Information processing system, information processing method, and program

Abstract

To associate a suitable image or the like with a predetermined item available in a virtual space.SOLUTION: The disclosed information processing system is provided with: a user input acquisition unit for acquiring a predetermined input from a user; an image acquisition unit for using a first machine learning model constructed by artificial intelligence to acquire a specific image obtained by inputting the predetermined input to the first machine learning model; and an association processing unit for associating the specific image with a predetermined item available in a virtual space.SELECTED DRAWING: Figure 20

Description

[Technical Field]

[0001] The present disclosure relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] A technique for adding an image suitable for an input document is known in relation to Word2Image and the like. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-221794 Summary of the Invention [Problem to be solved by the invention]

[0004] However, it is difficult to apply the above-described conventional techniques to predetermined items that can be used in virtual space.

[0005] Therefore, in one aspect, the present disclosure aims to apply images generated by AI (artificial intelligence) to predetermined items available in a virtual space. [Means for solving the problem]

[0006] In one aspect, a user input acquisition unit that acquires a predetermined input from a user; an image acquisition unit that utilizes a first machine learning model constructed by artificial intelligence to acquire a specific image obtained by inputting the predetermined input into the first machine learning model; An information processing system is provided, comprising: an association processing unit that associates the specific image with a predetermined item that can be used in a virtual space. [Effects of the Invention]

[0007] According to one aspect, the present disclosure makes it possible to associate suitable images and the like with predetermined items that can be used in a virtual space. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram of a system according to an embodiment of the present invention. [Figure 2] FIG. 1 is a block diagram of processing circuitry for performing computer-based operations according to the present disclosure. [Figure 3] 10 is a flowchart outlining an example of the flow of processing that may be performed in the system. [Figure 4] FIG. 4 is an explanatory diagram of the processing shown in FIG. 3, and is an image diagram of mixing in the semantic space. [Figure 5] FIG. 4 is an explanatory diagram of the processing shown in FIG. 3, and is an image diagram of a specific image. [Figure 6] FIG. 4 is an explanatory diagram of the process shown in FIG. 3, showing an image of an avatar and an item attached to the avatar. [Figure 7] FIG. 4 is an explanatory diagram of the process shown in FIG. 3, showing an image of items that can be placed in the virtual space. [Figure 8] FIG. 4 is an explanatory diagram of the processing shown in FIG. 3, showing an image of a combination of avatars and furniture in a virtual space. [Figure 9] 10 is a flowchart showing an overview of the flow of another example of processing that may be executed in the system. [Figure 10] FIG. 10 is an explanatory diagram of the process shown in FIG. 9, illustrating the difference in item texture. [Figure 11] 10 is a flowchart showing an overview of the flow of yet another example of processing that may be executed in the system. [Figure 12] FIG. 10 is an explanatory diagram of the process shown in FIG. 9, showing an image of the shape of an item that can be worn on an avatar. [Figure 13A] FIG. 10 is a diagram showing an example of a UI that allows generation / input of input information, instructions to mix a plurality of specific images, etc. [Figure 13B]FIG. 10 is a diagram illustrating an example of a UI that allows color adjustment. [Figure 13C] FIG. 10 is a diagram showing an example of a UI that allows item selection. [Figure 14] FIG. 10 is an explanatory diagram of item elements that can be managed for each pattern or part. [Figure 15] FIG. 10 is a diagram schematically illustrating an example of a control that can be used in the metaverse space. [Figure 16] 10 is a flowchart illustrating an example of a user-side operational procedure that can be implemented in the system. [Figure 17] FIG. 17 is an explanatory diagram of the procedure of FIG. 16, showing a screen in which a user is editing the clothes (kimono) of an avatar. [Figure 18] 10 is a flowchart of a process that may be implemented by a server device when a store review application is received. [Figure 19] 10 is a schematic flowchart illustrating an example of a uniqueness evaluation process. [Figure 20] FIG. 2 is a block diagram illustrating an example of the functions of a server device. [Figure 21] FIG. 10 is an explanatory diagram of simultaneous (collective) reflection on a plurality of predetermined items. [Figure 22] This is an image of the contest. DETAILED DESCRIPTION OF THE INVENTION

[0009] Each embodiment will be described in detail below with reference to the accompanying drawings. Note that in the accompanying drawings, for ease of viewing, only some of the reference symbols may be used for multiple components with the same attribute.

[0010] An overview of a system 1 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram of the system 1 according to this embodiment.

[0011] The system 1 includes a server device 10 and one or more terminal devices 20. For simplicity, three terminal devices 20 are shown in Fig. 1, but the number of terminal devices 20 is arbitrary.

[0012] The server device 10 is an information processing device such as a server managed by an operator that provides one or more content creation support services. The terminal device 20 is a device used by a user, such as a mobile phone, a smartphone, a tablet terminal, a PC (Personal Computer), a head-mounted display, or a game device. A plurality of terminal devices 20 can be connected to the server device 10 via the network 3, typically in a different manner for each user.

[0013] The terminal device 20 is capable of executing a content creation assistance application according to this embodiment. The content creation assistance application may be received by the terminal device 20 from the server device 10 or a predetermined application distribution server via the network 3, or may be stored in advance in a storage device provided in the terminal device 20 or in a storage medium such as a memory card readable by the terminal device 20. The server device 10 and the terminal device 20 are communicably connected via the network 3. For example, the server device 10 and the terminal device 20 cooperate to execute various processes related to content creation assistance.

[0014] The network 3 may include a wireless communication network, the Internet, a Virtual Private Network (VPN), a Wide Area Network (WAN), a wired network, or any combination of these.

[0015] In this embodiment, the server device 10 may be connected to a blockchain network 5 (see arrow R10). The blockchain network 5 is a network in which many computers are interconnected. Each connected computer acts as a node, recording processing requests notified to the blockchain network 5 by the server device 10, executing processing in response to the processing request from the user, and recording the results in storage managed by the node. The processing request is transmitted to each node, and each node executes the same processing for that processing request and records the output, thereby realizing that each node holds exactly the same information even in a distributed environment. The processing executed on this blockchain is also referred to as a smart contract. Some or all of the nodes of the blockchain network 5 may be realized by terminal devices 20, and some or all of the network related to the blockchain network 5 may be realized by network 3.

[0016] In the following, the system 1 realizes an example of an information processing system, but each element of a specific terminal device 20 (see the terminal communication unit 21 to the terminal control unit 25 in FIG. 1) may realize an example of an information processing system, or a plurality of terminal devices 20 may cooperate to realize an example of an information processing system. Also, the server device 10 may independently realize an example of an information processing system, or the server device 10 and one or more terminal devices 20 may cooperate to realize an example of an information processing system.

[0017] (Server device configuration) The configuration of the server device 10 will be described in detail. The server device 10 is configured by a server computer. The server device 10 may be realized by a plurality of server computers working together. For example, the server device 10 may be realized by a server computer that provides various types of content, a server computer that functions as various authentication servers, and the like working together. The server device 10 may also include a web server 820 (see FIG. 2). In this case, some of the functions of the terminal device 20, which will be described later, may be realized by a browser processing HTML documents and various programs (JavaScript (registered trademark)) associated with the HTML documents received from the web server 820 (see FIG. 2).

[0018] As shown in FIG. 1, the server device 10 includes a server communication unit 11, a server storage unit 12, and a server control unit 13.

[0019] The server communication unit 11 includes an interface (see the I / O interface 612, network controller 702, etc. in FIG. 2) that communicates with an external device wirelessly or via a wired connection and transmits and receives information. The server communication unit 11 may include, for example, a wireless LAN (Local Area Network) communication module or a wired LAN communication module. The server communication unit 11 is capable of transmitting and receiving information to and from the terminal device 20 via the network 3.

[0020] The server storage unit 12 is, for example, a storage device, and stores various information and programs required for various processes related to content creation support.

[0021] The server control unit 13 may include a dedicated microprocessor or a CPU (Central Processing Unit) that implements a specific function by loading a specific program, a GPU (Graphics Processing Unit), etc. (See CPU 601 in FIG. 2.) For example, the server control unit 13 cooperates with the terminal device 20 to execute a content creation support application in response to a user operation on the display unit 23 (touch panel) of the terminal device 20.

[0022] (Terminal Device Configuration) The following describes the configuration of the terminal device 20. As shown in Fig. 1, the terminal device 20 includes a terminal communication unit 21, a terminal storage unit 22, a display unit 23, an input unit 24, and a terminal control unit 25.

[0023] The terminal communication unit 21 includes an interface (see the I / O interface 612, the network controller 702, etc. in FIG. 2) that communicates with an external device wirelessly or via a wired connection and transmits and receives information. The terminal communication unit 21 may include a wireless communication module, a wireless LAN communication module, or a wired LAN communication module that supports mobile communication standards such as LTE (Long Term Evolution (registered trademark)), LTE-A (LTE-Advanced), a fifth-generation mobile communication system, or UMB (Ultra Mobile Broadband). The terminal communication unit 21 is capable of transmitting and receiving information to and from the server device 10 via the network 3.

[0024] The terminal storage unit 22 includes, for example, a primary storage unit and a secondary storage unit. For example, the terminal storage unit 22 may include a semiconductor memory, a magnetic memory, an optical memory, or the like. The terminal storage unit 22 stores various information and programs related to content creation support received from the server device 10. The information and programs related to content creation support may be acquired from an external device via the terminal communication unit 21. For example, a content creation support application program may be acquired from a predetermined application distribution server. Hereinafter, the application program may also be simply referred to as an application.

[0025] The display unit 23 includes a display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display (see also the display 609 in FIG. 2). The display unit 23 is capable of displaying a variety of images. The display unit 23 is configured, for example, with a touch panel, and functions as an interface that detects a variety of user operations. As described above, the display unit 23 may be built into a head-mounted display.

[0026] The input unit 24 may include physical keys or any other input interface, such as a pointing device like a mouse. The input unit 24 may also be capable of accepting non-contact user input, such as voice input, gesture input, or gaze input. For gesture input, sensors for detecting various user states (such as image sensors, acceleration sensors, and distance sensors), dedicated motion capture devices integrating sensor technology and cameras, or controllers such as joypads may be used. The gaze detection camera may also be located within a head-mounted display. As described above, the various user states may be, for example, the user's orientation, position, movement, or the like. In this case, the user's orientation, position, and movement are concepts that include not only the orientation, position, and movement of the user's hands and body, but also the gaze direction, position, movement, or the like of the broadcasting user.

[0027] The terminal control unit 25 includes one or more processors and controls the overall operation of the terminal device 20.

[0028] The terminal control unit 25 transmits and receives information via the terminal communication unit 21. For example, the terminal control unit 25 receives various information and programs related to content creation support from at least one of the server device 10 and another external server. The terminal control unit 25 stores the received information and programs in the terminal storage unit 22. For example, the terminal storage unit 22 may store a browser (internet browser) for connecting to a web server 820 (see FIG. 2).

[0029] The terminal control unit 25 starts a content creation support application in response to a user operation. The terminal control unit 25 executes processing related to content creation support in cooperation with the server device 10. For example, the terminal control unit 25 may output a GUI (Graphical User Interface) that detects a user operation on the screen of the display unit 23. The terminal control unit 25 can detect a user operation via the input unit 24. For example, the terminal control unit 25 can detect various operations by user gestures (operations corresponding to a tap operation, a long tap operation, a flick operation, a swipe operation, etc.). The terminal control unit 25 may transmit operation information to the server device 10.

[0030] 2 is a block diagram of a processing circuit 600 that executes computer-based operations according to the present disclosure. The processing circuit 600 described below is suitable as a hardware configuration that implements the server communication unit 11 to the server control unit 13 of the server device 10 shown in FIG. 1. The processing circuit 600 described below is also suitable as a hardware configuration that implements the terminal communication unit 21, the terminal storage unit 22, and the terminal control unit 25 of the terminal device 20 shown in FIG. 1.

[0031] The processing circuit 600 can be used to control any computer-based and cloud-based control process. The descriptions or blocks in the flowcharts can be understood as representing modules, segments, or portions of code containing one or more executable instructions for implementing specific logical functions or steps in the process. Alternative implementations are within the scope of the exemplary embodiments of the present invention, including performing functions out of the order shown or discussed, such as substantially simultaneously or in reverse order, depending on the functionality involved, as will be understood by those skilled in the art. The functions of the elements disclosed herein can be implemented using circuits or processing circuitry, which may include general-purpose processors, special-purpose processors, integrated circuits, application-specific integrated circuits (ASICs), conventional circuits, and / or combinations thereof, configured or programmed to perform the disclosed functions. A processor is a processing circuit or circuitry because it includes transistors and other circuits therein. A processor may be a programmed processor that executes a program stored in memory 602. In this disclosure, a processing circuit, unit, or means is hardware that performs or is programmed to perform the referenced functions. The hardware may be any hardware disclosed herein or otherwise known that is programmed or configured to perform the referenced functions.

[0032] 2, the processing circuit 600 is connected to a display controller 606, a storage controller 624, a network controller 702, a memory 602, an I / O interface 612, and the like, which are connected via a bus 628. In this case, the processing circuit 600 is connected to a display 609 via the display controller 606, and is connected to a keyboard, mouse 614, a touch screen 616, and peripheral devices 618 via the I / O interface 612. The processing circuit 600 also accesses the network 3 via the network controller 702. The display 609 and the display controller 606 may be connected via a standard connection method based on a video transfer standard, such as VGA, DVI, DisplayPort, or HDMI.

[0033] In FIG. 2, processing circuitry 600 includes a CPU 601 that executes one or more of the control processes discussed in this disclosure. Process data and instructions may be stored in memory 602. These processes and instructions may also be stored on a storage medium disk 604 (labeled "disk" in FIG. 2), such as a hard disk drive (HDD) or a portable storage medium, or may be stored remotely. Furthermore, the claimed developments are not limited by the form of computer-readable medium on which the instructions for the disclosed processes are stored. For example, the instructions may be stored on a CD, DVD, FLASH memory, RAM, ROM, PROM, EPROM, EEPROM, hard disk, or other non-transitory computer-readable medium of an information processing device with which processing circuitry 600 communicates, such as a server or computer. The processes may also be stored on network-based storage, cloud-based storage, or other mobile-accessible storage and executable by processing circuitry 600.

[0034] Additionally, the claimed development features may be provided as utility applications, background daemons, or operating system components, or combinations thereof, executing in conjunction with CPU 601 and an operating system such as Microsoft Windows®, UNIX®, Solaris®, LINUX®, Apple®, MAC-OS®, Apple iOS®, and other systems known to those skilled in the art.

[0035] The hardware elements for implementing the processing circuit 600 may be realized by various circuit elements. Furthermore, each function of the above-described embodiments may be realized by a circuit including one or more processing circuits. The processing circuit includes a specially programmed processor, for example, a processor (CPU) 601 as shown in FIG. XX. The processing circuit also includes devices such as application-specific integrated circuits (ASICs) and conventional circuit components arranged to perform the functions described.

[0036] 2, the processing circuit 600 may be a computer or a specific special-purpose machine. The processing circuit 600 is programmed to execute processes for controlling the device in which it is implemented (the server device 10 or the terminal device 20).

[0037] Alternatively, or additionally, CPU 601 may be implemented on a Field Programmable Gate Array (FPGA), an ASIC, a Programmable Logic Device (PLD), or using discrete logic circuitry, as will be appreciated by those skilled in the art. Furthermore, CPU 601 may be implemented as multiple processors operating cooperatively in parallel to execute instructions for various processes.

[0038] The processing circuit 600 of FIG. 2 also includes a network controller 702, such as an Ethernet PRO network interface card, for interfacing with network 3. As can be appreciated, network 3 can be a public network, such as the Internet, or a private network, such as a local area network (LAN) or wide area network (WAN), or any combination thereof, including a public switched telephone network (PSTN) or an integrated services digital network (ISDN), or a sub-network. Network 3 can also be wired, such as an Ethernet network or a universal serial bus (USB) cable, or wireless, such as a cellular network, including EDGE, 3G, 4G, and 5G wireless cellular systems. The wireless network can also be Wi-Fi, wireless LAN, Bluetooth, or other known forms of wireless communication. Furthermore, network controller 702 can be compliant with other direct communication standards, such as Bluetooth, near field communication (NFC), infrared, etc. 2 also shows an example of the configuration of the server device 10. In the example shown in Fig. 2, the server device 10 includes a remote computer 815, a Web server 820, a cloud storage server 825, and a computer server 830. Although detailed descriptions of the hardware configurations of the remote computer 815, the Web server 820, the cloud storage server 825, and the computer server 830 will not be given, they may be similar to the processing circuit 600.

[0039] Next, the system 1 will be described in further detail with reference to FIG. 3 onwards.

[0040] 3 is a flowchart showing an outline of an example of the flow of processing that may be executed in the system 1. FIGS. 4 to 8 are explanatory diagrams of the processing shown in FIG.

[0041] In FIG. 3, the processing is shown separately for the server device 10 and the terminal device 20. Note that the processing realized by the machine learning model (an example of a first machine learning model) is processing of the server device 10, but is shown separately for convenience. In the following, one terminal device 20 will be described, but similar functions can also be realized in other terminal devices 20. In addition, in the following, a user refers to a user of one terminal device 20 unless otherwise specified.

[0042] The user generates input information (an example of a predetermined input) via the terminal device 20 (step S2100) and transmits it to the server device 10 (step S2110). In FIG. 3, the input information is information related to an image imagined by the user. For example, if the user wants to obtain a desired image, the input information is information representing the desired image. The input information may include at least one of text, symbols, emojis, numbers, colors, textures, images, sounds, gestures (including motions), and any combination of two or more of these. Text is typically a character string that has meaning, but may also include meaningless character strings. The input information may also be input in a template format.

[0043] When the server device 10 acquires input information, it inputs the input information into a predetermined machine learning model and acquires a specific image (steps S2200, S2300). The predetermined machine learning model is a machine learning model constructed using artificial intelligence, and is a model that generates and outputs an image based on input such as the above-mentioned input information. Hereinafter, for the sake of distinction, a predetermined machine learning model that generates and outputs an image based on input such as the above-mentioned input information will also be referred to as an "image output model." The image output model may be constructed in any manner, but is preferably a model that can generate images that reflect various contexts based on the input information, for example. The image output model may utilize latent diffusion models or the like.

[0044] FIG. 4 is an explanatory diagram of an example of a method for generating input information, in which each character string is represented by a vector as an example of a mixing pattern in semantic space. The input information generation method is arbitrary, but it is also possible to mix concepts (such as meanings and contexts) that combine two or more characters. For example, as conceptually shown in FIG. 4, an image output model may be constructed to generate an image of character string C (e.g., a seagull as a seabird) based on character string A (e.g., bird) and another character string B (e.g., sea). In this case, a user can increase the likelihood of obtaining a desired specific image even if they cannot think of an appropriate character string by using not only the synthesis of multiple character strings but also synthesis by subtraction of multiple character strings. For example, synthesis by subtraction of character string C from character string B is equivalent to inputting character string A. The above-mentioned diffusion model has the advantage of embedding a directionality that approximates the target character string in the noise removal process, thereby making it possible to visualize details that are difficult to express by simple character string synthesis alone.

[0045] The specific image may be a still image or a video. The type and size of the specific image may be specified by information separate from the input information, or may be included in the input information. FIG. 5 shows an example of an image (specific image) G500 of a seagull flying over the sea. Such a specific image may be generated, for example, when the input information includes "bird" and "sea."

[0046] The input information may also be allowed to include character strings related to so-called negative words. Negative words are a concept similar to the "subtraction" involved in the synthesis of character strings described above, but are used to prevent images related to character strings related to negative words from being included. For example, if the input information includes "bird" and "sea" but also includes the negative word "seagull," a specific image may be generated that does not include a seagull.

[0047] The server device 10 may determine whether the input information contains predetermined prohibited words, and if the predetermined prohibited words are included, may notify the terminal device 20 of this fact and request the user to regenerate and resend the input information without the predetermined prohibited words. In this case, the predetermined prohibited words may include words that violate public order and morals, such as obscene words, slander, hate speech, etc., or words that infringe or are likely to infringe the intellectual property rights of others. The predetermined prohibited words may be stored and accumulated in the server storage unit 12 or the like in dictionary format.

[0048] 3, when the server device 10 acquires the specific image, it stores specific image information in the server storage unit 12 (step S2210). The specific image information includes image data of the specific image and input information used to generate the specific image, in a form in which the image data and the input information are associated with each other.

[0049] Next, the server device 10 generates a preview display of the specific image (step S2220) and enables output of the preview display on the terminal device 20. The user can determine the need for corrections, etc. while viewing the preview display on the terminal device 20 (step S2120). The preview display may be the specific image itself, or may be realized as a display reflecting any item available in the virtual space (e.g., a desired item designated by the user). In the latter case, the item may include an item that can be associated with an avatar in the virtual space (e.g., clothing 601 and 602 of avatar A6 as shown in FIG. 6), an item that can be placed in the virtual space (e.g., furniture B7 and its components IT701 and IT702 as shown in FIG. 7), or any combination thereof (e.g., a combination of avatars and furniture in the virtual space as shown in FIG. 8). In this case, the preview display may be a three-dimensional display and may be panned and rotated, similar to a CAD (Computer Aided Design) viewer. For example, if the item is clothing for the user's avatar, an avatar wearing the clothing reflecting a specific image may be generated, and a preview may be displayed together with the avatar.

[0050] When the user determines that the specific image thus generated does not need to be modified, the user generates a linking instruction for linking the specific image to any item available in the virtual space (for example, a desired item designated by the user) as the final version, and transmits the linking instruction to the server device 10 (step S2130). The linking instruction may include information for identifying the item to be linked.

[0051] When the server device 10 receives the association instruction (step S2230), it associates the specific image with the predetermined item, which is the item to be associated (step S2240). The association method is arbitrary. For example, if the predetermined item is clothing for the user's avatar, the association of the specific image may be achieved by including the specific image in part or all of the clothing. Such a reflection method may be specified by information separate from the input information, or may be included in the input information.

[0052] 3, the user can acquire a specific image by generating input information according to his or her own image without having to draw the image himself or herself, and the specific image can be reflected in any item available in the virtual space. Also, by providing a specific image as a base image, it is possible to generate a new design in any area (for example, an area in the virtual space).

[0053] 3, if the items to be associated are determined in advance, the input information generated in step S2100 may include the attributes and name of the items to be associated (i.e., the predetermined items). In this case, it may be possible to acquire a specific image taking into consideration the attributes, etc., of the predetermined items. Furthermore, if a preview display is not required, the input information may be transmitted in a lump sum to the server device 10 in a form including the association instruction of step S2130.

[0054] 11 is a flowchart showing an outline of the flow of another example of processing that may be executed in the system 1. FIG. 12 is an explanatory diagram of the processing shown in FIG.

[0055] 11 shows the processing separately for the server device 10 and the terminal device 20. As in FIG. 3, the processing realized by the machine learning model (an example of the second machine learning model) is the processing of the server device 10, but is shown separately for convenience.

[0056] The user generates input information via the terminal device 20 (step S4100) and transmits it to the server device 10 (step S4110). In FIG. 11, the input information is information related to the item shape imagined by the user. For example, if the user wants to obtain a desired item shape, the input information is information representing the item shape. The input information may include at least one of text, symbols, pictograms, numbers, colors, textures, images, sounds, gestures (including motions), and any combination of two or more of these. Text is typically a character string that has meaning, but may also include meaningless character strings. The input information may also be input in a template format.

[0057] When the server device 10 acquires the input information, it inputs the input information into a predetermined machine learning model to acquire the resulting item shape (steps S4200, S4300). The predetermined machine learning model is a machine learning model constructed using artificial intelligence, and is a model that generates and outputs an item shape based on input such as the input information described above. Hereinafter, for the sake of distinction, the predetermined machine learning model that generates and outputs an item shape based on input such as the input information described above will also be referred to as an "item shape output model." Note that the item shape output model may be a model separate from the image output model described above, and may be used as an integrated model.

[0058] The method for generating the input information is arbitrary and may be the same as the method described above with reference to FIG.

[0059] The item shape may be the shape of any item available in the virtual space. The item shape may be a three-dimensional shape or a two-dimensional shape depending on the attributes of the item. For example, if the item related to the item shape is clothing, the item shape may be in the form of a clothing pattern. Furthermore, if the item related to the item shape is a three-dimensional object, the item shape may be in the form of a drawing of the three-dimensional object, a three-dimensional shape, or a combination thereof. The type and size of the item related to the item shape may be specified by information separate from the input information, or may be included in the input information.

[0060] The input information may also be allowed to include character strings related to so-called negative words. For example, if the input information includes "car" and "sports" and also includes "Germany" as a negative word, an item shape related to a sports car other than a German car may be generated.

[0061] 3, the server device 10 may determine whether the input information contains predetermined prohibited words, and if the predetermined prohibited words are included, may notify the terminal device 20 of this fact and request the user to regenerate and resend the input information without the predetermined prohibited words. In this case, the predetermined prohibited words may include words that violate public order and morals, such as obscene words, slander, hate speech, etc., or words that infringe or are likely to infringe the intellectual property rights of others. The predetermined prohibited words may be stored and accumulated in the server storage unit 12 or the like in dictionary format.

[0062] When the server device 10 acquires the item shape, it stores the item shape information in the server storage unit 12 (step S4210). The item shape information includes data of the item shape and input information used to generate the item shape, in a form in which the data and the input information are associated with each other.

[0063] Next, the server device 10 generates a preview display of the item shape (step S4220) and enables output of the preview display on the terminal device 20. The user can determine the need for corrections, etc. while viewing the preview display on the terminal device 20 (step S4120). The preview display may be the item shape itself, or may be realized as the item shape reflected in an image (e.g., the specific image described above). The preview display may be a three-dimensional display and may be pannable or rotatable. For example, if the item shape is the shape of clothing for a user's avatar, the item shape may be a flat form such as a paper pattern, or may be a three-dimensional form worn by the user's avatar. In either case, the preview display may be realized three-dimensionally. In this case, for example, as shown in FIG. 12, the item shape may be previewed together with an avatar A6 wearing clothing items IT601A and IT602A that reflect the item shape.

[0064] If the user determines that no corrections or the like are necessary for the item shape generated in this manner, the user generates a shaping instruction for shaping any item available in the virtual space (for example, a desired item designated by the user) as a final version, and transmits the shaping instruction to the server device 10 (step S4130). The shaping instruction may include information for identifying the item to be shaped (predetermined item).

[0065] When the server device 10 receives the shaping instruction (step S4230), it shapes the predetermined item, which is the item to be shaped (step S4240). The shaping method is arbitrary. For example, if the predetermined item is clothing for the user's avatar, the shaping may be realized by making part or all of the clothing include the item shape. Furthermore, such shaping may be realized according to the size of the predetermined item. Such a reflection method may be specified by information separate from the input information, or may be included in the input information.

[0066] In this way, according to the process shown in Figure 11, a user can obtain an item shape by generating input information according to their own image without having to draw the item shape themselves, and can reflect the item shape on any item available in the virtual space.

[0067] 11, if the item to be associated is determined in advance, the input information generated in step S4100 may include the attributes and name of the item to be associated (i.e., the predetermined item). In this case, it may be possible to acquire an item shape that takes into account the attributes, etc. of the predetermined item.

[0068] 9 is a flowchart showing an outline of the flow of another example of processing that may be executed in the system 1. FIG. 10 is an explanatory diagram of the processing shown in FIG.

[0069] 9 shows the processing separately for the server device 10 and the terminal device 20. As in FIG. 3, the processing realized by the machine learning model (an example of a third machine learning model) is the processing of the server device 10, but is shown separately for convenience.

[0070] The user generates input information via the terminal device 20 (step S3100) and transmits it to the server device 10 (step S3110). In FIG. 9, the input information is information related to the texture of the item surface that the user imagines. For example, if the user wants to obtain a desired texture, the input information is information representing that texture. The input information may include at least one of text, symbols, pictograms, numbers, colors, textures, images, sounds, gestures (including motions), and any combination of two or more of these. Text is typically a character string that has meaning, but may also include meaningless character strings. The input information may also be input in a template format.

[0071] When the server device 10 acquires the input information, it inputs the input information into a predetermined machine learning model and acquires the resulting item texture (steps S3200, S3300). The predetermined machine learning model is a machine learning model constructed using artificial intelligence, and is a model that generates and outputs a texture (item texture) based on an input such as the input information described above. Hereinafter, for the sake of distinction, the predetermined machine learning model that generates and outputs a texture based on an input such as the input information described above will also be referred to as a "texture output model." Note that the texture output model may be a model separate from the image output model described above, or an integrated model.

[0072] The method for generating the input information is arbitrary and may be the same as the method described above with reference to FIG.

[0073] The item texture may represent the surface texture of any item available in the virtual space. The granularity of the item texture may be adjustable to make the texture visible depending on the attributes of the item. The type and size of the item related to the texture may be specified by information separate from the input information, or may be included in the input information.

[0074] The item texture may be a plain texture only, or may be a texture including a pattern, as shown in Fig. 10. In this case, the pattern may be a pattern that simply makes the texture easier to understand, or may be a pattern that can be used in combination with the texture. In the example shown in Fig. 10, the upper texture Tx1 has a relatively flat surface, while the lower texture Tx2 has a relatively high surface unevenness.

[0075] The input information may also be able to include character strings related to so-called negative words. For example, if the input information includes "exterior wall" and "apartment" and also includes "sprayed" as a negative word, a texture related to the exterior wall of an apartment building other than sprayed (for example, a texture including bricks and tiles) may be generated.

[0076] 3, the server device 10 may determine whether the input information contains predetermined prohibited words, and if the predetermined prohibited words are included, may notify the terminal device 20 of this fact and request the user to regenerate and resend the input information without the predetermined prohibited words. In this case, the predetermined prohibited words may include words that violate public order and morals, such as obscene words, slander, hate speech, etc., or words that infringe or are likely to infringe the intellectual property rights of others. The predetermined prohibited words may be stored and accumulated in the server storage unit 12 or the like in dictionary format.

[0077] When the server device 10 acquires the item texture, it stores the item texture information in the server storage unit 12 (step S3210). The item texture information includes data of the item texture and input information used to generate the item texture, in a form in which the data and the input information are associated with each other.

[0078] Next, the server device 10 generates a preview display of the item texture (step S3220) and enables output of the preview display on the terminal device 20. The user can determine the need for corrections, etc. while viewing the preview display on the terminal device 20 (step S3120). The preview display may be the item texture itself, or may be realized as an item texture reflected on an arbitrary item. The preview display may be a three-dimensional display and may be capable of panning and rotation. For example, if the target item is clothing for the user's avatar, an avatar dressed in clothing reflected in the item texture may be generated, and a preview display may be possible together with the avatar.

[0079] If the user determines that no modifications are necessary to the item texture thus generated, the user generates a correspondence instruction for associating the final version with any item available in the virtual space (for example, a desired item designated by the user), and transmits the instruction to the server device 10 (step S3130). The correspondence instruction may include information for identifying the item to be associated (predetermined item).

[0080] When the server device 10 receives the association instruction (step S3230), it associates the predetermined item, which is the item to be associated, with the item texture (step S3240). The association method is arbitrary. For example, if the predetermined item is clothing for the user's avatar, the association may be achieved by including the item texture in part or all of the clothing. Furthermore, such association may be achieved according to the size of the predetermined item. Such a reflection method may be specified by information separate from the input information, or may be included in the input information.

[0081] In this way, according to the process shown in FIG. 9, the user can obtain the desired item texture by generating input information according to their own image, without having to draw the item texture themselves, and can reflect that item texture on any item available in the virtual space.

[0082] 9, if the item to be associated is determined in advance, the input information generated in step S3100 may include the attributes and name of the item to be associated (i.e., the predetermined item). In this case, it may be possible to acquire an item texture that takes into account the attributes, etc., of the predetermined item.

[0083] Next, a UI (User Interface) suitable for the preview display described above will be described with reference to Figures 13A to 13C. The UIs shown in Figures 13A to 13C may be UIs available in a virtual space and may be positioned within the user's field of view.

[0084] FIG. 13A is a diagram showing an example of the UI 13 that allows generation / input of input information, instructions to mix a plurality of specific images, etc.

[0085] In the example shown in FIG. 13A, the UI13 includes four specific image display areas P13 and an input area K130. The input area K130 includes an input character output area K131 and a character input section K132. The four specific image display areas P13 may be areas that output specific images obtained by the method described above with reference to FIG. 3. Note that some or all of the four specific image display areas P13 may be capable of outputting item textures obtained by the method described above with reference to FIG. 9 and / or item shapes obtained by the method described above with reference to FIG. 11, instead of or in addition to the specific images obtained by the method described above with reference to FIG. 3.

[0086] The input character output area K131 may be an area that displays the various types of input information described above. The character input unit K132 may be a UI for inputting the various types of input information described above, and may be in the form of a keyboard, for example. Input of characters, etc. into the input character output area K131 may be realized by other inputs, such as voice input. The input character output area K131 may also list input candidate words derived based on artificial intelligence, etc. For example, words suitable as input information may be listed, such as words indicating patterns such as repeating patterns or seamless patterns, or words indicating image manipulation such as image synthesis, such as blending. In this case, the user can input desired characters without typing many characters. This is particularly suitable when the user wears a head-mounted display and stays in the metaverse space. This is because, unlike reality, in such an environment, it is often difficult to manually specify small details or enter detailed information.

[0087] In the UI13 shown in FIG. 13A , a user may select a desired specific image display area P13 from among a plurality of specific image display areas P13, thereby enabling the user to select a specific image, etc., displayed in the selected specific image display area P13. As described above, the selected specific image, etc., may be reflected in a predetermined item. Furthermore, by selecting two or more specific images, etc., from among the plurality of specific images, etc., displayed in the plurality of specific image display areas P13, the user may be able to mix specific images, mix item textures, combine specific images with item textures, combine specific images with item shapes, combine item textures with item shapes, or combine specific images, item textures, and item shapes. In this case, combining various parameters makes it easier to create a desired item, improving user convenience.

[0088] Such a UI 13 is suitable for the above-described preview display (see, for example, step S2120 in FIG. 3). For example, the user can fine-tune a specific image by operating the UI 13 on the preview display.

[0089] FIG. 13B is a diagram showing an example of the UI 14 that allows color adjustment.

[0090] In the example shown in FIG. 13B, the UI14 includes multiple sections (color attributes of materials) P140 representing multiple colors. Each of the multiple sections P140 may be assigned a different color, and the corresponding item may be colored using the corresponding color. While FIG. 13B shows a 20×20 array, a larger number of sections may be provided. The color settings for the multiple sections P140 may be user-customizable or may be provided as dynamically changing variables. Furthermore, the color settings are not limited to RGB values, and may include parameters such as transparency and material reflectivity. A pre-defined color set may be proposed depending on the item to be colored, or may be automatically set by AI or the like depending on the item to be colored. The overall form of the UI14 is also arbitrary and may change depending on the item to be colored. For example, when coloring the area around the eyes of a face, the overall form of the UI14 may be in the form of a cosmetic eyeshadow palette. Such a UI14 may also be automatically generated when an image including a base color set is provided.

[0091] 13B, the user may be able to select a desired one of the multiple sections P140 and select the color associated with the selected section P140. In this case, the selected color may be reflected in some or all of the predetermined items, as described above.

[0092] Such a UI 14 is suitable for the preview display described above (see, for example, step S2120 in FIG. 3). For example, the user can adjust the color, hue, etc. of a part or all of a specific image (or accordingly, a part or all of a predetermined item reflecting the specific image) by operating the UI 14 on the preview display. In addition, other parameters such as reflectance, roughness, and material (for example, the characteristics of the material of the item to be drawn) may be adjustable. However, reflectance, etc. may be adjustable as a texture.

[0093] FIG. 13C is a diagram showing an example of the UI 15 that allows item selection.

[0094] In the example shown in FIG. 13C, the UI15 includes multiple sections P150 for each item. A different item or an item portion (a part of an item) may be assigned to each of the multiple sections P150, and the rough shape of the corresponding item may be displayed. In FIG. 13C, the number of sections P150 is five, and the entire section is circular, but the number and shape are arbitrary. Such a circular shape is advantageous over a UI such as buttons, because even if the number of items increases (for example, from five to eight), it is only necessary to change the angle of the circular shape without increasing the number of UI such as buttons.

[0095] 13C, the user may select a desired section P150 from among the plurality of sections P150, thereby being able to select an item or a portion thereof associated with the selected section P150. In this case, the selected item or portion thereof may be editable by UI13 and / or UI14, as described above. Note that the items or portions thereof selectable in the plurality of sections P150 may be items owned by the user, etc.

[0096] Such UI 15 is suitable for the above-described preview display (see, for example, step S2120 in FIG. 3) for simultaneously editing multiple items. For example, the user can select and edit some or all of the items of the user's avatar by operating UI 15 on the preview display.

[0097] For example, in the example shown in FIG. 14, clothing and accessories that can be worn by an avatar are managed for each pattern and part. Specifically, in FIG. 14, an avatar wearing the clothing and accessories is shown schematically at the top, and patterns and parts for forming (drawing) the clothing and accessories are shown schematically at the bottom. Note that drawing on each pattern may be achieved using a stencil buffer or the like. Also, the placement of an image on a pattern may be adjusted by adjusting the position of two UV axes. By drawing a specific image on a single three-dimensional item via a corresponding pattern, the processing load can be reduced compared to when a specific image is pasted on a three-dimensional surface.

[0098] FIG. 15 schematically illustrates an example of a controller 1500 that can be used in the Metaverse space. In this case, the controller 1500 has a form similar to a laser pointer, and can activate or select a UI at the position pointed to by the pointer. For example, in FIG. 14, the location selected by the controller 1500 is schematically illustrated as point P14. In this case, the user may be able to operate the desired item by moving point P14 onto that part of the item. Also, the example illustrated in FIG. 15 illustrates the state of the controller 1500 of a user operating the UI 13 illustrated in FIG. 13A. Note that the controller 1500 may be able to move in response to an input from an input device (e.g., a controller) held in the hand of a user (a user wearing a head-mounted display) in the real world. In the example shown in FIG. 15, an input method is performed using an operator 1500, but as described above, the input method can take a variety of forms, such as specifying a part of the body by voice input or inputting a keyword instead of letters.

[0099] Note that the various UIs shown in FIG. 13A and the like are merely examples and can be changed in various ways. Also, UIs other than the various UIs shown in FIG. 13A and the like may be used. For example, a UI may be provided that allows the physical parameters of an item (e.g., rigidity, gravity or resistance, collision radius) to be set. Note that gravity and resistance are parameters that may be associated with items such as the avatar's hair or clothing, and are parameters that affect the dynamic behavior (such as swinging) of the hair or clothing. Furthermore, the collision radius is a parameter that defines the distance at which a collision (interference) with other items occurs in the virtual space. Default values ​​for these parameters may be automatically prepared for each attribute of the item by artificial intelligence.

[0100] Further functionality that may be implemented in the system 1 will now be described with reference to FIG.

[0101] Fig. 16 is a flowchart that schematically illustrates an example of a user-side operation procedure that can be implemented in system 1. Fig. 17 is an explanatory diagram of the procedure in Fig. 16, and is a screen showing a state in which a user is editing the clothes (kimono) of an avatar. Note that the screen shown in Fig. 17 may be a screen on display unit 23 of terminal device 20 that is in the form of a head-mounted display.

[0102] 16 shows an example of an operation procedure for placing items IT800 and IT801 such as furniture in a virtual space such as that shown in Fig. 8, and for editing the placed items and items IT601 and IT602 of the user's avatar A6. Various functions based on the following operation procedure can be realized by the user via, for example, the input unit 24 of the terminal device 20.

[0103] In step S1700, the user places items such as furniture in the virtual space. The virtual space in which a user can place items is arbitrary, and may be, for example, a space on an area (land) in the virtual space owned by the user. The items that can be placed may also be items owned by the user.

[0104] In step S1702, the user selects an item or a portion within an item to be edited from among various items in the virtual space. This selection may be realized, for example, via the UI 15 shown in FIG. 13C.

[0105] In step S1704, the user generates input information. The input information is as described above, and may be, for example, an original keyword. Note that the generation of the input information may be realized via the UI 13 shown in FIG. 13A, for example.

[0106] In step S1706, the user inputs negative words as part of the input information. The negative words are as described above. Note that the operation in step S1706 may be omitted as appropriate.

[0107] When step S1704 (and step S1706) is completed in this manner, a specific image is generated according to the input information, as described above with reference to Fig. 4. The specific image generated in this manner may be reflected in the part selected in step S1702 as a preview display. In other words, the part selected in step S1702 may be drawn in a manner that includes the generated specific image.

[0108] In step S1708, the user specifies a color variation of the specific image. The specification of the color variation of the specific image may be realized via the UI 14 shown in FIG. 13B, for example.

[0109] In step S1710, the user changes the specific image displayed in preview by mixing a reference image with the specific image. The reference image may be displayed in the specific image display area P13 of the UI 13 shown in FIG. 13A, for example, or may be achieved by the user selecting the specific image display area P13 including the reference image to be mixed. The reference image may be an image prepared in advance for mixing, or, as described above, may be another specific image generated based on other input information. Step S1710 is an optional operation and may be omitted as appropriate.

[0110] In step S1712, the user reviews the item to be edited or a portion within the item, which reflects the specific image thus obtained, in three dimensions by panning, rotating, etc.

[0111] In step S1714, the user repeats editing while changing the item to be edited or a portion within the item. For example, as shown in Fig. 17, with various UIs 13, 14, and 15 shown in Fig. 13A to 13C simultaneously displayed, the user may perform various operations using the operator 1500 shown in Fig. 15.

[0112] In step S1716, when the user has obtained an item that reflects the specific image in a satisfactory manner, the user applies for store review. The store review application is accepted by the server device 10, and the process therefor will be described later.

[0113] 16 illustrates editing of a specific image, but the same applies to the above-described item shape and item texture. After editing the item shape and item texture, the user may apply for store review. The store review application may be executed for each item.

[0114] 18 is a flowchart of a process that may be implemented by the server device 10 when a store review application is received. In FIG. 18, the process is shown separately for the server device 10, the terminal device 20, and the smart contract (blockchain network 5).

[0115] The user generates a store review application via the terminal device 20 (step S5100) and transmits it to the server device 10 (step S5110). The store review application may include information specifying the item for which the application is made.

[0116] When the server device 10 receives the store review application, it acquires information about the application target (step S5200). The information about the application target may include information about the item about which the application target is made, a specific image associated with the item about which the application target is made, an item shape that defines the shape of the item about which the application target is made, and an item texture associated with the item about which the application target is made.

[0117] The server device 10 evaluates the uniqueness of the item that is the subject of the application based on the acquired information of the item that is the subject of the application (step S5210). Uniqueness is a parameter that correlates with originality. Note that instead of evaluating uniqueness, similarity with other items may be evaluated equivalently. This is because high / low uniqueness corresponds to low / high similarity. Therefore, in the following description, uniqueness can be read as similarity, and in this case, a state of high uniqueness corresponds to a state of low similarity, and a state of low uniqueness corresponds to a state of high similarity.

[0118] The uniqueness evaluation method is optional, but is preferably as follows. When the item to be applied for includes a specific image generated based on input information, the uniqueness may be evaluated based on the similarity of the appearance, etc., between the specific image and other images. In this case, the uniqueness may take into account the input information (input information to the image output model) used to generate the specific image. For example, if the input information used to generate one specific image is similar to the input information used to generate another image, the uniqueness of the specific image may be calculated to be a low value. In this case, uniqueness can be calculated based on a comparison between input information, thereby reducing the processing load and increasing the reliability of the calculation results. The comparison between input information may utilize word embedding in natural language processing such as Word2vec. In Word2vec, word vectors of characters (words) included in the input information that are located close to each other in a vector space may be determined to have a high similarity relationship. By utilizing such natural language processing, the similarity between input information can be efficiently determined. Furthermore, the similarity between input information can be efficiently determined for a variety of languages. It is also possible to use comparison in latent space, such as the Diffusion Model, or to use word edit distance or Euclidean distance in CLIP (Contrastive Language-Image Pre-training), which may be used internally.

[0119] The server device 10 may further evaluate the intellectual property rights based on the acquired information on the application subject (step S5220). The evaluation of the intellectual property rights may be performed from the perspective of whether or not the appearance of the application subject item clearly infringes the design right, etc., of another person. The evaluation of the intellectual property rights may also be performed from the perspective of whether or not the application subject item includes a trademark related to the trademark right of another person. Although not shown in FIG. 18, an evaluation (check) may also be performed from the perspective of whether or not the appearance of the application subject item clearly violates public order and morals.

[0120] The server device 10 notifies the user of the uniqueness evaluation result (step S5230). The notified result may be displayed on the terminal device 20 (step S5120). At this time, the evaluation result of the intellectual property right does not have to be notified, but if the infringement is clearly infringing the rights of others or there is a high probability of this, a notification to that effect may be made. The same applies to cases where the infringement is clearly in violation of public order and morals or there is a high probability of this. If the infringement is clearly in violation of the rights of others or there is a high probability of this, and / or if the infringement is clearly in violation of public order and morals or there is a high probability of this, the application may be rejected.

[0121] Next, the server device 10 performs an application completion process to store the item to be applied for in a predetermined database or the like (step S5240). The item stored in this manner may be used when evaluating the uniqueness of another item to be applied for (step S5210). Although not shown in FIG. 18, when the application completion process is completed, a notification to that effect may be sent to the terminal device 20.

[0122] Thereafter, when the user makes an NFT request for the item that has undergone the application completion process (step S5130), the server device 10 executes the NFT process (step S5250). The NFT process includes issuing the target item as an NFT (Non-Fungible Token). In this case, the server device 10 may mint the NFT via a smart contract on the blockchain network 5 (step S5300). The NFT process may also include listing the issued NFT on a marketplace or the like.

[0123] FIG. 19 is a schematic flowchart illustrating an example of a uniqueness evaluation process.

[0124] In step S1000, the server device 10 acquires (extracts) input information associated with the specific image based on the specific image information of the specific image to be determined.

[0125] In step S1002, the server device 10 extracts images to be compared. The images to be compared may be stored in a given database. The images to be compared may be extracted one by one.

[0126] In step S1004, the server device 10 calculates the similarity between appearance elements between the image to be compared and the specific image to be determined. Appearance elements may include, for example, at least one of color, texture, and pattern. Appearance elements may also include other elements such as composition (arrangement). The method for calculating the similarity between appearance elements is arbitrary, and may be calculated as a score, for example. For example, an avatar wearing clothing may be rotated through a 360-degree azimuth angle range and / or a 90-degree elevation angle range, and the similarity (color and shape) of the captured image may be evaluated as a numerical value.

[0127] In step S1006, the server device 10 acquires (extracts) input information related to the image to be compared. The input information related to the image to be compared is input information used to generate the image to be compared, and is input information input to the image output model. Such input information may be associated with the image to be compared and stored in a given database. Note that in this embodiment, the image to be compared may be only an image associated with such input information.

[0128] In step S1008, the server device 10 calculates the similarity between the input information related to the specific image to be judged and the input information related to the image to be compared, based on the input information. As described above, the similarity between the input information may be calculated using Word2vec. This is because if the characters included in the input information input to the image output model match or are similar, the likelihood of generating a similar specific image increases.

[0129] Incidentally, the input information input to the image output model depends on the image output model, but may include a random number seed value to ensure the uniqueness of the specific image to be generated. In this case, if the random number seed values ​​included in the input information input to the image output model match, the likelihood of generating a similar specific image increases. Therefore, in this case, the server device 10 may further calculate the similarity between the input information based on the relationship between the random number seed values.

[0130] In step S1010, the server device 10 calculates a uniqueness value based on the similarity between the appearance elements calculated in step S1004 and the similarity between the input information calculated in step S1008. In this case, the uniqueness value may be calculated using only one (for example, the one with higher similarity) of the similarity between the appearance elements calculated in step S1004 and the similarity between the input information calculated in step S1008, or may be calculated by averaging or combining them.

[0131] In step S1012, the server device 10 determines whether all images to be compared have been extracted. That is, it determines whether evaluation of the uniqueness of the specific image to be judged for all images to be compared has been completed. If the determination result is "YES", the process proceeds to step S1014; otherwise, the process returns to step S1002, where a new image to be compared is extracted, and the process from step S1004 is repeated.

[0132] In step S1014, the server device 10 outputs a uniqueness value based on the evaluation result of the uniqueness of the specific image to be judged with respect to all the images to be compared. In this case, the uniqueness value for each image to be compared may be output, or only a specific value such as the minimum value (the uniqueness value for the most similar image to be compared) may be output.

[0133] 19, the uniqueness of the specific image to be determined is evaluated based on the similarity between appearance elements and the similarity between input information, which increases the reliability of the evaluation result compared to when uniqueness is evaluated based on only one of the similarity between appearance elements and the similarity between input information. However, in a modified example, the uniqueness of the specific image to be determined may be evaluated based on only one of the similarity between appearance elements and the similarity between input information.

[0134] Next, an example of the function of the server device 10 in the system 1 will be described with reference to FIG. 20 and subsequent figures.

[0135] In the following description, the functions of the server device 10 will be mainly described, but some or all of the functions of the server device 10 described below may be realized by one or more terminal devices 20.

[0136] FIG. 20 is a block diagram schematically illustrating an example of the functions of the server device 10. As shown in FIG.

[0137] 20 , the server device 10 includes an operation input acquisition unit 150, an image acquisition unit 152, an image association processing unit 154, a shape information acquisition unit 156, a shape assignment processing unit 158, an additional information acquisition unit 160, an item surface processing unit 162, an edit processing unit 164, a determination unit 166, a parameter calculation unit 168, an output processing unit 170, an information management unit 172, an image management unit 173, an item management unit 174, a token management unit 176, a contest processing unit 178, an evaluation information storage unit 190, and a user information storage unit 192. Note that each processing unit such as the operation input acquisition unit 150 can be realized by the server communication unit 11 and the server control unit 13 shown in FIG. 1. Furthermore, storage units such as the evaluation information storage unit 190 and the user information storage unit 192 can be realized by the server storage unit 12 shown in FIG. 1.

[0138] The operation input acquisition unit 150 acquires various user inputs by each user inputted via the input unit 24 of the terminal device 20. The various inputs are as described above.

[0139] The image acquisition unit 152 acquires a specific image based on the input information from the user. The method for acquiring the specific image may be as described above in relation to step S2200 in FIG.

[0140] The image association processing unit 154 associates a specific image with a predetermined item that can be used in the virtual space. The predetermined item may be as described above. The method for associating the specific image may be as described above in relation to step S2240 of FIG. 3.

[0141] The image matching processor 154 may simultaneously match the acquired specific image or a derivative image obtained by partially modifying the specific image to predetermined items associated with multiple avatars. A derivative image obtained by partially modifying a specific image may not be exactly the same image, but may have common features or features that can create a sense of unity when combined. In this case, specific images can be simultaneously matched to predetermined items associated with multiple avatars having a specific relationship, reducing the processing load compared to the case where similar specific images are separately acquired and matched. FIG. 21 schematically illustrates four avatars A1 to A4 performing in a band. The image matching processor 154 may simultaneously match specific images or derivative images obtained by partially modifying the specific image to multiple avatars of such friends. In this case, the matching instruction (see step S3130 in FIG. 9) may be generated by any one or more users associated with the multiple avatars. Alternatively, a matching instruction for simultaneously matching predetermined items associated with multiple avatars may be generated based on the matching instructions (see step S3130 in FIG. 9) from all users.

[0142] The above-mentioned specific relationship may include a relationship in which multiple avatars are all linked to one user (where one user is associated with the avatars of a group).In addition to or instead of such a relationship, the above-mentioned specific relationship may also include a relationship in which one user and one avatar are linked, but multiple users are also linked (for example, users are friends).

[0143] The shape information acquisition unit 156 acquires the item shape (an example of shape information) based on the information input by the user. The method for acquiring the item shape may be as described above in relation to step S4200 in FIG.

[0144] The shaping processing unit 158 ​​shapes the predetermined item based on the item shape. The method for shaping the predetermined item may be as described above in relation to step S4240 in FIG.

[0145] Similar to the image association processing unit 154, the shape assignment processing unit 158 ​​may assign shapes to predetermined items for multiple avatars simultaneously based on the acquired item shape or a derived item shape obtained by modifying a part of the item shape. In this case, shapes can be assigned at once to predetermined items for multiple avatars that have a specific relationship, such as a friend relationship, and the processing load can be reduced compared to when similar item shapes are acquired and associated separately for each item.

[0146] The additional information acquisition unit 160 acquires item surface information that can be reflected on the surface (appearance) of a predetermined item based on information input by the user. The item surface information may be information for setting or changing at least one of the pattern, fabric, decoration, and texture of the predetermined item. The method for acquiring the item texture may be as described above in relation to step S3200 in FIG. 9 . The method for acquiring other item surface information may be similar. Furthermore, when acquiring multiple pieces of item surface information, they may be acquired simultaneously or separately.

[0147] The item surface processing unit 162 sets or changes at least one of the pattern, fabric, decoration, and texture of a predetermined item based on the item surface information. The method for setting or changing the texture of a predetermined item based on the item texture may be as described above in relation to step S4240 in Figure 11. The same method may be used for setting or changing other item surface information.

[0148] Like the image matching processor 154, the item surface processor 162 may simultaneously set or change at least one of the patterns, fabrics, decorations, and textures of predetermined items for multiple avatars based on the acquired item surface information or a derived item shape obtained by modifying part of the item surface information. In this case, it is possible to set or change the predetermined items of multiple avatars that have a specific relationship, such as a friend relationship, all at once, which reduces the processing load compared to when similar item surface information is acquired and set or changed separately for each item.

[0149] The editing processor 164 edits the item shape based on information about the avatar to which a predetermined item is to be associated and information about the space to which the predetermined item is to be placed. For example, if the size of an avatar that matches the item shape is larger or smaller than the size of the avatar to which the shape is to be assigned, the editing processor 164 may change the item shape similarly in accordance with the size difference. Furthermore, if the size of the space to which a predetermined item (e.g., a bridge abutment) is to be assigned is larger or smaller than the size of the space to which the item to be assigned is to be placed, the editing processor 164 may change the item shape similarly in accordance with the size difference. This increases the versatility of the item shape, and as a result, reduces the processing load (e.g., the load required for processing, such as obtaining item shapes for different sizes).

[0150] The editing processor 164 also edits the item surface information based on information about the avatar associated with a specific item. For example, if the size of an avatar that matches the decoration associated with the item surface information is larger or smaller than the size of the associated avatar, the editing processor 164 may similarly change the decoration associated with the item surface information depending on the size difference. This increases the versatility of the item surface information, thereby reducing the processing load (e.g., the load required for processing, such as acquiring item surface information for each different size).

[0151] Here, the editing processor 164 may evaluate the corresponding 3D model of the avatar for editing based on, for example, VRM, which is a common standard for 3D avatars. In this case, it is possible to obtain predetermined items (and avatars associated with the predetermined items) that can be used on multiple avatar platforms (various services).

[0152] The determination unit 166 determines whether the input information acquired from the user satisfies a predetermined condition. The predetermined condition may be set from various perspectives. For example, the predetermined condition may include whether the input information contains a predetermined prohibited word. The predetermined prohibited word may be as described above. The predetermined condition may be satisfied when the possibility of infringing another person's intellectual property right is higher than a predetermined standard, or when the possibility of violating public order and morals is higher than a predetermined standard. The predetermined condition may be set as appropriate by the operator of this service.

[0153] The parameter calculation unit 168 calculates values ​​of parameters (examples of predetermined parameters) relating to various similarities, such as the above-mentioned uniqueness value, similarity between predetermined items, similarity between specific images, similarity between item shapes, similarity between item textures, etc. Note that the similarity between predetermined items may be evaluated in a state where any one of the specific image, item shape, and item texture is reflected.

[0154] The various similarity-related parameters and the method of calculating the values ​​thereof are arbitrary, but may be as described above with reference to FIG. 19, for example.

[0155] In this embodiment, the parameter calculation section 168 includes a first parameter calculation section 1681 and a second parameter calculation section 1682.

[0156] The first parameter calculation unit 1681 calculates the similarity between the appearance elements between the image to be compared and the specific image to be determined. The method of calculating the similarity between the appearance elements may be the same as that of step S1004 described above with reference to FIG. 19 , for example.

[0157] Furthermore, the first parameter calculation unit 1681 may calculate the similarity between the appearance elements based on the attributes of a predetermined item with which a specific image is associated. For example, the first parameter calculation unit 1681 may calculate the similarity between the appearance elements based on the relationship between the attributes of an item with which a comparison target image is associated and the attributes of a predetermined item with which a specific image is associated. In this case, the first parameter calculation unit 1681 may calculate the similarity between the appearance elements in such a manner that the similarity between the appearance elements is higher when the attributes match, are very similar, or have something in common than when they do not.

[0158] Furthermore, the first parameter calculation unit 1681 may change the calculation method of the similarity between appearance elements depending on the attributes of the predetermined item to which the specific image is associated. For example, if the predetermined item to which the specific image is associated is a three-dimensional item, the first parameter calculation unit 1681 may calculate the similarity between appearance elements based on three-dimensional views from multiple viewpoints. Alternatively, even if the predetermined item to which the specific image is associated is not a three-dimensional item, if it is an avatar item, the first parameter calculation unit 1681 may calculate the similarity between appearance elements based on three-dimensional views from multiple viewpoints when the item is attached to the avatar.

[0159] The second parameter calculation unit 1682 calculates the similarity between the pieces of input information. The method of calculating the similarity between the pieces of input information may be the same as that in step S1008 described above with reference to FIG.

[0160] In this case, the calculated value by the first parameter calculation unit 1681 and the calculated value by the second parameter calculation unit 1682 may be used in combination as described above with reference to FIG.

[0161] The output processing unit 170 outputs the value of the parameter relating to the similarity calculated by the parameter calculation unit 168. The method for outputting the value of the parameter relating to the similarity is arbitrary, and may be, for example, output for processing by the item management unit 174, which will be described later. Alternatively, the value of the parameter relating to the similarity may be output by notifying the owner of the predetermined item to be judged, or the like.

[0162] The information management unit 172 manages (stores, extracts, etc.) specific images and the like in association with input information. Specifically, the information management unit 172 may generate and manage the specific image information (step S2210) described above with reference to FIG. 3. In addition, the information management unit 172 may generate and manage the item texture information (step S3210) described above with reference to FIG. 9, the item shape information (step S4210) described above with reference to FIG. 11, etc. The various pieces of information generated and managed by the information management unit 172 can be suitably used for the parameter calculation unit 168 to calculate various similarity-related parameters, as described above.

[0163] If the input information satisfies a predetermined condition based on the determination result by the determination unit 166, the image management unit 173 prohibits or restricts the use or distribution in the virtual space of the specific image acquired based on the input information. As described above, the predetermined condition can be determined, for example, by the operator of the virtual space. This makes it possible to appropriately prevent situations such as specific images being randomly associated with items that can be used in the virtual space. Note that distribution in the virtual space may include sales in the virtual space market, etc.

[0164] The item management unit 174 permits, prohibits, or restricts the use or distribution of each predetermined item in the virtual space based on the value of the predetermined parameter calculated by the parameter calculation unit 168. For example, if a specific image is associated with a predetermined item by the image association processing unit 154, the item management unit 174 permits, prohibits, or restricts the use or distribution of the predetermined item in the virtual space with the associated specific image based on the value of the predetermined parameter calculated by the parameter calculation unit 168. Similarly, if a shape is assigned to a predetermined item by the shaping processing unit 158, the item management unit 174 permits, prohibits, or restricts the use or distribution of the predetermined item in the virtual space with the associated item surface information based on the value of the predetermined parameter calculated by the parameter calculation unit 168. Similarly, if item surface information is assigned to a predetermined item by the item surface processing unit 162, the item management unit 174 permits, prohibits, or restricts the use or distribution of the predetermined item in the virtual space with the associated item surface information based on the value of the predetermined parameter calculated by the parameter calculation unit 168.

[0165] Furthermore, similar to the image management unit 173, the item management unit 174 may prohibit or restrict the use or distribution in the virtual space of an item associated with a specific image acquired based on the input information when the input information satisfies a predetermined condition based on the judgment result by the judgment unit 166.

[0166] The token management unit 176 issues and manages tokens such as non-fungible tokens (NFTs) for predetermined items. The method of issuing NFTs for predetermined items may be as described in step S5250 above with reference to FIG. 18. In addition to issuance, the token management unit 176 may also record owners and transfers of ownership, and may replicate or destroy tokens in accordance with a paid or free request in a market, smart contract, or distributed processing module external to the system 1.

[0167] Furthermore, similar to the image management unit 173, the token management unit 176 may prohibit or restrict the issuance or circulation of tokens based on a specific image obtained based on the input information when the input information satisfies a predetermined condition based on the judgment result by the judgment unit 166.

[0168] The contest processing unit 178 executes processing related to holding various contests in the virtual space. The various contests are optional and may include a contest related to the predetermined items described above. FIG. 22 is an image diagram of a contest. FIG. 22 shows a fashion contest in which multiple users are showing off the predetermined items on a stage in the virtual space via avatars A11, A12, and A13 wearing the predetermined items associated with the specific images described above.

[0169] Evaluation results (e.g., voting results) from multiple users in a virtual space may be collected for predetermined items associated with specific images by the image association processing unit 154, or for avatars associated with predetermined items. Based on the evaluation results, the contest processing unit 178 may then perform various processes, such as announcing rankings and awarding prizes to winners. In this case, artificial intelligence based on a given logic may be used instead of or in addition to the evaluation results from multiple users. For example, in a contest with a theme or mission, whether the theme matches or the mission has been completed may be determined based on the artificial intelligence. More specifically, for example, in the case of a theme such as "cool adults," parameters such as maturity, coolness, and cuteness of the predetermined items worn by the avatars may be set, and the superiority or inferiority of the items may be determined by the artificial intelligence based on the values ​​of these parameters. In this case, the artificial intelligence may be constructed by learning past evaluation results by humans (e.g., reliable evaluators or operators).

[0170] The evaluation information storage unit 190 may store the above-mentioned various information generated and managed by the item management unit 174.

[0171] Information necessary for realizing the various processes described above may be stored for each user (e.g., for each user ID) in the user information storage unit 192. For example, information on the corresponding avatar (e.g., a VRM file) and information on various predetermined items owned by each user may be stored.

[0172] 20, the image matching processor 154, the shaping processor 158, and the item surface processor 162 each execute processing independently of one another, but this is not limited to this. That is, any combination of two or more of the image matching processor 154, the shaping processor 158, and the item surface processor 162 may function simultaneously. For example, the image matching processor 154 and the shaping processor 158 may function simultaneously to generate a predetermined item that simultaneously reflects the item shape and specific image obtained in the above-described manner.

[0173] Although each embodiment has been described in detail above, it is not limited to a specific embodiment, and various modifications and changes are possible within the scope of the claims. It is also possible to combine all or a plurality of the components of the above-described embodiments.

[0174] For example, in the above-described embodiment, the specific image, item shape, and item texture are acquired independently of each other, but this is not limited to this. That is, any combination of two or more of the specific image, item shape, and item texture may be acquired simultaneously. In this case, the machine learning model may also be constructed in an integrated manner.

[0175] In addition, the following supplementary notes are disclosed regarding the above-described embodiment.

[0176] (Appendix 1) a user input acquisition unit that acquires a predetermined input from a user; an image acquisition unit that utilizes a first machine learning model constructed by artificial intelligence to acquire a specific image obtained by inputting the predetermined input into the first machine learning model; and an association processing unit that associates the specific image with a predetermined item that can be used in a virtual space.

[0177] (Appendix 2) the predetermined item is rendered visibly in a virtual space by reflecting the specific image on a corresponding pattern; The information processing system described in Appendix 1, further comprising a pattern generation unit that generates the pattern using a machine learning model constructed by artificial intelligence.

[0178] The inventions described in the claims of the original application of this application are as follows: [1] a user input acquisition unit that acquires a predetermined input from a user; an image acquisition unit that utilizes a first machine learning model constructed by artificial intelligence to acquire a specific image obtained by inputting the predetermined input into the first machine learning model; and an association processing unit that associates the specific image with a predetermined item that can be used in a virtual space. [2] The information processing system according to [1], wherein the predetermined items include at least one of an item that can be associated with an avatar in a virtual space and an item that can be placed in the virtual space. [3] a shape information acquisition unit that utilizes a second machine learning model constructed by artificial intelligence to acquire shape information of the predetermined item obtained by inputting the predetermined input into the second machine learning model; The information processing system according to [1], further comprising a shaping processing unit that shapes the specified item based on the shape information. [4] an additional information acquisition unit that utilizes a third machine learning model constructed by artificial intelligence to acquire item surface information obtained by inputting the predetermined input into the third machine learning model; The information processing system described in [1] further comprises an item surface processing unit that sets or changes at least one of the pattern, fabric, decoration, and texture of the specified item based on the item surface information. [5] the predetermined item includes at least one of an item that can be associated with an avatar in a virtual space and an item that can be placed in the virtual space; The information processing system described in [3] further comprises an editing processing unit that edits the shape information based on information regarding an avatar to which the specified item is to be associated, or information regarding a space to which the specified item is to be placed. [6] the predetermined item includes an item that can be associated with an avatar in a virtual space; The information processing system described in [4] further comprises an editing processing unit that edits the item surface information based on information regarding the avatar to be associated with the specified item. [7] The information processing system according to [1], wherein the predetermined input includes at least one of text, symbols, emojis, numbers, colors, textures, images, sounds, gestures, and any combination of two or more of these. [8] The information processing system described in [1] further comprises a contest processing unit that collects evaluation results from multiple users in a virtual space regarding the specified item to which the specific image is associated by the association processing unit, or the avatar to which the specified item is associated. [9] The information processing system according to [1], wherein the association processing unit simultaneously associates the specific image or a derivative image obtained by modifying a part of the specific image with the predetermined item relating to a plurality of avatars.

[10] a calculation unit that calculates a value of a predetermined parameter related to the similarity between the predetermined item associated with the specific image by the association processing unit and another item available in the virtual space; The information processing system according to [1], further comprising: an output processing unit that outputs the value of the predetermined parameter calculated by the calculation unit.

[11] The information processing system described in

[10] , wherein the calculation unit calculates the value of the specified parameter related to one of the specified items to which the specific image is associated based on the specific image associated with the one specified item and the specified input used to acquire the specific image.

[12] The information processing system described in

[11] , wherein the calculation unit calculates the value of the specified parameter related to one of the specified items to which the specific image is associated, further based on the attributes of the one specified item.

[13] the calculation unit includes a first calculation unit that calculates a value of a first parameter related to a similarity between the specific image and an image associated with the other item; The information processing system according to

[11] , wherein the value of the predetermined parameter includes the value of the first parameter calculated by the first calculation unit or a value based thereon.

[14] The information processing system according to

[13] , wherein the first calculation unit calculates the value of the first parameter based on at least one of color, texture, and pattern.

[15] The information processing system according to

[13] , wherein the first calculation unit calculates the value of the first parameter based on three-dimensional views from multiple viewpoints.

[16] the calculation unit includes a second calculation unit that calculates a value of a second parameter related to a similarity between the predetermined input used to acquire the specific image and another input corresponding to the predetermined input used to generate an image associated with the other item; The information processing system according to

[10] , wherein the value of the predetermined parameter includes the value of the second parameter calculated by the second calculation unit or a value based thereon.

[17] The information processing system according to

[16] , wherein the second calculation unit calculates the value of the second parameter based on a relationship between the text included in the specified input and the text included in the other input.

[18] the predetermined input and the other input both further include a seed value of a random number; The information processing system described in

[16] , wherein the second calculation unit calculates the value of the second parameter based on the relationship between the seed value included in the specified input and the seed value included in the other input.

[19] The information processing system described in

[10] further comprises an item management unit that permits, prohibits, or restricts the use or distribution in a virtual space of the specified item to which the specific image is associated by the association processing unit based on the value of the specified parameter calculated by the calculation unit.

[20] An information processing system according to any one of [1] to

[17] , further comprising an information management unit that manages the specific image or the specific item to which the specific image is associated in association with the specific input. [twenty one] a determination unit that determines whether the predetermined input satisfies a predetermined condition; An information processing system according to any one of [1] to

[17] , further comprising an image management unit that prohibits or restricts the use or distribution in virtual space of the specific image obtained based on the specified input when the specified input satisfies the specified conditions. [twenty two] The information processing system described in

[21] , wherein the specified condition is satisfied when the possibility of infringing the intellectual property rights of others is higher than a specified standard, or when the possibility of violating public order and morals is higher than a specified standard. [twenty three] An information processing system according to any one of [1] to

[17] , further comprising a token management unit that issues and manages non-fungible tokens based on the specific image or the specified item to which the specific image is associated. [twenty four] Obtaining predetermined input from a user; Using a first machine learning model constructed by artificial intelligence, a specific image is obtained by inputting the predetermined input into the first machine learning model; An information processing method executed by a computer, comprising associating the specific image with a predetermined item available in a virtual space. [twenty five] Obtaining predetermined input from a user; Using a first machine learning model constructed by artificial intelligence, a specific image is obtained by inputting the predetermined input into the first machine learning model; Associating the specific image with a predetermined item available in the virtual space A program that causes a computer to perform a process. [Explanation of symbols]

[0179] 1 System 3 Network 5. Blockchain Network 10 Server device 11 Server Communication Unit 12 Server storage unit 13 Server control unit 20 Terminal equipment 21 Terminal communication unit 22 Terminal memory section 23 Display section 24 Input section 25 Terminal control unit 150 Operation input acquisition unit 152 Image acquisition unit 154 Image matching processing unit 156 Shape information acquisition unit 158 Shaping processing section 160 Additional information acquisition unit 162 Item Surface Treatment 164 Editing Processing Unit 166 Judgment section 168 Parameter Calculation Unit 1681 first parameter calculation unit (first calculation unit) 1682 second parameter calculation unit (second calculation unit) 170 Output Processing Unit 172 Information Management Department 173 Image Management Department 174 Item Management Department 176 Token Management Department 178 Contest Processing Unit 190 Evaluation information storage unit 192 User information storage unit

Claims

1. a user input acquisition unit that acquires a predetermined input from a user; an image acquisition unit that acquires a specific image obtained by inputting the predetermined input into a first machine learning model, the first machine learning model being constructed by artificial intelligence and generating and outputting an image that reflects a context based on input information; an association processing unit that associates the specific image with a predetermined item that can be used in the virtual space; an information processing system comprising: a calculation unit that calculates a value of a first parameter related to the similarity between an appearance element of the specified item to which the specific image is associated by the association processing unit and an appearance element of another item; and calculates a value of a similarity parameter related to the similarity between the specified item and the other item based on the value of the first parameter.

2. The information processing system according to claim 1 , wherein the predetermined items include at least one of an item that can be associated with an avatar in a virtual space and an item that can be placed in the virtual space.

3. a shape information acquisition unit that acquires shape information of the predetermined item obtained by inputting the predetermined input into a second machine learning model, the second machine learning model being constructed by artificial intelligence and generating and outputting an item shape based on input information; The information processing system according to claim 1 , further comprising a shaping processing unit that shapes the predetermined item based on the shape information.

4. an additional information acquisition unit that acquires item surface information obtained by inputting the predetermined input into a third machine learning model, the third machine learning model being constructed using artificial intelligence and generating and outputting an item texture based on input information; The information processing system according to claim 1 , further comprising an item surface processing unit that sets or changes at least one of a pattern, a fabric, a decoration, and a texture of the predetermined item based on the item surface information.

5. the predetermined item includes at least one of an item that can be associated with an avatar in a virtual space and an item that can be placed in the virtual space; The information processing system according to claim 3 , further comprising an editing processing unit that edits the shape information based on information about an avatar to be associated with the specified item or information about a space to be placed in the specified item.

6. the predetermined item includes an item that can be associated with an avatar in a virtual space; The information processing system according to claim 4 , further comprising an editing processing unit that edits the item surface information based on information about an avatar to be associated with the predetermined item.

7. The information processing system according to claim 1 , wherein the predetermined input includes at least one of text, symbols, pictograms, numbers, colors, textures, images, sounds, gestures, and combinations of any two or more of these.

8. The information processing system according to claim 1, further comprising a contest processing unit that collects evaluation results from a plurality of users in a virtual space regarding the specified item to which the specific image is associated by the association processing unit, or the avatar to which the specified item is associated.

9. The information processing system according to claim 1 , wherein the association processing unit simultaneously associates the specific image or a derivative image obtained by modifying a part of the specific image with the predetermined item related to a plurality of avatars.

10. The information processing system according to claim 1 , further comprising an output processing unit that outputs the value of the similarity parameter calculated by the calculation unit.

11. The information processing system according to claim 1 , wherein the calculation unit calculates the value of the similarity parameter related to the one predetermined item to which the specific image is associated, further based on an attribute of the one predetermined item.

12. The information processing system according to claim 1 , wherein the calculation unit calculates the value of the first parameter based on at least one of a color, a texture, and a pattern.

13. The information processing system according to claim 1 , wherein the calculation unit calculates the value of the first parameter based on three-dimensional views from a plurality of viewpoints.

14. the calculation unit calculates a value of a second parameter related to a similarity between the predetermined input used to acquire the specific image and another input corresponding to the predetermined input used to generate an image associated with the other item; The information processing system according to claim 1 , wherein the calculation unit further calculates the value of the similarity parameter based on the value of the second parameter.

15. The information processing system according to claim 14 , wherein the calculation unit calculates the value of the second parameter based on a relationship between text included in the predetermined input and text included in the other input.

16. the predetermined input and the other input both further include a seed value of a random number; The information processing system according to claim 14 , wherein the calculation unit calculates the value of the second parameter based on a relationship between the seed value included in the predetermined input and the seed value included in the other input.

17. The information processing system of claim 10, further comprising an item management unit that permits, prohibits, or restricts the use or distribution in a virtual space of the specified item to which the specific image is associated by the association processing unit based on the value of the similarity parameter calculated by the calculation unit and output by the output processing unit.

18. The information processing system according to claim 1 , further comprising an information management unit that manages the specific image or the specific item associated with the specific image in association with the specific input.

19. a determination unit that determines whether the predetermined input satisfies a predetermined condition; The information processing system according to claim 1, further comprising an image management unit that prohibits or restricts the use or distribution in a virtual space of the specific image obtained based on the specified input when the specified input satisfies the specified conditions.

20. 20. The information processing system according to claim 19, wherein the predetermined condition is satisfied when a possibility of infringing intellectual property rights of others is higher than a predetermined standard, or when a possibility of being contrary to public order and morals is higher than a predetermined standard.

21. The information processing system according to claim 1 , further comprising a token management unit that issues and manages non-fungible tokens based on the specific image or the predetermined item associated with the specific image.

22. a user input acquisition step of acquiring a predetermined input from a user; an image acquisition step of acquiring a specific image obtained by inputting the predetermined input into a first machine learning model, the first machine learning model being constructed by artificial intelligence and generating and outputting an image that reflects a context based on input information; a correlation processing step of correlating the specific image with a predetermined item that can be used in the virtual space; a calculation step of calculating a value of a first parameter related to the similarity between an appearance element of the specified item to which the specific image is associated by the association processing step and an appearance element of another item, and calculating a value of a similarity parameter related to the similarity between the specified item and the other item based on the value of the first parameter.

23. a user input acquisition process for acquiring a predetermined input from a user; an image acquisition process that acquires a specific image obtained by inputting the predetermined input into a first machine learning model, the first machine learning model being constructed by artificial intelligence and generating and outputting an image that reflects a context based on input information; a matching process for matching the specific image with a predetermined item that can be used in the virtual space; a calculation process for calculating a value of a first parameter related to the similarity between an appearance element of the specified item to which the specific image is associated by the association process and an appearance element of another item, and calculating a value of a similarity parameter related to the similarity between the specified item and the other item based on the value of the first parameter.

Images