Information processing device, information processing method, and information processing program

Abstract

To enable generation of appropriate images.SOLUTION: An information processing device disclosed herein comprises an acquisition unit, first generation unit, and second generation unit. The acquisition unit acquires introduction target information regarding an object for introduction to be subjected to image generation. The first generation unit generates target character information to be used for image generation on the basis of the introduction target information. The second generation unit generates an introduction image, or an image introducing the object for introduction from the target character information, using an image generation model which is a learning model trained to generate an image from character information.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, techniques for generating images based on various types of information such as text have been provided. For example, a technique has been proposed that outputs (generates) a recommended image based on an image selected by a user as an object to be combined with an object included in the recommended image.

Prior Art Literature

Patent Literature

[0003]

Patent Literature 1

Non-Patent Literature

[0004]

Non-Patent Literature 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, there is room for improvement in the conventional technology described above. This conventional technology simply generates images based on images selected by the user as the elements to be combined, and it can be difficult to generate images appropriately, such as when the user has not selected any images. Therefore, it is desirable to generate information used for image generation and then generate images based on this information to achieve appropriate image generation.

[0006] This application was made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that generate appropriate images. [Means for solving the problem]

[0007] The information processing device according to the present invention is characterized by comprising: an acquisition unit that acquires information about an item to be introduced that is the subject of image generation; a first generation unit that generates character information, which is character information used for image generation, based on the information about the item to be introduced; and a second generation unit that generates an introduction image, which is an image introducing the item to be introduced, from the character information using an image generation model, which is a learning model that has been trained to generate images from character information. [Effects of the Invention]

[0008] According to one embodiment, the effect is achieved that appropriate images can be generated. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows an example of information processing according to the embodiment. [Figure 2] Figure 2 shows an example of the configuration of an information processing system according to the embodiment. [Figure 3] Figure 3 shows an example of the configuration of an information processing device according to the embodiment. [Figure 4] Figure 4 shows an example of a model information storage unit according to the embodiment. [Figure 5]Figure 5 is a flowchart showing an example of information processing according to the present invention. [Figure 6] Figure 6 is a hardware configuration diagram showing an example of a computer that implements the functions of an information processing device. [Modes for carrying out the invention]

[0010] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0011] (Embodiment) [1. Information Processing] First, an example of information processing according to the embodiment will be explained using Figure 1. Figure 1 is a diagram showing an example of information processing according to the embodiment. In Figure 1, an example is shown in which the information processing system 1 uses a book as the subject of introduction and generates an image corresponding to that book. Note that a book is merely one example of a subject of introduction, and the subject of introduction is not limited to books but may be any subject, but this point will be explained later. Furthermore, in the following, the terminal device 10 among the devices included in the information processing system 1 will be described as the processing unit for image generation, but various processes such as image generation may be performed by any device of the information processing system 1, such as the server device 50, but this point will be explained later.

[0012] [1-1. Configuration of the Information Processing System] Before explaining Figure 1, the configuration of the information processing system 1 that realizes the information processing shown below will be explained using Figure 2. Figure 2 is a diagram showing an example configuration of the information processing system according to the embodiment. As shown in Figure 2, the information processing system 1 includes a plurality of terminal devices 10 and a server device 50. The terminal devices 10 and the server device 50 are connected to each other via a predetermined network N, either by wired or wireless means. Note that the information processing system 1 shown in Figure 2 may include a plurality of terminal devices 10 and a plurality of server devices 50.

[0013] Terminal device 10 is a computer (information processing device) used by a user. For example, terminal device 10 can be a smartphone, tablet, notebook PC (Personal Computer), desktop PC, mobile phone, PDA (Personal Digital Assistant), etc. In the following, terminal device 10 may be referred to as the user. In other words, the user can be read as terminal device 10. In the following, the case where terminal device 10 is a smartphone will be shown as an example.

[0014] The terminal device 10 generates text information (also called "target text information") used for image generation based on information about the subject to be introduced. The terminal device 10 also generates an image (also called "introduction image") introducing the subject from the target text information, using a trained model (also called "image generation model") that has been trained to generate images from text information (also called "text").

[0015] Furthermore, the terminal device 10 displays various types of information. For example, the terminal device 10 displays various types of information through various applications. For example, the terminal device 10 displays content such as web content. The terminal device 10 also displays images generated by image generation processing.

[0016] The terminal device 10 may appropriately use various conventional techniques related to content display, and execute various processes related to content display based on control information or the like. The terminal device 10 may execute various processes related to content display based on control information. The terminal device 10 may acquire, as control information, a script executed on a predetermined application such as a web browser, and execute the acquired script. Such control information corresponds to the display program and the like according to the embodiment, and is implemented by, for example, CSS (Cascading Style Sheets), JavaScript (registered trademark), HTML (HyperText Markup Language), or any language capable of describing the aforementioned display processing and the like. Hereinafter, the terminal device 10 and the like that execute the aforementioned display processing and the like in accordance with the display program according to the embodiment will be described in detail.

[0017] The server device 50 is a computer (information processing device) that provides various types of information used by the terminal device 10 for processing. For example, the server device 50 is a server managed by an administrator or the like of the information processing system 1. Note that the server device 50 may perform image generation processing, which will be described later.

[0018] The server device 50 provides various types of information to users. The server device 50 transmits various types of information to the terminal device 10 used by the user. For example, the server device 50 distributes various types of content such as web content. The server device 50 receives requests for providing various types of information from the terminal device 10, and transmits information corresponding to the received request to the terminal device 10. For example, the server device 50 receives a request for distributing web content from the terminal device 10, and distributes the requested web content to the terminal device 10.

[0019] For example, the server device 50 provides various types of information used for processing to the terminal device 10. The server device 50 may distribute various models such as an image generation model to the terminal device 10. Note that the model distribution may be performed by a device other than the server device 50.

[0020] [1-2. Overall Overview of Processing in Information Processing Systems] From here, we will explain an example of information processing performed by Information Processing System 1 using Figure 1. Note that detailed explanations of aspects of the information processing performed by Information Processing System 1 that are similar to conventional image generation processes will be omitted as appropriate.

[0021] In Figure 1, the terminal device 10 acquires information about the book T1 to be introduced. For example, the terminal device 10 acquires the text "XXXXXX," which is a sentence contained in book T1, as the information to be introduced BW1. In Figure 1, the texts "XXXXXX" and "YYYYYY" are shown as abstract strings, but each text is assumed to be a text that describes specific content. For example, the text "XXXXXX" is a text that contains specific content such as "...when you go through the tunnel you'll find yourself in a snow country..." and corresponds to a part of book T1, such as a paragraph in book T1.

[0022] Furthermore, the terminal device 10 obtains a text generation model M1 (also simply called "Model M1") from the server device 50, which generates text from the information to be introduced. For example, Model M1 is a text generation model that has been trained using various summarization techniques. Model M1 is a text generation model that takes character information as input and outputs text corresponding to that character information. For example, Model M1 extracts character information of high importance, such as characteristic strings, from the input character information and outputs appropriate text (also called "summon word," etc.) as input to the image generation model M2, which will be described later. Note that when the terminal device 10 trains Model M1, it may obtain data to be used in the training process of Model M1 (training data) from the server device 50, etc., and train Model M1 using the training data, but this point will be described later.

[0023] The terminal device 10 inputs the information to be introduced BW1 as input information to the model M1 (step S1-1). In Figure 1, the terminal device 10 inputs the text "XXXXXX", which is a passage from book T1, as input information to the model M1. The model M1, having received the input information, outputs the target character information AW1 (step S1-2). In Figure 1, the model M1, having received the information to be introduced BW1 from book T1, outputs the text "YYYYYY", as shown in the target character information AW1. For example, the text "YYYYYY" is a text that contains characteristic strings such as "tunnel" and "snow", and is suitable as input to the image generation model M2. Thus, the terminal device 10 uses the model M1 to generate the target character information AW1, which is suitable as input to the image generation model M2, from the information to be introduced BW1.

[0024] The terminal device 10 then generates an image using an image generation model M2 (also simply called "model M2") which takes text as input information and generates and outputs an image corresponding to that text. The terminal device 10 inputs the target character information AW1 as input information to model M2 (step S2-1). In Figure 1, the terminal device 10 inputs the appropriate text "YYYYYY" as input information to model M2 as input information to the image generation model M2.

[0025] Model M2, upon receiving input information, outputs an image corresponding to the input text (step S2-2). In Figure 1, Model M2, upon receiving target character information AW1, outputs an introductory image IM1 corresponding to the text "XXXXXX" in book T1. For example, introductory image IM1 is an image that depicts (visualizes) the content of the text "XXXXXX," and may include images of a tunnel and a snowy landscape. In this way, terminal device 10 generates an introductory image IM1 introducing book T1 using target character information AW1 corresponding to the information to be introduced BW1.

[0026] As described above, the terminal device 10 can generate appropriate image generation by using Model M1 to convert the information to be introduced into appropriate target character information for input to Model M2, and by inputting the generated target character information to Model M2. In Figure 1, for illustrative purposes, the case in which the subject of depiction is a concrete thing such as a landscape was explained as an example, but if the information to be introduced is abstract, the generated image may also be a depiction of an abstract image.

[0027] [1-3. System Configuration] The configuration of the information processing system 1 described above is merely an example, and the information processing system 1 can employ any device configuration and distribution of functions. In Figure 1, the case where the terminal device 10 is an information processing device that generates images is explained as an example, but in the information processing system 1, image generation may be performed by an information processing device other than the terminal device 10 used by the user. For example, in the information processing system 1, image generation may be performed by a server device (information processing device) such as the server device 50.

[0028] In this case, in the information processing system 1, the server device 50 generates an image (introduction image) introducing the subject to be introduced by the process shown in Figure 1. The server device 50 may then provide the generated introduction image to the user by transmitting it to the terminal device 10 used by the user. The terminal device 10 used by the user may then display the introduction image received from the server device 50.

[0029] Thus, in the information processing system 1, the information processing device that displays images (e.g., terminal device 10) and the information processing device that generates images (e.g., server device 50) may be separate entities. For example, in the information processing system 1, the server device 50 may be a providing device (information processing device) that generates and provides images to users using the terminal device 10, and the terminal device 10 may be a display device that displays images provided by the server device 50. Note that the configuration of the information processing system 1 described above is merely an example, and the information processing system 1 is not limited to the above; any device configuration and distribution of functions can be adopted.

[0030] [1-4. Other examples] The processes described above are merely examples, and the information processing system 1 may generate images using various types of information or provide the generated images to the user. Furthermore, any of the devices (information processing devices) included in the information processing system 1, such as the terminal device 10 or the server device 50, may perform the processes described as being performed by the information processing system 1.

[0031] For example, information processing system 1 may provide various services using the generated images. Information processing system 1 provides introductory images. For example, terminal device 10 transmits the introductory images to an external device such as server device 50. For example, terminal device 10 displays the introductory images.

[0032] For example, information processing system 1 provides content including introductory images. For example, terminal device 10 generates content including introductory images and provides the generated content. For example, terminal device 10 displays content including introductory images. For example, terminal device 10 displays content to promote sales of the product being introduced. For example, terminal device 10 generates content (sales content) that directs users to the trading site, etc., where the product being introduced is sold, and provides the generated sales content. Terminal device 10 generates sales content with a link (URL, etc.) to the trading site, etc., where the product being introduced is sold, and provides the generated sales content.

[0033] As described above, Information Processing System 1 generates images that describe the book using an image generation model. Information Processing System 1 extracts text of high importance from the text contained in the book to be introduced. Information Processing System 1 generates images from the extracted text using a model that has been trained to generate images from text. Information Processing System 1 provides content that includes the generated images as content introducing the book.

[0034] In this way, Information Processing System 1 extracts text of high importance from the book to be introduced. Information Processing System 1 performs text extraction using various summarization techniques. Information Processing System 1 inputs the extracted text into an image generation model to generate an image. The content, including the image generated by Information Processing System 1, is provided as content introducing the book. Note that the content may also be sales content related to sales, as described above.

[0035] For example, the information processing system 1 may generate images for each arbitrary unit, such as a paragraph, sentence, chapter, or scene. For example, the information processing system 1 may generate images using different methods depending on the type of book. For example, if the book is a novel, the information processing system 1 may generate an image for each paragraph. Also, for example, if the book is an essay, the information processing system 1 may generate an image for the entire book.

[0036] For example, information processing system 1 may generate an image for each paragraph and select an appropriate image from the generated set of images. For example, information processing system 1 may generate images according to the type of scene, such as a dialogue scene or a scene depicting a scene. For example, information processing system 1 may recognize and divide scenes (contexts) in a novel and generate an image for each scene. For example, information processing system 1 may use an image generation model that generates different types of images depending on the type of book. For example, if the book is a self-help book, information processing system 1 may generate images using an image generation model that generates abstract paintings.

[0037] For example, information processing system 1 may generate an image for each sentence in a chapter and select an image appropriate for that chapter from the generated image set. For example, information processing system 1 may learn the user's preferences. For example, information processing system 1 may generate and provide images according to user attributes. For example, information processing system 1 may generate and provide images for each type of book.

[0038] For example, information processing system 1 may train a model that generates explanatory text (also called an "explanatory text model") as a text generation model. In this case, information processing system 1 may train an image generation model so that a more appropriate image is output when the explanatory text output by the text generation model is input. For example, information processing system 1 generates an explanatory text model so that an explanatory text is output when the text of a book is input. For example, information processing system 1 may generate explanatory text from the generated explanatory text model using multiple explanatory text models with different connection coefficients, and then generate an image from an image generation model using this explanatory text.

[0039] For example, the information processing system 1 may accept user ratings of images. For example, the information processing system 1 may employ a descriptive text model capable of generating images with high user ratings. For example, the information processing system 1 may generate multiple different descriptive text models from the descriptive text model and repeat the above-described process.

[0040] For example, Information Processing System 1 may have a person (user) who is capable of creating appropriate explanatory texts create explanatory texts corresponding to books, and then train an explanatory text model using this person's explanatory text as ground truth data to generate an explanatory text model that generates appropriate explanatory texts. For example, Information Processing System 1 may generate moving images (videos). For example, Information Processing System 1 may generate videos from text (words). In this case, for example, Information Processing System 1 may provide content in which intermediate scenes become videos.

[0041] For example, information processing system 1 may generate images (illustrations) for adults and images (illustrations) for children using different image generation models. For example, information processing system 1 may create images of scenes that suit the user's (reader's) preferences (scenes they are likely to like). Also, for example, information processing system 1 may generate text so that the images are likely to be liked by the user (reader). For example, information processing system 1 may increase the level of detail in the depictions as the age increases.

[0042] For example, the information processing system 1 may change the art style for each category being introduced. For example, the information processing system 1 may generate images in an art style that suits the user's preferences (or that the user is likely to like). Alternatively, for example, the information processing system 1 may determine an art style based on a combination of category and user, a combination of books the user has read and the user, and generate images in the determined art style. In this case, for example, the information processing system 1 may change the art style using a model that transforms the style of an image (style transformation model). For example, the information processing system 1 may generate introduction images with a changed art style by inputting the generated introduction images into a style transformation model that transforms them into a desired style.

[0043] For example, information processing system 1 may generate different images depending on the category. For example, in the case of a blog, information processing system 1 may generate a poster as an image. For example, in the case of a novel, information processing system 1 may generate an image that reproduces the content. For example, information processing system 1 may generate a manga. For example, information processing system 1 may determine sound effects such as onomatopoeia, generate an image including keywords, and provide it. For example, information processing system 1 may estimate the author, generate an image corresponding to the estimated author, and provide it.

[0044] For example, the information processing system 1 may process books that are read aloud, such as audiobooks, or so-called "listenables." In this case, the information processing system 1 may generate images (also called "audio output-compatible images") for text that is being output aloud by the terminal device 10 used by the user, and the terminal device 10 may display the audio output-compatible image corresponding to the text while the text is being output aloud. For example, the information processing system 1 may generate audio output-compatible images for each part of the book, such as paragraphs or chapters, and while the book is being output aloud by the terminal device 10, it may display the audio output-compatible image corresponding to the audio output part of the book on the terminal device 10.

[0045] The above is merely an example, and the subject of introduction is not limited to books; it can be any subject. For example, the subject of introduction could be a product, service, or other item that you wish to advertise (the advertised item). Alternatively, the subject of introduction could be a news article, essay, blog, digital signage, etc., that introduces the subject. For example, if the subject of introduction is an advertised item, it could be a catchphrase. For example, information processing system 1 may input information about the advertised item into model M1 to generate text (a catchphrase) corresponding to the advertised item, and then input the generated catchphrase into model M2 to generate an advertising image corresponding to the advertised item as an introductory image. The above is merely an example, and information processing system 1 may generate introductory images for any subject.

[0046] Furthermore, the information processing system 1 may use the generated introductory images for various services. The information processing system 1 may also use the introductory images for searching. For example, the information processing system 1 may provide users with similar images extracted through a search process using the introductory images. For example, terminal device 10 may display similar images extracted through a search process using the introductory images. For example, server device 50 may transmit similar images extracted through a search process using the introductory images to terminal device 10 used by the user.

[0047] [2. Configuration of the Information Processing Device] Next, the configuration of a terminal device 10, which is an example of an information processing device, will be described using Figure 3. Figure 3 is a diagram showing an example configuration of an information processing device according to the embodiment. As shown in Figure 3, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, a storage unit 14, and a control unit 15. The terminal device 10 may also have a microphone (sound sensor) and a speaker that serve as an audio input / output interface. For example, the sound sensor and speaker of the terminal device 10 may be connected to the terminal device 10 so that they can communicate via external connection or the like.

[0048] (Communications Section 11) The communication unit 11 is implemented, for example, by a communication circuit. The communication unit 11 is connected by wire or wireless to a predetermined communication network (not shown) and transmits and receives information with an external information processing device. For example, the communication unit 11 is connected by wire or wireless to a predetermined network N (see Figure 2) and transmits and receives information with the server device 50.

[0049] (Input section 12) The input unit 12 receives various operations from the user. For example, the input unit 12 may accept various operations from the user via a display surface (e.g., output unit 13) using a touch panel function. Alternatively, the input unit 12 may accept various operations from buttons provided on the terminal device 10, or from a keyboard or mouse connected to the terminal device 10.

[0050] (Output section 13) The output unit 13 is a screen for displaying information. For example, the output unit 13 is a display screen for a tablet terminal, etc., which is implemented using a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various types of information. The output unit 13 may also function as a touch panel screen.

[0051] (Storage unit 14) The storage unit 14 is implemented by, for example, a semiconductor memory element such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disc. The storage unit 14 stores, for example, information related to applications installed on the terminal device 10 (e.g., image generation applications), such as programs. Furthermore, as shown in Figure 3, the storage unit 14 according to this embodiment has a model information storage unit 141, a generation information storage unit 142, and a user information storage unit 143. The storage unit 14 may also store various other types of information. For example, the storage unit 14 may store generated images. The storage unit 14 may also store information used by the terminal device 10 to display multiple images. The storage unit 14 may also store information used by the terminal device 10 to determine which image to display. For example, the storage unit 14 may store information indicating the display order of images.

[0052] (Model information storage unit 141) The model information storage unit 141 according to the embodiment stores information about the model. For example, the model information storage unit 141 stores information (model data) of a trained model (model) that has been trained (generated) through a training process. The model information storage unit 141 shown in Figure 4 stores the data used for training (training data) in association with the trained model (model). Figure 4 is a diagram showing an example of the model information storage unit according to the embodiment. In the example shown in Figure 4, the model information storage unit 141 includes items such as "model ID", "purpose", "model data", and "training data". In the example in Figure 4, the model information storage unit 141 stores the data used for training (training data) in association with the trained model (model).

[0053] The "Model ID" indicates identification information for identifying the model. The "Purpose" indicates the purpose of the corresponding model. The "Model Data" indicates the data of the model. Figure 4 shows an example where conceptual information such as "MDT1" is stored in "Model Data," but in reality, it includes various information that constitutes the model, such as information about the model's configuration (network configuration) and parameters. For example, "Model Data" includes information such as the nodes in each layer of the network, the functions adopted by each node, the connection relationships between nodes, and the connection coefficients set for the connections between nodes.

[0054] "Training data" refers to the data used to train a trained model (model). "Training data" stores information indicating the dataset used to train the corresponding model. For example, "training data" stores data (input information) and the corresponding correct answer information (output information) as training data (also called "training data"). Figure 4 shows an example where conceptual information such as "LDT1" is stored in "training data," but in reality, it includes various information about the data used to train the corresponding model, such as data (input information) and the corresponding correct answer information (output information).

[0055] Figure 4 shows that the model identified by model ID "M1" (model M1) is intended for "text generation." That is, model M1 is a model that outputs (generates) text corresponding to the input character information (text). It also shows that the model data for model M1 is model data MDT1. Furthermore, it shows that the training data used to train model M1 is training data LDT1.

[0056] Furthermore, the model identified by model ID "M2" (model M2) indicates that its purpose is "image generation." That is, model M2 is a model that outputs images corresponding to text information. It also indicates that the model data for model M2 is model data MDT2. Furthermore, it indicates that the training data used to train model M2 is training data LDT2.

[0057] Furthermore, the model information storage unit 141 may store various types of information depending on the purpose, not limited to those mentioned above.

[0058] (Generation information storage unit 142) The generation information storage unit 142 according to this embodiment stores various information related to image generation. For example, the generation information storage unit 142 stores various information used to generate images to be provided to the user.

[0059] The generation information storage unit 142 stores various information used for generating content that includes images. The generation information storage unit 142 stores various information used for generating content that includes images to be introduced. The generation information storage unit 142 stores various information used for generating content that includes predetermined music. For example, the generation information storage unit 142 stores the sound source (music data) of predetermined music to be added to the content. The generation information storage unit 142 stores various information used for generating content that includes special effects. For example, the generation information storage unit 142 stores the data (effect data) of special effects to be added to the content.

[0060] The generation information storage unit 142 stores various information used to generate content, which is a video containing the image of the item being introduced. The generation information storage unit 142 stores various information used to generate content containing the name of the item being introduced. The generation information storage unit 142 stores various information used to generate content containing the price of the item being introduced. The generation information storage unit 142 stores various information used to generate content containing a description of the item being introduced.

[0061] For example, the generation information storage unit 142 stores information used to generate content displayed on a display device such as the terminal device 10. For example, the generation information storage unit 142 stores image information used to generate content. For example, the generation information storage unit 142 may store images in various formats such as JPEG (Joint Photographic Experts Group), GIF (Graphics Interchange Format), and PNG (Portable Network Graphics) as image information used to generate content. In addition, the generation information storage unit 142 may store information in the format of CSS, JavaScript, or HTML as image information used to generate content.

[0062] The information generation storage unit 142 is not limited to the above and may store various types of information depending on the purpose.

[0063] (User information storage unit 143) The user information storage unit 143 according to this embodiment stores various information about the user. The user information storage unit 143 stores various information about the user who uses the terminal device 10. For example, the user information storage unit 143 stores various information about user attributes and various information about user behavior.

[0064] The user information storage unit 143 stores information about the user's future actions, such as planned activities. For example, the user information storage unit 143 stores information about planned activities (schedules) that the user has registered in a calendar application (also simply called "calendar"). The user information storage unit 143 stores schedule information related to the user's plans (schedules), such as the user's calendar.

[0065] The user information storage unit 143 stores information about the user's past actions, such as their activity history. The user information storage unit 143 stores various types of behavioral information, such as the user's actions on the internet. The user information storage unit 143 stores various attribute information about the user, such as their age, gender, address, and place of employment. For example, the user information storage unit 143 stores information about the user's preferences, such as the objects of their interest.

[0066] The user information storage unit 143 is not limited to the above and may store various types of information depending on the purpose. For example, the user information storage unit 143 may store other demographic attribute information or psychographic attribute information. For example, the user information storage unit 143 may store information such as name, family structure, income, and lifestyle. The user information storage unit 143 may also store information (terminal ID) that identifies the terminal device 10 used by the user.

[0067] (Control Unit 15) The control unit 15 is a controller, and is implemented by, for example, a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in a storage device such as the memory unit 14 inside the terminal device 10, using RAM as the working area. For example, these various programs include application programs that perform information processing. The control unit 15 is also a controller, and is implemented by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0068] As shown in Figure 3, the control unit 15 includes an acquisition unit 151, a learning unit 152, a first generation unit 153, a second generation unit 154, a display unit 155, and a transmission unit 156, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the control unit 15 is not limited to the configuration shown in Figure 3, and other configurations are also acceptable as long as they perform the information processing described later.

[0069] (Acquisition part 151) The acquisition unit 151 acquires various types of information. For example, the acquisition unit 151 acquires various types of information from the storage unit 14. For example, the acquisition unit 151 acquires various types of information from the model information storage unit 141, the generation information storage unit 142, the user information storage unit 143, etc. The acquisition unit 151 may also acquire various types of information from an external information processing device.

[0070] For example, the acquisition unit 151 acquires various information from the server device 50. For example, the acquisition unit 151 acquires various information used for processing from the server device 50. For example, the acquisition unit 151 acquires models such as model M1 and M2 from the server device 50.

[0071] The acquisition unit 151 receives various types of information. The acquisition unit 151 receives various operations from the user. For example, the acquisition unit 151 receives various operations from the user via the input unit 12. The acquisition unit 151 receives user operations. The acquisition unit 151 receives operations where the user moves their finger that is touching the screen. The acquisition unit 151 receives operations where the user selects the displayed content.

[0072] The acquisition unit 151 acquires information about the subject to be introduced for image generation. The acquisition unit 151 acquires information about the book to be introduced. The acquisition unit 151 acquires information about the text contained in the book.

[0073] (Learning Section 152) The learning unit 152 executes a learning process to learn a learning model (model). Note that the terminal device 10 does not need to have a learning unit 152 if it obtains learning models such as model M1 and M2 from the server device 50.

[0074] For example, the learning unit 152 performs learning processing based on various information acquired by the acquisition unit 131. The learning unit 152 performs learning processing based on information from an external information processing device and information stored in the storage unit 14. The learning unit 152 performs learning processing based on information stored in the model information storage unit 141. The learning unit 152 stores the model generated by learning in the model information storage unit 141.

[0075] The learning unit 152 performs learning processing. The learning unit 152 performs various types of learning. The learning unit 152 learns various types of information based on the information acquired by the acquisition unit 131. The learning unit 152 learns (generates) a model. The learning unit 152 learns various types of information such as the model. The learning unit 152 generates a model through learning. The learning unit 152 learns the model using various machine learning techniques. For example, the learning unit 152 learns the parameters of the model (network). The learning unit 152 learns the model using various machine learning techniques.

[0076] The learning unit 152 generates various learning models such as model M1. The learning unit 152 learns the network parameters. For example, the learning unit 152 learns the network parameters of various learning models such as model M1. The learning unit 152 generates various learning models such as model M1 by performing learning processing using the learning data stored in the model information storage unit 141. For example, the learning unit 152 generates a model used for text generation. The learning unit 152 generates various learning models such as model M1 by learning the network parameters of various learning models such as model M1.

[0077] The learning unit 152 performs learning processing based on the learning data (training data) stored in the model information storage unit 141. The learning unit 152 generates various learning models such as model M1 by performing learning processing using the learning data stored in the model information storage unit 141. For example, the learning unit 152 learns model M1, which is a text generation model that learns the characteristics of the relationship between character information and strings with high importance in that character information. The learning unit 152 learns model M1 that extracts character information from the information to be introduced and outputs the target character information. The learning unit 152 learns model M1 that extracts character information with high importance from the information to be introduced and outputs the target character information.

[0078] For example, the learning unit 152 trains model M1 using training data that associates the information to be introduced with the correct answer information, which is the text that would be desirable to be output when the information to be introduced is input to model M1. The correct answer information may also be text (summon word) that is appropriate as input to model M2. For example, the correct answer information may also be text that generates a desirable image when input to model M2. For example, the correct answer information may also be text that generates a desirable image when input to model M2 as an image corresponding to the information to be introduced. In other words, the correct answer information is text that is appropriate as input information to an image generation model.

[0079] For example, the learning unit 152 performs learning processing using methods such as backpropagation so that the character information (text) output by model M1 approaches the correct information associated with the information to be introduced (input information) input to model M1. For example, the learning unit 152 performs learning processing so that the character information (text) output by model M1, which is input information such as text contained in a book, approaches the correct information associated with that input information.

[0080] For example, the learning unit 152 adjusts the values ​​of the weights (i.e., connection coefficients) that are considered when values ​​are transmitted between nodes during the learning process. In this way, the learning unit 152 learns model M1 by processing such as backpropagation to correct the parameters (connection coefficients) so that the error between the output of model M1 and the correct information corresponding to the input is reduced. For example, the learning unit 152 generates model M1 by processing such as backpropagation to minimize a predetermined loss function. This allows the learning unit 152 to perform a learning process to learn the parameters of model M1.

[0081] The model training method is not limited to the methods described above, and any known technique can be applied. Furthermore, the generation of each model may be performed using various conventional machine learning techniques as appropriate. For example, model generation may be performed using supervised learning machine learning techniques such as SVM (Support Vector Machine). Alternatively, model generation may be performed using unsupervised learning machine learning techniques. For example, model generation may be performed using deep learning techniques. For example, model generation may be performed using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network) as appropriate. The above description of model generation is illustrative, and model generation may be performed using a training method appropriately selected according to the available information. In other words, the training unit 152 may generate model M1 by any method as long as it can train model M1 to output information corresponding to the correct answer information when input information included in the training data is input.

[0082] As described above, the learning method used by the learning unit 152 is not particularly limited, but for example, learning data may be prepared by linking data (input information) with correct answer information (output information), and this learning data may be input into a computational model based on a multilayer neural network for learning. Alternatively, methods based on DNNs such as CNNs and 3D-CNNs may be used. When dealing with time-series data such as audio, the learning unit 152 may use methods based on recurrent neural networks (RNNs) or LSTMs (Long Short-Term Memory units), which are extensions of RNNs.

[0083] (First generation unit 153) The first generation unit 153 generates various information. The first generation unit 153 generates various information based on the information acquired by the acquisition unit 151. The first generation unit 153 generates various information based on the information stored in the storage unit 14. The first generation unit 153 generates various information based on the information stored in the model information storage unit 141, the generation information storage unit 142, the user information storage unit 143, etc. The first generation unit 153 performs a decision process to determine various information. The first generation unit 153 performs an estimation process to estimate various information. The first generation unit 153 performs a decision extraction process to extract various information. The first generation unit 153 performs a selection process to select various information.

[0084] The first generation unit 153 generates target character information, which is character information used for image generation, based on the information to be introduced. The first generation unit 153 generates target character information by extracting character information from the information to be introduced. The first generation unit 153 generates target character information by extracting character information of high importance from the information to be introduced.

[0085] The first generation unit 153 generates target character information using a text generation model, which is a learning model that has learned the characteristics of the relationship between character information and strings of high importance in that character information. When character information is input, the first generation unit 153 generates target character information using a text generation model that outputs a string corresponding to that character information. The first generation unit 153 inputs the information to be introduced into the text generation model and generates target character information using the output information output by the text generation model.

[0086] (Second generation unit 154) The second generation unit 154 generates various types of information. The second generation unit 154 generates various types of information based on the information acquired by the acquisition unit 151. The second generation unit 154 generates various types of information based on the information stored in the storage unit 14. The second generation unit 154 generates various types of information based on the information generated by the first generation unit 153. The second generation unit 154 generates various types of information based on the information stored in the model information storage unit 141, the generation information storage unit 142, the user information storage unit 143, etc. The second generation unit 154 performs a decision process to determine various types of information. The second generation unit 154 performs an estimation process to estimate various types of information. The second generation unit 154 performs a decision extraction process to extract various types of information. The second generation unit 154 performs a selection process to select various types of information.

[0087] The second generation unit 154 generates an introductory image, which is an image that introduces the subject of introduction, from the target text information, using an image generation model that is a trained model that has been trained to generate images from text information. The second generation unit 154 generates an introductory image, which is an image generation model that outputs an image corresponding to the text information, when text information is input. The second generation unit 154 generates an introductory image that introduces the contents of the book. The second generation unit 154 generates an introductory image that introduces the contents of the text contained in the book. The second generation unit 154 generates content that includes the introductory image. The second generation unit 154 generates content that promotes the sale of the subject of introduction.

[0088] The second generation unit 154 executes a process to generate content to be provided to the user. The second generation unit 154 generates content to be displayed on the screen (output unit 13). The second generation unit 154 generates content using various conventional video generation technologies as appropriate. The second generation unit 154 uses the image of the subject to be introduced to generate video content about that subject. For example, the second generation unit 154 generates video content of the subject to be introduced using various technologies such as Java (registered trademark) as appropriate. The second generation unit 154 may also generate video content of the subject to be introduced based on CSS, JavaScript (registered trademark), or HTML format. Furthermore, for example, the second generation unit 154 may generate video content of the subject to be introduced in various formats such as JPEG (Joint Photographic Experts Group), GIF (Graphics Interchange Format), or PNG (Portable Network Graphics).

[0089] (Display section 155) The display unit 155 functions as a provider unit that provides information such as images and content generated by the second generation unit 154. The display unit 155 displays various types of information. For example, the transmission unit 156 displays various types of information according to user operations input by the input unit 12.

[0090] For example, the display unit 155 displays various information via the output unit 13. The display unit 155 displays various information based on the information acquired by the acquisition unit 151. The display unit 155 displays various information based on the information stored in the storage unit 14. The display unit 155 displays various information based on the information stored in the model information storage unit 141, the generation information storage unit 142, the user information storage unit 143, etc. The display unit 155 displays various information generated by the first generation unit 153 and the second generation unit 154.

[0091] The display unit 155 provides an introductory image generated by the second generation unit 154. The display unit 155 provides content including the introductory image. The display unit 155 provides content to promote sales of the product being introduced.

[0092] The display unit 155 displays an introductory image. The display unit 155 displays content including the introductory image. The display unit 155 displays content to promote sales of the product being introduced.

[0093] (Transmitter 156) The transmission unit 156 functions as a provider unit that provides information such as images and content generated by the second generation unit 154. The transmission unit 156 transmits various types of information. For example, the transmission unit 156 transmits various types of information to an external information processing device in accordance with user operations input by the input unit 12. The transmission unit 156 also transmits request information to an external information processing device that requests various types of information from the external information processing device in response to user operations.

[0094] The transmitting unit 156 provides the introductory image generated by the second generating unit 154. The transmitting unit 156 provides content including the introductory image. The transmitting unit 156 provides content to promote sales of the product being introduced.

[0095] The transmitting unit 156 transmits the promotional image to an external device. The transmitting unit 156 transmits content including the promotional image. The transmitting unit 156 transmits content to promote sales of the product being promoted.

[0096] The transmitting unit 156 transmits request information to the server device 50 requesting information. The transmitting unit 156 transmits request information requesting content delivery. The transmitting unit 156 transmits user action information to the server device 50. The transmitting unit 156 transmits action information indicating user operations.

[0097] Furthermore, if the information processing and other operations performed by the control unit 15 described above are carried out by a predetermined application, each part of the control unit 15 may be implemented by, for example, the predetermined application. For example, the information processing and other operations performed by the control unit 15 may be implemented by control information including JavaScript®. Also, if the information processing and other operations described above are carried out by a dedicated application, the control unit 15 may have, for example, an application control unit that controls a predetermined application (e.g., an image generation application) or a dedicated application.

[0098] [3. Information Processing Flow] Next, the procedure for information processing by the terminal device 10 according to this embodiment will be explained using Figure 5. Figure 5 is a flowchart showing an example of information processing according to this embodiment.

[0099] As shown in Figure 5, the terminal device 10 acquires information about the subject to be introduced for image generation (step S101). Then, based on the information about the subject to be introduced, the terminal device 10 generates target character information, which is character information used for image generation (step S102). Then, using an image generation model, which is a trained model that has been trained to generate images from character information, the terminal device 10 generates an introduction image, which is an image introducing the subject to be introduced, from the target character information (step S103).

[0100] [4. Effects] As described above, the information processing device according to the embodiment (terminal device 10 in the embodiment) includes an acquisition unit (acquisition unit 151 in the embodiment), a first generation unit (first generation unit 153 in the embodiment), and a second generation unit (second generation unit 154 in the embodiment). The acquisition unit acquires information about the subject to be introduced, which is the subject to be introduced for image generation. The first generation unit generates subject character information, which is character information used for image generation, based on the information about the subject to be introduced. The second generation unit uses an image generation model, which is a learning model that has been trained to generate images from character information, to generate an introduction image, which is an image introducing the subject to be introduced, from the subject character information.

[0101] Thus, the information processing device according to the embodiment can generate appropriate images by generating target character information used for image generation based on target information relating to the target of image generation, and by generating an introductory image that introduces the target from the target character information using an image generation model.

[0102] Furthermore, in the information processing device according to the embodiment, the second generation unit generates an introductory image using an image generation model that outputs an image corresponding to the character information when character information is input.

[0103] Thus, the information processing device according to the embodiment can generate appropriate images by generating introductory images using an image generation model that outputs an image corresponding to the character information when character information is input.

[0104] Furthermore, in the information processing apparatus according to the embodiment, the acquisition unit acquires information about books to be introduced.

[0105] Thus, the information processing device according to this embodiment can generate appropriate images by generating an image of a book based on information about the book to be introduced.

[0106] Furthermore, in the information processing apparatus according to the embodiment, the acquisition unit acquires the information to be introduced, which is text contained in a book.

[0107] Thus, the information processing device according to this embodiment can generate appropriate images by generating introductory images of books based on the introductory information, which is the text contained in the books.

[0108] Furthermore, in the information processing apparatus according to the embodiment, the first generation unit generates target character information by extracting character information from the information to be introduced.

[0109] Thus, the information processing device according to this embodiment can generate appropriate images by extracting character information from the information to be introduced, thereby generating target character information.

[0110] Furthermore, in the information processing apparatus according to the embodiment, the first generation unit generates target character information by extracting character information of high importance from the information to be introduced.

[0111] Thus, the information processing device according to this embodiment can generate appropriate images by extracting highly important character information from the information to be introduced, thereby generating target character information.

[0112] Furthermore, in the information processing apparatus according to the embodiment, the first generation unit generates target character information using a text generation model, which is a learning model that has learned the characteristics of the relationship between character information and strings of high importance in said character information.

[0113] Thus, the information processing device according to the embodiment can generate appropriate images by generating target character information using a text generation model, which is a learning model that has learned the characteristics of the relationship between character information and strings of high importance in said character information.

[0114] Furthermore, in the information processing apparatus according to the embodiment, the first generation unit generates target character information using a text generation model that outputs a string corresponding to the character information when character information is input.

[0115] Thus, the information processing device according to the embodiment can generate an appropriate image by generating target character information using a text generation model that outputs a string corresponding to the character information when character information is input.

[0116] Furthermore, in the information processing apparatus according to the embodiment, the first generation unit inputs the information to be introduced into a text generation model and generates target character information using the output information output by the text generation model.

[0117] Thus, the information processing device according to this embodiment can generate an appropriate image by inputting the information to be introduced into a text generation model and generating target character information using the output information output by the text generation model.

[0118] Furthermore, in the information processing device according to the embodiment, the second generation unit generates an introductory image that introduces the contents of the book.

[0119] Thus, the information processing device according to this embodiment can generate appropriate images by generating introductory images that introduce the contents of a book.

[0120] Furthermore, in the information processing apparatus according to the embodiment, the second generation unit generates an introductory image that introduces the content of the text contained in the book.

[0121] Thus, the information processing device according to this embodiment can generate appropriate images by generating introductory images that introduce the content of the text contained in the book.

[0122] Furthermore, the information processing device according to the embodiment includes a providing unit (a display unit 155 or a transmission unit 156 in the embodiment). The providing unit provides the introductory image generated by the second generation unit.

[0123] Thus, the information processing device according to this embodiment can provide information about appropriately generated images by providing the generated introductory images.

[0124] Furthermore, in the information processing device according to this embodiment, the providing unit transmits the introductory image to an external device.

[0125] Thus, the information processing device according to this embodiment can provide information about appropriately generated images by transmitting the featured images to an external device.

[0126] Furthermore, in the information processing device according to this embodiment, the providing unit displays an introductory image.

[0127] Thus, the information processing device according to this embodiment can provide information about appropriately generated images by displaying introductory images.

[0128] Furthermore, in the information processing device according to the embodiment, the providing unit provides content including introductory images.

[0129] Thus, the information processing device according to this embodiment can provide information about appropriately generated images by providing content including introductory images.

[0130] Furthermore, in the information processing device according to the embodiment, the provisioning unit provides content to promote the sale of the product being introduced.

[0131] Thus, the information processing device according to this embodiment can provide information about appropriately generated images by providing content that promotes the sale of the target product.

[0132] [5. Program] The processing performed by the terminal device 10 and server device 50 described above is realized by the information processing program according to the present invention. For example, the first generation unit 153 and the second generation unit 154 of the terminal device 10 are realized by the CPU, MPU, etc. of the terminal device 10, which executes information processing procedures related to the information processing program, for example, an image generation application, using RAM as a working area.

[0133] Furthermore, the processing performed by the terminal device 10 and server device 50 according to this application does not necessarily have to be entirely implemented by an information processing program. For example, information outside the terminal device 10 may be obtained by the OS (Operating System) of the terminal device 10. In other words, the information processing program itself may not execute the processing performed by the terminal device 10 as described above, but rather may implement the processing of the terminal device 10 as described above by receiving data obtained by the OS (for example, data used to display (play) content such as images).

[0134] [6. Hardware Configuration] The information processing device, such as the terminal device 10 described above, is implemented by a computer 1000 having a configuration such as that shown in Figure 6. Figure 6 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device. The computer 1000 has a CPU 1100, RAM 1200, ROM (Read Only Memory) 1300, HDD (Hard Disk Drive) 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0135] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, controlling various components. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0136] The HDD1400 stores programs executed by the CPU1100, as well as data used by such programs. The communication interface1500 receives data from other devices via a predetermined network N and sends it to the CPU1100, and transmits data generated by the CPU1100 to other devices via the predetermined network N.

[0137] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the generated data to output devices via the input / output interface 1600.

[0138] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0139] For example, when the computer 1000 functions as a terminal device 10 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 15 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined network N.

[0140] Although embodiments of the present application have been described in detail based on the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure lines of the invention.

[0141] [7. Other] Furthermore, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0142] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0143] Furthermore, the processes described in each of the embodiments described above can be combined as appropriate, provided that the processing content is not contradictory.

[0144] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit." For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of Symbols]

[0145] 1. Information Processing System 10. Terminal device (information processing device) 14 Storage section 141 Model Information Storage Unit 142 Generation information storage unit 143 User Information Storage Unit 15 Control Unit 151 Acquisition Department 152 Learning Department 153 1st generation part 154 Second generation part 155 Display section (provider section) 156 Transmitting Section (Providing Section) 50 Server Devices N Network

Claims

1. An acquisition unit that acquires information about the subject to be introduced for image generation, A first generation unit generates target character information, which is character information used for image generation, based on the aforementioned target information, A second generation unit uses an image generation model, which is a learning model trained to generate images from text information, to generate an introductory image that introduces the subject from the target text information, determines an art style that suits the user's preferences based on the category of the subject and the user to whom the introductory image is provided, and converts the art style of the introductory image to the determined art style. An information processing device characterized by comprising:

2. The second generation unit is, When text information is input, the introductory image is generated using the image generation model that outputs the image corresponding to the text information. The information processing apparatus according to feature 1.

3. The acquisition unit is, Obtain the aforementioned information regarding the books that are to be introduced. The information processing apparatus according to feature 2.

4. The acquisition unit is, The aforementioned information to be introduced is obtained from the text contained in the aforementioned book. The information processing apparatus according to claim 3.

5. The first generation unit is, By extracting text information from the aforementioned target information, the target text information is generated. The information processing apparatus according to feature 4.

6. The first generation unit is, By extracting the most important textual information from the aforementioned information to be introduced, the target textual information is generated. The information processing apparatus according to feature 5.

7. The first generation unit is, The target character information is generated using a text generation model, which is a learning model that has learned the characteristics of the relationship between character information and strings of high importance within that character information. The information processing apparatus according to feature 4.

8. The first generation unit is, When character information is input, the target character information is generated using the text generation model that outputs the string corresponding to the character information. The information processing apparatus according to feature 7.

9. The first generation unit is, The aforementioned target information is input to the text generation model, and the output information output by the text generation model is used to generate the target character information. The information processing apparatus according to feature 8.

10. The second generation unit is, Generate the introductory image that introduces the contents of the aforementioned book. The information processing apparatus according to claim 3.

11. The second generation unit is, The introductory image is generated to show the content of the text contained in the aforementioned book. The information processing apparatus according to feature 4.

12. A providing unit that provides the introductory image generated by the second generation unit. The information processing apparatus according to claim 1, characterized by comprising:

13. The aforementioned supply unit is, The aforementioned introductory image is transmitted to an external device. The information processing apparatus according to feature 12.

14. The aforementioned supply unit is, Display the aforementioned introductory image. The information processing apparatus according to feature 12.

15. The aforementioned supply unit is, Content including the aforementioned introductory image is provided. The information processing apparatus according to feature 12.

16. The aforementioned supply unit is, The content described above is provided to promote sales of the items introduced. The information processing apparatus according to feature 15.

17. A method of information processing performed by a computer, The process involves obtaining information about the subject to be introduced for image generation, and A first generation step generates target character information, which is character information used for image generation, based on the aforementioned information to be introduced. A second generation step involves using an image generation model, which is a trained model that has been trained to generate images from text information, to generate an introductory image that introduces the subject from the target text information, determining an art style that suits the user's preferences based on the category of the subject to be introduced and the user to whom the introductory image is provided, and converting the art style of the introductory image to the determined art style. An information processing method characterized by including

18. Procedure for obtaining information about the subject to be introduced for image generation, A first generation procedure for generating target character information, which is character information used for image generation, based on the aforementioned target information, A second generation procedure involves using an image generation model, which is a trained model that has been trained to generate images from text information, to generate an introductory image that introduces the subject from the target text information, determining an art style that suits the user's preferences based on the category of the subject to be introduced and the user to whom the introductory image is provided, and converting the art style of the introductory image to the determined art style. An information processing program characterized by causing a computer to execute it.

Images