Generation device and generation method

Abstract

A RAG system 20 according to the present disclosure comprises: a reception unit 21 that receives nail image generation request information including a request of a customer pertaining to a nail; a related image determination unit 22 that extracts tag information (feature information) indicating a feature of the nail on the basis of the nail image generation request information and acquires information pertaining to a sample image having the tag information; a generation unit 23 that generates a prompt for instructing generation of the nail image on the basis of the information pertaining to the sample image and information pertaining to the customer; and an acquisition unit 24 that inputs the prompt to a generative AI model, which generates a nail image, and acquires the nail image from the generative AI model.

Description

Generation device and generation method

[0001] One aspect of the present disclosure relates to a generating device and a generating method.

[0002] Nail salons offer plans that allow customers to choose designs they like (hereinafter referred to as "customer-created designs"). In these plans, customers can show the nail artist an image of a design they found on the internet, for example, and choose the colors and parts they want on the spot.

[0003] Patent Literature 1 is an example of a technology that supports the user in deciding on a design. Patent Literature 1 describes a technology that adjusts a nail design to suit the user's nails. The technology described in Patent Literature 1 allows the user to decide on a design from a selection of designs.

[0004] JP 2016-85725 A

[0005] When a customer's submitted design did not meet their expectations, they would instruct the nail artist on changes. Changes could include, but are not limited to, specifying different image designs for each finger, creating different designs for the right and left hands, changing the color, or changing the nail shape. However, the changes were so detailed that it was difficult for the customer and the nail artist to agree on the same image. Even with the invention described in Patent Document 1, instructing the artist on changes was cumbersome. Furthermore, nail salons are often fully booked, making it difficult to secure sufficient time for design confirmation.

[0006] Therefore, an object of the present disclosure is to provide a technology that can easily convey the image of a nail design accurately.

[0007] A generation device according to one aspect of the present disclosure includes a reception unit that receives nail image generation request information including a customer's requests regarding nails; a related image determination unit that extracts feature information indicating the features of the nail based on the nail image generation request information and acquires information regarding a sample image having the feature information; a generation unit that generates a prompt to instruct the generation of a nail image based on information regarding the sample image and information regarding the customer; and an acquisition unit that inputs the prompt to a generation AI model that generates a nail image and acquires a nail image from the generation AI model.

[0008] According to one aspect of the present disclosure, it is possible to provide a technology that can easily convey the image of a nail design accurately.

[0009] FIG. 1 is a block diagram showing an example of the configuration of a generation system. FIG. 2 is a diagram showing an example of a sample image tag information table. FIG. 3 is a flowchart showing an example of the operation of the RAG system. FIG. 4 is a diagram showing an example of a prompt. FIG. 5 is a block diagram showing another example of the configuration of a generation system. FIG. 6 is a diagram showing an example of a hardware configuration.

[0010] The present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0011] The creation system of the present disclosure supports, for example, nail design decisions. A customer of a nail salon brings a design they would like to have applied to the nail salon. The creation system creates a nail image showing the design that meets the customer's desire and provides it to the customer.

[0012] Fig. 1 is a diagram showing the device configuration of a generation system according to this embodiment. The generation system shown in Fig. 1 includes a terminal 10, a Retrieval-Augmented Generation (RAG) system 20, and a server device 30, which are configured to be able to communicate with each other via networks including a wireless communication network and a fixed communication network. The RAG system 20 constitutes a generation device that generates a prompt for generating a nail image in response to a request received from the terminal 10. A prompt is information indicating an instruction or question input to an AI (Artificial Intelligence) model in an interactive system such as a dialogue with an AI model or a command line interface (CLI).

[0013] The terminals 10 are devices used by users who are customers of the nail salon. The terminals 10 are, for example, personal computers, smartphones, tablet terminals, feature phones, server devices, game consoles, etc. Although only two terminals 10 are shown in FIG. 1 , the generation system may include any number of terminals 10 greater than or equal to two.

[0014] The terminal 10 receives input of nail image generation request information, which is information regarding instructions for generating a nail image, from a customer. The nail image generation request information includes the customer's requests regarding nails. The terminal 10 transmits the received nail image generation request information to the RAG system 20.

[0015] The nail image creation request information may include, for example, the name of the design, information specifying the nail shape, information specifying the color, information specifying the stone, information specifying the finger, and information indicating the purpose or use. The nail image creation request information may include information about the customer. The nail image creation request information may be represented by text or an image. The nail image creation request information may include an image of the customer's hand.

[0016] In one example, the name of the design may be "Baby Boomer" or the like. Information specifying the nail shape may be "square" or "point" or the like. Information specifying the color may be "white gradation" or the like. Information specifying the stone may be the presence or absence of a stone, the size of the stone (e.g., half the nail), the color of the glitter, or the shape of the stone. Information indicating the purpose or use may be information indicating a request such as "I want to change my mood," "I want to change my nails to be more on trend," or "I want nails that go with my clothes (e.g., furisode)." The purpose or use may be information regarding company rules or time, place, and occasion for work. The nail image generation request information may be specified for each finger. For example, the nail image generation request information may be "Baby Boomer nails for the index finger and ring finger, and solid white for the other fingers."

[0017] The storage device 15 is a non-transitory storage device that stores various information used in the production system. The storage device 15 may be a component of the RAG system 20. The storage device 15 may include multiple tables. For example, the storage device 15 may include a tag list table, a sample image tag information table, and an account information table.

[0018] The tag list table may store tag information (characteristic information) indicating characteristics of nails, such as, but not limited to, nail shape, design or type, color, purpose or use, etc.

[0019] In one example, the nail shape may be "square" or "point," etc. The design or type may be "baby boomer," "magnet," or "cheek nail," etc. The color may be "pink," "nude color," or "blue," etc. The purpose or use may be "office nail," "kimono," or "wedding," etc.

[0020] The sample image tag information table may store information about sample images showing nail design samples. For example, the sample image tag information table may store information about each sample image in association with at least one piece of tag information. That is, the information about each sample image includes at least one piece of tag information.

[0021] The account information table may store information about a customer (user information). The information about a customer may be information associated with the customer's user account or information received from the customer. The information about a customer may be information registered when the user account is registered, or may be information obtained from application log information, etc.

[0022] Examples of customer-related information include, but are not limited to, personal color, bone structure type, hand shape, and preference information. Personal color may be, for example, "yellow-based spring," "yellow-based autumn," "blue-based summer," or "blue-based winter." Bones may be, for example, "straight," "natural," or "wavy." Hand shape may be, for example, an image or text description (e.g., the size of each part of the hand). Preference information may be, for example, "likes simplicity," "likes cute designs," "fashion-conscious," or "prefers a simple look." Customer-related information may also be hobbies, favorite brands, etc.

[0023] The server device 30 is a device that stores a generative AI model 31 and enables the provision of questions or answers to a user using the generative AI model 31. The generative AI model is a model that, in response to the input of a prompt including input information, generates content according to any one or a combination of the instructions, context, question, and output format indicated by the prompt and returns the content as response information. The prompt may also include input information, in which case the generative AI model generates response information targeted at the input information. The generative AI model may be, for example, an interactive AI model that includes a large-scale language model (LLM) and a user interface (UI) for interacting with the user, enabling text or voice chat with the user. Examples of such generative AI models include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc. In this embodiment, an example is described in which the server device 30 provides questions, etc. using one generative AI model 31. However, the server device 30 may also provide questions, etc. using multiple generative AI models. 1 illustrates only one server device 30, the generation system may include multiple server devices 30. Furthermore, although the above describes an example of a large-scale language model, other AI models may also be used.

[0024] The RAG system 20 is configured to include, as functional components, a reception unit 21, a related image determination unit 22, a generation unit 23, and an acquisition unit 24. The RAG system 20 relays prompts corresponding to input information from the customer's terminal 10 to the server device 30, and relays response information from the server device 30 to the prompts to the customer service representative's terminal 10. The RAG system 20 also has a function to generate prompts based on input information from the terminal 10. The functions of each functional unit of the RAG system 20 will be described in detail below.

[0025] The reception unit 21 receives nail image generation request information. For example, the reception unit 21 receives nail image generation request information from the terminal 10 of the customer.

[0026] The related image determination unit 22 extracts tag information (feature information) indicating nail features based on the nail image generation request information received by the reception unit 21. For example, the related image determination unit 22 may break down the sentences in the nail image generation request information into words and obtain a distributed representation in which the words are represented by vectors. The related image determination unit 22 may use the distributed representation to calculate the similarity (relevance) with tag information in the tag list table of the storage device 15 and obtain tag information with a high degree of similarity (relevance). The degree of similarity may be determined based on a predetermined threshold or the like.

[0027] For example, the related image determination unit 22 may extract words by morphological analysis of the sentence of the nail image generation request information. The related image determination unit 22 may obtain a distributed representation using the extracted words and a technique such as Word2Vec.

[0028] The related image determination unit 22 searches for sample images having tag information from the sample image tag information table in the storage device 15. The related image determination unit 22 may create search results as information related to the sample images. The related image determination unit 22 may preferentially extract sample images with a large amount of matching tag information. The related image determination unit 22 may include the correspondence between the tag information and the sample images in the information related to the sample images.

[0029] The generation unit 23 generates a prompt for instructing the user to generate a nail image based on the information about the sample image and the information about the customer. The generation unit 23 may obtain the information about the customer from the account information table in the storage device 15, or may obtain the information about the customer from the nail image generation request information.

[0030] The generation unit 23 may determine a policy for customizing information about a sample image when generating a nail image based on the nail image generation request information, and may generate a prompt based on the policy. For example, the generation unit 23 may include an instruction to change tag information in the policy based on the nail image generation request information.

[0031] The generation unit 23 may include in the policy an instruction to change the nail shape of the tag information based on the nail image generation request information. For example, the nail image generation request information may include the design "Baby Boomer" and the nail shape "Square." Here, if the nail shape of the extracted "Baby Boomer" sample image is "Point," the policy may include an instruction to change the nail shape from "Point" to "Square." The generation unit 23 may include in the policy information specifying another sample image with a "Square" nail shape.

[0032] The generation unit 23 may include in the policy an instruction to change the design or type of the tag information based on the nail image generation request information. For example, the nail image generation request information may include the design "cheek nail and stone." Here, if the design of the extracted sample image is "cheek nail," the policy may include an instruction to add "stone" to the design. The generation unit 23 may include in the policy information specifying another sample image with the design "stone."

[0033] The generation unit 23 may include in the policy an instruction to change the color of the tag information based on the nail image generation request information. For example, the nail image generation request information may include the design "Baby Boomer" and detailed color specifications (e.g., a beige-based color and a gradation). Here, if the color of the extracted sample image of "Baby Boomer" differs from the detailed color specification (if the extracted sample image does not have tag information related to the detailed color specification), the generation unit 23 may include in the policy an instruction to change the color to the detailed color specification.

[0034] The generation unit 23 may include an instruction to change the color in the policy by using an image (color sample image) showing the changed color. The image showing the changed color may be a sample image registered in advance in the storage device 15 or an image received from the terminal 10.

[0035] The generation unit 23 may include in the policy an instruction to change the purpose or use of the tag information based on the nail image generation request information. For example, the nail image generation request information may include the design "Baby Boomer" and the purpose or use "I want it to look like it goes with a red furisode." The generation unit 23 may include in the policy an instruction to add an illustration that goes with a red furisode. The generation unit 23 may include in the policy an instruction to specify a sample image showing the illustration.

[0036] The generation unit 23 may include in the policy an instruction to generate variations of nail images. That is, the generation unit 23 may include in the policy an instruction to generate multiple nail images. For example, the generation unit 23 may include in the policy an instruction to generate multiple images using multiple sample images. For example, the nail image generation request information may include an abstract request such as "a look that goes well with a furisode kimono." The generation unit 23 may include in the policy an instruction to generate multiple images using multiple sample images extracted based on the abstract request.

[0037] The generation unit 23 may include in the policy an instruction to create an explanatory text indicating the concept for each variation of the nail image. The generation unit 23 may include in the policy an instruction to create an explanatory text using tag information.

[0038] The generation unit 23 may include in the policy an instruction to change the information about the sample image based on information about the customer. For example, the generation unit 23 may include in the policy an instruction to change the information about the sample image based on at least one of the customer's personal color, body type, hand shape, and preference information.

[0039] The generation unit 23 may include in the policy an instruction to modify the color of the sample image using an image of a color that matches the customer's personal color. In one example, if the customer's personal color is "yellow-based autumn," the generation unit 23 may include in the policy an instruction to modify the color of the "baby boomer" sample image using a sample image of a color that matches "yellow-based autumn."

[0040] The generation unit 23 may include in the policy an instruction to modify the design or nail shape of the sample image based on the bone structure type or hand shape of the customer. In one example, the policy may include an instruction to modify the design or nail shape of another sample image using a sample image of a design or nail shape that suits the bone structure type of the customer, "straight."

[0041] The generation unit 23 may include in the policy an instruction to modify the design or color of the sample image based on the customer's preference information. In one example, the generation unit 23 may include in the policy an instruction to add an illustration, a stone, or the like.

[0042] The prompt may include, for example, text expressions representing commands to be executed by the generative AI model (interactive AI model), tasks to be executed by the generative AI model, background / context to be considered by the generative AI model (e.g., roles, conditions), questions to be answered by the generative AI model, and output formats of response information from the generative AI model. The prompt may also include input information to be used as the target of commands / tasks to be executed by the generative AI model. Examples of such input information include data files with file names that include a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data includes document data, table data, graph data, and other data that can be processed by a default application program.

[0043] The acquisition unit 24 inputs a prompt to the generation AI model 31 that generates the nail image, and acquires the nail image from the generation AI model 31. The acquisition unit 24 may relay the nail image, which is a response result to the input of the prompt, to the terminal 10 of the customer service person.

[0044] The generated nail image may be an image of ten fingers. The generated nail image may be an image showing the image of the nail after treatment based on an image of the hand of the customer or another person. An explanatory text explaining the concept may be added to the nail image.

[0045] 2 is a diagram showing an example of a sample image tag information table stored in the storage device 15. The sample image tag information table may store a path and a classification of tag information in association with an image ID, which is an identifier that identifies an image. The path is information that indicates the storage location (folder) of the sample image, which is electronic data.

[0046] The classification of tag information may be tag (nail shape), tag (design or type), tag (color), tag (purpose or use), etc. Tag (nail shape) is a classification corresponding to the nail shape of the tag information. Tag (design or type) is a classification corresponding to the design or type of the tag information. Tag (color) is a classification corresponding to the color of the tag information. Tag (purpose or use) is a classification corresponding to the purpose or use of the tag information.

[0047] The classification of tag information may be an abstract atmosphere, a suitable personal color, or the like. In one example, the abstract atmosphere may be "simple" or "cute," and the suitable personal color may be "yellow-based, suitable for autumn," or the like. Furthermore, tag information does not have to be managed by classification.

[0048] In one example, the sample image tag information table stores the path " / ... / sample0001.jpg", the tag (nail shape) "square", the tag (design or type) "magnet", the tag (color) "pink", and the tag (purpose or use) "kimono" in association with the image ID "0001".

[0049] In another example, the sample image tag information table stores the path " / ... / sample0002.jpg", the tag (nail shape) "oval", the tag (design or type) "stone", the tag (color) "red and gold", and the tag (purpose or use) "furisode" in association with the image ID "0002".

[0050] In another example, the sample image tag information table stores the path " / ... / sample0003.jpg", the tag (nail shape) "point", the tag (design or type) "cheek nail", the tag (color) "pink", and the tag (purpose or use) "office nail" in association with the image ID "0003".

[0051] An example of an operation method (generation method) by the RAG system 20 will be described with reference to Fig. 3. Fig. 3 is a flowchart showing an example of the operation of the RAG system 20.

[0052] In step S1, the reception unit 21 receives nail image generation request information. For example, the reception unit 21 receives nail image generation request information from the terminal 10 of the customer.

[0053] In one example, the nail image generation request information is "Magnetic nails with a pattern that matches a red furisode kimono, and the shape is the highlight."

[0054] In step S2, the related image determination unit 22 extracts tag information (feature information) indicating nail features based on the nail image generation request information received by the reception unit 21. For example, the related image determination unit 22 may break down the sentences in the nail image generation request information into words and obtain a distributed representation in which the words are represented by vectors. The related image determination unit 22 may use the distributed representation to calculate the similarity (relevance) with tag information in the tag list table of the storage device 15 and obtain tag information with a high degree of similarity (relevance). The degree of similarity may be determined based on a predetermined threshold or the like.

[0055] In one example, the tag information extracted from the nail image generation request information is "magnet, red, long-sleeved kimono, point."

[0056] In step S3, the related image determination unit 22 searches for sample images having tag information from the sample image tag information table in the storage device 15. The related image determination unit 22 may create search results as information related to the sample images. The related image determination unit 22 may preferentially extract sample images with more matching tag information. The related image determination unit 22 may include the correspondence between the sample images and the tag information in the information related to the sample images.

[0057] An example of the correspondence between sample images and tag information is shown below. First sample image: Magnet Second sample image: Red, long-sleeved kimono Third sample image: Point

[0058] The first sample image may be the sample image identified by the image ID "0001" in Fig. 2. The first sample image has the tag (design or type) "magnet" as tag information.

[0059] The second sample image may be the sample image identified by the image ID "0002" in Fig. 2. The second sample image has the tag (color) "red" as tag information. The second sample image has the tag (purpose or use) "furisode" as tag information.

[0060] The third sample image may be the sample image identified by the image ID "0002" in Fig. 2. The third sample image has the tag (nail shape) "point" as tag information.

[0061] In step S4, the generation unit 23 generates a prompt for instructing the user to generate a nail image based on the information about the sample image and the information about the customer. The generation unit 23 may obtain the information about the customer from the account information table in the storage device 15, or may obtain the information about the customer from the nail image generation request information.

[0062] The generation unit 23 may determine a policy for customizing information about a sample image when generating a nail image based on the nail image generation request information, and may generate a prompt based on the policy. For example, the generation unit 23 may include an instruction to change tag information in the policy based on the nail image generation request information.

[0063] The generation unit 23 may include in the policy an instruction to change at least one of the nail shape, design or type, color, and purpose or use among the tag information based on the nail image generation request information. The generation unit 23 may include in the policy an instruction to change the tag information using an image (sample image) related to the changed tag information.

[0064] The generation unit 23 may include in the policy an instruction to generate variations of the nail image (plurality of nail images). The generation unit 23 may include in the policy an instruction to create an explanatory text indicating a concept for each variation of the nail image. The generation unit 23 may include in the policy an instruction to create an explanatory text using tag information.

[0065] The generation unit 23 may include in the policy an instruction to change the information about the sample image based on information about the customer. For example, the generation unit 23 may include in the policy an instruction to change the information about the sample image based on at least one of the customer's personal color, body type, hand shape, and preference information.

[0066] In step S5, the acquisition unit 24 inputs a prompt to the generation AI model 31 that generates the nail image, and acquires the nail image from the generation AI model 31. The acquisition unit 24 may relay the nail image, which is a response result to the input of the prompt, to the terminal 10 of the customer service person.

[0067] Figure 4 is a diagram showing an example of a prompt generated by the RAG system 20. The prompt shown in Figure 4 includes a role, a task, a condition, and a customer request.

[0068] The role may correspond to, for example, a person who is supposed to be involved in nail design. For example, the role may be designated as a professional (manicurist) who proposes nail designs. An example of a role is "You are a manicurist."

[0069] The task is information that indicates an outline of the command content to the generative AI model 31. An example of a task is "Please create a nail image according to the customer's request."

[0070] The condition may be, for example, a condition that the generated nail image must satisfy. An example of the condition is, "Please create multiple candidate images according to the customer's request using the first sample image of 'magnet,' the second sample image of 'red' and 'long-sleeved kimono,' the third sample image of 'points,' and so on."

[0071] The customer's request may be tag information corresponding to the customer's desire. For example, the customer's request may include, but is not limited to, nail shape, design or type, color, purpose or use, etc. An example of a customer's request is "magnet, red, furisode, accent."

[0072] The prompt may include a policy, for example, a policy to change at least one of the tag information, such as the shape, design or type, color, and purpose or use of the nail.

[0073] As described above, the RAG system 20 (generation device) according to one aspect of the present disclosure comprises a reception unit 21 that receives nail image generation request information including customer requests regarding nails, a related image determination unit 22 that extracts tag information (feature information) indicating the characteristics of the nail based on the nail image generation request information and acquires information regarding a sample image having the tag information, a generation unit 23 that generates a prompt to instruct the generation of a nail image based on information regarding the sample image and information regarding the customer, and an acquisition unit 24 that inputs a prompt to a generation AI model that generates a nail image and acquires a nail image from the generation AI model.

[0074] A generation method according to one aspect of the present disclosure includes the steps of receiving nail image generation request information including a customer's requests regarding nails, extracting tag information (feature information) indicating the characteristics of the nail based on the nail image generation request information and obtaining information regarding a sample image having the tag information, generating a prompt to instruct the generation of a nail image based on the information regarding the sample image and information regarding the customer, and inputting the prompt to a generation AI model that generates the nail image and obtaining the nail image from the generation AI model.

[0075] In a generation device and a generation method according to one aspect of the present disclosure, information about a sample image having tag information extracted from nail image generation request information is obtained, a prompt for instructing the generation of a nail image is generated based on the information about the sample image and information about the customer, and the prompt is input to a generation AI model 31. The generation AI model 31 is controlled by the prompt that takes into account the information about the sample image and information about the customer, so a nail image is generated that corresponds to the information about the sample image and information about the customer. In other words, a nail image with a design that the customer has in mind is generated by AI based on the nail image generation request information (text, image, etc.). Because nail images that match the customer's requests and the customer can be proposed, the customer can more easily accurately communicate the image of the nail design to, for example, a manicurist. Furthermore, because the customer's image is visualized, the time required for consultations and treatments at the nail salon can be shortened.

[0076] The generation unit 23 determines a policy for customizing information about sample images when generating a nail image based on the nail image generation request information, and generates a prompt based on the policy. By reflecting the policy based on the nail image generation request information in the prompt, it is possible to propose a nail image that further meets the customer's needs.

[0077] The generation unit 23 includes an instruction to change the tag information in the policy based on the nail image generation request information. By changing the tag information of the sample image, it is possible to propose a nail image that better suits the customer's needs.

[0078] The generation unit 23 includes in the policy an instruction to change at least one of the nail shape, design or type, color, and purpose or use from the tag information based on the nail image generation request information. By changing the detailed nail features from the tag information, it is possible to propose a nail image that better suits the customer's needs.

[0079] The generation unit 23 includes in the policy an instruction to generate variations of the nail image. By using variations of the nail image, it is possible to propose nail images that better suit the customer's needs.

[0080] The generation unit 23 includes in the policy an instruction to change the information about the sample image based on the information about the customer. By reflecting the policy based on the information about the customer in the prompt, it is possible to propose a nail image that is more suitable for the customer.

[0081] The generation unit 23 includes in the policy an instruction to change the information about the sample image based on at least one of the customer's personal color, bone structure type, hand shape, and preference information. By reflecting the policy based on information using detailed characteristics about the customer in the prompt, it is possible to propose nail images that are more suited to the customer.

[0082] The generation system is not limited to the configuration shown in FIG. 1 , but may be configured as shown in FIG. 5 , in which the generative AI model 31 is implemented in the RAG system 20. This configuration can be realized by installing an application that executes the functions of the generative AI model 31 in the RAG system 20. Also, while FIGS. 1 and 5 show an example in which the storage device 15 is implemented outside the RAG system 20 (for example, on a network), the storage device 15 may also be implemented in the RAG system 20.

[0083] The generative AI model 31 may be implemented in a terminal or on a network. The RAG system 20 may be implemented in a terminal or on a network. The storage device 15 may be implemented in a terminal or on a network.

[0084] The present disclosure has the following configuration. [1] A generation device comprising: a receiving unit that receives nail image generation request information including a customer's requests regarding nails; a related image determination unit that extracts feature information indicating nail features based on the nail image generation request information and acquires information related to a sample image having the feature information; a generation unit that generates a prompt to instruct the generation of a nail image based on information about the sample image and information about the customer; and an acquisition unit that inputs the prompt to a generative AI model that generates the nail image and acquires the nail image from the generative AI model. [2] The generation device described in [1], in which the generation unit determines a policy for customizing information about the sample image when generating the nail image based on the nail image generation request information, and generates the prompt further based on the policy. [3] The generation device described in [2], in which the generation unit includes an instruction to change the feature information in the policy based on the nail image generation request information. [4] The generation device described in [3], in which the generation unit includes an instruction to change at least one of the feature information, namely, nail shape, design or type, color, and purpose or use, based on the nail image generation request information. [5] The generation device according to any one of [2] to [4], wherein the generation unit includes in the policy an instruction to generate variations of the nail image. [6] The generation device according to any one of [2] to [5], wherein the generation unit includes in the policy an instruction to change information about the sample image based further on information about the customer. [7] The generation device according to [6], wherein the generation unit includes in the policy an instruction to change information about the sample image based on at least one of personal color, bone structure type, hand shape, and preference information of the customer.[8] A generation method comprising the steps of: receiving nail image generation request information including a customer's requests regarding nails; extracting feature information indicating the features of the nail based on the nail image generation request information and acquiring information related to a sample image having the feature information; generating a prompt to instruct the generation of a nail image based on the information related to the sample image and information related to the customer; and inputting the prompt into a generation AI model that generates the nail image and acquiring the nail image from the generation AI model.

[0085] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0086] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0087] For example, the RAG system 20 constituting the generation system according to an embodiment of the present disclosure may function as a computer that performs processing of the control method of the present disclosure. FIG. 6 is a diagram illustrating an example of the hardware configuration of the RAG system 20 according to an embodiment of the present disclosure. The above-described RAG system 20 may be physically 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. The RAG system 20 may be configured as a computer device including at least one processor such as a CPU or GPU, or may be configured as a computer device including multiple processors or may be configured to include multiple computer devices. The terminal 10 and the server device 30 may also have a similar hardware configuration.

[0088] In the following description, the term "device" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the RAG system 20 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

[0089] Each function in the RAG system 20 is realized by loading specified software (programs) onto hardware such as a processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via a communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0090] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned reception unit 21, related image determination unit 22, generation unit 23, acquisition unit 24, etc. may be realized by the processor 1001.

[0091] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with the programs. The programs used are programs that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the reception unit 21, the related image determination unit 22, the generation unit 23, and the acquisition unit 24 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used for other functional blocks. While the above-described various processes have been described as being executed by a single processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0092] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a control method according to an embodiment of the present disclosure.

[0093] Storage 1003 is a computer-readable recording medium, and may be composed of 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 disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0094] The communication device 1004 is hardware (transmission / reception device) for communicating 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. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the above-mentioned reception unit 21, acquisition unit 24, etc. may be realized by the communication device 1004.

[0095] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0096] Furthermore, 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 between each device.

[0097] The RAG system 20 may also 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 realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0098] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, 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.

[0099] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0100] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0101] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0102] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0103] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0104] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0105] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0106] 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. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0107] 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). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0108] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0109] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0110] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0111] 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 terminology.

[0112] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0113] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0114] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0115] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0116] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0117] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0118] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0119] 10...terminal, 20...RAG system (generation device), 21...reception unit, 22...related image determination unit, 23...generation unit, 24...acquisition unit, 30...server device, 31...generated AI model

Claims

1. A generation device comprising: a reception unit that receives nail image generation request information including a customer's requests regarding nails; a related image determination unit that extracts feature information indicating the features of the nail based on the nail image generation request information and acquires information related to a sample image having the feature information; a generation unit that generates a prompt to instruct the generation of a nail image based on the information related to the sample image and information related to the customer; and an acquisition unit that inputs the prompt to a generation AI model that generates the nail image and acquires the nail image from the generation AI model.

2. The generation device according to claim 1, wherein the generation unit determines a policy for customizing information about the sample image when generating the nail image based on the nail image generation request information, and generates the prompt further based on the policy.

3. The generating device according to claim 2, wherein the generating unit includes in the policy an instruction to change the characteristic information based on the nail image generation request information.

4. The generation device according to claim 3, wherein the generation unit includes in the policy an instruction to change at least one of the nail shape, design or type, color, and purpose or use among the characteristic information based on the nail image generation request information.

5. The generating device according to claim 2, wherein the generating unit includes in the policy an instruction for generating variations of the nail image.

6. The generating device according to claim 2, wherein the generating unit includes in the policy an instruction to change information about the sample image further based on information about the customer.

7. The generating device according to claim 6, wherein the generating unit includes in the policy an instruction to change information about the sample image based on at least one of the customer's personal color, bone structure type, hand shape, and preference information.

8. A generation method comprising the steps of: receiving nail image generation request information including a customer's requests regarding nails; extracting feature information indicating the features of the nail based on the nail image generation request information and obtaining information about a sample image having the feature information; generating a prompt to instruct the generation of a nail image based on the information about the sample image and information about the customer; and inputting the prompt into a generation AI model that generates the nail image and obtaining the nail image from the generation AI model.

Images