Device and method

Abstract

The present invention generates an image with a style tailored to a reader.　A prompt generation device 100 according to the present disclosure comprises: a feature amount acquisition unit 102 that acquires a feature amount of a user group; a prompt generation unit 103 that generates manga generation instruction information (generation instruction information) including the feature amount of the user group and a storyboard image (target image); and a prompt processing unit 104 that transmits the manga generation instruction information to a generative AI model 400 to generate a manga (generated images) according to the feature amount and the storyboard image. Here, the manga generation instruction information is a prompt to be entered into the generative AI model 400.

Description

Apparatus and method

[0001] The present invention relates to an apparatus and method for utilizing generative AI models.

[0002] Patent Document 1 describes a manga generation method that makes it possible to generate manga that matches user attributes such as nationality, age, etc. Specifically, it describes determining a level corresponding to a combination of personal attribute information (nationality, age, gender, etc.), searching for image data that corresponds to the combination of manga-specific information and level, searching for name data that corresponds to the manga-specific information, level, and language, and synthesizing the searched image data and name data to generate electronic manga data.

[0003] Japanese Patent Application Laid-Open No. 2004-213248

[0004] However, the invention described in Patent Document 1 is unable to generate manga that matches the style of the specified reader, and is limited to searching for image data that matches the user's attributes (level).

[0005] Therefore, an object of the present disclosure is to provide an apparatus and method capable of generating an image with a style suited to the reader.

[0006] The device disclosed herein includes a feature acquisition unit that acquires features of a user group, a generation unit that generates generation instruction information including the features of the user group and a target image, and a transmission unit that transmits the generation instruction information to a generation AI to generate a generated image according to the features and the target image.

[0007] According to the present disclosure, an image with a style suited to the reader can be generated.

[0008] FIG. 1 is a diagram showing a system configuration including a prompt generation device 100, which is a style transfer device of the present disclosure. FIG. 2 is a diagram showing a specific example of a reader table. FIG. 3 is a diagram showing a specific example of a reader group table. FIG. 4 is a diagram showing the functional configuration of a reader data generation device 300 of the present disclosure. FIG. 5 is a diagram showing an overview of processing using the prompt generation device 100. FIG. 6 is a block diagram showing the functional configuration of the prompt generation device 100. FIGS. 7(a) to 7(c) are schematic diagrams of the style DB 105. FIG. 8 is a diagram showing an example of a style determination prompt P generated by the prompt generation device 100. FIG. 9 is a diagram showing an example of the comic generation prompt. FIGS. 10(a) to 10(c) are diagrams showing answer results generated by the LLM in response to the style determination prompt. FIG. 11 is a flowchart showing the operation of the reader data generation device 300. FIG. 12 is a flowchart showing the operation of the prompt generation device 100. FIG. 13 is a flowchart showing the operation of the prompt generation device 100 (processing when an LLM is used). Fig. 14 is a diagram illustrating the configuration of a user terminal 500 on which the prompt generation device 100 or the generation AI model 400 is installed. Fig. 15 is a diagram illustrating an example of the hardware configuration of the prompt generation device 100 according to an embodiment of the present disclosure.

[0009] 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.

[0010] 1 is a diagram showing a system configuration including a prompt generation device 100, which is a style transfer device of the present disclosure. As shown in the figure, this system includes the prompt generation device 100, a reader DB 200, a character DB 250, a reader data generation device 300, and a generation AI model 400. A user terminal 500 can access each device and DB that make up this system.

[0011] The user terminal 500 is a device that instructs the generation of an image such as a manga. A user who wants to generate a manga image operates the user terminal 500 to send the prompt, which is a manga generation instruction and a name image, to the prompt generation device 100. The prompt generation device 100 references the art style DB to determine an art style corresponding to each user group stored in the reader group table. The prompt generation device 100 generates a prompt (generation instruction information) including the art style and the name image and sends it to the generation AI model 400. The prompt generation device 100 receives the answer result from the generation AI model 400. In the present disclosure, the answer result is a manga drawn in an art style that matches the user's preferences. This image is based on the name image and is an image with a converted art style. Note that the prompt generation device 100 may have a generation AI model (e.g., an LLM) other than the generation AI model 400 determine the art style using a prompt containing specified information.

[0012] The name image includes character instruction information (e.g., the character's name, a number indicating the character, etc.). The prompt generation device 100 may then refer to the character DB 250 to obtain character setting information corresponding to the instruction information specified in the name image and generate a prompt that includes this information. For example, the character setting information may include information indicating the character's appearance (gender, age, build, long hair, etc.) and information indicating the character's personality. Such setting information affects the comic image.

[0013] The reader DB 200 is a database that stores a reader table and a reader group table. The reader table contains pre-registered information. The reader group table is information generated by the reader data generation device 300 based on the reader table.

[0014] FIG. 2 is a diagram showing a specific example of a reader table. As shown in the figure, the reader table stores user IDs, age groups, genders, and hobbies and preferences in association with each other. The user ID is an identifier for identifying a user. In the present disclosure, hobbies and preferences are information indicating a preferred manga genre. In FIG. 2, these preferences include "likes of battle manga," "likes of romance manga," "likes of school manga," and "likes of comedy manga." Naturally, other genres of manga may also be included. This reader table may be created by a survey or the like, or may be generated based on the browsing history of an online manga site. In other words, the manga viewed by a user and its genre may be linked to the user ID, acquired by a reader data management server (not shown), and registered in the reader data table.

[0015] Figure 3 shows a specific example of a reader group table. Figures 3(a) to 3(c) show group tables for groups A to C. For example, Figure 3(a) shows the contents of group A, and is a table that associates age, gender, and percentages of hobbies and preferences. Figures 3(b) and 3(c) are similar.

[0016] This reader group table is a table generated by the reader data generation device 300, and as will be described later, is a table in which readers are grouped based on age and gender, and the proportions of hobbies and preferences are calculated within the group.

[0017] The prompt generation device 100 then references the reader DB 200 (reader group table) to generate a prompt to instruct the generation of a manga in a style suitable for the specified user, and sends the prompt to the generation AI model 400. The prompt generation device 100 can receive a manga generated in the user's preferred style from the generation AI model 400 as a response result.

[0018] 4 is a diagram showing the functional configuration of reader data generation device 300 of the present disclosure. As shown in the figure, reader data generation device 300 is configured to include grouping processing unit 301 and feature extraction unit 302. Reader data generation device 300 then accesses reader DB 200 and generates a reader group table based on the reader table.

[0019] The grouping processing unit 301 is a unit that groups readers based on factors such as age and gender. In the present disclosure, the grouping processing unit 301 groups readers based on age and gender, but it may group readers based on either one of these factors, or may consider other factors instead of or in addition to these, such as residence or occupation.

[0020] The feature extraction unit 302 is a part that extracts feature amounts for each reader group. In the present disclosure, feature amounts indicate the proportions of hobbies and preferences (see FIG. 3 ). The feature extraction unit 302 extracts feature amounts that are the proportions of hobbies and preferences based on the grouped age groups and genders, and stores them in the reader DB 200 in the form of a reader group table.

[0021] 5 is a diagram showing an overview of processing using the prompt generation device 100. The prompt generation device 100 accepts a name image and a comic generation instruction from a user terminal 500. The prompt generation device 100 also acquires, from an art style database, art styles corresponding to each reader group stored in the reader group table. This art style database defines art styles for each age group, gender, and hobbies and preferences.

[0022] The prompt generation device 100 also acquires the characteristics of the reader group (information on the percentage of favorite manga) from the reader DB 200. The prompt generation device 100 then generates a prompt (generation instruction information) including the characteristics, art style, and name image of the reader group, and sends it to the generation AI model 400.

[0023] The generative AI model 400 generates an answer result based on the prompt. In this disclosure, the answer result is, for example, a manga that is optimal for reader group A, i.e., a manga image whose art style has been modified based on the name image. As shown in the figure, a manga optimized for each reader group is generated by the generative AI model 400.

[0024] As described above, the prompt generation device 100 may include character setting information in the prompt by referencing the character DB 250. In this case, the name image includes character designation information for reflecting the character setting information. For example, the character depicted in the name image is A (character designation information such as its identifier), and the character DB stores character A's designation information (appearance, personality, etc.).

[0025] 6 is a block diagram showing the functional configuration of the prompt generation device 100. As shown in the figure, the prompt generation device 100 includes an instruction acquisition unit 101, a feature acquisition unit 102, a prompt generation unit 103, a prompt processing unit 104, and an image style DB 105. Note that the image style DB 105 may be located outside the device.

[0026] The instruction acquisition unit 101 is a part that acquires, from the user terminal 500, a name image and manga generation instructions for generating a manga. The name image is an image that serves as the base of the manga. Generally, a name image is an image that roughly represents the frame layout when drawing a manga, as well as the composition, dialogue, and character placement for each frame. The composition and character placement may be expressed in rough sketches. The generation AI model 400 converts the manga expressed in these rough sketches into the final manga form according to the art style. The manga generation instructions are instruction information for generating a manga. In addition, in the present disclosure, the name image includes character instruction information, and the information is written so as to reflect the character setting information stored in the character DB 250.

[0027] The feature amount acquiring unit 102 acquires the feature amount of each reader group from the reader DB 200. As described above, the feature amount is information indicating the tendency of favorite manga genres, and is information indicating the proportion for each genre.

[0028] The prompt generation unit 103 generates a prompt (generation instruction information) based on the art style, name image, comic generation instructions, and group feature values. Specifically, the prompt generation unit 103 acquires feature values ​​corresponding to the reader group from the reader DB 200 (reader group table). Then, the prompt generation unit 103 references the art style DB 105 to acquire the art style corresponding to the reader group. That is, the prompt generation unit 103 acquires an art style corresponding to the reader group (age, gender, hobbies, and preferences) from the art style DB. It is preferable to acquire an art style that matches the hobbies and preferences without considering the proportion of the hobbies and preferences. If there is no art style that perfectly matches the age, gender, and hobbies and preferences, it is also possible to acquire a corresponding art style by ignoring those with a low proportion of the hobbies and preferences. The prompt generation unit 103 then generates a prompt that includes the art style, feature values, name image, and comic generation instructions.

[0029] 7(a) to 7(c) are schematic diagrams of the art style DB 105. As shown in the diagrams, the art style DB 105 stores art style information such as art style and drawing touch in association with age, gender, and hobbies and preferences.

[0030] In this disclosure, the style database is used to acquire the style corresponding to the reader group, but this is not limited to this. The style corresponding to the reader group may also be acquired using the LLM or other generation AI. In this case, the prompt generation unit 103 performs the following operations.

[0031] That is, the prompt generation unit 103 generates two types of prompts: a style determination prompt that causes a generation AI such as an LLM (hereinafter referred to as an LLM) to set a style, and a manga generation prompt that causes the generation AI model 400 to generate a manga.

[0032] More specifically, regarding the style determination prompt, the prompt generation unit 103 acquires feature amounts (proportions of favorite manga) corresponding to each reader group from the reader DB 200 based on the manga creation instruction acquired by the instruction acquisition unit 101. The prompt generation unit 103 then generates a style determination prompt based on the acquired name image and feature amounts.

[0033] FIG. 8 shows an example of a style determination prompt P generated by the prompt generation device 100. This style determination prompt P is information indicating instructions for determining the style of a manga that is given before the manga is generated. This style determination prompt P is composed of an instruction section P1, a user information section P2, a feature section P3, and a name image section P4. The instruction section P1 is a fixed phrase and is a predetermined instruction sentence. The user information section P2 indicates the user's characteristics, in this case, age and gender. The feature section P3 indicates hobbies and preferences, in this case, indicating the tendency (percentage) of preferred manga.

[0034] Furthermore, when the prompt generation unit 103 acquires the art style information from the LLM, it generates the manga generation prompt. That is, the prompt generation unit 103 generates the manga generation prompt using the acquired art style information and the name image acquired from the user terminal 500.

[0035] 9 shows an example of the manga creation prompt. As shown in the figure, the manga creation prompt P10 is composed of a fixed form section P11, a style information section P12, and a name image section P13. The fixed form section P11 instructs the user to create a manga based on the style information and the name image. The style information section P12 indicates the acquired style information, including the era of the style, the touch of the drawing, color intensity, line thickness, and tone density. The name image section P13 is an image acquired from the user terminal 500.

[0036] The prompt processing unit 104 transmits the style determination prompt and the manga generation prompt generated by the prompt generation unit 103 to the LLM and the generation AI model 400, respectively, and acquires the resulting answers. Figure 10 shows the answer results generated by the LLM in response to the style determination prompt. Figure 10(a) shows the style information that is the answer result generated by the LLM for user group A, Figure 10(b) shows the style information for user group B, and Figure 10(c) shows the style information for user group C.

[0037] For example, as shown in FIG. 10( a), the following answer results (artistic style information) are generated for user group A: art style: 2000s, art touch: xx, color intensity: xx, line thickness: xx, and tone intensity: xx. The artistic style is indicated, for example, by smooth and delicate brushstrokes or strong and rough brushstrokes. Color intensity is indicated by a range from bright and vivid colors to pale and soft colors. Line thickness is indicated by a thick and strong outline or a thin and delicate line. Tone intensity is indicated by a strong contrast between light and dark, an overall soft tone, or the like. These pieces of information may be expressed as numerical information. For example, the artistic style may be graded, with delicate brushstrokes being 0 and strong and rough brushstrokes being 10.

[0038] The art style is indicated by decade in the above. This refers to the art style that became mainstream in the 2000s, but since there is a wide range of eras and it may be difficult to identify the specific art style, other art styles may also be expressed. For example, a manga artist or manga that is popular with a certain generation and gender may be identified, and the art style may be made to resemble that of that artist or manga. The prompt may include information identifying the manga artist or manga, or a representative manga (image information).

[0039] Next, the operation of the reader data generation device 300 configured as described above will be described. FIG. 11 is a flowchart showing the operation of the reader data generation device 300. The grouping processing unit 301 acquires reader data from the reader DB 200 (reader table) (S101). The grouping processing unit 301 groups the reader data (age, gender, hobbies and preferences (favorite manga trends (genres))) obtained from the reader table based on age and gender (S102). The feature extraction unit 302 extracts features for each grouped reader group (age and gender) (S103). That is, the feature extraction unit 302 extracts the proportion of hobbies and preferences (favorite manga trends (genres)) as a feature. The feature extraction unit 302 stores the feature (favorite manga trends) for each reader group in the reader DB 200 (reader group table) (S104).

[0040] Next, the operation of the prompt generation device 100 will be described. Fig. 12 is a flowchart showing the operation of the prompt generation device 100. The instruction acquisition unit 101 acquires a manga creation instruction and a name image from the user terminal 500 (S201). The feature acquisition unit 102 acquires features (tendencies in favorite manga) representing the hobbies and preferences corresponding to each reader group from the reader DB 200 (reader group table) (S202).

[0041] The prompt generation unit 103 references the art style DB 105 to determine an art style that corresponds to the hobbies and preferences of the reader group (S203). After determining the art style, the prompt generation unit 103 generates a manga generation prompt based on the art style and the name image (S204). The prompt processing unit 104 then transmits the manga generation prompt to the generation AI model 400 and receives the response result (a manga that reflects the art style) (S205). The prompt processing unit transmits the received response result to the user terminal 500 (S206). Processes S204 to S206 are executed for each reader group. That is, a prompt for generating an art style appropriate for the reader group is generated and transmitted to the generation AI model 400, and the generation AI model 400 generates a manga in the specified art style. The prompt generation device 100 receives the response result, which is a manga.

[0042] Through this process, the prompt generation device 100 can determine an art style that corresponds to the user group and have the generation AI model 400 generate a manga that conforms to that art style.

[0043] In the above process S203, the prompt generating unit 103 may have the LLM determine the style, in which case the following process is carried out.

[0044] 13, the prompt generator 103 generates a style determination prompt (see FIG. 7) using the reader group's preferences (S203a). The prompt processor 104 sends the generated style determination prompt to the LLM (S203b), causes the LLM to determine the style, and receives the resulting response (style information) (S203c). Processing S204 is then executed.

[0045] In the above description, character DB 250 can be used to reflect character setting information in image generation. That is, in process S204, prompt generation unit 103 generates a manga generation prompt including an art style and a name image, and character setting information can be included in the manga generation prompt. That is, prompt generation unit 103 can refer to character DB 250 to obtain character setting information corresponding to the instruction information of the character shown in the name image, and include the character setting information in the manga generation prompt.

[0046] Here, we will explain the configuration of the user terminal 500 on which the prompt generation device 100 or the generation AI model 400 is installed. Figure 14(a) shows an example configuration when the user terminal 500 has the functions of the prompt generation device 100. In this case, the user terminal 500 accesses an external knowledge DB (in this disclosure, the character DB 250 and the reader DB 200), uses it to generate a prompt, sends it to the generation AI model 400, and obtains the results.

[0047] 14(b) shows an example of a configuration in which a user terminal 500 is equipped with a prompt generation device 100 and a generative AI model 400. As shown in the figure, the user terminal 500 accesses an external knowledge DB (in this disclosure, the character DB 250 and the reader DB 200), uses it to generate a prompt, outputs it to the built-in generative AI model 400, and obtains the results.

[0048] Next, the effects of the prompt generation device 100 of the present disclosure will be described. The prompt generation device 100 of the present disclosure includes a feature acquisition unit 102 that acquires features of a user group, a prompt generation unit 103 that generates cartoon generation instruction information (generation instruction information) including the features of the user group and a name image (target image), and a prompt processing unit 104 that transmits the cartoon generation instruction information to a generation AI model 400 and generates a cartoon (generated image) based on the features and name image. The cartoon generation instruction information here is a prompt that is input to the generation AI model 400.

[0049] In the above, the feature amount is information indicating the proportion of the hobbies and preferences of the users belonging to the user group. For example, a name image is an image made up of a rough sketch, and a manga image is an image that is a clean copy based on the name image, and the hobbies and preferences that are the feature amount indicate the manga genres that the users belonging to the user group like.

[0050] This configuration makes it possible to generate manga tailored to user groups, particularly manga tailored to the user's attributes and hobbies. In the present disclosure, in order to have the generation AI model 400 generate manga, even simple prompts can output images in each person's preferred style, broadening the scope of creativity. Furthermore, while until now, manga could only be provided in the style and characters selected by the business operator for a certain manga purpose, manga can now be provided in each reader's preferred style and characters, allowing manga to be provided according to the purpose.

[0051] In the present disclosure, the prompt generation unit 103 refers to an art style DB 105 that associates user groups with art styles, selects an art style corresponding to the user group, and generates manga generation instruction information based on the selected art style. More specifically, the prompt generation device 100 further includes an art style DB 105 that associates user groups with art styles, and the prompt generation unit 103 refers to the art style DB 105 to select an art style corresponding to the user group.

[0052] According to this configuration, a style of illustration corresponding to each reader group can be determined, and a manga can be generated from the name image based on that style of illustration, thereby generating a manga appropriate for the reader group.

[0053] The prompt generating unit 103 also references the character DB 250 that stores character information (character instruction information, character setting information), and generates comic book creation instruction information based on the character information specified in the name image.

[0054] In the present disclosure, the name image includes character instruction information. For example, because it is not clear what kind of character the character roughly drawn in the name image is, it is not possible to determine from letters, etc., who the character is, what their appearance is, or what their personality is. Therefore, instruction information for the character (character name, identifier, or number) is entered in the name image, and based on this, character DB 250 is referenced to extract setting information for the character (appearance, personality, etc.), which is then written in the manga generation instruction information (prompt). This allows the generation AI model 400 to generate a manga image based on the setting information in addition to the drawing style.

[0055] The prompt generation unit 103 may also generate a style determination prompt (style determination instruction information) to have a generation AI such as an LLM determine a style, and generate an image generation prompt (manga generation instruction information) based on the style determined based on the style determination prompt. For example, the prompt generation unit 103 generates the style determination prompt (style determination instruction information) based on each group attribute and feature amount in the reader group table. Then, when the prompt generation unit 103 acquires a style corresponding to the style determination prompt from the generation AI such as an LLM, it generates an image generation prompt based on the acquired style and name image.

[0056] The method of using image DB 105 may not necessarily be able to determine an appropriate style of painting, but in the present disclosure, a generative AI model such as LLM can be used to determine the style of painting, enabling detailed style setting.

[0057] All or some of the generation AI model 400, LLM, reader DB 200, and character DB 250 may be located in the prompt generation device 100 or the user terminal 500. Furthermore, the user terminal 500 may have the functions of the prompt generation device 100 and function as the prompt generation device 100. The LLM and generation AI model 400 include a type in which the generation AI model is located inside the user terminal 500, such as "tsuzumi." In this type, the RAG app is also provided on the user terminal 500. However, the information accessed by the RAG (knowledge DB) may be located inside the user terminal 500 or on the network. Furthermore, there is a type in which the LLM and generation AI model are located on the network, such as ChatGPT. In this type, the RAG app is provided on the user terminal 500. However, the information accessed by the RAG (knowledge DB) is located on the network.

[0058] The generative AI model 400 disclosed herein is an AI model that handles images for style conversion such as stable diffusion, and is distinguished from the generative AI model that handles natural language described below. A generative AI model, such as an LLM, is a model that can generate content in response to a prompt containing input information, according to the instructions, context, question, and output format indicated by the prompt, and return the content as response information. The prompt can 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 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, the prompt generation device 100 is capable of providing a content provision function using multiple types of interactive AI models. These interactive AI models may be stored within the prompt generation device 100, or may be stored in another device connected to the prompt generation device 100 via a network so that information can be exchanged with the user via the prompt generation device 100. Although only one prompt generation device 100 is shown in the figure, multiple prompt generation devices 100 may be included.

[0059] The device and method of the present disclosure have the following configuration.

[0060] [1] An apparatus comprising: a feature acquisition unit that acquires features of a user group; a generation unit that generates generation instruction information including the features of the user group and a target image; and a transmission unit that transmits the generation instruction information to a generation AI to generate a generated image according to the features and the target image.

[0061] [2] The device according to [1], wherein the feature amount is information indicating a ratio of hobbies and preferences of users belonging to the user group.

[0062] [3] The device described in [2], wherein the target image is a name image consisting of a rough sketch, the generated image is a manga image that is neatly drawn based on the name image, and the hobbies and preferences indicate the manga genres that users belonging to the user group like.

[0063] [4] The device described in any one of [1] to [3], wherein the generation unit refers to an art style DB that associates user groups with art styles, selects an art style corresponding to the user group, and generates generation instruction information based on the selected art style.

[0064] [5] The device according to any one of [1] to [3], wherein the generation unit generates style determination instruction information, causes a generation AI that handles natural language to determine the style, and generates generation instruction information based on the style determined based on the style determination instruction information.

[0065] [6] The device according to [5], wherein the generating unit generates the style determination instruction information based on the group attributes of the user group and the feature amount.

[0066] [7] The device according to [6], wherein the generation unit, upon obtaining a style according to the style determination instruction information from the generation AI, generates the generation instruction information based on the style and a target image.

[0067] [8] The device according to any one of [1] to [7], wherein the generation unit references a character DB that stores character information and generates the generation instruction information based on character information specified in the target image.

[0068] [9] The device according to [8], wherein the character DB stores, as character information, instruction information for identifying a character and setting information of the character.

[0069]

[10] A method for an apparatus, comprising: a feature acquisition step of acquiring features of a user group; a generation step of generating generation instruction information including the features and a target image; and a transmission step of transmitting the generation instruction information to a generation AI to generate a generated image according to the features and the target image.

[0070] In this disclosure, a prompt is information indicating an instruction or question entered by a user in an interactive system such as an interaction with a generative AI model or a command line interface (CLI).

[0071] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or 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 connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0072] 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.

[0073] For example, the prompt generation device 100 according to an embodiment of the present disclosure may function as a computer that performs processing of the prompt generation method of the present disclosure. Fig. 15 is a diagram illustrating an example of the hardware configuration of the prompt generation device 100 according to an embodiment of the present disclosure. The prompt generation device 100 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage device 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0074] In the following description, the term "device" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the prompt generation device 100 may be configured to include one or more of the devices shown in the figures, or may be configured to exclude some of the devices.

[0075] Each function in the prompt generating device 100 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0076] The processor 1001, for example, runs an operating system to control the entire computer. The processor 1001 may be configured as 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 prompt generation unit 103 may be realized by the processor 1001.

[0077] The processor 1001 also loads programs (program code), 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 these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the prompt generation unit 103 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.

[0078] 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 referred to as a register, a cache, a main memory (primary storage device), etc. The memory 1002 may store executable programs (program codes), software modules, etc. for implementing a prompt generation method according to one embodiment of the present disclosure.

[0079] 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.

[0080] 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, or a communication module. The communication device 1004 may 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 instruction acquisition unit 101, the feature acquisition unit 102, the prompt processing unit 104, etc. may be realized by the communication device 1004. The communication device 1004 may be implemented with a transmission unit and a reception unit that are physically or logically separated.

[0081] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives 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).

[0082] 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.

[0083] Furthermore, prompt generation device 100 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 realized by such hardware. For example, processor 1001 may be implemented using at least one of these pieces of hardware.

[0084] 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.

[0085] 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.

[0086] 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 sent to another device.

[0087] 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).

[0088] 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).

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0095] 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.

[0096] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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."

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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."

[0105] 100...prompt generation device, 200...reader DB, 250...character DB, 300...reader data generation device, 400...generated AI model, 500...user terminal, 301...grouping processing unit, 302...feature extraction unit, 101...instruction acquisition unit, 102...feature acquisition unit, 103...prompt generation unit, 104...prompt processing unit.

Claims

1. An apparatus comprising: a feature acquisition unit that acquires features of a user group; a generation unit that generates generation instruction information that is a prompt that instructs a generation AI to generate an image, the generation instruction information including the features of the user group and a target image; and a transmission unit that transmits the generation instruction information to the generation AI to generate a generated image according to the features and the target image.

2. The device according to claim 1, wherein the feature is information indicating the proportion of hobbies and preferences of users belonging to the user group.

3. The device described in claim 2, wherein the target image is a name image consisting of a rough sketch, the generated image is a manga image that is neatly drawn based on the name image, and the hobbies and preferences indicate the manga genres that users belonging to the user group like.

4. The device according to claim 1, wherein the generation unit refers to an art style database that associates user groups with art styles, selects an art style corresponding to the user group, and generates generation instruction information based on the selected art style.

5. The device described in claim 1, wherein the generation unit generates style determination instruction information, has a generation AI that handles natural language determine the style, and generates generation instruction information based on the style determined based on the style determination instruction information.

6. The device according to claim 5, wherein the generation unit generates the style determination instruction information based on the group attributes of the user group and the feature amount.

7. The device according to claim 6, wherein the generation unit, upon obtaining a style corresponding to the style determination instruction information from the generation AI, generates the generation instruction information based on the style and the target image.

8. The device according to claim 1, wherein the generation unit references a character DB that stores character information and generates the generation instruction information based on character information specified in the target image.

9. The device according to claim 8, wherein the character DB stores, as character information, instruction information for identifying a character and setting information for the character.

10. A method for an apparatus, comprising: a feature acquisition step for acquiring features of a user group; a generation step for generating generation instruction information including the features and a target image; and a transmission step for transmitting the generation instruction information to a generation AI to generate a generated image according to the features and the target image.

Images