Image generation system and image generation method

Abstract

To allow a user to select fashion items that suit the user.SOLUTION: An image generation system 100 is configured to: store, for each of fashion items, combination data of a name of the fashion item and information on color category of the fashion item; determine, based on input data, a color category corresponding to a user from among multiple preset color categories; search for the combination data for each of the fashion item to extract name of a fashion item that corresponds to the determined color category corresponding to the user; and input a keyword based on the extracted name of the fashion item and an image of the user to a machine learning model to generate and output a simulation image that simulates the user wearing the fashion item.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an image generation system and an image generation method for generating an image of a user.

Background Art

[0002] Patent Document 1 describes identifying a user's personal color, selecting a combination with a relatively high score associated with the personal color from among a plurality of kimonos and a plurality of ways of wearing them, and outputting combination information indicating the selected combination.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the system described in Patent Document 1, it is not possible to confirm whether a user truly suits themselves. Therefore, it is difficult to allow the user to select a fashion item that suits them.

[0005] Therefore, an object of the present invention is to provide an image generation system and an image generation method that can allow a user to select a fashion item that suits them.

Means for Solving the Problems

[0006] The image generation system of the present invention includes a storage unit that stores combination data of the name of a fashion item and information regarding the color system of the fashion item for each of a plurality of fashion items, a discrimination unit that discriminates, based on input data, a color system corresponding to a user from among a plurality of preset color systems, an extraction unit that extracts the name of a fashion item corresponding to the discriminated color system corresponding to the user by searching the storage unit for the combination data for each of the plurality of fashion items, and a generation unit that generates and outputs a simulated image simulating a state in which the user wears a fashion item by inputting a keyword based on the extracted name of the fashion item and the user's image into a machine learning model.

Advantages of the Invention

[0007] According to the present invention, it is possible to cause a user to select a fashion item that suits the user.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Best Mode for Carrying Out the Invention

[0009] Embodiments of the present disclosure will be described with reference to the accompanying drawings. Where possible, the same parts are denoted by the same reference numerals, and duplicate descriptions are omitted.

[0010] FIG. 1 is a diagram showing the configuration of an image generation system 100 according to the present disclosure. The image generation system 100 is configured to enable data communication between a plurality of terminal devices 10 and a plurality of servers 11, 12, 13 via a communication network (not shown). In this figure, for convenience, only one of the plurality of terminal devices 10 is shown. As will be described later, the image generation system 100 generates and outputs a simulated image simulating a state in which a user wears various fashion items based on an image of the user provided from the terminal device 10. Here, the fashion item is not particularly limited as long as it is an item for decoration that can be worn on the body by the user, and includes clothes worn on the whole body, upper body, or lower body such as Western clothes or kimonos, accessories such as necklaces, earrings, or bracelets, as well as items such as mufflers, gloves, shawls, stoles, ear muffs, headphones, hats, socks, and shoes.

[0011] In the present disclosure, the terminal device 10 is a terminal used by a user, and provides data related to the user, in addition to an image of the user, to the servers 11, 12, 13, and outputs various data such as images provided by the servers 11, 12, 13. Examples of the terminal device 10 include personal computers, smartphones, tablet terminals, feature phones, and server devices.

[0012] The Web server 11 relays various data transmitted and received between the database server 12 and the image generation server 13 and the terminal device 10. That is, the Web server 11 provides Web page data to the terminal device 10 so as to display a Web page, allows various data to be input on the Web page, and allows various data to be output on the Web page, thereby relaying the various data.

[0013] As shown in FIG. 1, the database server 12 includes, as functional components, an extraction unit 21, an input data generation unit 22, and an item information storage unit (memory unit) 23.

[0014] The extraction unit 21 extracts the names of fashion items corresponding to the personal color, which is a color system corresponding to the user of the terminal device 10 discriminated by the image generation server 13, and the user attribute information regarding the attributes of the user input from the terminal device 10 via the Web server 11, by searching a plurality of combination data stored in the item information storage unit 23. Then, the extraction unit 21 extracts the names of fashion items for each wearing part of the user by repeating the search of the above-described plurality of combination data.

[0015] Figure 2 shows an example of the configuration of a plurality of combination data stored in the item information storage unit 23. As shown in the figure, in the item information storage unit 23, combination data is stored for each of a plurality of fashion items, and the combination data includes an "item name" representing the name of the fashion item, a "brand" representing the vendor of the fashion item, a "gender" representing the gender of the user who is recommended to wear the fashion item, a "recommended age group" representing the age group of the user who is recommended to wear the fashion item, a "size" representing the size of the fashion item, a "fashion line" representing the line of the fashion item itself, and a "color" representing information regarding the corresponding color of the personal color among the colors of the fashion item. For example, as an example of the combination data, data including "item name: Tops AAA High Neck Knit Black", "brand: AAA", "gender: Ladies", "recommended age group: 20s", "size: M", "fashion line: Casual", and "color: Black" can be cited. The "item name" included in the combination data includes information regarding the wearing part of the fashion item by the user in addition to the name of the fashion item itself (in the above example, "Tops"). Also, the "brand", "gender", "recommended age group", "size", "fashion line", and "color" included in the combination data are attribute specific information regarding attributes related to the user preferences of the fashion item.

[0016] Here, in the item information storage unit 23, it is sufficient that a plurality of combination data is stored such that the wearing part of the fashion item can be specified. Information regarding the wearing part may be included in the "item name" included in the combination data as described above, or the combination data may be stored in a plurality of storage areas in the item information storage unit 23 divided by wearing part.

[0017] FIG. 3 shows an example of the configuration of user attribute information input from the terminal device 10. As shown in the figure, the user attribute information includes "Name" representing the user's name, "Gender" representing the user's gender, "Age" representing the user's age, "Height" representing the user's height, "Build" representing the user's body shape, "Favorite Fashion", "Favorite Color", "Favorite Brand", etc. representing the user's fashion preference. For example, as an example of user attribute information, it includes "Name: XXX ZZZ", "Age: female", "Height: 165 cm", "Build: normal", "Favorite Fashion: casual style", "Favorite Color: black", "Favorite Brands: AAA, BBB".

[0018] An example of the data search function by the extraction unit 21 for the data shown in FIGS. 2 and 3 will be described. The extraction unit 21 is based on the personal color corresponding to the user and "Gender", "Age", "Favorite Fashion", "Favorite Color", "Favorite Brand" included in the user attribute information, and is associated with attribute specific information that harmonizes with them. It extracts a set of "Item Names" for each wearing part, which are also associated with "Color" that harmonizes with the personal color. For example, when the personal color corresponding to the user is "Blue-based winter" and the user attribute information includes "Gender: female", "Age: 27 years old", "Favorite Fashion Style: casual style", "Favorite Color: black", and "Favorite Brands: AAA, BBB", it extracts the "Item Name: Tops AAA High-neck Knit Black" corresponding to the attribute specific information "Brand: AAA", "Gender: Ladies", "Recommended Age Group: 20s", "Fashion Style: casual", and "Color: black" that comprehensively harmonize with them. At this time, the extraction unit 21 may extract the item name corresponding to the attribute specific information "Size" that matches the "Height" and "Build" included in the user attribute information. By repeating the above data search, the extraction unit 21 randomly extracts a plurality of sets of names of fashion items for different wearing parts.

[0019] The input data generation unit 22 creates a prompt (keyword) to be input to the machine learning model based on the combination of the names of the fashion items for each extracted wearing part. That is, the input data generation unit 22 creates a combination of names obtained by removing the data related to the wearing part from the names of the fashion items for each wearing part. Based on the example of the combination data shown in FIG. 2, for example, as a prompt, "AAA high-neck knit black, BBB baggy jeans navy" is created. Further, the input data generation unit 22 creates a plurality of prompts by repeating the creation of prompts for a plurality of combinations of the names of the fashion items. Then, the input data generation unit 22 provides the plurality of prompts generated for the user of the terminal device 10 to the image generation server 13.

[0020] Referring again to FIG. 1, the image generation server 13 includes, as functional components, a discrimination unit 24, a generation unit 25, and an image data storage unit 26.

[0021] The discrimination unit 24 discriminates a personal color corresponding to the user from among a plurality of preset types of personal colors (color systems) using the image data of a part of the user's body provided from the terminal device 10 via the Web server 11. For example, as the image data, an image of the user's palm or the skin including the upper arm part taken by a camera built into the terminal device 10 is used. The plurality of types of personal colors are, for example, four systems of "yellow-based spring", "yellow-based autumn", "blue-based summer", and "blue-based winter", and a system in which the harmony degrees with respect to a plurality of colors related to fashion items are known is set. When discriminating the personal color, the image data of a part of the user's body is input into a machine learning model for image classification, and based on the probabilities for each of the resulting plurality of personal colors, the personal color with a relatively high probability is discriminated as the personal color corresponding to the user. As this machine learning model, a model that has been pre-learned using a model such as CNN (Convolutional Neural Network) and ViT (Vision Transformer) with data in which text data representing a personal color is tagged for the image data of a part of an arbitrary user's body as learning data is used. Then, the discrimination unit 24 provides the personal color corresponding to the discriminated user of the terminal device 10 to the database server 12.

[0022] The generation unit 25 generates a plurality of simulated images simulating the state in which the user wears fashion items for each of the plurality of prompts, using the image data of the user's body provided from the terminal device 10 via the web server 11 and a plurality of prompts regarding the user of the terminal device 10 provided from the database server 12. For example, as the image data, an image of the user's whole body or upper body taken by a camera built in the terminal device 10 is used. That is, the generation unit 25 inputs one of the plurality of prompts and the image data of the user's body into a machine learning model different from the machine learning model used by the discrimination unit 24, and uses that machine learning model to generate a simulated image simulating the state in which the user wears a plurality of fashion items for each wearing part included in the prompt.

[0023] As the machine learning model used by the generation unit 25, for example, an image generation model based on a diffusion model or the like, in which an Inpainting function for correcting a part of the input image is implemented, can be used. As such a machine learning model, a model constructed by learning using, as learning data, image data of a user's body and image data of fashion items, each of which is a large amount of image data tagged with text representing the name of the fashion item, can be used. FIG. 4 shows an example of the learning data for the machine learning model used by the generation unit 25. Thus, as the learning data for the machine learning model, data in which the image data G1 of the fashion item is tagged with the text T1 which is the name of the fashion item is used. However, as the machine learning model used by the generation unit 25, a model post-learned by a method such as LoRA (Low-Rank Adaptation) or DreamBooth may be used with respect to a pre-trained model.

[0024] In addition, the generation unit 25 stores a plurality of simulated images generated for each of a plurality of prompts related to the user of the terminal device 10 in the image data storage unit 26 in association with the plurality of prompts, and causes the terminal device 10 to display (output) the images via the Web server 11. Further, when the generation unit 25 receives a selection input of a simulated image from among the plurality of simulated images on the Web page displayed on the terminal device 10 by the Web server 11, the generation unit 25 outputs data regarding the fashion item included in the simulated image selected according to the selection input to the terminal device 10. Specifically, the generation unit 25 reads out the prompt associated with the selected simulated image from the image data storage unit 26, and outputs data corresponding to the name of the fashion item included in the prompt. Examples of the data corresponding to the name of the fashion item include data such as an image of the fashion item alone and a URL (Uniform Resource Locator) of an access destination on the Internet for purchasing the fashion item. Thereby, the user of the terminal device 10 can efficiently obtain information on fashion items suitable for the user (for example, information for purchase).

[0025] FIG. 5 shows an image of the simulated image G3 generated and output by the generation unit 25. As shown in the figure, by inputting the image data G2 of the user's body and the prompt related to the user into a machine learning model that has been learned in advance using a large amount of image data G1 of fashion items by the generation unit 25, a simulated image G3 in which the user is simulatedly wearing a plurality of fashion items corresponding to the names of the plurality of fashion items included in the prompt is generated.

[0026] The procedure of the image generation process by the image generation system 100 configured as described above, that is, the flow of the image generation method according to the present embodiment will be described. FIG. 6 is a flowchart showing the procedure of the image generation process by the image generation system 100.

[0027] When image generation processing is started by an instruction input or the like from the user of the terminal device 10 to the web server 11, the web server 11 receives user attribute information from the terminal device 10 (step S01). Next, the web server 11 receives input of image data of a part of the user's body and image data of the user's whole body from the terminal device 10 (step S02).

[0028] Thereafter, the image generation server 13 discriminates a personal color corresponding to the user by using the image data of a part of the user's body (step S03). Then, based on the discriminated personal color corresponding to the user and the user attribute information, the database server 12 extracts a plurality of sets of combination data of the names of fashion items for each wearing part of the user (step S04). Further, the database server 12 creates a plurality of prompts based on the plurality of sets of combination data (step S05).

[0029] Next, the image generation server 13 inputs the plurality of prompts and the image data of the user's whole body into a machine learning model to generate a plurality of simulated images (step S06). Then, the image generation server 13 outputs the generated plurality of simulated images to the terminal device 10 (step S07). On the other hand, when a selection input is received for the plurality of simulated images displayed from the terminal device 10, data regarding the plurality of fashion items included in the selected simulated image is output to the terminal device 10 from the image generation server 13 (step S08). Thus, the image generation processing is terminated.

[0030] Next, a modification example of the present disclosure will be described.

[0031] In the above disclosure, the discrimination unit 24 of the image generation server 13 discriminates the personal color by inputting the user's image into the machine learning model, but the processing is not limited to this. For example, the terminal device 10 may receive an answer to a question on a web page and discriminate the personal color based on the content of the answer.

[0032] In addition, the type of the machine learning model used in the image generation server 13 is not limited to the types of models described in the above-described embodiments, and various types of models can be used.

[0033] In addition, the device configuration of the above-described image generation system 100 is not limited to the configuration including the above-described servers 11, 12, and 13, and the image generation system 100 can be configured by any number of one or more devices. Further, the functional units provided in the above-described database server 12 and image generation server 13 may be provided in any device included in the image generation system 100. Also, a part of the functional units may be provided in the terminal device 10.

[0034] Next, the operation and effect of the image generation system of the present disclosure will be described. The image generation system 100 of the present disclosure stores, for each of a plurality of fashion items, combination data of the name of the fashion item and information regarding the color system of the fashion item, determines a personal color corresponding to the user from among a plurality of preset personal colors based on input data, searches for the combination data for each of the plurality of fashion items, extracts the name of the fashion item corresponding to the personal color determined for the user, and inputs, into a machine learning model, a prompt based on the extracted name of the fashion item and the image data of the user, thereby generating and outputting a simulated image simulating a state in which the user wears the fashion item.

[0035] Through such an operation, the name of a fashion item that matches the user's personal color is extracted, and by inputting a prompt based on the name of the fashion item and the user's image data into a machine learning model, an image simulating the state in which the user is wearing the fashion item can be generated and output. As a result, the user can visually confirm whether the fashion item suits them, and can efficiently select a fashion item that suits them.

[0036] Here, the image generation system 100 of the present disclosure stores, as combination data, attribute identification information regarding attributes in association with the name of a fashion item, and extracts the name of a fashion item associated with the attribute identification information corresponding to the user attribute information regarding the attributes of the input user.

[0037] Thereby, a fashion item that suits the user's attributes can be extracted, and an image simulating the state in which the extracted fashion item is worn can be generated and output. As a result, the user can be made to more efficiently select a fashion item that suits them.

[0038] The image generation system 100 of the present disclosure stores, as combination data, the name of a fashion item so as to be able to specify the wearing position of the fashion item, and by searching the combination data for each of a plurality of fashion items, extracts the name of a fashion item for each wearing position, and inputs a prompt based on the name of the fashion item for each wearing position thus extracted into a machine learning model.

[0039] Thereby, a fashion item for each wearing position can be extracted, and an image simulating the state in which the fashion item for each wearing position is worn can be generated and output. As a result, the user can be made to comprehensively select a fashion item that suits them.

[0040] In addition, in response to the selection of the simulated image, the image generation system 100 of the present disclosure outputs data related to the fashion item corresponding to the name of the fashion item included in the prompt used for generating the simulated image.

[0041] Thereby, data related to the fashion item selected by the user can be output, and subsequent processes such as the purchase process of the fashion item can be smoothed, for example.

[0042] The image generation system 100 of the present invention has the following configuration.

[0043] [1] A storage unit that stores combination data of the name of the fashion item and information related to the color system of the fashion item for each of a plurality of fashion items; A discrimination unit that discriminates a color system corresponding to the user from a plurality of preset color systems based on input data; An extraction unit that extracts the name of the fashion item corresponding to the discriminated color system corresponding to the user by searching the combination data for each of the plurality of fashion items from the storage unit; A generation unit that generates and outputs a simulated image simulating the state in which the user wears the fashion item by inputting a keyword based on the name of the extracted fashion item and the image of the user into a machine learning model. Image generation system.

[0044] [2] The storage unit stores, as the combination data, attribute specific information related to attributes in association with the name of the fashion item. The extraction unit extracts the name of the fashion item associated with the attribute specific information corresponding to the user attribute information related to the attributes of the input user. The image generation system according to [1] above.

[0045] [3] The memory unit stores, as the combination data, the name of the fashion item and the wearing part of the fashion item in a manner that enables identification. The extraction unit extracts the name of the fashion item for each wearing part by searching the combination data for each of a plurality of fashion items from the memory unit. The generation unit inputs keywords based on the name of the fashion item for each wearing part extracted into the machine learning model. The image generation system according to [1] above.

[0046] [4] The generation unit outputs data related to the fashion item corresponding to the name of the fashion item included in the keyword used for generating the simulated image according to the selection of the simulated image. The image generation system according to [1] above.

[0047] [5] A step in which the memory unit stores combination data of the name of the fashion item and information related to the color scheme of the fashion item for each of a plurality of fashion items. A step in which the discrimination unit discriminates the color scheme corresponding to the user from a plurality of preset color schemes based on the input data. A step in which the extraction unit extracts the name of the fashion item corresponding to the color scheme corresponding to the discriminated user by searching the combination data for each of a plurality of fashion items from the memory unit. A step in which the generation unit inputs a keyword based on the name of the extracted fashion item and the image of the user into a machine learning model to generate and output a simulated image simulating the state in which the user wears the fashion item. An image generation method comprising the above steps.

[0048] The block diagrams used in the description of the above embodiments show blocks of functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one physically or logically combined device, or two or more physically or logically separated devices may be directly or indirectly (e.g., using wired, wireless, etc.) connected and realized using these multiple devices. The functional block may be realized by combining software with the above one device or the above multiple devices.

[0049] Functions include, but are not limited to, judgment, decision, determination, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, solution, selection, selection, establishment, comparison, assumption, expectation, regarded as, notification (broadcasting), notification (notifying), communication (communicating), transfer (forwarding), configuration (configuring), reconfiguration (reconfiguring), allocation (allocating, mapping), assignment (assigning), etc. For example, a functional block (component) that functions to transmit is called a transmitting unit or a transmitter. In any case, as described above, the realization method is not particularly limited.

[0050] For example, servers 11, 12, 13, etc. that make up the image generation system 100 in one embodiment of the present disclosure may function as a computer that performs the processing of the image generation method of the present disclosure. FIG. 7 is a diagram showing an example of the hardware configuration of servers 11, 12, 13 according to one embodiment of the present disclosure. Physically, the above-described servers 11, 12, 13 may be configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. Note that the servers 11, 12, 13 may be configured as a computer device including at least one processor such as a CPU or a GPU, may be configured as a computer device including a plurality of processors, or may be configured including a plurality of computer devices. The terminal device 10 may also adopt a similar hardware configuration.

[0051] In the following description, the term "device" can be read as a circuit, a device, a unit, etc. The hardware configuration of the servers 11, 12, 13 may be configured to include one or more of each device shown in the figure, or may be configured without including some devices.

[0052] Each function in the servers 11, 12, 13 is realized by causing the processor 1001 to perform calculations by loading a predetermined software (program) onto hardware such as the processor 1001 and the memory 1002, and controlling communication by the communication device 1004, or controlling at least one of reading and writing data in the memory 1002 and the storage 1003.

[0053] Processor 1001 controls the entire computer by operating, for example, an operating system. Processor 1001 may be constituted by a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like. For example, the above-described extraction unit 21, input data generation unit 22, determination unit 24, generation unit 25, and the like may be realized by processor 1001.

[0054] Further, processor 1001 reads a program (program code), software module, data, etc. from at least one of storage 1003 and communication device 1004 into memory 1002, and executes various processes according thereto. As the program, a program for causing a computer to execute at least a part of the operations described in the above-described embodiments is used. For example, extraction unit 21, input data generation unit 22, determination unit 24, generation unit 25 may be stored in memory 1002 and realized by a control program operating in processor 1001, and other functional blocks may be realized in the same manner. Although it has been described that the above-described various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. Processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

[0055] The memory 1002 is a computer-readable recording medium and may be constituted by at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may be referred to as a register, a cache, a main memory (main storage device), etc. The memory 1002 can store a program (program code), a software module, etc. executable for implementing the image generation method according to an embodiment of the present disclosure.

[0056] The storage 1003 is a computer-readable recording medium and may be constituted by at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital versatile disc, a Blu-ray (registered trademark) disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. The storage 1003 may be referred to as an auxiliary storage device. The above-described recording medium may be, for example, a database including at least one of the memory 1002 and the storage 1003, a server, or other appropriate media.

[0057] The communication device 1004 is hardware (a transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. in order to implement at least one of, for example, frequency division duplex (FDD) and time division duplex (TDD). For example, the above-described extraction unit 21, determination unit 24, generation unit 25, etc. may be implemented by the communication device 1004.

[0058] The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives an external input. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs an output to the outside. Note that the input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).

[0059] Also, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus or may be configured using different buses for each device.

[0060] In addition, the servers 11, 12, and 13 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be implemented by the hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0061] The notification of information is not limited to the aspects / embodiments described in the present disclosure, and other methods may be used. For example, the notification of information may be carried out by physical layer signaling (e.g., downlink control information (DCI), uplink control information (UCI)), upper layer signaling (e.g., radio resource control (RRC) signaling, medium access control (MAC) signaling, notification information (master information block (MIB), system information block (SIB))), other signals, or a combination thereof. Further, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC connection setup message, an RRC connection reconfiguration message, or the like.

[0062] The processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in the present disclosure may be reordered as long as there is no contradiction. For example, for the methods described in the present disclosure, the elements of various steps are presented using an exemplary order and are not limited to the specific order presented.

[0063] The input / output information etc. may be stored in a specific location (e.g., memory), or may be managed using a management table. The information etc. to be input / output may be overwritten, updated, or appended. The output information etc. may be deleted. The input information etc. may be transmitted to other devices.

[0064] The determination may be made based on a value represented by 1 bit (0 or 1), may be made based on a boolean value (Boolean: true or false), or may be made based on a numerical comparison (e.g., comparison with a predetermined value).

[0065] Each aspect / embodiment described in the present disclosure may be used alone, may be used in combination, or may be switched and used during execution. Also, the notification of predetermined information (e.g., notification of "being X") is not limited to being explicitly performed, and may be performed implicitly (e.g., not performing the notification of the predetermined information).

[0066] As described above in detail regarding the present disclosure, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described in the present disclosure. The present disclosure can be implemented as modifications and variations without departing from the spirit and scope of the present disclosure defined by the claims. Therefore, the description of the present disclosure is for illustrative purposes and has no restrictive meaning for the present disclosure.

[0067] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether called by the name of software, firmware, middleware, microcode, a hardware description language, or by another name.

[0068] Also, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, when software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cables, optical fiber cables, twisted pairs, digital subscriber line (DSL), etc.) and wireless technologies (such as infrared rays, microwaves, etc.), at least one of these wired technologies and wireless technologies is included within the definition of the transmission medium.

[0069] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0070] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Also, a signal may be a message. Also, a component carrier (CC) may be referred to as a carrier frequency, a cell, a frequency carrier, etc.

[0071] Also, the information, parameters, etc. described in this disclosure may be represented using absolute values, relative values from a predetermined value, or corresponding other information. For example, a radio resource may be indicated by an index.

[0072] The names used for the above-described parameters are not limiting in any way. Furthermore, the mathematical formulas and the like using these parameters may be different from those explicitly disclosed in the present disclosure. Since various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable names, the various names assigned to these various channels and information elements are not limiting in any way.

[0073] In the present disclosure, terms such as "mobile station (MS)", "user terminal", "user equipment (UE)", and "terminal" may be used interchangeably.

[0074] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable term.

[0075] As used herein, the terms "determining" and "deciding" may encompass a wide variety of actions. "Determining" and "deciding" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up (e.g., searching a table, database, or other data structure), ascertaining, and considering something as having been "determined" or "decided". "Determining" and "deciding" may also include receiving (e.g., receiving information), transmitting (e.g., transmitting information), inputting, outputting, accessing (e.g., accessing data in a memory), and considering something as having been "determined" or "decided". "Determining" and "deciding" may further include resolving, selecting, choosing, establishing, comparing, and considering something as having been "determined" or "decided". That is, "determining" and "deciding" may include considering something as having been determined or decided by performing some action. Also, "determining (deciding)" may be replaced with "assuming", "expecting", "considering", etc.

[0076] The terms "connected" and "coupled", or any variations thereof, mean any direct or indirect connection or coupling between two or more elements, and can include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements can be physical, logical, or a combination thereof. For example, "connected" may be read as "accessed". As used in this disclosure, two elements can be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, and also using electromagnetic energy having wavelengths in the radio frequency region, microwave region, and optical (both visible and invisible) regions, as some non-limiting and non-exhaustive examples.

[0077] As used in this disclosure, the recitation "based on" does not mean "based only on" unless otherwise specified. In other words, the recitation "based on" means both "based only on" and "based at least on".

[0078] Any reference to an element using designations such as "first", "second", etc. used in this disclosure does not generally limit the quantity or order of those elements. These designations can be used in this disclosure as a convenient way to distinguish between two or more elements. Thus, references to a first and a second element do not mean that only two elements can be employed, or that the first element must precede the second element in any form.

[0079] In this disclosure, when the terms "include", "including", and their variations are used, these terms are intended to be inclusive, similar to the term "comprising". Further, the term "or" used in this disclosure is not intended to be exclusive.

[0080] In the present disclosure, for example, when articles are added by translation, such as a, an, and the in English, the present disclosure may include that the nouns following these articles are in the plural form.

[0081] In the present disclosure, the term "A and B are different" may mean that "A and B are different from each other". Note that the term may also mean that "A and B are different from C respectively". Terms such as "separate" and "coupled" may also be interpreted in the same way as "different".

Description of Reference Numerals

[0082] 100... Image generation system, 1001... Processor, 21... Extraction unit, 23... Item information storage unit (memory unit), 24... Discrimination unit, 25... Generation unit, G3... Simulated image.

Claims

1. a storage unit that stores, for each of a plurality of fashion items, combined data of the name of the fashion item and information regarding the color scheme of the fashion item; a determination unit that determines, based on input data, a color scheme corresponding to the user from among a plurality of preset color schemes; an extraction unit that extracts the name of a fashion item corresponding to the color scheme corresponding to the determined user by searching the storage unit for the combined data for each of the plurality of fashion items; a generation unit that generates and outputs a simulated image simulating a state in which the user wears the fashion item by inputting, into a machine learning model, a keyword based on the name of the extracted fashion item and an image of the user; An image generation system.

2. The storage unit stores, as the combined data, attribute identification information regarding an attribute in association with the name of the fashion item; The extraction unit extracts the name of the fashion item associated with the attribute identification information corresponding to user attribute information regarding the attribute of the input user; The image generation system according to claim 1.

3. The storage unit stores, as the combined data, the name of the fashion item in a manner capable of specifying the wearing position of the fashion item; The extraction unit extracts the name of the fashion item for each wearing position by searching the storage unit for the combined data for each of the plurality of fashion items; The generation unit inputs, into the machine learning model, a keyword based on the name of the fashion item for each extracted wearing position; The image generation system according to claim 1.

4. The generation unit outputs data regarding the fashion item corresponding to the name of the fashion item included in the keyword used for generating the simulated image in response to the selection of the simulated image; The image generation system according to claim 1.

5. a step in which a storage unit stores, for each of a plurality of fashion items, combined data of the name of the fashion item and information regarding the color scheme of the fashion item; a step in which a determination unit determines, based on input data, a color scheme corresponding to the user from among a plurality of preset color schemes; The extraction unit extracts the names of fashion items corresponding to the color scheme corresponding to the determined user by searching the combination data for each of the plurality of fashion items from the storage unit; The generation unit inputs the keyword based on the name of the extracted fashion item and the image of the user into a machine learning model, and generates and outputs a simulated image simulating the state in which the user wears the fashion item; An image generation method comprising the steps of.

Images