Information processing apparatus, method for controlling information processing apparatus, and storage medium

Abstract

To appropriately generate a unified design expressing an impression intended by a user by combining a plurality of pieces of merchandise.SOLUTION: The information processing apparatus includes a designation unit that designates a design element to be reflected in one or more products for which a design is to be generated and a creation condition for creating the one or more products, and a generation unit that generates a design of the one or more products by changing a color arrangement of the design element such that at least one color having a hue angle different from any color of the color arrangement included in the design element is included, based on the design element and the creation condition designated by the designation unit.SELECTED DRAWING: Figure 9

Description

[Technical Field]

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

[0002] A method has been proposed for generating a poster by preparing a template that stores information such as the shape or arrangement of images, text, graphics, etc. that make up the poster, and automatically arranging the images, text, graphics, etc. according to the template. Patent Document 1 discloses a technology for generating a poster by selecting templates in order of smallest difference between the impression evaluation value of the template and the impression evaluation value of the image. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2017-059123 Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, a template with a small difference between the impression evaluation value of the template and the impression evaluation value of the image is selected, but no consideration is given to generating a poster that expresses the impression intended by the user. Furthermore, no consideration is given to generating a design that forms a brand by combining multiple products, not just a single product such as a poster. There is a demand for appropriately generating a unified design that expresses the impression intended by the user by combining multiple products. [Means for solving the problem]

[0005] The information processing device according to the present disclosure is characterized by comprising: a designation means for specifying design elements to be reflected in one or more commercial products for which a design is to be generated and creation conditions for creating the one or more commercial products; and a generation means for generating a design for the one or more commercial products by changing the color scheme of the design elements based on the design elements and creation conditions specified by the designation means so that the design elements include at least one color with a different hue angle than any of the colors in the color scheme included in the design elements. [Effects of the Invention]

[0006] According to the technology of the present disclosure, it is possible to appropriately generate a unified design that expresses the impression intended by the user by combining multiple commercial products. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 2 is a block diagram showing the hardware configuration of a product generation device. [Figure 2] Software block diagram of the product creation application. [Figure 3] A diagram explaining a skeleton. [Figure 4] FIG. 10 is a diagram illustrating a color scheme pattern. [Figure 5] FIG. 10 is a diagram showing a display screen provided by a commercial material creation application. [Figure 6] FIG. 10 is a diagram showing a display screen provided by a commercial material creation application. [Figure 7] 10 is a flowchart showing a poster generation process illustrating a process for quantifying a poster impression. [Figure 8] FIG. 1 is a diagram illustrating subjective evaluation of posters. [Figure 9] 10 is a flowchart showing a product generation process. [Figure 10] FIG. 10 is a diagram illustrating a color scheme list. [Figure 11] FIG. 4 is a diagram illustrating a coloration pattern acquisition unit. [Figure 12] FIG. 10 is a diagram illustrating a subjective evaluation of color scheme patterns. [Figure 13]FIG. 10 is a diagram illustrating a skeleton selection method. [Figure 14] 10A and 10B are diagrams illustrating a method for selecting a color scheme and a font. [Figure 15] FIG. 2 is a software block diagram illustrating the layout unit in detail. [Figure 16] 10 is a flowchart showing a layout process. [Figure 17] FIG. 4 is a diagram for explaining input to a layout section. [Figure 18] FIG. 4 is a diagram for explaining the operation of a layout unit. [Figure 19] FIG. 10 is a diagram showing a display screen provided by a commercial material creation application. [Figure 20] Software block diagram of the product creation application. [Figure 21] 10 is a flowchart showing a product generation process. [Figure 22] FIG. 3 is a diagram illustrating a combination generation unit. [Figure 23] FIG. 3 is a diagram illustrating a combination generation unit. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. Note that the following embodiments do not limit the present disclosure, and not all combinations of features described in the embodiments are necessarily essential to the solutions of the present disclosure. Note that identical components will be described with the same reference numerals. Furthermore, each process (step) in a flowchart will be indicated with a reference numeral beginning with "S."

[0009] In this embodiment, "merchandise" refers to printed matter such as posters, pamphlets, store menus, postcards, etc., and is, for example, the design of advertising media for users.

[0010] In this embodiment, a "brand" refers to a design that expresses the identity (corporate philosophy, vision, code of conduct, or distinctive features) of a company or store. To gain widespread recognition for a brand, it is necessary to convey a message to users through a design with a consistent worldview. A unified design with a consistent worldview is crucial for brand recognition. To achieve this, it is necessary to create a unified design across all user-facing points of contact, such as product packaging, store design, and promotional materials (websites, brochures, posters, nouns, postcards). A unified design requires the inclusion of similar design elements across multiple products. Examples of design elements include logos (symbol marks), fonts, patterns, and colors. Including these design elements across multiple products creates a sense of unified design, allowing users to recognize a consistent worldview. Furthermore, a brand can be expressed by combining multiple products. For example, a brochure and a poster may have different background colors, but combining the brochure and poster creates a design that expresses the brand. Expressing a brand through the combination of multiple products broadens the scope of expression, and seasonal designs can be created as series.

[0011] In this embodiment, an example of automatically generating a design for multiple products that has a unified look and expresses the user's intended brand impression by combining multiple products will be described. This enables even a user without design knowledge to generate multiple products to raise brand awareness.

[0012] [First embodiment] In this embodiment, a method for automatically generating multiple commercial materials by running an application (hereinafter also referred to as "app") for creating commercial materials on a commercial material generation device will be described as an example. In the following description, unless otherwise specified, "image" includes still images captured by a camera, frame images extracted from a video, and illustrations created with a paint tool or the like.

[0013] 1 is a block diagram showing the hardware configuration of a product material generation device 100. The product material generation device 100 is an information processing device, such as a personal computer (hereinafter referred to as a "PC"), a tablet terminal, or a smartphone. In this embodiment, the product material generation device is described as a PC. The product material generation device 100 includes a CPU 101, a ROM 102, a RAM 103, an HDD 104, a display 105, a keyboard 106, a pointing device 107, a data communication unit 108, and a GPU 109.

[0014] A CPU (Central Processing Unit) 101 comprehensively controls the product material generation device 100, and realizes the operation of this embodiment by, for example, reading a program stored in a ROM 102 into a RAM 103 and executing it. Although FIG. 1 shows one CPU, the device may be configured with multiple CPUs.

[0015] The ROM 102 is a general-purpose ROM and stores, for example, a program executed by the CPU 101. The RAM 103 is a general-purpose RAM and is used, for example, as a working memory for temporarily storing various pieces of information when the CPU 101 executes a program.

[0016] The HDD (Hard Disk Drive) 104 is a storage medium (storage unit) for storing image files, a database for holding processing results such as image analysis, and skeletons used by a commercial material creation application. The HDD 104 is merely an example and is not limited to this. The storage medium may be a solid state drive (SSD), flash memory, cloud storage, or the like.

[0017] The display 105 is a display device that displays to the user a user interface screen (UI screen) of this embodiment and multiple electronic commercial materials as layout results of image data (hereinafter also referred to as "images"). The keyboard 106 and pointing device 107 accept instructions and operations from the user. In this embodiment, the display 105, keyboard 106, and pointing device 107 are separate entities, but the display 105, keyboard 106, and pointing device 107 may be integrated into a touch panel equipped with a touch sensor function.

[0018] The keyboard 106 is used, for example, when a user inputs the generation conditions for one or more products to be created on the UI displayed on the display 105. The pointing device 107 is used, for example, when a user clicks a button on the UI displayed on the display 105. The data communication unit 108 communicates with external devices via a wired or wireless network. For example, the data communication unit 108 transmits data laid out using an automatic layout function to a printer or server that can communicate with the product generation device 100. The GPU (Graphics Processing Unit) 109 is a processor capable of high-speed data processing through parallel processing. The CPU 101 and GPU 109 can cooperate to perform high-speed calculations. The data bus 110 connects the blocks in FIG. 1 to each other so that they can communicate with each other. Note that the configuration shown in FIG. 1 is merely an example and is not limited thereto. For example, the product generation device 100 may not have the display 105 and may display the UI on an external display.

[0019] The commercial material creation application in this embodiment is stored in HDD 104. The commercial material creation application is started by the user performing an operation such as clicking or double-clicking the application icon displayed on display 105 with pointing device 107.

[0020] 2 is a software block diagram of a commercial material creation application. The commercial material creation application includes a creation condition specification unit 201, a text specification unit 202, an image specification unit 203, a design element specification unit 204, a key design specification unit 205, a generated commercial material display control unit 206, and a commercial material creation unit 210. The commercial material creation unit 210 includes an image acquisition unit 211, an image analysis unit 212, a skeleton acquisition unit 213, a design element acquisition unit 214, a color scheme pattern acquisition unit 215, a skeleton selection unit 216, a color scheme pattern selection unit 217, a picture selection unit 218, and a logo selection unit 219. The commercial material creation unit 210 further includes a font selection unit 220, a layout unit 221, an impression estimation unit 222, and a commercial material selection unit 223.

[0021] When the merchandise creation application is installed in merchandise creation device 100, a startup icon is displayed on the top screen (desktop) of the OS (operating system) running on merchandise creation device 100. When the user operates (e.g., double-clicks) the startup icon displayed on display 105 with pointing device 107, the following operation is executed: The merchandise creation application program stored in HDD 104 is loaded into RAM 103 and executed by CPU 101, and the merchandise creation application is launched.

[0022] The above-described commercial material creation application includes program modules corresponding to the components shown in Fig. 2. CPU 101 executes each program module, causing CPU 101 to function as each component shown in Fig. 2. The following describes each component shown in Fig. 2, explaining the various processes executed by each component. Fig. 2 also shows a software block diagram of a commercial material generation unit 210 that executes the automatic commercial material creation function.

[0023] The creation condition specification unit 201 specifies product creation conditions to the product generation unit 210 in response to UI operations using the pointing device 107. In this embodiment, the product creation conditions include one or more product types and usage categories to be created, the number of colors to be added, and whether or not to generate different backgrounds. The product size is linked to the product type. Furthermore, depending on the product, multiple sizes may be available. In this case, the actual width and height values ​​may be specified, or a paper size such as A1 or A2 may be specified. The usage category indicates the purpose for which the product will be used. Specific examples include restaurants, school events, and sales. The number of colors to be added is determined by specifying how many colors to add to the product design to be generated in addition to the color information included in the key design specified in the key design specification unit 205 (described later). The setting for whether or not to generate different backgrounds is determined by specifying whether to use the background information included in the key design specified in the key design specification unit 205 (described later) as is, or whether to use other backgrounds as well. The creation condition specification unit 201 outputs the specified creation conditions to the skeleton acquisition unit 213, the color scheme pattern acquisition unit 215, and the picture selection unit 218. In Fig. 2, an arrow does not point directly from the creation condition specification unit 201 to the picture selection unit 218, but the specified creation conditions are output to the picture selection unit 218 via one or more processing units. In the following explanation, when an arrow does not point directly to the target processing unit, various information is similarly output to the target processing unit via one or more processing units.

[0024] The text specification unit 202 specifies character information to be placed in the commercial material to be generated by UI operations using the keyboard 106. The character information to be placed represents, for example, character strings representing a title, date and time, location, etc. The type of character information may vary depending on the type of commercial material to be created selected by the creation condition specification unit 201. For example, if a poster is selected, a title, subtitle, and main text are specified. If a postcard is selected, a title, address, and contact information are displayed. If multiple commercial materials are selected, overlapping information may be specified individually or collectively. Furthermore, the text specification unit 202 associates each piece of character information with the type of information, such as a title, date and time, or location, and outputs the information to the skeleton acquisition unit 213 and the layout unit 221.

[0025] The image designation unit 203 designates one or more image data stored in the HDD 104 to be placed on one or more commercial materials. The designated images may be designated individually depending on the type of commercial material to be created selected by the creation condition designation unit 201, or a common image may be designated. The image data may be designated based on the structure of a file system containing the image data, such as a device and directory, or may be designated by accompanying information for identifying the image, such as the date and time of shooting, or attribute information. The image designation unit 203 outputs the file path of the designated image to the image acquisition unit 211.

[0026] The design element specification unit 204 specifies design elements to be reflected in one or more commercial materials to be created. The specified design elements include color schemes, patterns, logos, fonts, and target impressions. Furthermore, the design element specification unit 204 specifies the degree of design specification reflection, which indicates the extent to which the specified design elements are reflected in the generated commercial material design. The color schemes, patterns, logos, and fonts are specified as items to be added to the selection list when generating commercial materials. The target impression is the impression that a group of commercial materials consisting of multiple commercial materials is ultimately required to maintain. In this embodiment, a UI operation using the pointing device 107 specifies the intensity of a word expressing an impression, indicating the degree to which that impression is to be conveyed. The design element specification unit 204 outputs the specified design element information to the design element acquisition unit 214. Details of "impression" will be described later. The design element specification unit 204 does not necessarily have to specify a design element. For example, it may be effective only when the user specifies design elements for the commercial material design to be generated. Furthermore, the design specification reflection level does not have to be specified. By specifying design elements and the design specification reflection level, the user can control the generated design.

[0027] The key design specification unit 205 specifies a key design to be reflected in one or more products to be created. A key design is a product design created in advance. The key design may be created in advance using a product creation application or another design creation application. The input format may be raster data such as JPEG or BMP (bitmap). It may also be vector data containing drawing commands. For example, a common PDL such as PDF (Portable Document Format) proposed by Adobe, XPS proposed by Microsoft, or HP-GL / 2 proposed by HP may be used. There may be one or more key designs. The key design specification unit 205 outputs the file path of the specified key design to the design element acquisition unit 214.

[0028] Next, a detailed description will be given of the configuration of the product generation unit 210. Differences in product types can be realized by the skeleton acquisition unit 213 selecting a skeleton of the target product type.

[0029] The image acquisition unit 211 acquires one or more image data items specified by the image designation unit 203 from the HDD 104. The image acquisition unit 211 outputs the acquired image data to the image analysis unit 212. The image acquisition unit 211 also outputs the number of acquired images to the skeleton acquisition unit 213. The images stored in the HDD 104 include still images and frame images extracted from videos. The still images and frame images are acquired from an imaging device such as a digital camera or a smart device. The imaging device may be included in the product generation device 100 or an external device. If the imaging device is an external device, the images are acquired via the data communication unit 108. As another example, the still images may be illustration images created using image editing software or computer graphics images (CG images) created using computer graphics production software. The still images and extracted images may be images acquired from a network or a server via the data communication unit 108. Examples of images acquired from a network or a server include social networking service images (hereinafter referred to as "SNS images"). Furthermore, the program executed by the CPU 101 analyzes data attached to each image to determine the storage source. For example, SNS images may be acquired from an SNS via an application, and the acquisition destination may be managed within the application. Note that the images are not limited to the above-described images, and may be other types of images.

[0030] The image analysis unit 212 performs an analysis process on the image data acquired from the image acquisition unit 211, and acquires information indicating image feature amounts. Specifically, the image analysis unit 212 performs an object recognition process and a main color extraction process, which will be described later, and acquires information indicating image feature amounts of the image data. The image analysis unit 212 also associates the acquired information indicating the image feature amounts with the image data and outputs the image data to the layout unit 221.

[0031] The skeleton acquisition unit 213 acquires, from the HDD 104, one or more skeletons that meet the conditions specified in the creation condition specification unit 201, the text specification unit 202, the design element acquisition unit 214, and the image acquisition unit 211. In this embodiment, a skeleton is information that indicates the arrangement of character strings, images, figures, etc. to be placed on multiple commercial materials.

[0032] FIG. 3 illustrates an example of a poster skeleton for various commercial materials. Three graphic objects 302, 303, and 304, one image object 305, and four text objects 306, 307, 308, and 309, which are objects on which text is to be placed, are arranged on skeleton 301 in FIG. 3(a). Each object is recorded with its position, size, and angle, as well as metadata necessary for generating a poster. FIG. 3(b) illustrates an example of metadata. For example, text objects 306 to 309 store, as metadata attributes, the type of text information to be placed. Here, text object 306 represents the title, text object 307 represents the subtitle, and text objects 307 and 308 represent the main text. Furthermore, graphic objects 302, 303, and 304 store, as metadata attributes, the shape of the graphic and a color scheme number (color scheme ID) indicating the color scheme pattern. Here, the attributes of graphic objects 302 and 303 are rectangular, and the attribute of graphic object 304 is elliptical. Also, graphic object 302 is assigned color scheme number 1, and graphic objects 303 and 304 are assigned color scheme number 2. Here, the color scheme number is information referenced during color assignment, as described below, and different color scheme numbers are assigned different colors. Graphic objects may be drawn in a uniform color. Graphic objects may also be drawn by cutting out a pattern from a background illustration in the shape of a graphic object. Note that the object types and metadata are not limited to these. For example, map objects for placing maps and barcode objects for placing two-dimensional codes or barcodes may be used. Furthermore, metadata for character objects may include metadata indicating the line spacing and character spacing. The metadata may include the purpose of the skeleton and be used to control whether or not to use the skeleton depending on the purpose.

[0033] Skeletons may be managed separately for multiple products. For example, skeletons for multiple products, menu skeletons, postcards, tri-fold leaflets, calendar skeletons, and banner skeletons may be used. Furthermore, skeletons may be managed as groups across multiple products based on their relative placement. For example, a first group of skeletons may be a skeleton group that creates a luxurious feel, with the same skeleton group ID stored in the metadata of each skeleton. This allows the skeleton used to create one product to be used for another product to be determined. As a result, even when designs are created for multiple products, skeletons that can generate a consistent design across multiple products may be managed separately based on the width-to-height ratio. A skeleton with a width-to-height ratio that matches the size of the product specified in the creation condition specification unit 201 can be acquired. Skeletons may be stored on the HDD 104 in, for example, CSV format or in a database format (DB format) such as SQL. The skeleton acquisition unit 213 outputs one or more skeletons acquired from the HDD 104 to the skeleton selection unit 216 .

[0034] The design element acquisition unit 214 acquires design elements to be used in design generation from the design element information specified in the design element specification unit 204 and the key design specified in the key design specification unit 205. The design element acquisition unit 214 extracts color schemes, patterns, logos, fonts, and impression values ​​from the key design file specified in the key design specification unit 205. The extracted impression values ​​are used as the target impression. A specific method for extracting design elements will be described later. The design element acquisition unit 214 merges the design elements extracted from the key design and the design elements specified in the design element specification unit 204. As an example, in the case of target impression values, the average value of the target impression values ​​is used as the target impression value after merging. Furthermore, the target impression value may not be the average value, but may be a maximum or minimum value. If a reflection rate is specified in the design element specification unit 204, merging may be performed according to the reflection rate. Merging in this manner allows the user's intention to be accurately reflected. Specifically, merging is performed using the following formula (1). Merging may also be performed after changing the reflection rate from 0 to 1.

[0035] Post-merging target impression value = reflection degree * specified target impression value + (1 - reflection degree) * extracted target impression value Equation (1) Furthermore, for other design elements such as color schemes, patterns, logos, and fonts, design element acquisition unit 214 creates lists and stores them in a form that allows those specified in design element specification unit 204 to be distinguished from those extracted from the key design. Design element acquisition unit 214 outputs the merged pattern or logo to skeleton acquisition unit 213. Furthermore, design element acquisition unit 214 outputs the merged target impression value to skeleton selection unit 216. Design element acquisition unit 214 outputs the merged target impression value and the reflection degree specified in design element specification unit 204 to color scheme pattern selection unit 217, pattern selection unit 218, logo selection unit 219, font selection unit 220, and product selection unit 223. Design element acquisition unit 214 outputs the merged color scheme list to color scheme pattern acquisition unit 215, and outputs the merged pattern list to pattern selection unit 218. Furthermore, the design element acquisition unit 214 outputs the merged logo list to the logo selection unit 219 and outputs the merged font list to the font selection unit 220.

[0036] The coloration pattern acquisition unit 215 acquires the main color list of the image from the image analysis unit 212, the coloration list from the design element acquisition unit 214, and the number of additional colors from the creation condition specification unit 201, and acquires a coloration pattern accordingly. A coloration pattern is a combination of colors to be used for a commercial material. Furthermore, if a color is specified by the creation condition specification unit 201, the coloration pattern acquisition unit 215 also acquires a coloration pattern including the specified color from the HDD 104 and outputs it to the layout unit 221.

[0037] FIG. 4 is a diagram showing an example of a color scheme table. In this embodiment, a color scheme pattern is represented as a combination of four colors. The color scheme ID column in FIG. 4 is an ID for uniquely identifying a color scheme pattern. When a newly generated color scheme pattern is stored in the table, the color scheme pattern acquisition unit 215 assigns an ID other than color scheme IDs already in use. In FIG. 4, only IDs up to 4 are allowed, but the number of IDs increases by the number of color scheme patterns to be registered. For example, in FIG. 4, color scheme IDs up to 4 are stored. When a new color scheme pattern is stored there, a color scheme ID of 5 is assigned to the new color scheme pattern and the new color scheme pattern is stored in the color scheme table. The Color 1 to Color 4 columns represent colors in RGB order, with each RGB color value ranging from 0 to 255 ((R, G, B) = (0 to 255, 0 to 255, 0 to 255)). Note that, although a color scheme pattern consisting of a combination of four colors is used in this embodiment, other numbers of colors may be used, or multiple colors may be mixed.

[0038] The skeleton selection unit 216 selects, from the skeletons acquired from the skeleton acquisition unit 213, a skeleton that matches the type of product specified by the creation condition specification unit 201 and matches the target impression merged by the design element acquisition unit 214. The skeleton selection unit 216 then outputs the selected skeleton to the layout unit 221. The selected skeleton satisfies the following conditions: one or more skeletons are selected for one type of product, and one or more skeletons that match the target impression are selected for each product type. Because the overall layout of each product is determined by the skeleton, preparing various types of skeletons in advance can increase the variety of each product after generation.

[0039] The color scheme pattern selection unit 217 outputs one or more color scheme patterns that match the target impression merged in the design element acquisition unit 214 from the color scheme patterns acquired in the color scheme pattern acquisition unit 215 to the layout unit 221. The picture selection unit 218 outputs one or more pictures that match the target impression merged in the design element acquisition unit 214 from the picture list merged in the design element acquisition unit 214 to the layout unit 221. The logo selection unit 219 outputs one or more logos that match the target impression merged in the design element acquisition unit 214 from the logo list merged in the design element acquisition unit 214 to the layout unit 221.

[0040] The font selection unit 220 outputs to the layout unit 221 one or more font patterns that match the target impression merged in the design element acquisition unit 214 from the fonts merged in the design element acquisition unit 214. A font pattern is a combination of at least one of a title font, a subtitle font, and a body font.

[0041] The layout unit 221 creates one or more types of product data of at least the number specified by the creation condition specification unit 201 by laying out various data for each of the one or more skeletons obtained from the skeleton selection unit 216. The layout unit 221 arranges text obtained from the text specification unit 202 and image data obtained from the image analysis unit 212 for each skeleton. The layout unit 221 then applies a color pattern obtained from the color pattern selection unit 217 to the arranged image data, and applies a font pattern selected from the font selection unit 220 to the arranged image data. Furthermore, the layout unit 221 arranges a pattern selected from the pattern selection unit 218 in a graphic area for each skeleton. Furthermore, the layout unit 221 arranges a logo selected from the logo selection unit 219 in a graphic area for each skeleton. The layout unit 221 outputs the one or more generated product data to the impression estimation unit 222.

[0042] The impression estimation unit 222 estimates an impression of each of the one or more pieces of product data acquired from the layout unit 221, and links the estimated impression (estimated impression) to each piece of product data. The impression estimation unit 222 then outputs each of the one or more pieces of product data linked with the estimated impression to the product selection unit 223. The product selection unit 223 selects product data based on the result of comparing the target impression merged in the design element acquisition unit 214 with the estimated impressions of the multiple pieces of product data linked with the estimated impressions acquired from the impression estimation unit 222. The selected product data is saved in the HDD 104. The product selection unit 223 outputs each selected product data to the generated product display control unit 206.

[0043] The generated product display control unit 206 outputs a product image to the display 105 according to the product data acquired from the product selection unit 223. The product image is, for example, bitmap data. The generated product display control unit 206 displays the product image on the display 105. The product creation application may be provided with a function that allows the user to edit the layout, color, or shape of images, text, and graphics through additional operations after the generation result is displayed on the display 105, and further change the design to the user's desired design. Furthermore, if the application is equipped with a function that prints the product data stored in the HDD 104 on a printer according to the conditions specified by the creation condition specification unit 201, the user can obtain a printed copy of the created product.

[0044] <<Example of display screen>> 5 is a diagram showing an example of an application launch screen 501 provided by a commercial material creation application. Application launch screen 501 is displayed on display 105. A user specifies a key design, commercial material creation conditions, content (text and images), and design elements via application launch screen 501. Creation condition specification unit 201, text specification unit 202, image specification unit 203, design element specification unit 204, and key design specification unit 205 acquire the user's specifications via this UI screen.

[0045] The title box 502, subtitle box 503, and main text box 504 accept specification of text information to be placed on one or more commercial products. In this embodiment, three types of text information are accepted, but this is not limited to this. For example, additional text information such as location or date and time may be accepted. Furthermore, all specifications do not need to be complete; some boxes may be left blank. The display may also change depending on the specification made in the product specification area 512. For example, if a poster is selected, boxes for specifying the title, subtitle, and main text are displayed. If a postcard is selected, boxes for specifying the title, address, and contact information are displayed. If multiple commercial products are selected, overlapping boxes may be specified individually or collectively. The display may also change depending on the specification made in the category specification area 511. For example, if food and drink is selected, boxes for specifying the address and contact information are displayed. If an event is selected, boxes for specifying the venue and date and time are displayed. The text specification unit 202 acquires the text specification from the user via these UI screens.

[0046] Image designation area 505 is an area that displays an image to be placed in the commercial material. Image 506 represents a thumbnail of the designated image. Add image button 507 is a button for adding an image to be placed. When the user presses add image button 507, image designation unit 203 displays a dialog screen for selecting a file saved in HDD 104 and accepts the user's selection of an image file. A thumbnail of the selected image is then added to image designation area 505. The designated image may be designated individually depending on the type of commercial material to be created selected in creation commercial material designation area 512, which will be described later, or a common image may be designated. Image designation unit 203 acquires the image designation content from the user through this UI screen.

[0047] The key design specification area 508 is an area that displays the key design used in creating a commercial product. The key design 509 shows a thumbnail of the specified key design. The key design is, for example, a design of a commercial product that has already been created. The add key design button 510 is a button for adding a key design to be placed. When the user presses the add key design button 510, the key design specification unit 205 displays a dialog screen for selecting a file saved in the HDD 104 and accepts the user's selection of a key design file. Then, a thumbnail of the selected key design is added to the key design specification area 508. The key design specification unit 205 acquires the key design specification contents from the user through these UI screens.

[0048] The category specification area 511 is composed of a list box that allows the user to set the usage category of the product being created. While the category specification area 511 is optional, its presence allows the user to control the creation of products that fit the category. The product creation area 512 is composed of multiple checkboxes that determine the type of product to be created. This allows the user to arbitrarily select one or more types of product to create. The user can enable or disable the checkbox for the product they want to create by clicking with the pointing device 107. The additional key color count specification area 513 allows the user to specify the number of key colors included in the color scheme selected when creating the product. While the additional key color count specification area 513 is optional, the presence of the additional key color count specification area 513 allows the user to increase the number of key colors in the color scheme used in the created product by increasing the number of additional key colors. This allows the user to control the creation of a wider variety of color variations. The background difference specification area 514 is composed of a checkbox that indicates whether to create different backgrounds. The background difference designation area 514 is not necessary, but if the background difference designation area 514 is present, the user can control whether or not to generate a commercial material with a changed background. The user can enable or disable a checkbox for generating a different background by clicking with the pointing device 107. The creation condition designation unit 201 acquires creation conditions from the user through these UI screens.

[0049] The design element specification area 515 allows the user to specify design elements individually. The design element specification area 515 is composed of the following UI: The color scheme specification box 517 is used to input color information to be used in creating a commercial material. Color 518 shows a thumbnail of the specified color. The add color button 519 is a button for adding a specified color. When the add color button 519 is pressed, a list for specifying a color is displayed by clicking the pointing device 107, and the color can be specified. Furthermore, a UI (not shown) for specifying a color by clicking the pointing device 107 may be further displayed and specified. For example, it is a UI for displaying a color palette listing multiple colors and selecting from the list.

[0050] The design specification box 520 is used to input information about the design to be used in creating the commercial material. In this embodiment, a list for specifying the design is displayed and the design can be specified by clicking with the pointing device 107. Alternatively, the design may be specified by selecting a file in which the design is saved by clicking with the pointing device 107. The file may be an image file (JPEG or BMP (bitmap)), or may be vector data (PDF).

[0051] The logo specification box 521 is used to input information about the logo to be used in creating the product. In this embodiment, a list for specifying a logo is displayed and the logo can be specified by clicking the pointing device 107. Alternatively, the logo can be specified by selecting a file in which the logo is saved by clicking the pointing device 107. The file may be an image file (JPEG or BMP (bitmap)), or vector data (PDF).

[0052] The font specification box 522 is used to input information about the font to be used in generating the commercial material. In this embodiment, a list for specifying a font is displayed and the font can be specified by clicking the pointing device 107. Alternatively, the font may be specified by clicking the pointing device 107 and selecting a file in which the font is saved.

[0053] Design element information radio button 523 is a button that controls whether the settings of each design element are enabled or disabled. By pressing design element information radio button 523 to set it to ON or OFF, the user can set whether the settings of each design element information are enabled or disabled. Figure 5 shows the state in which the color scheme and pattern are enabled.

[0054] Impression sliders (hereinafter also referred to as "impression slider bars" or "impression setting sliders") 524 to 527 are objects that set one target impression factor for one or more products to be created. For example, impression slider 524 is a slider that sets a target impression factor related to luxury. The target impression is set so that the more rightward the impression slider is slid, the more luxurious the product, and the more leftward the impression slider is slid, the less luxurious (cheaper) the product. Furthermore, by combining the target impression factors set by each impression slider, a target impression is set that reflects not only the target impression factor set by one impression slider, but also the target impression factors set by other impression sliders. For example, assume that a user operates the product creation application screen to set impression slider 524 to the right of the center of the slider and impression slider 527 to the left of the center of the slider. In this case, a product with an elegant impression, i.e., a high level of luxury but a low level of weight, is generated. For example, if the user sets the impression slider 524 to the right of the center and the impression slider 527 to the right of the center, a product with a luxurious impression, such as a high level of luxury and dignity, is generated. In this way, by combining the target impression factors indicated by multiple impression sliders, even if the common target impression factor of "luxury" is set, it is possible to set different target impressions, such as a "refined" target impression and a "gorgeous" target impression. In other words, the target impression is determined by multiple factors indicating impressions, but it may also be determined by a single factor indicating impressions. In this embodiment, the leftmost position of the slider is set to -2, and the rightmost position is set to +2, and the value is corrected to an integer value between -2 and +2. These values ​​indicate the impression, -2 is low, -1 is slightly low, 0 is neutral, +1 is slightly high, and +2 is high. The purpose of correcting from -2 to +2 is to match the scale with the estimated impression and facilitate the distance calculation described below. This is merely an example, and values ​​between 0 and 1 may be used for normalization.

[0055] The impression radio button 528 controls whether each target impression setting is enabled or disabled. The user can enable or disable each target impression setting by pressing the impression radio button 528 to set it to ON / OFF. For example, by selecting OFF for the impression radio button 528, that impression is excluded from impression control. For example, a user who wants to create a product with a low dynamism and a subdued feel but has no particular preferences for other impressions can generate a product that is specialized for low dynamism by turning OFF the impression radio buttons 528 other than dynamism. Note that FIG. 5 shows a state in which luxury and familiarity are set to ON and dynamism and profoundness are set to OFF. This allows for highly flexible control, such as using all target impressions for product generation or only some of the target impressions for product generation. Note that the impression radio button 528 may be omitted if setting each slider to the leftmost position is equivalent to not setting each target impression (e.g., if the impression slider 524 is set to the leftmost position and luxury is set to 0). In this case, when the user wishes to invalidate the setting of each target impression, the user can invalidate the setting of each target impression by setting each impression slider to the leftmost position.

[0056] The reflection level slider bar 529 sets the weight of the design element information set above to be reflected in the product generation. The leftmost position indicates a weight of 0%, which means the input brand information is ignored. The rightmost position indicates a weight of 100%, which means the input brand information is always used. For example, if the reflection level is specified as shown in Figure 5, the design element specified reflection level will be 40%, and the frequency or probability that the specified design element will be used in the design element acquisition unit 214 described above will be 40%.

[0057] The design element specification area 515 may be provided with a check box that enables the design element specification area 515. When the user wants to specify a design element individually, the design element may be specified by enabling the check box. If the design element specification area 515 using the check box is disabled, the design element specification reflection rate will be 0%.

[0058] The design element specification area 515 may acquire design elements of the key design specified in the key design specification area 508 and reflect them in the UI. By pressing the key design reflect button 516, the key design is sent from the key design specification unit 205 to the design element acquisition unit 214, and the design elements are extracted. The extracted design elements are shared by the design element specification unit 204 and reflected in the design element specification area 515. In this way, it is easy to specify missing elements or elements to be changed while referring to the design elements of the key design. The design elements that can be specified in the design element specification area 515 shown in FIG. 5 are just an example, and other design-related items may also be included.

[0059] Reset button 530 is a button for resetting each setting information on application launch screen 501. When the user presses OK button 531, creation condition specification unit 201, text specification unit 202, image specification unit 203, design element specification unit 204, and key design specification unit 205 output the contents set on application launch screen 501 to product generation unit 210. At that time, creation condition specification unit 201 acquires the following information: the type of product to be created from creation product specification area 512, the usage category of the multiple products to be created from category specification area 511, the number of additional key colors from additional key color number specification area 513, and information indicating whether background difference generation is enabled from background difference specification area 514.

[0060] The design element specification unit 204 obtains a color from the color scheme specification box 517, a design from the design specification box 520, a logo from the logo specification box 521, and a font from the font specification box 522. The design element specification unit 204 obtains whether the design element information is valid from the design element information radio button 523. The design element specification unit 204 obtains the target impressions of the multiple commercial materials to be created from the impression sliders 524 to 527 and the impression radio button 528. Furthermore, the design element specification unit 204 obtains the reflection degree of the design element information from the reflection degree slider bar 529.

[0061] The text designation unit 202 acquires character information to be placed on the commercial material from the title box 502, subtitle box 503, and body box 504. The image designation unit 203 acquires the file path of the image to be placed on the commercial material from the image designation area 505. The key design designation unit 205 acquires the file path of the key design from the key design designation area 508.

[0062] The creation condition specification unit 201, text specification unit 202, image specification unit 203, design element specification unit 204, and key design specification unit 205 may process the values ​​set on the application startup screen 501. For example, the text specification unit 202 may remove unnecessary blank characters at the beginning or end of the input character information. The design element specification unit 204 may also correct the target impression values ​​specified by the impression sliders 524 to 527.

[0063] FIG. 6 is a diagram showing an example of a product preview screen on which multiple product images generated by the generated product display control unit 206 are displayed on the display 105. FIGS. 6(a) to 6(f) show that the displayed content changes depending on the information specified by the user on the application startup screen 501. When the OK button 531 on the application startup screen 501 is pressed, the screen displayed on the display 105 transitions to a product preview screen 601. Because the product generation unit 210 generates one or more products, multiple product images are displayed as a list on the product preview screen 601. When the user clicks on one product with the pointing device 107, the product is selected. Multiple products may be selected.

[0064] The edit button 602 is a button for editing one or more selected products via a UI that provides an editing function (not shown). The print button 603 is a button for printing the displayed multiple types of products via a printer control UI (not shown). The save button 604 is a button for saving the displayed multiple types of products to the HDD 104 in a predetermined format that can be re-edited. The predetermined format may be CSV format or JSON format. The saved information includes the estimated impression of the products and brand information (logo, design, key color, font).

[0065] The Display Next Candidate button 606 is a button for displaying the generated product images that have not been displayed. The number of products that can be displayed on the product preview screen 601 is determined in advance based on the screen size, and is enabled when the number of products that can be displayed is greater than the number of generated products. When the Display Next Candidate button 606 is pressed, products that are not currently displayed are displayed, and displayed products are no longer displayed. Products that are no longer displayed may be displayed one at a time, or multiple products may be displayed at once. The number of products that are no longer displayed may be set by the user in a designation area (not shown).

[0066] The Display Previous Candidate button 605 is a button for re-displaying products that were no longer displayed when the Display Next Candidate button 606 was pressed. When the Display Next Candidate button 606 is pressed, the Display Previous Candidate button 605 becomes enabled. When the Display Previous Candidate button 605 is pressed, the products that were displayed before the Display Next Candidate button 606 was pressed are displayed, and the products that were displayed when the Display Next Candidate button 606 was pressed are no longer displayed.

[0067] 6(a) to 6(f) are used to explain in detail how the information set by the user on the application launch screen 501 is displayed as different product preview screens. FIG. 6(a) shows an example of a product preview screen on the application launch screen 501 when the following setting information is specified: one type of product to be created, one key design, one additional key color, no content, no design elements, and background differences are disabled. Product images 607 and 608 show examples generated using design elements extracted from the key design specified in the key design specification area 508. The only difference between product images 607 and 608 is the background color. By changing the background color while maintaining the key design, this setting allows the user to appropriately generate a product design that expresses the brand impression intended by the user by combining the set key design with the generated product.

[0068] FIG. 6(b) is a diagram showing an example of a product preview screen for the application launch screen 501 when setting information enables background differences compared to the setting information in FIG. 6(a). FIG. 6(b) shows an example in which the background of the product image 609 is different from that in FIG. 6(a). By enabling background differences, products with many different backgrounds can be generated. This increases the variety of product designs that users can choose from, making it possible to appropriately generate product design combinations that better express the brand impression that best suits the user's intentions.

[0069] FIG. 6(c) shows an example of a preview screen for multiple products in the application startup screen 501 when the setting information has been increased in number of additional key colors compared to the setting information in FIG. 6(a). FIG. 6(c) shows an example in which the number of colors used has increased compared to FIG. 6(a). Color 610, represented by a diagonal line slanting downward to the right, is a color added from the product image 607. Increasing the number of additional key colors increases the number of colors used in a single product, making it possible to create a product with a new brand image. This increases the variety of product designs available to users, making it possible to appropriately create a product design combination that better expresses the brand impression that best suits the user's intentions.

[0070] FIG. 6(d) is a diagram showing an example of a product preview screen when multiple types of products are selected on the app launch screen 501, compared to the setting information in FIG. 6(a). FIG. 6(d) shows an example in which product images 611 and 612 have been added based on the selected product types compared to FIG. 6(a). By selecting multiple types of products, multiple types of products can be generated at once, allowing for the creation of combinations of different product types. This allows for the appropriate creation of a product design that expresses the impression of the brand created by combining multiple product types that the user desires.

[0071] FIG. 6(e) is a diagram showing an example of a product preview screen when content settings have been made to the application startup screen 501 in comparison with the setting information in FIG. 6(a). FIG. 6(e) shows an example in which the title text 614 and image 613 have been changed based on the content set compared to FIG. 6(a). By setting the content, the user can control the content included in the generated product. This allows for the appropriate generation of a product design combination that expresses the brand impression that matches the user's intentions, using the content set by the user.

[0072] FIG. 6(f) is a diagram showing an example of a product preview screen for the application launch screen 501 when design element settings have been made in comparison with the setting information in FIG. 6(a). FIG. 6(f) shows an example in which the shape and color of the illustration 615 and the design of the background pattern 616 have been changed by the design elements that have been set compared with FIG. 6(a). Specifically, the shape of the illustration 615 changes by changing the impression value of the design elements. The color of the illustration 615 changes depending on the color scheme of the design elements. The background pattern 616 changes depending on the design element design. By setting the design elements, the user can control the design of the product to be generated. This allows the user to control the design and appropriately generate a product design combination that expresses the impression of the brand.

[0073] 《Quantifying impressions of multiple products》 Here, a method for quantifying the impressions of multiple commercial products will be described. This is a pre-processing required for the commercial product generation process, which is required for executing the impression estimation process described later in S914 of FIG. 9. In this embodiment, the process for quantifying the impression of a poster will be described as an example. By performing similar processing on other commercial products, impressions can be quantified. Furthermore, for commercial products with similar sizes or uses, the quantification results for one impression may be used to quantify the other impression.

[0074] The process of quantifying the impression of a poster is performed by a vendor or the like who develops the poster creation application during the development stage of the poster creation application. The process of quantifying the impression of a poster may be executed by the merchandise generation device 100, or may be executed by an information processing device different from the merchandise generation device 100. When executed by an information processing device different from the merchandise generation device 100, the process of quantifying the impression of a poster is executed by the CPU of that information processing device.

[0075] The process of quantifying poster impressions quantifies the impressions people have of various posters. At the same time, a correspondence between the poster image and the poster impression is derived. This makes it possible to estimate the impression of the poster from the generated poster image. If the impression can be estimated, it becomes possible to control the impression of the poster by modifying the poster image, or to search for a poster image that has a certain target impression. The poster impression quantification process is performed, for example, in the product material generation device 100 by running an impression learning application for learning the impression of the poster image in advance of the poster generation process.

[0076] Fig. 7 is a flowchart showing the poster impression quantification process. The flowchart shown in Fig. 7 is implemented, for example, by CPU 101 reading a program stored in HDD 104 into RAM 103 and executing it. The poster impression quantification process will be described with reference to Fig. 7.

[0077] In S701, CPU 101 acquires subjective evaluations of impressions of a poster. FIG. 8 illustrates an example of a method for subjectively evaluating impressions of a poster. CPU 101 presents a poster to multiple evaluators and acquires subjective evaluations of the impressions of the poster from the multiple evaluators. Measurement methods such as the Semantic Differential (SD) method or the Likert scale are used. FIG. 8 illustrates an example of a questionnaire using the SD method. Adjective pairs expressing impressions are presented to multiple evaluators, and scores are assigned to the adjective pairs associated with the target poster. After acquiring subjective evaluation results for multiple posters from the multiple evaluators, CPU 101 calculates the average of the responses to each adjective pair and sets the average as a representative score for the corresponding adjective pair. Note that the subjective evaluation method for impressions may be other than the SD method, as long as words expressing impressions and corresponding scores are determined.

[0078] In S702, the CPU 101 performs a factor analysis of the subjective evaluation results acquired by the subjective evaluation acquisition unit. Since the number of adjective pairs increases the number of dimensions and complicates control when the subjective evaluation results are left as they are, it is desirable to reduce the number of dimensions to an efficient level using an analytical method such as principal component analysis or factor analysis. In this embodiment, the description is given assuming that the number of dimensions has been reduced to four factors using factor analysis. Naturally, this number varies depending on the adjective pairs selected for the subjective evaluation or the factor analysis method. Furthermore, the output of the factor analysis is assumed to be standardized. That is, each factor is scaled so that the mean is 0 and the variance is 1 for the poster used in the analysis. This allows the impressions of -2, -1, 0, +1, and +2 specified by the design element specification unit 204 to directly correspond to -2σ, -1σ, the mean value, +1σ, and +2σ for each impression, facilitating the calculation of the distance between the target impression and the estimated impression (described later). In this embodiment, the four factors are luxury, familiarity, dynamism, and solidity, as shown in Figure 5. These are names given for convenience to convey impressions to users through the user interface, and each factor is composed of multiple adjective pairs that interact with each other.

[0079] In S703, the CPU 101 associates poster images with impressions. While it is possible to quantify posters that have undergone subjective evaluation using the method described above, it is also necessary to estimate impressions for posters to be created in the future without subjective evaluation. The association between poster images and impressions can be achieved by learning a model that estimates impressions from poster images, for example, using a deep learning method using a Convolution Neural Network (CNN) or a machine learning method using a decision tree. In this embodiment, the impression learning unit performs supervised deep learning using a CNN, with the poster image as input and four factors as output. That is, a deep learning model is created by learning the subjectively evaluated poster images and the corresponding impressions as correct answers, and an impression is estimated by inputting an unknown poster image into the learning model.

[0080] The deep learning model created above is stored in, for example, HDD 104, and the impression estimation unit 222 loads the deep learning model stored in HDD 104 into RAM 103 and executes it. The impression estimation unit 222 converts the poster data acquired from the layout unit 221 into an image, and estimates the impression of the poster by running the deep learning model loaded in RAM 103 on the CPU 101 or GPU 109. While a deep learning method is used in this embodiment, this is not limiting. For example, when using a machine learning method such as a decision tree, it is also possible to extract feature amounts such as the average brightness value or edge amount of the poster image by image analysis, and create a machine learning model that estimates the impression based on the feature amounts.

[0081] FIG. 9(a) is a flowchart showing a product generation process performed by the product generation unit 210 of the product creation application. As described above, the flowchart shown in FIG. 9(a) is started when the user sets various setting items on the product creation application and presses the OK button. The flowchart shown in FIG. 9(a) is realized, for example, by the CPU 101 reading a program stored in the HDD 104 into the RAM 103 and executing it. In this embodiment, the description will be given assuming that the components shown in FIG. 2, which function when the CPU 101 executes the above-described product creation application, execute the processing. The product generation process will be described with reference to FIG. 9(a).

[0082] In S901, the commercial material creation application displays the application startup screen 501 on the display 105. The user inputs each setting via the UI screen of the application startup screen 501 using the keyboard 106 or the pointing device 107.

[0083] In S902, the creation condition specification unit 201, text specification unit 202, image specification unit 203, design element specification unit 204, and key design specification unit 205 acquire their corresponding settings from the application startup screen 501. The creation condition specification unit 201 acquires information on the type of product to be created, category, number of additional key colors, and whether or not different backgrounds can be generated. The type of product to be created is acquired from the creation product specification area 512. In FIG. 5, two types, banner and postcard, are indicated. The category is acquired from the category specification area 511. In FIG. 5, food and drink is indicated. The number of additional key colors specifies the number of key colors to be added to the product to be created. In FIG. 5, it is indicated that one color is added. The information on whether or not different backgrounds can be generated specifies whether or not the background of the product to be created is changed from the key design. In FIG. 5, it indicates that the background is changed. The text specification unit 202 acquires character information to be placed on multiple products from the title box 502, subtitle box 503, and body box 504. In FIG. 5, the title indicates that "Tittle2Tittle2Tittle2" will be acquired. The subtitle indicates that a space will be acquired. The main text indicates that four lines of "TextTextText" will be acquired. The image designation unit 203 acquires the image specified in the image designation area 505. In FIG. 5, an image of vertical lines will be acquired. The design element designation unit 204 acquires the color scheme, pattern, logo, font, impression, and their reflection degree. The color scheme is acquired from the color specified in the color scheme designation box 517. Furthermore, whether or not the color scheme will be used for product creation is acquired using the design element information radio button 523. In FIG. 5, the color scheme is represented by vertical lines, indicating that it will be used for product creation. The pattern is acquired from the pattern specified in the pattern designation box 520. Furthermore, information on whether or not the pattern will be used for product creation is acquired from the state of the radio button. In FIG. 5, the pattern is a tilted brick pattern, indicating that it will be used for product creation. The logo is acquired from the logo designated in the logo designation box 521. Furthermore, information as to whether or not the logo is to be used for creating a commercial material is acquired from the state of the radio button.In FIG. 5, no logo is specified, indicating that it will not be used in product creation. The font is acquired from the font specification box 522. Furthermore, information indicating whether the font will be used in product creation is acquired from the status of the radio button. In FIG. 5, a Gothic font is specified, but it is indicated that it will not be used in product creation. The impression is acquired from the setting values ​​of impression sliders 524 to 527 as the target impression factor. Furthermore, whether it will be used as the target impression is acquired from impression radio button 528. In FIG. 5, luxury is -1, familiarity is +1, dynamism is -0.8, and profoundness is 0. Furthermore, it is indicated that luxury and familiarity are used as the target impressions, and dynamism and profoundness are not used as the target impressions. The key design specification unit 205 acquires the key design specified in the key design specification area 508. In FIG. 5, key design 509 is acquired.

[0084] In S903, the image acquisition unit 211 acquires image data. Specifically, the image acquisition unit 211 identifies an image file corresponding to an image in the settings acquired in S902. Then, the image data of the identified image file is read from the HDD 104 to the RAM 103.

[0085] In S904, the image analysis unit 212 performs an analysis process on the image data acquired in S903 to acquire information indicating feature amounts. Examples of information indicating feature amounts include meta information stored in the image and information indicating image feature amounts that can be acquired by analyzing the image. This information is used in the object recognition process and primary color extraction process, which are analysis processes. In this embodiment, the object recognition process and primary color extraction process are executed as analysis processes, but are not limited to these. Other analysis processes may also be executed. Furthermore, the process of S904 may be omitted.

[0086] The processing performed by the image analysis unit 212 in S904 is described in detail below. The image analysis unit 212 performs object recognition processing on the image acquired in S903. Here, a known method can be used for the object recognition processing. In the object recognition processing, objects are recognized using a classifier created by deep learning. The classifier outputs a likelihood between 0 and 1 of whether a pixel constituting the image is a pixel constituting each object. If the likelihood of a certain object exceeds a threshold, the classifier recognizes that the object is present in the image. By recognizing object images, the image analysis unit 212 can obtain the type and position of objects such as pets (e.g., dogs or cats), flowers, food, buildings, ornaments, and landmarks. Furthermore, the image analysis unit 212 performs primary color extraction processing on the image acquired in S903. Here, a known method can be used for the primary color extraction processing. In this embodiment, the number of pixels for each pixel value is calculated, and the most frequent value is used as the primary color. If pixel values ​​are used, similar colors such as gradations may be treated as different colors, which may not be optimal as primary colors. The number of pixels grouped into a predetermined color difference range as the same color may be calculated. This allows a primary color to be set taking similar colors into account, and a primary color close to human perception can be extracted. Furthermore, the primary color degree may be calculated using not only the number of pixels but also the saturation and lightness of the extracted pixel values, as well as the color difference between the extracted pixel and its surrounding pixels. Highly saturated colors, bright colors, and dark colors stand out and are therefore easily recognized as primary colors. Furthermore, colors with large color differences from surrounding pixels stand out and are therefore easily recognized as primary colors. Specifically, the primary color degree is calculated so that the higher the saturation, the higher the primary color degree; the further the lightness is from gray, the higher the primary color degree; and the larger the color difference from surrounding pixels, the higher the primary color degree. An example of the calculation formula is shown in Equation (2). If the number of pixels is Pn, the saturation is S, the lightness is L, and the color difference from surrounding pixels is ΔE, then Primary color intensity Mc=Pn*(S+|50-L|+ΔE) Equation (2) The color with the highest calculated primary color degree Mc is extracted as the primary color. This allows for the extraction of a primary color that is closer to human perception. The primary color extraction process may be performed using a classifier created by deep learning, or a clustering method such as K-means. There may be more than one primary color. The extracted primary colors are stored in RAM 103 as a list in a format that indicates that the color scheme was extracted from the image. Figure 10(b) shows a list of color schemes extracted by the image analysis unit 212. The image analysis unit 212 stores the RGB values ​​of the colors and the type of original data in a table format in RAM 103 as "Image 1." If there are multiple images, the type of original data is stored in RAM 103 as "Image 2," indicating which image the color scheme was extracted from.

[0087] In S905, the type of product to be created and the number of products to be created for each product type are determined. The number of product types to be created is the number of product types acquired in S902. In FIG. 5, this number is two. Furthermore, the number of products to be created is a predetermined number for each product type. The number of products may be specified by a setting (not shown) on the application launch screen 501 in FIG. 5. This number of products affects the product generation time and the number of variations. A larger number of products allows for more variations to be generated, but the generation time increases. A smaller number of products reduces the number of variations, but the generation time decreases. The user can specify whether to prioritize the variety of products to be generated or the generation time by specifying this setting on the application launch screen 501 in FIG. 5. This allows the user to control the variety of products to be generated and the generation time. In this embodiment, the number of products is five. That is, in FIG. 5, it is determined that a total of 10 products will be generated: five postcards and five banners. In this embodiment, a product set is a combination of products, with one product selected for each product type. In FIG. 5 , multiple product sets are generated by combining two products, one postcard and one banner. In this embodiment, five products are generated, but other numbers may be used. Creating a larger number of products makes it easier to generate a product set that closely matches the target impression and has high design similarity between the products. Creating a smaller number of products allows for faster generation. The processes of S908 to S915, described below, are repeated for each product type to be created. Furthermore, the processes of S909 to S914 are repeated for each product to be created. In other words, the processes of S909 to S914 are repeated a number of times: (number of product types to be created * number of products to be created). In this embodiment, two product types and five products are generated, so the processes of S909 to S914 are repeated 10 times.

[0088] In S906, the design element acquisition unit 214 acquires design elements to be used in the commercial material to be created. Specifically, the design element acquisition unit 214 extracts design elements from the key design specified by the key design specification unit 205. If the key design is vector data, the color scheme, pattern, logo, and font are extracted from the tag information. For example, if the key design is stored as SVG data (Scalable Vector Graphics data), a large drawing area is extracted as a pattern, and a small drawing area is extracted as a logo. If a font name is present in the text tag area, it is extracted as the font. The color scheme is extracted from the color values ​​included in the tag data. Alternatively, after rasterizing the vector data, the color scheme information may be acquired from the raster data by performing the above-described primary color extraction process. Alternatively, if the key design is raster data, the color scheme, pattern, logo, and font may be acquired after image area separation using a machine learning model such as Deep Learning. The color schemes extracted for each key design are stored in RAM 103 as a color scheme list, the designs as a design list, the logos as a logo list, and the fonts as a font list. Furthermore, the design element acquisition unit 214 acquires the design elements specified by the design element specification unit 204. The acquired color schemes, designs, logos, and fonts are stored in their respective lists. If the actual data of the designs, logos, and fonts stored in the lists has been saved in advance on the HDD 104, they are sequentially read into RAM 103. In the case of raster data, images are extracted from the results of image area separation and sequentially stored in RAM 103. The color scheme list is stored in a format that allows the color schemes extracted from the key design to be distinguished from the color schemes specified by the design element specification unit 204. The color scheme list will be described in detail with reference to FIG. 10. FIG. 10(a) shows the list of color schemes acquired by the design element specification unit 204. The design element acquisition unit 214 stores the RGB values ​​of the colors and the type of original data in a table format in RAM 103 as "design element specification." 10(c) shows the color scheme list acquired from the key design. The design element acquisition unit 214 stores the RGB values ​​of the colors and the type of original data in the RAM 103 in a table format as "Key Design 1."In Figure 10(c), the color scheme extracted as "Key Design 1" is four colors. If there are multiple key designs, the type of original data is set to "Key Design 2," for example, and stored in RAM 103 in a format that indicates which key design the color scheme was extracted from.

[0089] In S907, the coloring pattern acquisition unit 215 acquires a coloring pattern to be used for the commercial material to be created. Fig. 9(b) is a flowchart showing the process of acquiring a coloring pattern by the coloring pattern acquisition unit 215. The coloring pattern acquisition process will be described in detail using Fig. 9(b).

[0090] In S921 of FIG. 9(b), coloration pattern acquisition unit 215 acquires the coloration list shown in FIG. 10(b) from image analysis unit 212 and the coloration list shown in FIG. 10(a) or FIG. 10(c) from design element acquisition unit 214. The coloration list (FIG. 10(b)) acquired from image analysis unit 212 is registered in a new coloration list and stored in RAM 103. This makes it possible to acquire a coloration that matches the image specified by the user. Of the coloration lists acquired from design element acquisition unit 214, the coloration list (FIG. 10(a)) specified by design element specification unit 204 is also registered in the new coloration list. FIG. 10(d) shows the new coloration list. Coloration pattern acquisition unit 215 stores the RGB values ​​of the colors and the type of original data in a table format in RAM 103 as "new colors." The coloration list used in the process of S922 is the coloration list extracted from the key design designated in the key design designation unit 205 (see FIG. 10(c)).

[0091] In S922, the color scheme pattern acquisition unit 215 selects one color scheme from the color scheme list determined in the process of S921 and determines the hue of the color scheme. A specific determination method will be explained using FIG. 11(a). FIG. 11(a) shows a hue wheel, with a hue angle from 0 degrees to 360 degrees divided into 12 representative colors. For example, starting from color 1101, the representative colors are yellow, yellow-green, green, blue-green, blue, blue-purple, purple, red-purple, red, red-orange, orange, and yellow-orange, going clockwise. The hue angle between each hue is calculated, and the color closest to the hue angle of the selected color scheme is determined. The color with the closest hue is set as the hue of the selected color scheme.

[0092] In S923, the coloration pattern acquisition unit 215 determines the hues of the new coloration candidate from the hues of the selected coloration. The new coloration candidate hues are different from the hues of the selected coloration. Specifically, the new coloration candidate hues are the complementary color, the contrasting color close to the complementary color, or the analogous color close to the hues of the selected coloration. In FIG. 11(a), if color 1101 is the hue of the selected coloration, the complementary color is color 1102, the contrasting colors are colors 1103 to 1106, and the analogous colors are colors 1107 to 1108. From the candidate colors 1102 to 1108, the creation condition specification unit 201 determines the number of colors corresponding to the number of additional key colors as the hues of the new coloration candidate hues. In FIG. 5, the number of additional key colors is 1, so one hue is determined for the new coloration candidate hues. The determination method may involve randomly selecting the hues of the new coloration candidate hues. For example, the hue of the new color scheme may be determined by rotating the color wheel clockwise or counterclockwise by a predetermined angle. The predetermined angle may be 30 degrees or 60 degrees. More preferably, the hue is determined based on the target impression value acquired by the design element acquisition unit 214. Specifically, the hue closest to the target impression is determined based on the impressions of the candidate hues. For example, red, red-orange, yellow, and yellow-orange are determined when the dynamism value is high, while blue-purple, blue, and blue-green are determined when the dynamism value is low. Furthermore, orange, yellow-orange, yellow, yellow-green, and green are determined when the affinity value is high, while red-purple, purple, blue-purple, and blue are determined when the affinity value is low. Hues may also be determined based on the target impression and the hue relationship. For example, hues in complementary or contrasting relationships are determined when the dynamism value is high, and similar colors are determined when the dynamism value is low. This allows for the creation of commercial materials for color schemes that match the target impression set by the user.

[0093] In S924, the coloration pattern acquisition unit 215 determines the saturation and lightness based on the colors of the selected coloration and the hue of the new coloration determined in S923. Specifically, the lightness and saturation of the new coloration are set to those of the selected coloration, and the hue is set to the hue of the new coloration. This allows colors with a different hue from the selected coloration but the same lightness and saturation as the selected coloration to be determined as the new coloration. The determined coloration is stored in the new coloration list ( FIG. 10(d) ). Colors with the same lightness and saturation are colors whose lightness and saturation differences between the selected coloration and the determined coloration are within a predetermined range. The determined coloration also includes colors within a range that humans perceive as the same color. For example, colors whose spatial distance ΔE in the CIEL*a*b* color space between the determined coloration and the new coloration is 2.0 or less are also included in the determined coloration. Other thresholds may be used as long as they are within the range that humans perceive as the same color. In addition, the sRGB color gamut may not be able to express the lightness and saturation of colors with the same lightness and saturation. In such cases, the lightness and saturation of the new color scheme may be determined based on the relationship between the hues of the selected color scheme and the new color scheme. This will be explained in detail with reference to FIG. 11(b). FIG. 11(b) shows a plane of lightness and saturation at a certain hue angle in the CIEL*a*b* color space, with color gamut 1109 representing the sRGB color gamut. If the selected color scheme is located at color 1110, the maximum saturation color in the sRGB gamut for the hue of the selected color scheme can be represented as color 1111. Furthermore, the maximum saturation color in the sRGB gamut for the hue of the new color scheme is represented as color 1112. Color 1113 represents a neutral color (L*=50) on the gray axis (a*=0, b*=0) of the sRGB gamut. An example of a method for determining a new color scheme (color 1114) will be explained with reference to FIG. 11(b). First, the method for determining lightness will be explained. Lightness is determined based on the ratio of the lightness difference between color 1113 and color 1111, and the lightness difference between color 1113 and color 1110. Specifically, if the lightness of the selected color scheme (color 1110) is Ls, the lightness of the maximum saturation color (color 1111) in the hue of the selected color scheme is Lsh, and the lightness of the maximum saturation color (color 1112) of the new color scheme is Lnh, then lightness is determined by the following formula (3):

[0094] Lightness of new color scheme = 50 + ((Ls-50)*(Lnh-50) / (Lsh-50)) Equation (3) For example, if the lightness (Lsh) of color 1111 is 70, the lightness (Ls) of color 1110 is 60, and the lightness (Lnh) of color 1112 is 30, then the lightness of color 1114 in the new color scheme will be 40.

[0095] Next, a method for determining saturation will be described. The saturation is determined from the saturation ratio between color 1110 and color 1111 and the saturation of color 1112. Specifically, if the saturation of the selected color scheme (color 1110) is Hs, the saturation of the maximum saturation color (color 1111) in the hue of the selected color scheme is Hsh, and the saturation of the maximum saturation color (color 1112) of the new color scheme is Snh, then the saturation is determined by the following formula (4):

[0096] Saturation of the new color scheme = Snh * (Hs / Hsh) Equation (4) For example, if the saturation (Hsh) of color 1111 is 80, the saturation (Hs) of color 1110 is 50, and the saturation (Snh) of color 1112 is 60, then the saturation of color 1114 is 37.5. By performing the above calculations, it is possible to determine the lightness and saturation of a new color scheme even for hues that do not have the same saturation and lightness. In this embodiment, the new color scheme determined above also includes colors within a predetermined range that humans perceive as the same color. The predetermined range refers, for example, to a spatial distance ΔE in the CIEL*a*b* color space of 2.0 or less. Other thresholds may be used as long as they are within the range within which humans perceive the same colors.

[0097] More preferably, a subjective evaluation may be performed in advance by a human for each hue, and the saturation and lightness that produce the same impression may be determined. The subjective evaluation method will be explained using FIG. 12. FIG. 12 illustrates a subjective evaluation in which a color that gives the same impression as color 1201 is selected from the 3x3 patches on the right. The central patch of the 3x3 patches has the lightness and saturation calculated using the above formula. From the central patch, there are nine patches with increments of +5 and -5 in the lightness direction and +5 and -5 in the saturation direction. A specific example of subjective evaluation is a case in which color 1201 is combined with 12 colors with different hue angles and 12 tones of lightness and saturation represented by the PCCS tone map, for a total of 144 colors, and subjective evaluation is performed for each of the 12 color wheels. Here, PCCS stands for Practical Color Coordinate System. This allows the subjective evaluation to determine the lightness and saturation as values ​​that humans perceive as being the same. This allows for the determination of colors in a new color scheme that appears natural to the human eye.

[0098] In S925, the coloration pattern acquisition unit 215 determines whether new coloration patterns have been determined for all coloration patterns in the coloration list passed to S922. If new coloration patterns have been determined for all coloration patterns, the process proceeds to S926. If new coloration patterns have not been determined for all coloration patterns, the process returns to S922.

[0099] In S926, a color scheme pattern is obtained from the colors in the determined new color scheme list (FIG. 10(d)). If there are any identical colors in the new color scheme list, they are merged to create a unique color. The color scheme pattern is based on the color scheme pattern extracted from the key design. A color stored in the new color scheme list (FIG. 10(d)) is replaced with one color from the color scheme pattern in the color scheme list extracted from the key design (FIG. 10(c)), and stored as a new color scheme pattern in the color scheme pattern list. This makes it possible to obtain a color scheme pattern with a hue different from the key color. FIG. 4 shows the color scheme pattern list obtained in S926. The color scheme pattern obtaining unit 215 stores RGB values ​​of multiple colors in RAM 103 in table format. In FIG. 4, the color scheme pattern extracted from the key design is obtained from the color scheme list (FIG. 10(c)). Specifically, it is the color whose original data in FIG. 10(c) is "Key Design 1." In FIG. 10(c), there are four colors with RGB values ​​of (255,228,1), (223,133,67), (213,151,206), and (169,241,223). In S926, one of these four colors is replaced. In FIG. 4, the color with RGB value (255,228,1) is replaced with the new color scheme list (FIG. 10(d)). That is, the color with RGB value (255,228,1) is replaced with four colors with RGB values ​​of (71,59,133), (157,109,121), (122,43,122), and (1,80,157). This indicates that four new color scheme patterns are obtained. In addition to replacing the first color, other colors included in the color scheme pattern may be changed according to the new color scheme. Specifically, the hue angles of other colors may be changed depending on the hue angle difference between the color before replacement and the new color scheme. An example of a processing method will be described with reference to FIG. 11(c). As explained in FIG. 11(a), FIG. 11(c) shows a color wheel. In FIG. 11(c), the color pattern of the key design is colors 1115 to 1118, and the new color scheme is color 1119. In this case, color 1115 is changed to color 1119. Accordingly, the hue angles of colors 1116 to 1118 are changed.Specifically, since the color 1115 and color 1119 change their hues by one in the clockwise direction, the other colors also change their hue angles by one in the clockwise direction. In FIG. 11(c), color 1116 changes to color 1120, color 1117 changes to color 1121, and color 1118 changes to color 1122. The changed color scheme changes from color 1119 to color 1122 and is stored in the color scheme pattern list. The method of replacing only one color and the method of changing other colors may be performed in parallel. While the above example shows clockwise rotation, counterclockwise rotation is also acceptable. Furthermore, a method of rotating by a predetermined angle may be adopted. Specifically, the predetermined angle may be 30 degrees or 60 degrees. This allows for an increased variety of new color scheme patterns.

[0100] Furthermore, a new color scheme may be added from a pre-stored group of preferred color scheme patterns in accordance with the new color scheme and the color scheme pattern of the key design. If a pre-stored group of color scheme patterns contains the same color as both the new color scheme and at least one color in the color scheme pattern of the key design, that color scheme pattern is stored as a new color scheme pattern in the color scheme pattern list (Figure 4). This allows for the creation of a product with greater variety. Also, if there is no color scheme pattern for the key design, a new color scheme may be added from a pre-stored group of preferred color scheme patterns in accordance with the new color scheme. This allows for the creation of a product even when a key design is not specified. A method of adding colors may also be used. In this case, the number of colors included in one color scheme pattern increases. For example, adding one color to the color scheme pattern table in Figure 4 creates color 5.

[0101] The above describes a method for changing the color scheme pattern by selecting one color from the new color scheme list. However, two or more colors may be replaced. When replacing two or more colors, the colors not to be replaced are determined from the color scheme pattern extracted from the key design. Then, based on the relationship between hues, a color with the optimal hue angle relationship for one of the colors not to be replaced is selected from the new color scheme list (Figure 10(d)). Specifically, the same process as in S923 is performed for one of the colors not to be replaced, and the hue angles of the complementary, contrasting, and analogous colors are obtained. For the number of colors to be replaced, the color with the hue angle closest to the obtained hue angle is selected from the new color scheme list (Figure 10(d)). The selected color is replaced with the replacement color. The replaced color scheme pattern is stored in the color scheme pattern table of Figure 4. This allows a color scheme pattern in which two or more colors are replaced to be generated. This concludes the explanation of S907. Returning to the explanation of Figure 9(a).

[0102] In S908, the skeleton acquisition unit 213 acquires skeletons that meet various set conditions for the product type to be processed. In this embodiment, it is assumed that each skeleton is described in a separate file and stored in the HDD 104. The skeleton acquisition unit 213 sequentially reads skeleton files from the HDD 104 to the RAM 103, leaving skeletons that meet the set conditions on the RAM 103, and deleting skeletons that do not meet the conditions from the RAM 103. Here, FIG. 9(c) is a flowchart showing the condition determination process performed by the skeleton acquisition unit 213. The condition determination process of the skeleton acquisition unit 213 will be described in detail using FIG. 9(c). The processes from S931 to S937 are subflows of S908.

[0103] In S931 of FIG. 9(c), the skeleton acquisition unit 213 determines whether the size of the skeleton loaded into RAM 103 matches the size preset for the type of product to be processed. In FIG. 5, the poster is A2, the postcard is 100 mm x 148 mm, and the banner is 360 mm x 45 mm. Note that while the sizes are checked to match here, it is also sufficient to check that the aspect ratios match. In this case, the skeleton acquisition unit 213 enlarges or reduces the coordinate system of the loaded skeleton to acquire a skeleton that matches the size of the product to be processed.

[0104] In S932, the skeleton acquisition unit 213 determines whether the purpose category specified by the creation condition specification unit 201 matches the category of the skeleton. For skeletons to be used only for a specific purpose, the purpose category is written in the skeleton file, and the skeleton is not acquired unless that purpose category is selected. This prevents a skeleton designed specifically for a specific purpose, such as one that uses graphics to evoke a school or a sporting goods pattern, from being used in other purpose categories. Note that if a purpose category is not set on the application launch screen 501, the processing of S932 is skipped.

[0105] In S933, the skeleton acquisition unit 213 determines whether the number of image objects of the loaded skeleton matches the number of images acquired by the image acquisition unit 211. In S934, the skeleton acquisition unit 213 determines whether the character objects of the loaded skeleton match the character information specified in the text designation unit 202. Specifically, the skeleton acquisition unit 213 determines whether the type of character information specified in the text designation unit 202 is present in the skeleton. For example, assume that character strings are specified in the title box 502 and the body box 504 on the application launch screen 501, and that a blank is specified in the subtitle box 503. In this case, all character objects in the skeleton are searched, and if both a character object with "title" set as the type of character information in metadata and a character object with "body" specified are found, the skeleton is determined to be suitable; otherwise, the skeleton is determined to be unsuitable.

[0106] In S935, the skeleton acquisition unit 213 determines whether or not a graphic object exists in the loaded skeleton. If a picture is specified in the creation condition specification unit 201, a graphic object must exist to draw the picture. If a picture is not specified in the creation condition specification unit 201, the processing of S935 is skipped. In S936, the skeleton acquisition unit 213 determines whether or not a logo object exists in the loaded skeleton. If a logo is specified in the creation condition specification unit 201, an object must exist to draw the logo. If a logo is not specified in the creation condition specification unit 201, the processing of S936 is skipped. In S937, as a result of executing the processing from S931 to S936, skeletons that match all the determination processes remain in RAM 103. The skeleton acquisition unit 213 selects the skeletons remaining in RAM 103 as skeletons to be used for poster generation.

[0107] The skeleton acquisition unit 213 stores in RAM 103 skeletons whose skeleton size, usage category, number of image objects, type of text objects, number of graphic objects, and number of logo objects all match the set conditions. In this embodiment, the skeleton acquisition unit 213 examines all skeleton files on HDD 104, but this is not limiting. For example, the poster creation application may store in advance in HDD 104 a database that associates file paths of skeleton files with search conditions. In this case, the skeleton acquisition unit 213 can quickly acquire skeleton files by searching the database and loading only matching skeleton files from HDD 104 into RAM 103. The search conditions include, for example, skeleton size, number of image objects, type of text objects, number of graphic objects, and number of logo objects. This concludes the description of S908. Returning to the description of FIG. 9(a),

[0108] In S909, the skeleton selection unit 216 selects a skeleton from the skeletons acquired in S908 that matches the target impression specified by the design element specification unit 204. Here, FIG. 13 is a diagram illustrating how the skeleton selection unit 216 selects a skeleton, using a poster skeleton as an example. Similar processing is performed for other types of merchandise. FIG. 13(a) is a diagram illustrating an example of a table linking skeletons to impressions. The skeleton name column in FIG. 13(a) lists the skeleton file name, and the luxury, familiarity, dynamism, and profoundness columns show numbers (numeric values) indicating the degree of influence each skeleton has on each impression. These numerical values ​​indicate that the impression is low (-2), slightly low (-1), neutral (0), slightly high (+1), and high (+2). First, the skeleton selection unit 216 calculates the distance between the target impression acquired from the design element specification unit 204 and the impression of each skeleton shown in the skeleton impression table of FIG. 13(a). For example, if the target impression is "luxury +1, familiarity -1, dynamism -2, and solidity +2," the distance calculated by the skeleton selection unit 216 is as shown in FIG. 13(b). In this embodiment, Euclidean distance is used as the distance (hereinafter, simple distance will be referred to as "Euclidean distance"). The smaller the Euclidean distance value, the closer the target impression and the impression of the skeleton are. Next, the skeleton selection unit 216 selects the top N skeletons with the smallest distance values ​​in FIG. 13(b). In this embodiment, the skeleton selection unit 216 selects the top two skeletons. That is, the skeleton selection unit 216 selects Skeleton 1 and Skeleton 4. Here, "N" can be set to any integer greater than or equal to 1.

[0109] Furthermore, the value range of each impression in the skeleton impression table of FIG. 13(a) does not need to be the same as the value range of the impression specified in the design element specification unit 204. In this embodiment, the value range of the impression specified in the design element specification unit 204 is -2 to +2, but the value range of the impression in the skeleton impression table may be different. In this case, the value range of the skeleton impression table is scaled to match the value range of the target impression, and then the above distance is calculated. Furthermore, the distance calculated by the skeleton selection unit 216 is not limited to Euclidean distance; it may be any distance between vectors that can be calculated, such as Manhattan distance or cosine similarity. Furthermore, impressions for which the target impression has been set to OFF using the design element information radio button 523 are excluded from the distance calculation.

[0110] The skeleton impression table is created in advance by, for example, fixing the color scheme, font, and image and text data to be placed on the skeleton, generating a poster image based on each skeleton, and estimating its impression. The pre-created skeleton impression table is saved on HDD 104. That is, by estimating the impressions of poster images that use the same text color and image, but have different text or image placements, the relative characteristics compared to other skeletons are tabulated. In this process, it is desirable to perform processes such as standardizing the estimated impressions overall, averaging the impressions of multiple poster images generated from a single skeleton using multiple color schemes or images, and canceling the impressions due to the color schemes or images used. This allows the impact of placement on the impression to be tabulated, for example, that the impression of a skeleton with a small image is determined by elements such as graphics or text, regardless of the image, and that a tilted image or text placement creates a stronger sense of dynamism. Figure 13(c) shows an example of skeletons corresponding to Skeletons 1 to 4 in Figure 13(a). For example, Skeleton 1 has a regular arrangement of image objects and text objects, and the image area is small, resulting in a low sense of dynamism. Skeleton 2 has circular graphic objects and image objects, resulting in a high sense of familiarity and a low sense of solidity. Skeleton 3 has large image objects and tilted graphic objects placed on top of the image objects, resulting in a high sense of dynamism. Skeleton 4 has images placed across the entire skeleton and minimized text objects, resulting in a high sense of solidity and a low sense of dynamism. As such, when a poster image includes text or images, poster images with different target impressions are generated depending on how the text or images are arranged. Note that the method for creating the skeleton impression table is not limited to this. The skeleton impression table may be estimated from characteristics of the layout information, such as the area or coordinates of the image and title string. Alternatively, the skeleton impression table may be adjusted by user operation. The skeleton impression table is stored on HDD 104, and the skeleton selection unit 216 reads the skeleton impression table from HDD 104 into RAM 103 and references it.

[0111] In S910, the color scheme selection unit 217 selects a color scheme that matches the target impression specified by the design element specification unit 204 from the color scheme patterns acquired in S907. The method for selecting a color scheme that matches the target impression is the same as the method used in S909. The method involves referencing an impression table corresponding to the color scheme and selecting a color scheme according to the target impression. FIG. 14(a) shows an example of a color scheme impression table that links color scheme patterns with impressions. The color scheme selection unit 217 calculates the distance between the impression values ​​indicated by the columns for luxury and dignity in FIG. 14(a) and the target impression value, and selects the top N color scheme patterns with the smallest distance values. In this embodiment, the top two color scheme patterns are selected. Note that, like the skeleton impression table, the color scheme impression table can tabulate the impression trends of color scheme patterns by fixing the skeleton, font, and image other than the color scheme pattern and creating and estimating impressions of posters with different color scheme patterns. In the method of selecting a color scheme pattern that matches a specified color, a color close to the color contained in the color scheme pattern is selected. For example, if a color whose distance ΔE in the CIE L*A*B* color space is 2.0 or less is included, the color whose ΔE is 2.0 or less is selected. Another criterion for judgment may be whether the distance ΔRGB in the RGB color space is 1.0 or less. Specifically, if the specified color is (R, G, B) = (0, 67, 69), in Figure 14(a), "Color 1" of "Color Scheme ID 1" has a ΔRGB of 1.0 or less, so "Color Scheme ID 1" is selected.

[0112] In S911, the pattern selection unit 218 selects a pattern combination that matches the target impression from the pattern list acquired by the design element acquisition unit 214. The method for selecting a pattern combination that matches the target impression is the same as in S909, in which an impression table corresponding to the patterns is referenced and patterns are selected according to the target impression.

[0113] In S912, the logo selection unit 219 selects a logo combination that matches the target impression from the logo list acquired by the design element acquisition unit 214. The method for selecting a logo combination that matches the target impression is the same as in S909, whereby an impression table corresponding to the logo is referenced and a logo is selected according to the target impression. Furthermore, in S912, the font selection unit 220 selects a font combination that matches the target impression specified by the design element acquisition unit 214. The method for selecting a font combination that matches the target impression is the same as in S909, whereby an impression table corresponding to the font is referenced and a font is selected according to the target impression. FIG. 14(b) shows an example of a font impression table that links fonts and impressions. The font selection unit 220 calculates the distance between the impression values ​​indicated by the columns for luxury and dignity in FIG. 14(b) and the target impression value, and selects the top N fonts with the smallest distance values. Note that, like the skeleton impression table, the font impression table can tabulate trends in font impressions by creating and estimating impressions of posters with different fonts while fixing the skeleton, color pattern, and image other than the font. The method for selecting a font combination that matches a specified font is to select a font combination that includes the specified font. Furthermore, a font combination that is close to the impression value of the font of the font combination that includes the specified font may be further selected. This allows a font that is close to the impression of the specified font to be selected.

[0114] In S913, the layout unit 221 generates a poster by setting character information, images, color schemes, fonts, designs, and logos for the skeletons selected by the skeleton selection unit 216. The processing of S913 and the processing of the layout unit 221 will be described in detail with reference to Figures 15, 16, 17, and 18.

[0115] FIG. 15 is an example of a software block diagram illustrating the layout unit 221 in detail. The layout unit 221 includes a color allocation unit 1501, an image layout unit 1502, an image correction unit 1503, a font setting unit 1504, a text layout unit 1505, a text decoration unit 1506, a picture setting unit 1507, and a logo layout unit 1508. FIG. 16 is a flowchart illustrating the processing of S910 in detail. FIG. 17 is a diagram illustrating information input to the layout unit 221. FIG. 17(a) is a table summarizing the character information specified in the text specification unit 202 and the images specified in the image specification unit 203. FIG. 17(b) is an example of a table showing color patterns acquired from the color pattern selection unit 217, and FIG. 17(c) is an example of a table showing fonts acquired from the font selection unit 220. FIG. 18 is a diagram illustrating the processing steps of the layout unit 221.

[0116] The processing of S913 will be described in detail using FIG. 16. That is, the processing from S1601 to S1610 is a subflow of S913. In S1601, the layout unit 221 lists all combinations of skeletons obtained from the skeleton selection unit 216, color patterns obtained from the color pattern selection unit 217, and fonts obtained from the font selection unit 220. The layout unit 221 generates poster data for each combination in order by performing the following layout processing. For example, if the number of skeletons obtained from the skeleton selection unit 216 is 3, the number of color patterns obtained from the color pattern selection unit 217 is 2, and the number of fonts obtained from the font selection unit 220 is 2, the layout unit 221 generates 3 x 2 x 2 = 12 pieces of poster data. Next, in S1601, the layout unit 221 selects one of the listed combinations and executes the processing from S1602 to S1609.

[0117] In S1602, the color scheme assignment unit 1501 assigns a color scheme pattern acquired from the color scheme selection unit 217 to a skeleton acquired from the skeleton selection unit 216. FIG. 18(a) is a diagram showing an example of a skeleton. In this embodiment, an example will be described in which a color scheme pattern in which the color scheme ID in FIG. 17(b) is 1 is assigned to a skeleton 1801 in FIG. 18(a). The skeleton 1801 in FIG. 18(a) includes two graphic objects 1802 and 1803, one image object 1804, and three text objects 1805, 1806, and 1807. First, the color scheme assignment unit 1501 assigns colors to the graphic objects 1802 and 1803. Specifically, the color scheme assignment unit 1501 assigns corresponding colors from a color scheme pattern based on color scheme numbers, which are metadata described in the graphic objects. Next, the color allocation unit 1501 assigns, for example, the last color in the color scheme to character objects whose metadata is type and whose attribute is "title." That is, in this embodiment, color 4 is assigned to the character placed in character object 1805. Next, for character placed in character objects whose metadata is type and whose attribute is other than "title," the color is set based on the brightness of the background of the character object. In this embodiment, if the brightness of the background of the character object is equal to or less than a threshold, the character color is set to white. If the brightness of the background of the character object is higher than the threshold, the character color is set to black. FIG. 18B shows the state of the skeleton 1808 after the color allocation process. The color allocation unit 1501 outputs the colored skeleton data to the image arrangement unit 1502.

[0118] In S1603, the image arrangement unit 1502 arranges the skeleton data acquired from the color scheme assignment unit 1501 based on analysis information accompanying the image data acquired from the image analysis unit 212. In this embodiment, the image arrangement unit 1502 assigns image data 1701 to an image object 1804 within the skeleton. Furthermore, if the aspect ratios of the image object 1804 and the image data 1701 differ, the image arrangement unit 1502 performs trimming so that the aspect ratio of the image data 1701 matches the aspect ratio of the image object 1804. More specifically, based on the object position obtained by the image analysis unit 212 analyzing the image data 1701, trimming is performed so that the object area reduced by trimming is minimized. Note that the trimming method is not limited to this, and other trimming methods may be used, such as trimming the center of the image or devising a composition so that the face position forms a triangular composition. The image placement unit 1502 outputs the skeleton data to which the images have been assigned to the image correction unit 1503 .

[0119] In S1604, the image correction unit 1503 acquires skeleton data with images assigned from the image placement unit 1502 and corrects the images placed on the skeleton. In this embodiment, if the image resolution is insufficient, upsampling processing is performed using super-resolution processing. First, the image correction unit 1503 determines whether the image placed on the skeleton meets a certain resolution. For example, assume that an image of 1600 (px) x 1200 (px) is assigned to a 200 mm x 150 mm area on the skeleton. In this case, the print resolution of the image can be calculated using equation (5). TIFF2026014557000002.tif16105

[0120] Next, if it is determined that the print resolution of the image is less than the threshold, the image correction unit 1503 increases the resolution by super-resolution processing. On the other hand, if it is determined that the print resolution of the image is equal to or greater than the threshold and has sufficient resolution, image correction is not performed. In this embodiment, super-resolution processing is performed when the print resolution of the image is less than 300 dpi.

[0121] In S1605, the font setting unit 1504 sets the font acquired from the font selection unit 220 to the image-corrected skeleton data acquired from the image correction unit 1503. FIG. 17C shows an example of a font combination selected by the font selection unit 220. In this embodiment, an example of font assignment will be described in which the font ID "2" in FIG. 17C is assigned to the image-corrected skeleton data. In this embodiment, fonts are set for character objects 1805, 1806, and 1807 of a skeleton 1808. Note that in posters, a font that is easy to see is often set for the title from the perspective of eye-catchingness, and a font that is easy to read from the perspective of visibility is set for the other characters. Therefore, in this embodiment, the font selection unit 220 selects two types of fonts: a title font and a body font. The font setting unit 1504 sets the title font to the character object 1805 whose attribute is "title." The font setting unit 1504 sets the body font to the other character objects 1806 and 1807. The font setting unit 1504 outputs the skeleton data with the font set to the text layout unit 1505. In this embodiment, the font selection unit 220 selects two types of fonts, but this is not limited thereto. For example, only the title font may be selected. In this case, the font setting unit 1504 also uses the font corresponding to the title font as the body font. That is, if the title is a Gothic font, a typical Gothic font with high readability is selected for character objects other than the title. Also, if the title is a Mincho font, a typical Mincho font is selected for character objects other than the title, and a body font that matches the type of title font is set. Naturally, the title font and the body font may be the same. Alternatively, the title font may be used for character objects of the title and subtitle, and the body font may be used for other character objects. Different fonts may be used depending on the degree of prominence desired, such as using the title font for character objects with a font size equal to or larger than a predetermined value.

[0122] In S1606, the text layout unit 1505 lays out the text specified by the text designation unit 202 in the skeleton data with font settings obtained from the font setting unit 1504. In this embodiment, each piece of text shown in FIG. 17(a) is assigned by referring to the metadata attributes of the skeleton character objects. That is, "Summer Big Thank You Sale," whose attribute is the title, is assigned to character object 1805, and "Blow Away the Midsummer Heat," whose attribute is the subtitle, is assigned to character object 1806. Since no text is set, nothing is assigned to character object 1807. FIG. 18(c) shows skeleton 1809, which is an example of skeleton data after processing by the text layout unit 1505. The text layout unit 1505 outputs the skeleton data with text layout to the text decoration unit 1506.

[0123] In S1607, the text decoration unit 1506 decorates the character objects in the skeleton with the text already placed, obtained from the text placement unit 1505. In this embodiment, if the color difference between the title character and its background area is equal to or less than a threshold, a process of adding a border to the title character is performed. This improves the readability of the title. The text decoration unit 1506 outputs the decorated skeleton data to the picture setting unit 1507.

[0124] In S1608, the picture setting unit 1507 sets a picture to a graphic object determined to be a background area in the text-decorated skeleton data obtained from the text decoration unit 1506. The graphic object determined to be a background area is the graphic object with color scheme number 1. In FIG. 18(b), a picture is set to the background area of ​​the skeleton 1808. When setting a picture, the color is changed to the color scheme assigned by the color scheme assignment unit 1501, and then the picture is set to the background area. FIG. 18(d) is an example of a picture that has been set. If a picture has not been set by the creation condition specification unit 201, the picture set in the skeleton data is set. The picture setting unit 1507 outputs the skeleton data with the picture set to the logo placement unit 1508.

[0125] In S1609, the logo placement unit 1508 places the logo on the logo object in the skeleton data with the image set therein obtained from the image setting unit 1507. FIG. 18(d) is an example of the logo placed. If no logo is set in the creation condition specification unit 201, S1609 is skipped. The logo placement unit 1508 outputs the skeleton data with the logo placed therein, i.e., the product data with all layout steps completed, to the impression estimation unit 222.

[0126] In S1610, the layout unit 221 determines whether all product data has been generated. If the layout unit 221 determines that product data has been generated for all skeletons, color patterns, font combinations, pictures, and logos for the product to be processed, the layout process ends and the process proceeds to S911. If it determines that all product data has not been generated, the process returns to S1601, and product data is generated for combinations that have not yet been generated. This concludes the explanation of S913. Returning to the explanation of Figure 9(a).

[0127] In S914, the impression estimation unit 222 estimates an impression for the product data generated in S913 and links the estimate to the product data. Specifically, a rendering process is performed on the product data generated in S913. Next, an impression of the rendered product image is estimated. Finally, the estimated impression is linked to the product data. The rendering process is a process of converting product data into image data. For example, even if the color scheme is the same, different skeletons will result in different layouts, which will result in different colors being used and occupying different areas. Therefore, this process is performed at this timing because it is necessary to evaluate not only the individual impression trends of the color scheme or skeleton but also the final product impression. This allows the evaluation of not only the impression of individual elements of the product, such as color scheme and layout, but also the impression of the final product, including images and text, laid out.

[0128] In S915, it is determined whether all product data has been generated for the number of products to be created for one product type determined in S905. In this embodiment, there are five pieces of product data. If product data for the number of products to be created has not been generated, the process returns to S909, and uncreated product data is generated. If product data for the number of products to be created has been generated, the process proceeds to S916.

[0129] In S916, it is determined whether all product data has been generated for the product types to be created determined in S905. In this embodiment, five pieces of product data are generated for each of the three product types. In other words, 15 pieces of product data are generated. If product data for the number of products to be created for all product types has not been generated, the target product type is changed, and processing returns to S908, where product data for the newly set product type is generated for the number of products to be created. If product data for the number of products to be created for all product types has been generated, the generation process ends, and processing proceeds to S917.

[0130] In S917, the product selection unit 223 selects a product set to be output to the display 105 (presented to the user) based on the estimated impression acquired from the impression estimation unit 222. Specifically, the product selection unit 223 first calculates the impression distance between the estimated impression linked to the product data (product design) and the target impression. The calculated impression distance is stored in association with the product data. In this embodiment, 15 product data items are generated, so 15 impression distances are calculated. Euclidean distance is used for the impression distance. The smaller the Euclidean distance, the closer the target impression is to the estimated impression. Furthermore, the distance calculated by the product selection unit 223 is not limited to Euclidean distance; any distance between vectors, such as Manhattan distance or cosine similarity, may be calculated. Next, the product selection unit 223 calculates the total impression distance for each product set. In this embodiment, one product set includes two products: postcards and banners. The two calculated impression distances are added together to calculate the total impression distance. The calculated total impression distance is linked to the product set and saved. Next, the product selection unit 223 selects a product set from the total impression distance linked to the product set. If one product set is displayed, the product set with the smallest total impression distance is selected. In this embodiment, since multiple product sets are displayed on the product preview screen 601 of FIG. 6, the product sets with the smallest total impression distance are selected based on the number of product sets displayed. Alternatively, a product set with a total impression distance equal to or less than a predetermined threshold may be selected. In this case, if it is not possible to select enough product sets to display on the product preview screen, the process returns to S908, and different product data may be generated.

[0131] In S918, the generated product display control unit 206 displays the product preview screen 601 of Fig. 6 on the display 105. Specifically, the generated product display control unit 206 renders the multiple product data included in the product set selected by the product selection unit 223 in S915, and outputs the rendered data to the display 105. This completes the description of the poster generation process flow for generating a poster by the user specifying an impression.

[0132] As described above, this embodiment makes it possible to appropriately generate a unified design that expresses the user's intended impression by combining multiple products. That is, it is possible to appropriately generate a unified design for a group of products consisting of the currently created product and a previously created product designated as a key design. More specifically, in this embodiment, to generate a design that expresses the user's intended brand impression, each element constituting the product, such as a skeleton, color scheme, or font, is combined based on the target impression for each product. Furthermore, by estimating the overall impression of the product and selecting a product that is closest to the target impression from one or more poster candidates, it is possible to generate a product that not only reflects the individual elements but also the overall impression that is in line with the user's intention. Furthermore, by obtaining color scheme patterns with different hues from the color scheme of the key design, it is possible to appropriately generate a product with a unified design by combining multiple products.

[0133] [Modification of the first embodiment] In the first embodiment, the product preview screen 601 displayed the generated product set. However, the target impression and brand information may also be set on the product preview screen. FIG. 19 illustrates an example of a UI for setting a key design and design elements on the product preview screen 1901. Components with the same numbers as those in FIG. 5 perform the operations described in the description of FIG. 5. Components with the same numbers as those in FIG. 6 perform the operations described in the description of FIG. 6. The generated product display control unit 206 displays the product preview screen 1901 on the display 105 in S918. The product preview screen 1901 includes a key design specification area 508 as a UI for setting a key design. The design element specification area 515 includes a color scheme specification box 517, a picture specification box 520, a logo specification box 521, a font specification box 522, and a reflection level slider bar 529 as UIs for setting design elements. Furthermore, in design element specification area 515, impression sliders 524 to 527 and impression radio button 528 of application startup screen 501 are arranged as a UI for setting a target impression.

[0134] The product preview screen 1901 includes a Reflect button 1902 that reflects the set information. The user changes the target impression and brand information while checking the previewed product images 607 and 608. Then, by pressing the Reflect button 1902, the process proceeds to S902, and processing from S902 to S918 is executed. As a result of executing this processing, the generated product display control unit 206 displays on the display 105 the previewed product images 607 and 608 that reflect the key design and design element settings set on the product preview screen 1901. This allows the user to set the key design and design elements while checking the generated product set. As a result, it becomes possible to appropriately generate multiple products with a unified design by combining multiple products while expressing the user's intended impression, without performing cumbersome screen transitions.

[0135] [Second embodiment] In the first embodiment, an example was described in which a skeleton, color scheme, and font, which are components of a product, are selected based on a target impression to generate the product. In this embodiment, the combination generation unit uses a genetic algorithm to search for a combination of components of the product that will create an overall impression of the poster close to the target impression. This allows for more flexible and appropriate generation of product components that are optimal for the target impression without pre-calculating a skeleton impression table, color scheme impression table, or font impression table. Furthermore, by combining multiple products, it becomes possible to appropriately generate multiple products with a unified design. As in the first embodiment, the design color of the generated product includes at least one color with a hue angle different from any of the colors in the color scheme included in the design elements.

[0136] Fig. 20 is a software block diagram of a commercial material creation application in this embodiment. In the configuration of the block diagram shown in Fig. 20, a combination generation unit 2002 is configured instead of the skeleton selection unit 216, color pattern selection unit 217, picture selection unit 218, logo selection unit 219, and font selection unit 220 in Fig. 2. Note that components with the same numbers as in Fig. 2 perform the same processes as those described in the first embodiment, and therefore will not be described here.

[0137] The multiple skeleton acquisition unit 2001 acquires skeletons for the product types specified in the creation condition designation unit 201. In order to use a search algorithm, all skeletons for the specified product types are acquired and stored in the RAM 103.

[0138] The combination generation unit 2002 acquires one or more skeletons for each product type from the multiple skeleton acquisition unit 2001, and acquires product data and an estimated product impression from the impression estimation unit 222. The combination generation unit 2002 acquires a target impression from the design element acquisition unit 214. The combination generation unit 2002 acquires a color scheme pattern list, a font list, a design list, and a logo list from the HDD 104. Furthermore, the combination generation unit 2002 generates combinations of product components (skeletons, color scheme patterns, fonts) and design elements (logos, designs) used for product generation for each product type. As an example, in this embodiment, two combinations of postcards and banners are generated. One combination for each product type is defined as one product set combination. The combination generation unit 2002 outputs the generated product set combinations to the layout unit 221.

[0139] The combination selection unit 2003 selects a product combination for which the distance between the estimated impression of the product data acquired from the impression estimation unit 222 and the target impression acquired by the design element acquisition unit 214 is equal to or less than a threshold value, and stores the combination in the RAM 103. The combination selection unit 2003 also determines whether the number of selected and stored products reaches the specified number of products.

[0140] 21 is a flowchart showing the processing of the merchandise generation unit 210 of the merchandise creation application in this embodiment. Note that, among the processing of this flowchart, the processing assigned the same numbers as those in the flowchart of FIG. 9(a) is the same as the processing described in the first embodiment, and therefore the description thereof will be omitted here. Note that, in the processing of this flowchart, the processing of S909 to S912 and the processing of S915 and S916 shown in FIG. 9(a) are omitted.

[0141] In S2101, the multiple skeleton acquisition unit 2001 acquires skeletons for the number of product types specified in the creation condition specification unit 201. Specifically, the processes from S921 to S926 in FIG. 9(b) are repeated for the number of specified product types. In order to use the search algorithm, all skeletons for the specified product types are acquired. As an example, in FIG. 5, all skeletons for postcards and banners are acquired.

[0142] In the explanation of S2102, the operation at the first execution and the operation from the second loop onwards will be explained separately. First, at the first execution of S2102, the combination generation unit 2002 acquires tables for skeletons, color schemes, fonts, logos, and designs used in generating commercial materials. The tables used by the combination generation unit 2002 will be explained using FIG. 4 and FIG. 22. FIG. 22(a) shows a list of skeletons acquired by the combination generation unit 2002 from the multiple skeleton acquisition unit 2001. FIG. 22(b) shows a list of fonts acquired by the combination generation unit 2002 from the design element acquisition unit 214. FIG. 22(c) shows a list of logos acquired by the combination generation unit 2002 from the design element acquisition unit 214. FIG. 22(d) shows a list of designs acquired by the combination generation unit 2002 from the design element acquisition unit 214. FIG. 22(e) shows a list of color scheme patterns acquired by the combination generation unit 2002 from the color scheme pattern acquisition unit 215. Regardless of which color scheme pattern is selected, the color of the generated product design will include at least one color with a hue angle different from any of the color scheme colors included in the design elements. Although only up to four IDs are listed in Figures 4 and 22(a) to 22(d), the number of IDs may be four or more. In this embodiment, a case will be described in which the skeleton ID is 115, the color scheme ID is 20, the font ID is 21, the logo ID is 35, and the design ID is 10. The combination generation unit 2002 generates randomly specified combinations of products from the above five tables, for each product type. In this embodiment, 100 product set combinations are generated. Figure 22(e) shows a product set combination table generated in this embodiment. Furthermore, if a design element is specified in the design element specification unit 204, the same ID is set between the products. Figure 22(e) shows a combination table when a design element is specified as a design element. The same design ID is set for product 1 and product 2. Furthermore, if a reflection rate is specified in the design element specification unit 204, the ratio of the same IDs between product 1 and product 2 is determined based on the set value. Specifically, if the reflection rate of the design element is specified as 0.3, 30 of the 100 combinations will have the same ID, and the remaining 70 will be random combinations.Thereafter, the combination generation unit 2002 executes the processes of S913, S914, and S2103 for all the generated combinations.

[0143] Next, the processing of the second loop and subsequent loops of S2102 will be described. The combination generation unit 2002 calculates an evaluation value from the estimated impression obtained from the impression estimation unit 222 and links it to the product set combination table. The method for calculating the evaluation value is the same as the method for calculating the total impression distance in S917. Figure 23 is a diagram explaining the operation of S2102 from the second loop onwards. Figure 23(a) is a table linking the above evaluation values ​​to Figure 22(d). The evaluation value column in Figure 23(a) indicates the evaluation value of the product set generated by the combination in the corresponding row. The combination generation unit 2002 generates a new combination table from Figure 23(a). Figure 23(b) is the newly generated combination table. In this embodiment, new combinations are generated using tournament selection or uniform crossover in a genetic algorithm. First, N combinations are randomly selected from the table in Figure 23(a). Here, N=3, for example. Next, from the selected combinations, the top two combinations with the lowest evaluation values ​​(i.e., close to the target impression and high design similarity) are selected. Finally, new combinations are generated by randomly swapping each element of the two selected combinations (skeleton ID, color scheme ID, font ID, logo ID, and design ID). For example, combinations IDs 1 and 2 in Figure 23(b) show the results generated from combinations IDs 1 and 3 in Figure 23(a), with the color scheme IDs swapped. Figure 23(b) shows the results of repeating the above procedure to generate 100 new combinations. Note that regardless of which color scheme pattern is selected for the new combinations generated, the colors in the product design will contain at least one color with a different hue angle than any of the colors in the color scheme included in the design elements.

[0144] This allows efficient combination search based on the evaluation value of the total impression distance. While 100 combinations were generated in this embodiment, this is not limited to this. While tournament selection or uniform crossover was used, this is not limiting. For example, ranking selection, roulette selection, one-point crossover, or other methods may be used. Mutation may be incorporated to prevent the system from falling into a local optimum. While skeletons (layouts), color patterns, fonts, logos, and designs are used as the components of the commercial material to be searched, other components may also be used. By increasing the number of components to be searched, posters with greater variety can be generated, thereby broadening the range of impression expression.

[0145] In S2103, the combination selection unit 2003 calculates the evaluation value of the total impression distance in the same manner as in S2102, and creates the same table as in FIG. 23(a). The combination selection unit 2003 saves in RAM 103 product sets whose evaluation value of the total impression distance is equal to or less than a predetermined threshold. The combination selection unit 2003 then determines whether the product sets saved in RAM 103 have reached a predetermined number of combinations. If the combination selection unit 2003 determines that the predetermined number of combinations has been reached, the process proceeds to S917. If the combination selection unit 2003 determines that the predetermined number of combinations has not been reached, the process returns to S2101. That is, the process of S2101 in the second loop described above is executed, and the processes of S2102 to S2103 are repeatedly executed until the number of product sets whose evaluation value of the total impression distance is equal to or less than the threshold and saved in RAM 103 reaches the predetermined number.

[0146] If a predetermined number or more product sets with evaluation values ​​below a threshold are stored, the combination selection unit 2003 may compare the evaluation values ​​of each of the stored product sets and ultimately store in RAM 103 only the product sets with the lowest evaluation values. Product sets determined to have higher evaluation values ​​based on the comparison results may then be deleted from RAM 103. In this embodiment, a search for combinations of poster components and design elements is performed using a genetic algorithm, but the search method is not limited to this, and other search methods, such as a neighborhood search method or a Tabu search method, may also be used.

[0147] As described above, according to this embodiment, by searching for a combination of components and design elements to be used in the products, it is possible to generate a product set with a unified design that closely matches the target impression using multiple generated products. This is particularly effective when generating a product set based on images or text information input by a user. For example, consider a case where the images have a dynamic impression, but the user wants to generate a product set with a subdued impression as a whole. This embodiment can evaluate the overall impression of the products and search for a combination of skeletons, color patterns, fonts, logos, and designs that are close to the target impression and have a high degree of design similarity. Therefore, to suppress the impression of the image, the components of the products can be controlled to match the image, such as by using a skeleton with a small image area or a more subdued font or color scheme. Furthermore, even if the impression intended by the user differs from the impression conveyed by the brand information, a skeleton with a small area for displaying the brand information can be used. This embodiment can flexibly find a combination of components and design elements that are optimal for the overall impression of the product set. As a result, by combining multiple products, it is possible to create a variety of products with a unified design.

[0148] [Other embodiments] The above-described embodiments can also be realized by executing the following process. That is, software (programs) that realize the functions of the above-described embodiments are supplied to a system or device via a network or various storage media, and a computer (CPU, MPU, etc.) of the system or device reads and executes the program. The program may be executed by a single computer or by multiple computers in cooperation with each other. Furthermore, all of the above-described processes do not need to be implemented by software; some or all of the processes may be implemented by hardware such as an ASIC. Furthermore, the CPU is not limited to a single CPU that performs all processes; multiple CPUs may perform processes in cooperation with each other as appropriate. The functions of the above-described embodiments are not necessarily realized by a computer reading and executing program code. The above-described functions may also be realized by an operating system (OS) running on a computer that performs some or all of the actual processes based on the instructions of the program code.

[0149] The disclosure of the above-described embodiment includes the following configurations.

[0150] (Configuration 1) An information processing device characterized by comprising: a designation means for designating design elements to be reflected in one or more commercial products for which a design is to be generated and creation conditions for creating the one or more commercial products; and a generation means for generating a design for the one or more commercial products by changing the color scheme of the design elements based on the design elements and creation conditions specified by the designation means so that the design elements include at least one color with a different hue angle than any of the colors in the color scheme included in the design elements.

[0151] (Configuration 2) The information processing device described in Configuration 1, characterized in that the colors of the different hue angles are colors obtained by rotating the color wheel clockwise or counterclockwise by a predetermined angle based on one color selected from the design elements.

[0152] (Configuration 3) The information processing device according to Configuration 2, wherein the predetermined angle is 30 degrees or 60 degrees.

[0153] (Configuration 4) The information processing device described in Configuration 1, characterized in that the colors of the different hue angles are complementary colors of one color selected from the design elements, contrasting colors close to the complementary colors, or similar colors close to the one selected color.

[0154] (Configuration 5) The information processing device according to any one of configurations 1 to 4, characterized in that the difference in lightness and saturation between the colors of the different hue angles and one color selected from the design elements is within a predetermined range.

[0155] (Configuration 6) The information processing device described in any one of configurations 1 to 5, characterized in that the design elements include a first design element and a second design element, and the generation means changes the color scheme of the first design element but does not change the color scheme of the second design element.

[0156] (Configuration 7) The information processing device described in Configuration 6, characterized in that the generation means generates a design for the one or more products by changing the color scheme of the first design element in the design of the one or more products based on a target impression, which is the impression required for a group of products consisting of multiple products including the one or more products.

[0157] (Configuration 8) The information processing device described in Configuration 7, characterized in that in a design of a combination of one or more products, the total impression distance obtained by adding up the distances between the target impression and the impressions linked to the design of each of the products is less than or equal to a threshold value.

[0158] (Configuration 9) An information processing device according to configuration 8, characterized in that the distance between the target impression and the impression associated with each generated design of each of the products is calculated using one of Euclidean distance, Manhattan distance, or cosine similarity.

[0159] (Configuration 10) The information processing device according to configuration 1, wherein the generating means generates designs for the combination of the one or more commercial products using a genetic algorithm.

[0160] (Configuration 11) The information processing device according to configuration 10, wherein the genetic algorithm is any one of tournament selection, uniform crossover, ranking selection, roulette selection, and one-point crossover.

[0161] (Configuration 12) The information processing device according to any one of configurations 1 to 11, further comprising a display control means for displaying on a display device a user interface screen (UI screen) for specifying the design elements and the creation conditions.

[0162] (Configuration 13) The information processing device according to configuration 12, wherein the display control means displays a preview of the design of the one or more commercial materials generated by the generation means on the UI screen.

[0163] (Configuration 14) An information processing device described in any one of configurations 1 to 13, characterized in that the design elements include color schemes, pictures, logos, and fonts, and the creation conditions include information on the type of product to be created, the purpose for which the product will be used, the number of key colors to be added to the product, and whether or not to change the background.

[0164] (Configuration 15) A program for causing a computer to function as the information processing device according to any one of configurations 1 to 14.

[0165] (Configuration 16) A control method for an information processing device, characterized by comprising: a step of specifying design elements to be reflected in one or more commercial products for which a design is to be generated and creation conditions for creating the one or more commercial products; and a step of generating a design for the one or more commercial products by changing the color scheme of the design elements based on the design elements and creation conditions specified in the specification step so that the design elements include at least one color with a hue angle different from any of the colors in the color scheme included in the design elements.

Claims

1. a designation means for designating design elements to be reflected in one or more commercial products for which a design is to be generated and creation conditions for creating the one or more commercial products; a generating means for generating a design for the one or more commercial products by changing the color scheme of the design elements based on the design elements and the generating conditions specified by the specifying means so that the design elements include at least one color having a different hue angle from any of the colors in the color scheme included in the design elements; An information processing device comprising:

2. 2. The information processing device according to claim 1, wherein the colors of different hue angles are colors obtained by rotating a color wheel by a predetermined angle clockwise or counterclockwise with respect to one color selected from the design elements.

3. 3. The information processing apparatus according to claim 2, wherein the predetermined angle is 30 degrees or 60 degrees.

4. 2. The information processing device according to claim 1, wherein the colors of different hue angles are complementary colors of one color selected from the design elements, contrasting colors close to the complementary colors, or similar colors close to the one selected color.

5. 2. The information processing device according to claim 1, wherein a difference in lightness and a difference in saturation between the colors of the different hue angles and one color selected from the design elements are within a predetermined range.

6. the design elements include a first design element and a second design element; 2. The information processing apparatus according to claim 1, wherein the generating means changes the color scheme of the first design element but does not change the color scheme of the second design element.

7. The information processing device described in claim 6, characterized in that the generation means generates a design for the one or more products by changing the color scheme of the first design element in the design of the one or more products based on a target impression, which is the impression required for a group of products consisting of multiple products including the one or more products.

8. The information processing device according to claim 7, characterized in that in a design of a combination of one or more products, a total impression distance obtained by adding up the distances between the target impression and the impressions linked to the designs of each of the products is less than a threshold value.

9. 9. The information processing device according to claim 8, wherein the distance between the target impression and the generated impression associated with each of the designs of each of the commercial products is calculated using one of Euclidean distance, Manhattan distance, and cosine similarity.

10. 2. The information processing apparatus according to claim 1, wherein the generating means generates a design for the combination of the one or more commercial products using a genetic algorithm.

11. 11. The information processing apparatus according to claim 10, wherein the genetic algorithm is any one of tournament selection, uniform crossover, ranking selection, roulette selection, and one-point crossover.

12. 2. The information processing apparatus according to claim 1, further comprising: a display control means for displaying on a display device a user interface screen (UI screen) for specifying the design elements and the creation conditions.

13. 13. The information processing apparatus according to claim 12, wherein the display control means displays a preview of the design of the one or more commercial materials generated by the generation means on the UI screen.

14. The design elements include color schemes, images, logos, and fonts; The information processing device according to claim 1, characterized in that the creation conditions include information on the type of product to be created, the purpose for which the product will be used, the number of key colors to be added to the product, and whether or not to change the background.

15. A program for causing a computer to function as the information processing device according to any one of claims 1 to 14.

16. a step of specifying design elements to be reflected in one or more commercial products for which a design is to be generated and creation conditions for creating the one or more commercial products; a step of generating a design for the one or more commercial products by changing the color scheme of the design elements based on the design elements and the creation conditions specified in the specifying step so that the design elements include at least one color with a different hue angle than any of the colors in the color scheme included in the design elements; 1. A method for controlling an information processing device, comprising:

Images