchaser, may download the digital object DO[1] created by user U[1] from the object management device 40. Furthermore, at least one of user U[2], the first purchaser, and user U[3], the second purchaser, may transfer ownership of the digital object DO[1] created by user U[1] by transferring the NFT associated with the digital object DO[1] while keeping the digital object DO[1] created by user U[1] stored in the object management device 40. In this case, users U[1] to U[4] can view the digital object DO[1] stored in the object management device 40. As an example, if the digital object DO[1] is a video, the object management device 40 streams the digital object DO to terminal devices 50[1] to 50[4], allowing users U[1] to U[4] to view the digital object DO[1].

[0027] 3, for convenience of explanation, the NFT classification device 10, the NFT management system 20, the account management device 30, and the object management device 40 are depicted as separate entities. However, the account management device 30 functions as one node included in the blockchain BC. Furthermore, at least one of the NFT classification device 10 and the object management device 40 may function as one node included in the blockchain BC.

[0028] 1-2-2: Configuration of the Account Management Device Fig. 5 is a block diagram showing an example configuration of the account management device 30. As shown in Fig. 5, the account management device 30 includes a processing device 31, a storage device 32, an input device 34, and a communication device 35. The elements included in the account management device 30 are connected to each other by one or more buses for communicating information.

[0029] The processing device 31 is a processor that controls the entire account management device 30. The processing device 31 is configured, for example, using one or more chips. The processing device 31 is configured, for example, using a central processing unit (CPU) that includes an interface with peripheral devices, an arithmetic unit, and a register. Note that some or all of the functions of the processing device 31 may be realized by hardware such as a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA). The processing device 31 executes various processes in parallel or sequentially.

[0030] The storage device 32 is a recording medium that can be read and written by the processing device 31. The storage device 32 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a ROM, an EPROM, and an EEPROM. The volatile memory is, for example, a RAM.

[0031] The storage device 32 stores multiple programs, including a control program PR3, to be executed by the processing device 31. Furthermore, in order for the account management device 30 to function as a node in the blockchain BC, the storage device 32 stores data managed in the blockchain BC. The data managed in the blockchain BC includes an account database ADB. In the account database ADB, account information for users U[1] to U[4] is associated one-to-one with wallet information indicating the locations of wallets WL[1] to WL[4] provided in each of terminal devices 50[1] to 50[4], which will be described later. As will be described later, wallet WL is a module that electronically stores NFTs held by user U. Wallets WL[1] to WL[4] are associated one-to-one with terminal devices 50[1] to 50[4].

[0032] The storage device 32 also functions as a work area for the processing device 31 .

[0033] The input device 34 is a device that accepts operations by an administrator of the NFT classification system 1. For example, the input device 34 is configured to include a keyboard, a touchpad, a touch panel, or a pointing device such as a mouse.

[0034] The communication device 35 is hardware serving as a transmitting / receiving device for communicating with other devices. The communication device 35 is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 35 may include a connector for wired connection and an interface circuit corresponding to the connector. The communication device 35 may also include a wireless communication interface. Examples of the connector and interface circuit for wired connection include products that comply with wired LAN, IEEE 1394, and USB. Examples of the wireless communication interface include products that comply with wireless LAN, Bluetooth (registered trademark), etc.

[0035] The processing device 31 functions as a communication control unit 311 and a management unit 312 by, for example, reading and executing a control program PR3 from the storage device 32.

[0036] The communication control unit 311 causes the communication device 35 to send and receive various data between the NFT classification device 10, information processing devices other than the account management device 30 included in the blockchain BC, the object management device 40, and terminal devices 50[1] to 50[4].

[0037] The management unit 312 manages the account database ADB. More specifically, the management unit 312 manages the account information of users U[1] to U[4] stored in the account database ADB, and the wallet information of wallets WL[1] to WL[4]. The management unit 312 may also manage NFTs stored in wallets WL[1] to WL[4] provided in terminal devices 50[1] to 50[4]. The management of NFTs includes the management unit 312 requesting the blockchain BC to issue or transfer NFTs associated with digital objects DO.

[0038] 1-2-3: Configuration of Object Management Device Fig. 6 is a block diagram showing an example configuration of the object management device 40. As shown in Fig. 6, the object management device 40 includes a processing device 41, a storage device 42, an input device 44, and a communication device 45. The elements included in the object management device 40 are connected to each other by one or more buses for communicating information.

[0039] The processing device 41 is a processor that controls the entire object management device 40. The processing device 41 is configured, for example, using one or more chips. The processing device 41 is configured, for example, using a central processing unit (CPU) that includes an interface with peripheral devices, an arithmetic unit, and a register. Note that some or all of the functions of the processing device 41 may be realized by hardware such as a DSP, ASIC, PLD, and FPGA. The processing device 41 executes various processes in parallel or sequentially.

[0040] The storage device 42 is a recording medium that can be read and written by the processing device 41. The storage device 42 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a ROM, an EPROM, and an EEPROM. The volatile memory is, for example, a RAM.

[0041] The storage device 42 stores a plurality of programs including a control program PR4 to be executed by the processing device 41. The storage device 42 stores an object database ODB. The object database ODB stores digital objects DO[1] to DO[p], where p is an integer equal to or greater than 1.

[0042] More specifically, in the object database ODB, digital objects DO[1] through DO[p] are associated with metadata for the digital objects DO[1] through DO[p]. The metadata includes identifiers for the digital objects DO[1] through DO[p], an identifier for the author, and information indicating the title of the work. Furthermore, in the object database ODB, in order to associate each of the digital objects DO[1] through DO[p] with an NFT, the identifiers for the digital objects DO[1] through DO[p] and the identifiers of the NFTs corresponding to the digital objects DO[1] through DO[p] are stored in association with each other. The NFT identifiers may be, for example, public keys.

[0043] The storage device 42 also functions as a work area for the processing device 41 .

[0044] The input device 44 is a device that accepts operations by an administrator of the NFT classification system 1. For example, the input device 44 is configured to include a keyboard, a touchpad, a touch panel, or a pointing device such as a mouse.

[0045] The communication device 45 is hardware serving as a transmitting / receiving device for communicating with other devices. The communication device 45 is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 45 may include a connector for wired connection and an interface circuit corresponding to the connector. The communication device 45 may also include a wireless communication interface. Examples of the connector and interface circuit for wired connection include products that comply with wired LAN, IEEE 1394, and USB. Examples of the wireless communication interface include products that comply with wireless LAN, Bluetooth (registered trademark), etc.

[0046] The processing device 41 functions as a communication control unit 411, a management unit 412, and an extraction unit 413, for example, by reading and executing a control program PR4 from the storage device 42.

[0047] The communication control unit 411 causes the communication device 45 to send and receive various data between the NFT classification device 10, the NFT management system 20 including the account management device 30, and the terminal devices 50[1] to 50[4].

[0048] The management unit 412 manages the object database ODB. For example, when a user U[1] uploads a digital object DO[1] created by the user U[1] using the terminal device 50[1] to the object management device 40, the management unit 412 acquires the digital object DO[1] created by the user U[1] from the terminal device 50[1] via the communication device 45. The management unit 412 also stores the digital object DO[1] acquired from the terminal device 50[1] in the object database ODB together with its metadata.

[0049] When user U[2] purchases digital object DO[1] and downloads the digital object DO[1] from the object management device 40 to terminal device 50[2], the management unit 412 outputs the digital object DO[1] to the terminal device 50[2] via the communication device 45. Furthermore, when user U[2] subsequently sells the digital object DO[1], the management unit 412 may obtain the digital object DO[1] from the terminal device 50[2] via the communication device 45. In this case, the management unit 412 stores the digital object DO[1] obtained from the terminal device 50[2] together with its metadata in the object database ODB.

[0050] The same applies when user U[3] buys and sells digital object DO[1].

[0051] The extraction unit 413 extracts feature quantities indicating characteristics of each of the digital objects DO[1] to DO[p] stored in the object database ODB. The feature quantities, for example, indicate characteristics related to at least one of the characters, images, and audio contained in each of the digital objects DO[1] to DO[p]. Character-related features, for example, may be characteristics related to the type of characters contained in each of the digital objects DO[1] to DO[p]. Image-related features, for example, may be characteristics related to the pixels constituting the images contained in each of the digital objects DO[1] to DO[p]. Audio-related features, for example, may be characteristics related to the results of processing the waveforms of the audio contained in each of the digital objects DO[1] to DO[p]. Data indicating the feature quantities is expressed as an m-dimensional feature vector, where m is an integer greater than or equal to 1. The feature quantity corresponding to the m-dimensional feature vector is an example of a "first feature quantity." The above m-dimensional feature vector is an example of a "first vector."

[0052] The features extracted by the extraction unit 413 are stored in the object database ODB together with the digital objects DO[1] to DO[p] to which each feature corresponds. As an example, the features may be stored in the object database ODB as metadata for the digital objects DO[1] to DO[p]. Furthermore, as described below, the features stored in the object database ODB are transmitted to the NFT classification device 10 via the communication device 45.

[0053] 1-2-4: Configuration of Terminal Device Fig. 7 is a block diagram showing an example configuration of the terminal device 50. As shown in Fig. 7, the terminal device 50 includes a processing device 51, a storage device 52, a display 53, an input device 54, a speaker 55, and a communication device 56. The elements included in the terminal device 50 are connected to each other by one or more buses for communicating information.

[0054] The processing device 51 is a processor that controls the entire terminal device 50. The processing device 51 is configured, for example, using one or more chips. The processing device 51 is configured, for example, using a central processing unit (CPU) that includes an interface with peripheral devices, an arithmetic unit, and a register. Note that some or all of the functions of the processing device 51 may be realized by hardware such as a DSP, an ASIC, a PLD, and an FPGA. The processing device 51 executes various processes in parallel or sequentially.

[0055] The storage device 52 is a recording medium that can be read and written by the processing device 51. The storage device 52 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a ROM, an EPROM, and an EEPROM. The volatile memory is, for example, a RAM.

[0056] Wallet WL is stored in storage device 52. There is a one-to-one correspondence between terminal device 50[1] to terminal device 50[4] and wallet WL[1] to wallet WL[4]. Also, since there is a one-to-one correspondence between user U[1] to user U[4] and terminal device 50[1] to terminal device 50[4], there is a one-to-one correspondence between user U[1] to user U[4] and wallet WL[1] to wallet WL[4].

[0057] Wallet WL is a module that electronically stores NFTs held by user U. As an example, account information for users U[1] to U[4] may be used as public keys in a public key cryptosystem, and private keys corresponding to the public keys may be stored in wallets WL[1] to WL[4]. There is a one-to-one correspondence between the multiple pieces of account information for users U[1] to U[4] as public keys and the multiple private keys stored in wallets WL[1] to WL[4].

[0058] The storage device 52 also stores a plurality of programs including a control program PR5 to be executed by the processing device 51. The storage device 52 also functions as a work area for the processing device 51.

[0059] The display 53 is a device that displays images and text information. The display 53 displays various images under the control of the processing device 51. For example, various display panels such as a liquid crystal panel and an organic EL panel are suitably used as the display 53.

[0060] The input device 54 is a device that accepts operations by the user U. For example, the input device 54 is configured to include a keyboard, a touchpad, a touch panel, or a pointing device such as a mouse. Here, if the input device 54 is configured to include a touch panel, it may also serve as the display 53.

[0061] The speaker 55 is a device that emits sound. The speaker 55 emits various sounds under the control of the processing device 51. For example, sound data, which is a digital signal, is converted into a sound signal, which is an analog signal, by a DA converter (not shown). The amplitude of the sound signal is amplified by an amplifier (not shown). The speaker 55 emits the sound represented by the sound signal after the amplitude has been amplified.

[0062] The communication device 56 is hardware serving as a transmitting / receiving device for communicating with other devices. The communication device 56 is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 56 may include a connector for wired connection and an interface circuit corresponding to the connector. The communication device 56 may also include a wireless communication interface. Examples of the connector and interface circuit for wired connection include products that comply with wired LAN, IEEE 1394, and USB. Examples of the wireless communication interface include products that comply with wireless LAN, Bluetooth (registered trademark), etc.

[0063] The processing device 51 functions as a communication control unit 511, a display control unit 512, and a voice control unit 513, for example, by reading and executing a control program PR5 from the storage device 52.

[0064] The communication control unit 511 causes the communication device 56 to transmit and receive various data between the NFT classification device 10, the NFT management system 20 including the account management device 30, and the object management device 40.

[0065] The various data include data instructing the account management device 30 to manage the data stored in the account database ADB. The data also includes an NFT issuance request and an NFT transfer request. The NFT issuance request and NFT transfer request are generated based on an operation by the user U using the input device 54. The various data also include a digital object DO transmitted and received between the object management device 40 and the object management device 40.

[0066] The display control unit 512 causes the display 53 to display a still image or a video showing the digital object DO.

[0067] The audio control unit 513 causes the speaker 55 to emit the audio included in the digital object DO.

[0068] 1-2-5: Configuration of NFT Classification Device Fig. 8 is a block diagram showing an example configuration of the NFT classification device 10. As shown in Fig. 8, the NFT classification device 10 includes a processing device 11, a storage device 12, an input device 14, and a communication device 15. The elements included in the NFT classification device 10 are connected to each other by one or more buses for communicating information.

[0069] The processing device 11 is a processor that controls the entire NFT classification device 10. The processing device 11 is configured, for example, using one or more chips. The processing device 11 is configured, for example, using a central processing unit (CPU) including an interface with peripheral devices, an arithmetic unit, and a register. Note that some or all of the functions of the processing device 11 may be realized by hardware such as a DSP, an ASIC, a PLD, and an FPGA. The processing device 11 executes various processes in parallel or sequentially.

[0070] The storage device 12 is a recording medium that can be read and written by the processing device 11. The storage device 12 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a ROM, an EPROM, and an EEPROM. The volatile memory is, for example, a RAM.

[0071] The storage device 12 stores a plurality of programs including a control program PR1 to be executed by the processing device 11. The storage device 12 also functions as a work area for the processing device 11.

[0072] The input device 14 is a device that accepts operations by an administrator of the NFT classification system 1. For example, the input device 14 is configured to include a keyboard, a touchpad, a touch panel, or a pointing device such as a mouse.

[0073] The communication device 15 is hardware serving as a transmitting / receiving device for communicating with other devices. The communication device 15 is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 15 may include a connector for wired connection and an interface circuit corresponding to the connector. The communication device 15 may also include a wireless communication interface. Examples of the connector and interface circuit for wired connection include products that comply with wired LAN, IEEE 1394, and USB. Examples of the wireless communication interface include products that comply with wireless LAN, Bluetooth (registered trademark), etc.

[0074] The processing device 11 functions as a communication control unit 111, an acquisition unit 112, a first determination unit 113, a second determination unit 114, and a classification unit 115, for example, by reading and executing a control program PR1 from the storage device 12.

[0075] The communication control unit 111 causes the communication device 15 to send and receive various data between the NFT management system 20 including the account management device 30, the object management device 40, and the terminal devices 50[1] to 50[4].

[0076] The acquisition unit 112 acquires, from the object management device 40, a plurality of feature amounts that correspond one-to-one to the plurality of digital objects DO[1] to DO[p]. More specifically, the acquisition unit 112 acquires, from the object management device 40, a plurality of the m-dimensional feature vectors described above as data indicating the plurality of feature amounts. As described above, one digital object DO corresponds to one NFT. Furthermore, one digital object DO corresponds to one m-dimensional feature vector. In other words, one NFT corresponds to one m-dimensional feature vector.

[0077] In addition, the acquisition unit 112 acquires, from the blockchain BC, history data HD indicating in which of one or more wallets WL each of the multiple NFTs has been stored.

[0078] Based on the history data HD acquired by the acquisition unit 112, the first determination unit 113 determines a feature quantity indicating a relationship between each of the multiple NFTs and one or more wallets WL in which each of the multiple NFTs has been stored. Data indicating the feature quantity is expressed as an n-dimensional feature vector. That is, the first determination unit 113 determines the n-dimensional feature vector. Note that n is an integer equal to or greater than 1. Furthermore, n and m may have the same value, or may have a different value from m. The feature quantity corresponding to the n-dimensional feature vector is an example of a "second feature quantity." Furthermore, the n-dimensional feature vector is an example of a "second vector."

[0079] The first determination unit 113 determines, by any method, a feature that indicates a relationship between each of the multiple NFTs and one or more wallets WL in which each of the multiple NFTs has been stored. As an example, the first determination unit 113 can determine the feature by a method using graph embedding or a method using metric learning. Specific details of the method using graph embedding and the method using metric learning are described below.

[0080] (a) Method Using Graph Embedding Based on the history data HD, the first determination unit 113 performs graph embedding for a graph G that includes a plurality of NFT nodes NN corresponding to a plurality of NFTs and one or more wallet nodes WN corresponding to one or more wallets WL. As a result, the first determination unit 113 can determine a feature amount that indicates the relationship between each of the plurality of NFTs and one or more wallets WL in which each of the plurality of NFTs has been stored.

[0081] Specifically, the first determination unit 113 first determines a graph G in which a plurality of NFT nodes NN and one or more wallet nodes WN are connected to one another by edges ED. FIG. 9 is a diagram illustrating an example of graph G. In the example illustrated in FIG. 9, graph G includes NFT nodes NN1 to NN3 and wallet nodes WN1 to WN2. In graph G, each of NFT nodes NN1 to NN3 is connected by edges ED1 to ED5 to each of wallet nodes WN1 to WN2 corresponding to wallets WL in which the corresponding NFTs have been stored, either currently or in the past. In the example illustrated in FIG. 9, the NFT corresponding to NFT node NN1 has been stored in the wallet WL corresponding to wallet node WN1, and therefore NFT node NN1 and wallet node WN1 are connected by edge ED1. Because the NFT corresponding to NFT node NN2 was previously stored in the wallet WL corresponding to wallet node WN1, NFT node NN2 and wallet node WN1 are connected by edge ED2. Because the NFT corresponding to NFT node NN2 was previously stored in the wallet WL corresponding to wallet node WN2, NFT node NN2 and wallet node WN2 are connected by edge ED3. Because the NFT corresponding to NFT node NN3 was previously stored in the wallet WL corresponding to wallet node WN1, NFT node NN3 and wallet node WN1 are connected by edge ED4. Because the NFT corresponding to NFT node NN3 was previously stored in the wallet WL corresponding to wallet node WN2, NFT node NN3 and wallet node WN2 are connected by edge ED5.

[0082] Next, the first determination unit 113 sets an initial vector for each of the multiple NFT nodes NN and one or more wallet nodes WN. As an example, the above-mentioned m-dimensional vector is set as the initial vector for the NFT node NN. As described above, the m-dimensional vector indicates the feature amount of the digital object DO associated with the NFT corresponding to the NFT node NN. As another example, a vector of random values ​​is set for the NFT node NN. As another example, a vector indicating the degree of the graph G is set for the NFT node NN. As another example, a vector of random values ​​is set for the wallet node WN. As another example, a vector indicating the feature amount of the wallet WL corresponding to the wallet node WN is set for the wallet node WN. The feature amount of the wallet WL is, for example, the number of NFTs held in the wallet WL, or, if cryptocurrency is stored in the wallet WL, the balance of the cryptocurrency.

[0083] Next, the first determination unit 113 performs graph embedding as unsupervised learning using the graph G based on the history data HD acquired by the acquisition unit 112. The graph embedding is machine learning that uses a GNN (Graph Neural Network) as an algorithm. As a result, the n-dimensional feature vectors corresponding to the NFT nodes NN1 to NN3 and the wallet nodes WN1 to WN2 are determined.

[0084] (b) Method Using Distance Learning The first determination unit 113 randomly arranges, in a common vector space VS, a plurality of NFT nodes NN corresponding to a plurality of NFTs and one or more wallet nodes WN corresponding to one or more wallets WL. FIG. 10 is a diagram illustrating an example of the vector space VS. In the example illustrated in FIG. 10, the vector space VS is a three-dimensional space defined using x, y, and z axes. However, the vector space VS is not limited to a three-dimensional space and may be a space of any dimension. NFT nodes NN1 to NN3 and wallet nodes WN1 to WN2 are randomly arranged in the vector space VS.

[0085] Next, the first determination unit 113 sets an initial vector for each of the multiple NFT nodes NN and one or more wallet nodes WN, similar to the method using graph embedding. As an example, the above m-dimensional vector is set as the initial vector for the NFT node NN. Alternatively, as another example, a vector of random values ​​is set for the NFT node NN. For example, if a vector having components (x, y, z) = (x1, y1, z1) is set as the initial vector for the NFT node NN1, the coordinates of the NFT node NN1 in the vector space VS are (x, y, z) = (x1, y1, z1).

[0086] As another example, a vector of random values ​​is set in the wallet node WN. Alternatively, as another example, a vector indicating the feature amount of the wallet WL corresponding to the wallet node WN is set in the wallet node WN. The feature amount of the wallet WL is, for example, the number of NFTs held in the wallet WL, or, if cryptocurrency is stored in the wallet WL, the balance of the cryptocurrency. For example, if a vector having components (x, y, z) = (x2, y2, z2) is set as the initial vector for the wallet node WN1, the coordinates of the wallet node WN1 in the vector space VS are (x, y, z) = (x2, y2, z2).

[0087] Next, the first determination unit 113 executes distance learning as unsupervised learning, utilizing the distance between each NFT node NN included in the multiple NFT nodes NN1 to NN3 and each wallet node WN included in one or more wallet nodes WN1 to WN2, based on the history data HD acquired by the acquisition unit 112. As a result, in the vector space VS, the distance between an NFT node NN and a wallet node WN that are highly correlated with each other decreases, and the distance between an NFT node NN and a wallet node WN that are low in correlation with each other increases.

[0088] Finally, the first determination unit 113 determines the above-mentioned n-dimensional feature vectors corresponding to each of the NFT nodes NN1 to NN3 and the wallet nodes WN1 to WN2 based on the coordinate values ​​of the NFT nodes NN1 to NN3 and the wallet nodes WN1 to WN2 in the vector space VS after metric learning. For example, if the coordinates of the NFT node NN1 in the vector space VS after metric learning are (x, y, z) = (x3, y3, z3), the components of the feature vector corresponding to the NFT node NN1 are (x, y, z) = (x3, y3, z3). Similarly, if the coordinates of the wallet node WN1 in the vector space VS after metric learning are (x, y, z) = (x4, y4, z4), the components of the feature vector corresponding to the wallet node WN1 are (x, y, z) = (x4, y4, z4). In the example shown in FIG. 10, since the vector space VS is three-dimensional, the feature vectors corresponding to the NFT nodes NN1 to NN3 and the wallet nodes WN1 to WN2 are both three-dimensional. That is, n = 3. However, n may be any integer other than 3.

[0089] Each of NFT nodes NN1 to NN3 corresponds to an NFT. That is, the first determination unit 113 determines an n-dimensional vector corresponding to one NFT. Also, each of wallet nodes WN1 to WN2 corresponds to a wallet WL. That is, the first determination unit 113 determines an n-dimensional vector corresponding to one wallet WL.

[0090] 8 , the second determination unit 114 generates an (m+n)-dimensional vector corresponding to one NFT by arranging in a row an m-dimensional vector corresponding to one NFT acquired by the acquisition unit 112 and an n-dimensional vector corresponding to the one NFT determined by the first determination unit 113. The (m+n)-dimensional vector is an example of a "third vector." Note that the second determination unit 114 may generate the "third vector" by arranging in a row the m-dimensional vector, the n-dimensional vector, and another vector corresponding to the one NFT.

[0091] Furthermore, for each of a plurality of combinations having two NFTs among the plurality of NFTs, the second determination unit 114 determines an index indicating the degree of similarity between the two NFTs based on the (m+n)-dimensional vector. For example, the second determination unit 114 calculates the Euclidean distance or cosine similarity between two (m+n)-dimensional vectors that correspond one-to-one to the two NFTs, and uses the calculation result as an index indicating the degree of similarity between the two NFTs.

[0092] The classification unit 115 classifies the multiple NFTs based on multiple indicators determined by the second determination unit 114 that correspond one-to-one to the multiple combinations each having two NFTs. Specifically, if the Euclidean distance or cosine similarity between two (m+n)-dimensional vectors calculated by the second determination unit 114 is within a preset threshold, the classification unit 115 classifies the two NFTs corresponding to the two (m+n)-dimensional vectors into the same NFT collection CL. On the other hand, if the Euclidean distance or cosine similarity exceeds the threshold, the classification unit 115 classifies the two NFTs corresponding to the two (m+n)-dimensional vectors into different NFT collections CL. The classification unit 115 classifies the multiple NFTs by performing the above classification on all combinations each having two NFTs generated from the multiple NFTs.

[0093] Alternatively, the classification unit 115 may classify the multiple NFTs without using multiple indices that correspond one-to-one to the multiple combinations of two NFTs. Specifically, the classification unit 115 clusters multiple (m+n)-dimensional vectors that correspond one-to-one to the multiple NFTs using, for example, the k-means algorithm. The classification unit 115 may classify the multiple NFTs that correspond one-to-one to the multiple (m+n)-dimensional vectors based on the clustering results of the multiple (m+n)-dimensional vectors.

[0094] The classification results of multiple NFTs by the classification unit 115 are output to the blockchain BC, for example, via the communication device 15.

[0095] The classification unit 115 classifies the plurality of NFTs, so that the plurality of digital objects DO associated one-to-one with the plurality of NFTs are classified into one or more NFT collections CL.

[0096] 1-3: Operation of NFT Classification Device FIG. 11 is a flowchart showing the operation of the NFT classification device 10.

[0097] In step S1, the processing device 11 functions as the acquisition unit 112. The processing device 11 acquires a plurality of feature amounts that correspond one-to-one to a plurality of digital objects DO[1] to DO[p] from the object management device 40. More specifically, the processing device 11 acquires a plurality of m-dimensional feature vectors from the object management device 40 as data indicating the plurality of feature amounts.

[0098] In step S2, the processing device 11 functions as the acquisition unit 112. The processing device 11 acquires, from the blockchain BC, history data HD indicating in which wallet WL, among one or more wallets WL, each of the multiple NFTs has been stored.

[0099] In step S3, the processing device 11 functions as the first determination unit 113. Based on the history data HD acquired in step S2, the processing device 11 determines a feature quantity indicating a relationship between each of the multiple NFTs and one or more wallets WL in which each of the multiple NFTs has been stored. Data indicating the feature quantity is expressed as an n-dimensional feature vector. That is, the processing device 11 determines the n-dimensional feature vector.

[0100] In step S4, the processing device 11 functions as the second determination unit 114. The processing device 11 generates an (m+n)-dimensional vector corresponding to one NFT by arranging the m-dimensional vector corresponding to one NFT acquired in step S1 and the n-dimensional vector corresponding to the one NFT determined in step S3 in a row.

[0101] In step S5, the processing device 11 functions as the second determination unit 114. For each of a plurality of combinations having two NFTs among the plurality of NFTs, the processing device 11 determines an index indicating the degree of similarity between the two NFTs based on the (m+n)-dimensional vector generated in step S4.

[0102] In step S6, the processing device 11 functions as the classification unit 115. The processing device 11 classifies the multiple NFTs based on the multiple indicators that correspond one-to-one to the multiple combinations having two NFTs, as determined in step S5.

[0103] 1-4: Effects of the First Embodiment The NFT classification device 10 according to this embodiment includes an acquisition unit 112, a first determination unit 113, and a classification unit 115. The acquisition unit 112 acquires, for each of a plurality of digital objects DO associated one-to-one with a plurality of NFTs, a first feature amount indicating a characteristic of the digital object DO. The first determination unit 113 determines a second feature amount indicating a relationship between each of the plurality of NFTs and one or more wallets WL in which each of the plurality of NFTs has been stored. The classification unit 115 classifies the plurality of NFTs based on the first feature amount and the second feature amount.

[0104] The NFT classification device 10, having the above configuration, can classify multiple digital objects DO associated one-to-one with multiple NFTs into one or more NFT collections CL more easily than when using conventional technology. In conventional technology, classifying multiple digital objects DO into one or more NFT collections CL required cumbersome work. In particular, the more the number of digital objects DO increases, the more cumbersome work required. The NFT classification device 10 according to the present disclosure can classify multiple digital objects DO associated one-to-one with multiple NFTs into one or more NFT collections CL more easily than when using conventional technology.

[0105] Furthermore, in the NFT classification device 10 according to this embodiment, the first feature amount indicates a feature relating to at least one of characters, images, and sounds contained in each of the multiple digital objects DO.

[0106] With the above configuration, the NFT classification device 10 can classify multiple digital objects DO that are associated one-to-one with multiple NFTs into one or more NFT collections CL based on features related to characters, images, and sounds included in each of the digital objects DO. For example, if multiple digital objects DO include common characters, common images, or common sounds, the NFT classification device 10 can classify the multiple digital objects DO into the same NFT collection CL.

[0107] In addition, in the NFT classification device 10 of this embodiment, the first determination unit 113 determines the above-mentioned second feature by performing graph embedding for a graph G including multiple NFT nodes NN corresponding to multiple NFTs and one or more wallet nodes WN corresponding to one or more wallets WL, based on history data HD indicating in which of one or more wallets WL each of multiple NFTs has been stored.

[0108] With the above configuration, the NFT classification device 10 can determine the second feature based on a graph G that includes a plurality of NFT nodes NN corresponding to a plurality of NFTs and one or more wallet nodes WN corresponding to one or more wallets WL. As a result, the NFT classification device 10 can more easily classify a plurality of digital objects DO that are associated one-to-one with a plurality of NFTs into one or more NFT collections CL compared to when using conventional technology.

[0109] Furthermore, in the NFT classification device 10 according to this embodiment, the first determination unit 113 determines the above-mentioned second feature by performing distance learning using the distance between each NFT node NN included in multiple NFT nodes NN and each wallet node WN included in one or more wallet nodes WN in a vector space VS in which multiple NFT nodes NN corresponding to multiple NFTs and one or more wallet nodes WN corresponding to one or more wallets WL are arranged, based on history data HD indicating in which wallet WL each of multiple NFTs has been stored.

[0110] With the above configuration, the NFT classification device 10 can determine the second feature based on distance learning using the distance between each NFT node NN included in the plurality of NFT nodes NN and each wallet node WN included in the one or more wallet nodes WN in a vector space VS in which the plurality of NFT nodes NN and one or more wallet nodes WN are arranged. As a result, the NFT classification device 10 can classify multiple digital objects DO associated one-to-one with multiple NFTs into one or more NFT collections CL more easily than when using conventional technology.

[0111] The NFT classification device 10 according to this embodiment further includes a second determination unit 114. The second determination unit 114 determines, for each of a plurality of combinations each having two NFTs among the plurality of NFTs, an index indicating the degree of similarity between the two NFTs based on two third vectors that correspond one-to-one to the two NFTs. The classification unit 115 classifies the plurality of NFTs based on the indexes that correspond one-to-one to the plurality of combinations each having two NFTs among the plurality of NFTs determined by the second determination unit 114. The third vector includes a first vector indicating a first feature amount and a second vector indicating a second feature amount.

[0112] With the above configuration, the NFT classification device 10 classifies multiple NFTs using an index determined based on a third vector including a first vector indicating a first feature amount and a second vector indicating a second feature amount. As a result, the NFT classification device 10 can more easily classify multiple digital objects DO associated one-to-one with multiple NFTs into one or more NFT collections CL compared to when using conventional technology.

[0113] In the NFT classification device 10 according to this embodiment, the classification unit 115 classifies the plurality of NFTs by clustering third vectors corresponding to each of the plurality of NFTs. The third vectors include a first vector representing a first feature amount and a second vector representing a second feature amount.

[0114] With the above configuration, the NFT classification device 10 classifies multiple NFTs using a third vector including a first vector indicating a first feature amount and a second vector indicating a second feature amount. As a result, the NFT classification device 10 can classify multiple digital objects DO associated one-to-one with multiple NFTs into one or more NFT collections CL more easily than when using conventional technology.

[0115] 2: Modifications The present disclosure is not limited to the above-described exemplary embodiments. Specific modifications are exemplified below. Two or more modifications selected from the following examples may be combined. Furthermore, the above-described embodiments and the following modifications may be combined in any manner as long as they are not mutually inconsistent.

[0116] 2-1: Variation 1 In the above embodiment, each of wallets WL[1] to WL[4] is provided in terminal device 50[1] to terminal device 50[4]. However, all of wallets WL[1] to WL[4] may be provided in the account database ADB provided in account management device 30.

[0117] 2-2: Variation 2 In the above embodiment, the NFT classification system 1 includes an account management device 30. However, the NFT classification system 1 does not necessarily need to include the account management device 30. In this case, user U[1] may use terminal device 50[1] to issue an NFT corresponding to a digital object DO[1] created by user U[1] and register it in the blockchain BC. User U[2], the first purchaser of the digital object DO[1] associated with the NFT, may use terminal device 50[2] to rewrite transaction data TD stored in block BL used in the blockchain BC in connection with the transfer of the NFT. The same applies to user U[3], the second purchaser. In these cases, terminal devices 50[1] to 50[3] preferably function as a single node included in the blockchain BC.

[0118] 2-3: Modification 3 In the above embodiment, the NFT classification device 10 acquires multiple feature amounts that correspond one-to-one to multiple digital objects DO[1] to DO[p] from the object management device 40. However, the NFT classification device 10 may acquire the digital objects DO[1] to DO[p] themselves from the object management device 40, instead of multiple feature amounts. In this case, the NFT classification device 10 extracts feature amounts for each of the digital objects DO[1] to DO[p] acquired from the object management device 40.

[0119] 3: Others (1) In the above-described embodiment, storage device 12, storage device 32, storage device 42, and storage device 52 are exemplified by ROM and RAM, but they may also be flexible disks, magneto-optical disks (e.g., compact disks, digital versatile disks, Blu-ray (registered trademark) disks), smart cards, flash memory devices (e.g., cards, sticks, key drives), CD-ROMs (Compact Disc-ROMs), registers, removable disks, hard disks, floppy (registered trademark) disks, magnetic strips, databases, servers, or other suitable storage media. The program may also be transmitted from a network via a telecommunications line. The program may also be transmitted from a communications network (NET) via a telecommunications line.

[0120] (2) In the above-described embodiments, the described information, signals, etc. may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0121] (3) In the above-described embodiment, input and output information may be stored in a specific location (for example, a memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0122] (4) In the above-described embodiment, the determination may be made based on a value (0 or 1) represented using one bit, a Boolean value (true or false), or a comparison of numerical values ​​(e.g., comparison with a predetermined value).

[0123] (5) The order of the exemplary procedures, sequences, flowcharts, etc. illustrated in the above-described embodiments may be rearranged unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0124] (6) Each function illustrated in Figures 1 to 11 is realized by any combination of hardware and / or software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wires, wirelessly, etc.) and these multiple devices. A functional block may be realized by combining software with the single device or the multiple devices.

[0125] (7) The programs exemplified in the above-described embodiments should be broadly construed to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., regardless of whether they are called software, firmware, middleware, microcode, hardware description language, or by other names.

[0126] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0127] (8) In each of the foregoing embodiments, the terms "system" and "network" are used interchangeably.

[0128] (9) The information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0129] (10) In the above-described embodiments, the NFT classifier device 10, the account management device 30, the object management device 40, and the terminal devices 50[1] to 50[4] may be mobile stations (MS). A mobile station may also be referred to by those skilled in the art as a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, or some other appropriate term. In addition, in the present disclosure, terms such as "mobile station," "user terminal," "user equipment (UE)," and "terminal" may be used interchangeably.

[0130] (11) In the above-described embodiments, the terms "connected," "coupled," or any variations thereof refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be a physical coupling or connection, a logical coupling or connection, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0131] (12) In the above embodiments, the phrase "based on" does not mean "based only on," unless otherwise specified. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0132] (13) As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching a table, database, or other data structure), and ascertaining something that is considered to be a "determining." Also, "determining" and "determining" may include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and so on. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0133] (14) In the above embodiments, when the terms "include," "including," and variations thereof are used, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used in this disclosure, is not intended to be an exclusive or.

[0134] (15) In this disclosure, where articles are added by translation, such as a, an, and the in English, this disclosure may include the nouns following these articles being plural.

[0135] (16) In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

[0136] (17) Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0137] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0138] 1...NFT classification system, 10...NFT classification device, 11...processing device, 12...storage device, 14...input device, 15...communication device, 20...NFT management system, 30...account management device, 31...processing device, 32...storage device, 34...input device, 35...communication device, 40...object management device, 41...processing device, 42...storage device, 44...input device, 45...communication device, 50...terminal device, 51...processing device, 52...storage device, 53...display, 54...input device, 55...speaker, 56...communication device, 111...communication control unit, 112...acquisition unit, 113...first determination unit, 114...second determination unit, 115...classification unit, 311...communication control unit, 312...management unit logic unit, 411...communication control unit, 412...management unit, 413...extraction unit, 511...communication control unit, 512...display control unit, 513...audio control unit, ADB...account database, BC...blockchain, BH...hash value, BL...block, CL...NFT collection, DO...digital object, ED...edge, G...graph, HD...history data, NA...NFT art, NET...communication network, NN...NFT node, NV...nonce value, ODB...object database, PR...control program, SD...state data, TD...transaction data, U...user, VS...vector space, WL...wallet, WN...wallet node

Claims

1. An NFT classification device comprising: an acquisition unit that acquires, for each of a plurality of digital objects that are associated one-to-one with a plurality of NFTs, a first feature that indicates a characteristic of the digital object; a first determination unit that determines a second feature that indicates a relationship between each of the plurality of NFTs and one or more wallets in which each of the plurality of NFTs has been stored; and a classification unit that classifies the plurality of NFTs based on the first feature and the second feature.

2. The NFT classification device according to claim 1, wherein the first feature indicates a feature related to at least one of text, images, and sounds contained in each of the plurality of digital objects.

3. The NFT classification device described in claim 1, wherein the first determination unit determines the second feature by performing graph embedding on a graph including a plurality of NFT nodes corresponding to the plurality of NFTs and one or more wallet nodes corresponding to the one or more wallets, based on historical data indicating in which of the one or more wallets each of the plurality of NFTs has been stored.

4. The NFT classification device described in claim 1, wherein the first determination unit determines the second feature by performing distance learning using the distance between each NFT node included in the plurality of NFT nodes and each wallet node included in the one or more wallet nodes in a vector space in which the plurality of NFT nodes corresponding to the plurality of NFTs and the one or more wallet nodes corresponding to the one or more wallets are arranged, based on historical data indicating in which of the one or more wallets each of the plurality of NFTs has been stored.

5. The NFT classification device of claim 1, further comprising a second determination unit that determines, for each of a plurality of combinations having two NFTs among the plurality of NFTs, an index indicating the degree of similarity between the two NFTs based on two third vectors that correspond one-to-one to the two NFTs, and the classification unit classifies the plurality of NFTs based on a plurality of indexes that correspond one-to-one to the plurality of combinations having two NFTs among the plurality of NFTs determined by the second determination unit, and the third vector includes a first vector that indicates the first feature and a second vector that indicates the second feature.

6. The NFT classification device of claim 1, wherein the classification unit classifies the plurality of NFTs by clustering third vectors corresponding to each of the plurality of NFTs, and the third vectors include a first vector indicating the first feature amount and a second vector indicating the second feature amount.

Images