JP6914569B2 - Information processing equipment and programs - Google Patents

Description

The present invention relates to an information processing device and a program.

In recent years, Fashion Tech has been attracting attention as a technology applicable to the fashion field. The introduction of Fashion Tech is expected to transform the business model in the fashion field.

For example, Japanese Patent Application Laid-Open No. 2013-235528 discloses a technique for easily generating appropriate coordination for a user. According to Japanese Patent Application Laid-Open No. 2013-235528, it is possible to provide a user with an objective coordination proposal.

Fashion brands are offering new fashion items to the market by continuing to create designs that reflect the individuality of the brand. Therefore, the designers of each fashion brand design so as to reflect the individuality of the brand. The stronger the individuality of a fashion brand, the more difficult it tends to be to create innovative designs.

Since the technique of JP2013-235528A proposes a combination of existing fashion items, it is premised on the existence of existing fashion items. Therefore, it is difficult to create a new design.

An object of the present invention is to provide a novel design while retaining the individuality of an existing item.

One aspect of the present invention is
It is equipped with a means for storing design image information corresponding to a design in which multiple categories are mixed, which is output from a generative model corresponding to a combination of multiple categories.
It has a means to accept the specification of multiple categories from the user.
A means for presenting design image information corresponding to a combination of a plurality of categories specified by the user from the plurality of design image information is provided.
It is an information processing device.

According to the present invention, it is possible to provide a novel design while retaining the individuality of an existing item.

It is a block diagram which shows the structure of the information processing system of 1st Embodiment. It is a functional block diagram of the information processing system of FIG. It is explanatory drawing of the outline of 1st Embodiment. It is a figure which shows the data structure of the item information database of 1st Embodiment. It is a figure which shows the data structure of the design image information database of 1st Embodiment. It is explanatory drawing of the design image generation processing of 1st Embodiment. It is a sequence diagram of the design image presentation process of 1st Embodiment. It is a figure which shows the screen example displayed in the information processing of FIG. 7. It is explanatory drawing of the outline of 2nd Embodiment. It is a sequence diagram of the design image generation processing of the 2nd Embodiment. It is a detailed flowchart of the generation of the design image of FIG. It is a figure which shows the screen example displayed in the information processing of FIG. It is explanatory drawing of the outline of the modification of 2nd Embodiment. It is a figure which shows the data structure of the feature information database of the modification of 2nd Embodiment. It is a sequence diagram of the design image generation processing of the modification of the 2nd Embodiment. It is a figure which shows the screen example displayed in the information processing of FIG. It is explanatory drawing of the outline of 3rd Embodiment. It is a figure which shows the data structure of the user information database of 3rd Embodiment. It is a figure which shows the data structure of the model information database of 3rd Embodiment. It is a sequence diagram of the design image generation processing of the 3rd Embodiment. It is a figure which shows the example of the screen which is displayed in the information processing of FIG. It is a detailed flowchart of the generation of the design image of FIG. It is explanatory drawing of the outline of the modification 1 of the 3rd Embodiment. It is a sequence diagram of the design image generation processing of the modification 1 of the 3rd Embodiment. It is a figure which shows the example of the screen which is displayed in the information processing of FIG. It is a figure which shows the example of the screen which is displayed in the information processing of FIG. It is explanatory drawing of the outline of the modification 2 of the 3rd Embodiment. It is explanatory drawing of the outline of the modification 3 of the 3rd Embodiment. It is explanatory drawing of the outline of 4th Embodiment. It is a sequence diagram of the design image generation processing of 4th Embodiment. It is a figure which shows the example of the screen which is displayed in the information processing of FIG. It is a detailed flowchart of the generation of the design image of FIG.

Hereinafter, one embodiment of the present invention will be described in detail with reference to the drawings. In addition, in the drawing for demonstrating the embodiment, the same components are in principle the same reference numerals, and the repeated description thereof will be omitted.

(1) First Embodiment The first embodiment will be described.

(1-1) Configuration of Information Processing System The configuration of the information processing system will be described. FIG. 1 is a block diagram showing a configuration of an information processing system according to the first embodiment. FIG. 2 is a functional block diagram of the information processing system of FIG.

As shown in FIG. 1, the information processing system 1 includes a client device 10 and a server 30.
The client device 10 and the server 30 are connected via a network (for example, the Internet or an intranet) NW.

The client device 10 is an example of an information processing device that transmits a request to the server 30. The client device 10 is, for example, a smartphone, a tablet terminal, or a personal computer.

The server 30 is an example of an information processing device that provides the client device 10 with a response in response to a request transmitted from the client device 10. The server 30 is, for example, a web server.

(1-1-1) Configuration of Client Device The configuration of the client device 10 will be described.

As shown in FIG. 2, the client device 10 includes a storage device 11, a processor 12, an input / output interface 13, and a communication interface 14.

The storage device 11 is configured to store programs and data. The storage device 11 is, for example, a combination of a ROM (Read Only Memory), a RAM (Random Access Memory), and a storage (for example, a flash memory or a hard disk).

The program includes, for example, the following program.
・ OS (Operating System) program ・ Application (for example, web browser) program that executes information processing

The data includes, for example, the following data.
-Database referenced in information processing-Data obtained by executing information processing (that is, the execution result of information processing)

The processor 12 is configured to realize the function of the client device 10 by activating the program stored in the storage device 11. The processor 12 is an example of a computer.

The input / output interface 13 is configured to acquire a user's instruction from an input device connected to the client device 10 and output information to an output device connected to the client device 10.
The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof.
The output device is, for example, a display.

The communication interface 14 is configured to control communication between the client device 10 and the server 30.

(1-1-2) Server Configuration The configuration of the server 30 will be described.

As shown in FIG. 2, the server 30 includes a storage device 31, a processor 32, an input / output interface 33, and a communication interface 34.

The storage device 31 is configured to store programs and data. The storage device 31 is, for example, a combination of a ROM, a RAM, and a storage (for example, a flash memory or a hard disk).

The program includes, for example, the following program.
・ OS program ・ Application program that executes information processing

The data includes, for example, the following data.
・ Database referenced in information processing ・ Execution result of information processing

The processor 32 is configured to realize the function of the server 30 by activating the program stored in the storage device 31. The processor 32 is an example of a computer.

The input / output interface 33 is configured to acquire a user's instruction from an input device connected to the server 30 and output information to an output device connected to the server 30.
The input device is, for example, a keyboard, a pointing device, a touch panel, or a combination thereof.
The output device is, for example, a display.

The communication interface 34 is configured to control communication between the server 30 and the client device 10.

(1-2) Outline of First Embodiment An outline of the first embodiment will be described. FIG. 3 is an explanatory diagram of an outline of the first embodiment.

As shown in FIG. 3, the server 30 stores a generation model (CATEGORYixj) corresponding to a combination of a plurality of categories and a design image information (CATEGORYixj) output by each generation model (CATEGORYixj). Each generative model (CATEGORYixj) is constructed by inputting item image information of a plurality of categories. Each design image information (CATEGORYixj) corresponds to a combination of a plurality of categories.

When the user specifies a plurality of categories "CATEGORY1" and "CATEGORY2", the server 30 selects the design image information (CATEGORY1x2) corresponding to the combination of the plurality of categories specified by the user from among the plurality of design image information (CATEGORYixj). ) Is presented.

(1-3) Database The database of the first embodiment will be described. The following database is stored in the storage device 31.

(1-3-1) Item Information Database The item information database of the first embodiment will be described. FIG. 4 is a diagram showing a data structure of the item information database of the first embodiment.

As shown in FIG. 4, the item information database includes an "item ID" field, an "item name" field, a "category" field, and an "item image" field.
Each field is associated with each other.

The item ID is stored in the "item ID" field. The item ID is an example of item identification information that identifies an item. The item is, for example, a fashion item. Fashion items include, for example, at least one of the following:
・ Clothes, shoes, underwear, bags, accessories, glasses

The Item Name field stores information about the item name of the item (eg, text).

The Category field stores category information about the item's category. The "Category" field includes a plurality of subfields ("Brand" field and "Type" field).

The "brand" field stores brand information (for example, information about the brand name) about the brand of the item (for example, a fashion brand).

The "Type" field stores type information about the type of item (for example, "SHIRT" or "SHOES").

The item image information is stored in the "item image" field. The image information is, for example, at least one of the images taken from at least one direction on the front, side, and back of the item.

(1-3-2) Design image information database This actual form of the design image information database will be described. FIG. 5 is a diagram showing a data structure of the design image information database of the first embodiment.

As shown in FIG. 5, the design image information database includes a "design image ID" field, a "category" field, and a "design image" field.
Each field is associated with each other.

The design image ID is stored in the "design image ID" field. The design image ID is an example of the design image identification information that identifies the design image information.

The "category" field stores category information (for example, brand information) of a plurality of items that are the basis of design image information.

The design image information output by the generated model is stored in the "design image" field.

(1-4) Information Processing The information processing of the first embodiment will be described.

(1-4-1) Design image generation process The design image generation process of the first embodiment will be described. FIG. 6 is an explanatory diagram of the design image generation process of the first embodiment.

FIG. 6 shows an example of processing for generating design image information corresponding to a combination of brand i and brand j.

The storage device 31 stores a trained generative model (for example, GAN (Generation Adversarial Networks) or DCGAN (Deep Convolutional Generative Adversarial Networks)) for each combination of a plurality of brands. For example, the generative model (BRANDixj) corresponding to the brands "BRANDi" and "BRANDj" is learned from the item image information (BRANDi) of the brand "BRANDi" and the item image information (BRANDj) of the brand "BRANDj".

As shown in FIG. 6, the processor 32 selects a generation model (BLANDixj) corresponding to the combination of the brands “BRANDi” and “BRANDj” from the generation models stored in the storage device 31.

The processor 32 refers to the item information database (FIG. 4) and refers to the information in the "item image" field associated with the brands "BRANDi" and "BRANDj" (ie, the item image information of the brand "BRANDi" and the brand "BRANDj". Item image information) is selected.

The generative model (BRANDixj) outputs design image information (BRANDixj) corresponding to the brands "BRANDi" and "BRANDj".

The processor 32 adds a new record to the design image information database (FIG. 5). The following information is stored in each field of the new record.
-A new design image ID is stored in the "design image ID" field.
-Brand information is stored in the "Category" field.
-The design image information output from the generated model is stored in the "design image" field.

(1-4-2) Design image presentation process The design image presentation process of the first embodiment will be described. FIG. 7 is a sequence diagram of the design image presentation process of the first embodiment. FIG. 8 is a diagram showing an example of a screen displayed in the information processing of FIG. 7.

As shown in FIG. 7, the client device 10 executes the reception of the user instruction (S110).
Specifically, the processor 12 displays the screen P10 (FIG. 8) on the display.

The screen P10 includes the operation object B100 and the field objects F100 to F101.
The field objects F100 to F101 are objects that accept the designation of brand information from the user.
The operation object B100 is an object that confirms the designation of the field objects F100 to F101.

After step S110, the client device 10 executes the design request (S111).
Specifically, when the user specifies the brand with the field objects F100 to F101 and operates the operation object B100, the processor 12 transmits the design request data to the server 30. The design request data includes a combination of brand information specified by the field objects F100 to F101.

After step S111, the server 30 executes the design image selection (S130).
Specifically, the processor 32 refers to the design image information database (FIG. 5) to display information in the "design image" field (that is, design image information) associated with the combination of brands included in the design request data. select.

After step S130, the server 30 executes the design response (S131).
Specifically, the processor 32 transmits the design response data to the client device 10. The design response data includes the design image information selected in step S130.

After step S131, the client device 10 executes the display of the design image (S112).
Specifically, the processor 12 displays the screen P11 (FIG. 8) on the display.

The screen P11 includes the operation object B110 and the image objects IMG110 to IMG113.
The image objects IMG110 to IMG113 are image objects corresponding to the design image information included in the design response data.

According to the first embodiment, the server 30 presents the design image information output from the generative model corresponding to the combination of the plurality of categories specified by the user. This makes it possible to provide a novel design while retaining the individuality of existing items.

Further, according to the first embodiment, when presenting a plurality of design image information, the user can select the desired design image information.

Further, according to the first embodiment, when presenting one design image information, it is possible to propose the design image information corresponding to the condition specified by the user without letting the user select it.
In this case, the server 30 may select the design image information to be included in the design response data from the plurality of design image information output by the generation model, based on the user information about the user.

(2) Second Embodiment The second embodiment will be described. The second embodiment is an example of generating design image information in response to a user instruction.

(2-1) Outline of the Second Embodiment The outline of the second embodiment will be described. FIG. 9 is an explanatory diagram of an outline of the second embodiment.

As shown in FIG. 9, the server 30 stores item image information corresponding to a plurality of categories.
The server 30 receives designations of a plurality of categories (“CATEGORY 1” and “CATEGORY 2”) from the user via the client device 10.
The server 30 generates a generative model (CATEGORY1x2) using the item image information (CATEGORY1 and CATEGORY2) of a plurality of categories specified by the user.
The generative model (CATEGORY1x2) outputs design image information (CATEGORY1x2) corresponding to a plurality of categories specified by the user.
The server 30 presents the design image information (CATEGORY1x2) output from the generation model (CATEGORY1x2) to the user via the client device 10.

(2-2) Design Image Generation Process The design image generation process of the second embodiment will be described. FIG. 10 is a sequence diagram of the design image generation process of the second embodiment. FIG. 11 is a detailed flowchart of the generation of the design image of FIG. FIG. 12 is a diagram showing an example of a screen displayed in the information processing of FIG.

As shown in FIG. 10, the client device 10 executes steps S110 to S111 in the same manner as the design image presentation process (FIG. 7) of the first embodiment.

After step S111, the server 30 executes the design image generation (S230).

As shown in FIG. 11, the server 30 executes the item image selection (S2300).
Specifically, the processor 32 refers to the item image information database (FIG. 4) and refers to the information in the "item image" field associated with the brand information included in the design request data (that is, the information of the brand specified by the user). Item image information) is selected.

After step S2300, the server 30 executes the construction of the generation model (S2301).
Specifically, the processor 32 learns the generative model by inputting the item image information selected in step S2300 into the generative model stored in the storage device 31.

After step S2301, the server 30 executes the output of the design image (S2302).
Specifically, the processor 32 gives an output instruction to the generative model. The generative model outputs design image information in response to an output instruction.

After step S230, the server 30 executes step S131 in the same manner as the design image presentation process (FIG. 7) of the first embodiment.

After step S131, the client device 10 executes the display of the design image (S210).
Specifically, the processor 12 displays the screen P20 (FIG. 12) on the display.

The screen P20 includes image objects IMG110 to IMG113 and operation objects B200.
The operation object 200 is an object that receives a user instruction for resending the design request data to the server 30.

When the user operates the operation object B200, the processor 12 re-executes step S111. As a result, the server 30 regenerates the design image information. The generative model outputs different design image information each time step S2301 is executed.
In this case, the processor 12 displays the screen P21 (FIG. 12) on the display.
The screen P21 includes image objects IMG210 to IMG213 and operation objects B200. The image objects IMG210 to IMG213 are design image information generated in response to the operation of the operation object B200. The design image information generated in response to the operation of the operation object B200 is different from the design image information generated before the operation of the operation object B200. As a result, new design image information can be presented.

According to the second embodiment, the server 30 inputs the item image information of the category specified by the user into the generation model according to the designation of the category of the user. The generative model outputs different design image information each time a combination of item image information is input. As a result, new design image information can be provided each time the design image generation process is executed.

Further, according to the second embodiment, new design image information is presented after the operation object B200 is operated by the user. This allows the user to easily obtain the desired design image.

(2-3) Modification Example A modification of the second embodiment will be described. A modification of the second embodiment is an example of generating design image information using a generative model learned from item image information associated with feature information.

(2-3-1) Outline of Modified Example An outline of the modified example of the second embodiment will be described. FIG. 13 is an explanatory diagram of an outline of a modified example of the second embodiment.

As shown in FIG. 13, the server 30 stores the item image information and the feature information in association with each other.
The server 30 accepts the designation of a plurality of categories (“CATEGORY 1” and “CATEGORY 2”) and the designation of design features from the user via the client device 10.
The server 30 uses item image information (CATEGORY1 and CATEGORY2) of a plurality of categories specified by the user, and feature information corresponding to the design feature specified by the user among the feature information associated with each item image information. To train the generative model (CATEGORY1x2).
The generative model (CATEGORY1x2) outputs design image information (CATEGORY1x2) corresponding to a combination of a plurality of categories specified by the user and a feature specified by the user.
The server 30 presents the design image information (CATEGORY1x2) output from the generation model (CATEGORY1x2) to the user via the client device 10.

(2-3-2) Feature Information Database A feature information database of a modification of the second embodiment will be described. FIG. 14 is a diagram showing a data structure of a feature information database of a modified example of the second embodiment.

The feature information database of FIG. 14 stores feature information related to item features.
The feature information database includes an "image ID" field, an "image link" field, and a "feature" field.
Each field is associated with each other.

An image ID is stored in the "image ID" field. The image ID is an example of image identification information that identifies item image information.

The "image link" field stores information about the file name of the item image information.

Feature information (eg, feature vector) is stored in the "feature" field. The feature of the item is, for example, at least one of the following.
・ Target gender (for example, for men, women, or unisex)
・ Usage scene (for example, business, casual, or formal)
・ Size, color, taste, silhouette

(2-3-3) Design image generation processing The design image generation processing of the modified example of the second embodiment will be described. FIG. 15 is a sequence diagram of a design image generation process of a modified example of the second embodiment. FIG. 16 is a diagram showing an example of a screen displayed in the information processing of FIG.

As shown in FIG. 15, in the client device 10, the client device 10 executes the reception of the user instruction (S211).
Specifically, the processor 12 displays the screen P22 (FIG. 16) on the display.

The screen P22 includes the operation object B220 and the field objects F100 to F101 and F220.
The field object F220 is an object that accepts the designation of desired design features from the user.
The operation object B220 is an object that confirms the designation of the field objects F100 to F101 and F220.

After step S211 the client device 10 executes the design request (S212).
Specifically, when the user specifies the brand with the field objects F100 to F101, specifies the design features with the field objects F210, and operates the operation object B210, the processor 12 transmits the design request data to the server 30. do. The design request data includes a combination of brand information specified by the field objects F100 to F101 and a feature specified by the field object F210.

After step S212, the server 30 executes step S230 in the same manner as in FIG.
Specifically, after executing step S2300 as in FIG. 11, the processor 32 includes the selected item image information and the feature information associated with the item image information in the design request data in step S2301. The generation model is trained by inputting the feature information corresponding to the features to be generated into the generation model.
After step S2301, the processor 32 executes step S2302 in the same manner as in FIG. As a result, the generative model outputs the design image information.

After step S230, the server 30 executes S131 in the same manner as in FIG. 7.
After step S131, the client device 10 executes step S210 in the same manner as in FIG.

According to the modified example of the second embodiment, the generation model is trained using the item image information corresponding to the combination of the brand information specified by the user and the feature information corresponding to the feature specified by the user. Thereby, it is possible to easily obtain the design image information in which the desired feature of the user is more strongly reflected.

(3) Third Embodiment The third embodiment will be described. The third embodiment is an example of generating design image information according to at least one of user information and user instruction.

(3-1) Outline of the Third Embodiment The outline of the third embodiment will be described. FIG. 17 is an explanatory diagram of an outline of the third embodiment.

As shown in FIG. 17, the server 30 stores a combination of item image information and feature information of a plurality of categories and a generative model constructed by a combination of item image information and feature information of a plurality of categories. ..
The server 30 receives from the user a plurality of categories "CATEGORY1" and "CATEGORY2", and at least one of user information and user instructions regarding the user, via the client apparatus 10.
The server 30 selects a generation model (CATEGORY1x2) corresponding to a plurality of categories "CATEGORY1" and "CATEGORY2" specified by the user.
The server 30 adjusts the parameters of the selected generative model (CATEGORY1x2) based on at least one of the user information and the user instruction.
The generated model (CATEGORY1x2) with adjusted parameters outputs design image information (CATEGORY1x2) corresponding to a plurality of categories specified by the user.
The server 30 presents the design image information (CATEGORY1x2) output from the generation model (CATEGORY1x2) to the user via the client device 10.

(3-2) Database The database of the third embodiment will be described. The following database is stored in the storage device 31.

(3-2-1) User Information Database The user information database of the third embodiment will be described. FIG. 18 is a diagram showing a data structure of the user information database of the third embodiment.

The user information database of FIG. 18 stores user information about the user.
The user information database includes a "user ID" field, a "user name" field, a "user attribute" field, a "user image" field, a "user size" field, a "user preference" field, and an "action history". Includes fields and.
Each field is associated with each other.

The user ID is stored in the "user ID" field. The user ID is an example of user identification information that identifies a user.

The Username field stores information about the user's name (eg, text).

The "user attribute" field stores user attribute information related to the user's attribute. The "User Attribute" field includes a plurality of subfields (eg, "Gender" field and "Age" field).

The Gender field stores information about the user's gender.

The Age field stores information about the user's age.

The "user image" field stores user image information of the user (for example, image information including the user's face or whole body).

The User Size field stores user size information about the size of the user. The user size information is one of the following.
An index related to the size of the user's clothes (for example, S, M, or L)
・ Indicators related to the size of the user's body (for example, slender, standard, or big silhouette)
-Information on measurement results measured by a measuring device capable of measuring the size of each part of the user's body (for example, height, neck circumference, chest circumference, waist, and thigh).

In the "user preference" field, user preference information regarding the user's preference is stored. The user preference information is, for example, at least one of the following.
-Preferences for art (eg, music, movies, or paintings) -Preferences for brand nationality (eg, Japanese brand, French brand, or Italian brand) -Atmosphere of items (eg feminine, simple, avant-garde, etc. Or basic)
-Item genre (for example, American casual or mode)
・ Preference for behavior on social networks (information reacted on social networks or information posted on social networks)

The "Purchase History" field stores purchase history information regarding the history of items purchased by the user. The purchase history information is, for example, the item ID of the item purchased by the user.

(3-2-2) Model Information Database The model information database of the third embodiment will be described. FIG. 19 is a diagram showing a data structure of the model information database of the third embodiment.

The model information database of FIG. 19 stores model information related to the generative model.
The model information database includes a "model ID" field, a "model name" field, and a "category" field.
Each field is associated with each other.

The model ID is stored in the "model ID" field. The model ID is an example of model identification information that identifies the generated model.

The "model name" field stores information about the model name (eg, text).

The "Category" field stores category information (for example, brand information) regarding the combination of categories corresponding to the generative model.

(3-3) Design image generation process The design image generation process of the third embodiment will be described. FIG. 20 is a sequence diagram of the design image generation process of the third embodiment. FIG. 21 is a diagram showing an example of a screen displayed in the information processing of FIG. 20. FIG. 22 is a detailed flowchart of the generation of the design image of FIG.

As shown in FIG. 20, the client device 10 executes the reception of the user instruction (S310).
Specifically, the processor 12 displays the screen P30 (FIG. 21) on the display.

The screen P30 includes the operation object B300 and the field objects F100 to F101 and F300 to F303.
The field object F300 is an object that receives a user instruction for designating a user ID.
The field object F301 is an object that receives a user instruction for designating a usage scene of a desired item.
The field object F302 is an object that receives a user instruction for designating a taste of a desired item.
The field object F303 is an object that receives a user instruction for designating a mixing ratio of a plurality of brands input to the field objects F100 to F101.
The operation object B300 is an object that receives a user instruction for confirming the input to the field objects F100 to F101 and F300 to F302.

After step S310, the client device 10 executes the design request (S311).
Specifically, when the user inputs a user instruction to the field objects F101 to F101 and at least one of the field objects F300 to F302 and operates the operation object B300, the processor 12 transmits the design request data to the server 30. Send to. The design request data includes the following information.
-Combination of brand information specified by field objects F100 to F101-User instruction specified by at least one of field objects F300 to F303 (that is, at least one of a user ID, a desired usage scene, and a desired taste). User instructions regarding)

After step S311 the server 30 executes the design image generation (S330).

As shown in FIG. 22, the server 30 executes the selection of the generation model (S3300).
Specifically, the processor 32 refers to the model information database (FIG. 19) to identify information (that is, model ID) in the "model ID" field associated with the brand information included in the design request data. The identified model ID identifies the selected generative model.

After step S3301, the server 30 executes parameter adjustment (S3301).

In the first example of step S3301, when the design request data includes the user ID specified by the field object F300, the processor 32 refers to the user information database (FIG. 18) and is associated with the "user" associated with the user ID. Identify the user attribute information stored in the Attributes field.
The processor 32 adjusts the parameters of the generation model selected in step S3300 based on the combination of brand information included in the design request data and the specified user attribute information.

In the second example of step S3301, when the design request data includes the user ID specified by the field object F300, the processor 32 refers to the user information database (FIG. 18) and is associated with the "user" associated with the user ID. Identify the user preference information stored in the Preferences field.
The processor 32 adjusts the parameters of the generation model selected in step S3300 based on the combination of brand information included in the design request data and the specified user preference information.

In the third example of step S3301, when the design request data includes the user ID specified by the field object F300, the processor 32 refers to the user information database (FIG. 18) and associates the "purchase" associated with the user ID. Identify the purchase history information (eg, item ID) stored in the History field.
The processor 32 identifies the feature information of the item image information associated with the identified item ID with reference to the feature information database (FIG. 14).
The processor 32 adjusts the parameters of the generation model selected in step S3300 based on the combination of brand information included in the design request data and the identified feature information.

In the fourth example of step S3301, when the design request data includes the user ID specified by the field object F300, the processor 32 refers to the user information database (FIG. 18) and is associated with the "user" associated with the user ID. Identify the user image information stored in the Image field.
The processor 32 extracts the feature amount related to the feature amount of the user's body by applying the feature amount analysis to the user image information. Body features include, for example, at least one of body shape, height, facial contours, facial site placement, skin color, and hair color.
The processor 32 adjusts the parameters of the generation model selected in step S3300 based on the combination of brand information included in the design request data and the extracted features.

In the fifth example of step S3301, when the design request data includes the information about the usage scene specified by the field object F301, the processor 32 is selected in step S3300 based on the information about the usage scene included in the design request data. Adjust the parameters of the generated model.

In the sixth example of step S3301, when the design request data includes the information about the taste specified by the field object F302, the processor 32 generates the product selected in step S3300 based on the information about the taste included in the design request data. Adjust model parameters.

In the seventh example of step S3301, when the design request data contains the mixing ratio specified by the field object F303, the processor 32 of the generation model selected in step S3300 based on the mixing ratio included in the design request data. Adjust the parameters.

After step S3301, the server 30 executes the output of the design image (S3302).
Specifically, the processor 32 gives an output instruction to the generative model whose parameters have been adjusted in step S3301. The generative model outputs design image information in response to an output instruction.

After step S330, the server 30 executes step S131 in the same manner as in FIG. 7.
After step S331, the client device 10 executes step S210 in the same manner as in FIG.

According to the third embodiment, the parameters of the generative model are adjusted according to at least one of the user information and the user instruction. This makes it possible to present design image information that reflects the individuality of the user and the combination of existing items.

(3-4) Modification Example A modification of the third embodiment will be described.

(3-4-1) Modification 1
A modification 1 of the third embodiment will be described. The first modification of the third embodiment is an example of correcting the design image information according to the user information.

(3-4-1-1) Outline of Modified Example 1 An outline of Modified Example 1 of the third embodiment will be described. FIG. 23 is an explanatory diagram of an outline of the first modification of the third embodiment.

As shown in FIG. 23, the server 30 causes the generation model corresponding to the combination of a plurality of categories (“CATEGORY1” and “CATEGORY2”) specified by the user to output the design image information (CATEGORY1x2).
After presenting the design image information (CATEGORY1x2) to the user, the server 30 corrects the design image information (CATEGORY1x2) based on the correction instruction specified by the user to generate the corrected image information (CATEGORY1x2).
The server 30 presents the corrected image information (CATEGORY1x2) to the user.

(3-4-1-2) Design Image Generation Process The design image generation process of Modification 1 of the third embodiment will be described. FIG. 24 is a sequence diagram of the design image generation process of the first modification of the third embodiment. FIG. 25 is a diagram showing an example of a screen displayed in the information processing of FIG. 24. FIG. 26 is a diagram showing an example of a screen displayed in the information processing of FIG. 24.

As shown in FIG. 24, the client device 10 executes steps S310 to S311 in the same manner as in FIG.
After step S311 the server 30 executes steps S330 and S131 as in FIG.

After step S131, the client device 10 executes the display of the design image (S410).
Specifically, the processor 12 displays the screen P40 (FIG. 25) on the display.

The screen P40 includes image objects IMG110 to IMG113, and operation objects B200 and B400.
The operation object 400 is an object that receives a user instruction for correction.

When the user operates the image object IMG110 and the operation object B400, the processor 12 displays the screen P41 (FIG. 25) on the display.

The screen P41 includes the operation object B410 and the field objects F410 to F412.
The field object F410 is an object that receives a user instruction for changing the shape of at least one of the image objects IMG110 to IMG113 (for example, an image object specified by the user). As an example, the user can enter a "smaller" or "larger" user instruction into the field object F410.
The field object F411 is an object that receives a user instruction for adding a part to at least one of the image objects IMG110 to IMG113 (for example, an image object specified by the user). As an example, the user can enter at least one user instruction of a "pocket" and a "button" into the field object F411.
The field object F412 is an object that receives a user instruction for reflecting a brand image on at least one of the image objects IMG110 to IMG113 (for example, an image object specified by the user). As an example, the user can input at least one user instruction of "logo" and "pattern" into the field object F412.
The operation object B411 is an object that receives a user instruction for confirming the contents input to the field objects F410 to F412.

After step S410, the client device 10 executes the correction request (S411).
Specifically, the processor 12 transmits the correction request data to the server 30. The correction request data includes user instructions input to the field objects F410 to F412.

After step S411, the server 30 executes the correction (S430).

Specifically, the storage device 31 stores an image correction filter corresponding to a user-instructed item that can be accepted by the field objects F410 to F412.
From the image correction filter stored in the storage device 31, the processor 32 outputs a user instruction (user instruction for changing the shape, a user instruction for adding an item, and a brand image) included in the correction request data. Select an image correction filter that corresponds to at least one of the user instructions to reflect). As an example, when the user size information is "detailed", the processor 32 selects an image correction filter that reduces the design image information by 10%. When the user size information is "big silhouette", the processor 32 selects an image correction filter that enlarges the design image information by 15%.
The processor 32 generates the corrected image information by applying the selected image correction filter to the design image information generated in step S330.

After step S430, the server 30 executes the correction response (S431).
Specifically, the processor 32 transmits the correction response data to the client device 10. The correction response data includes the correction image information generated in step S4302.

After step S431, the client device 10 executes the display of the corrected image (S412).
Specifically, the processor 12 displays the screen P41 (FIG. 26) on the display.

The screen P41 includes image objects IMG420 to IMG423.
The image objects IMG420 to IMG423 are objects corresponding to the corrected image information included in the correction response data.

According to the first modification of the third embodiment, the design image information is corrected according to the instruction of the user. As a result, the user's preference can be reflected in the design image information.

(3-4-2) Modification 2
A modification 2 of the third embodiment will be described. The second modification is an example of correcting the design image information based on the user size information measured by the measuring device.

(3-4-2-1) Outline of Modified Example 2 An outline of Modified Example 2 of the third embodiment will be described. FIG. 27 is an explanatory diagram of an outline of a modification 2 of the third embodiment.

As shown in FIG. 27, the server 30 causes the generation model corresponding to the combination of a plurality of categories (“CATEGORY1” and “CATEGORY2”) specified by the user to output the design image information (CATEGORY1x2).
After the design image information (CATEGORY1x2) is presented to the user, the user measures the size of each part of his / her body using a measuring device.
The server 30 generates the corrected image information (CATEGORY1x2) by correcting the design image information (CATEGORY1x2) based on the user size information regarding the size measured by the measuring device.
The server 30 presents the corrected image information (CATEGORY1x2) to the user.

(3-4-2-2) Design image generation process The design image generation process of Modification 2 of the third embodiment will be described.

In the first example of step S430 of FIG. 24, the processor 32 refers to the user information database (FIG. 18) and refers to the user size information (user regarding the measurement result by the measuring device) associated with the user ID included in the design request data. Size information) is specified.
In the second example of step S430, the processor 32 acquires the user size information regarding the measurement result by the measuring device from the measuring device or the client device 10. The processor 32 specifies the measurement result as user size information.

The processor 32 selects an image correction filter corresponding to the specified user size information from the image correction filters stored in the storage device 31. More specifically, when the user size information is information related to the measurement result, the processor 32 corrects each part of the design image information according to the size of each part of the user's body.

The processor 32 generates the corrected image information by applying the selected image correction filter to the design image information generated in step S330.

According to the second modification of the third embodiment, the design image information is corrected based on the user size information (for example, information on the measurement result measured by the measuring device). Thereby, the design image information suitable for the user's body can be presented to the user.

(3-4-3) Modification 3
A modified example 3 of the third embodiment will be described. Modification 3 of the third embodiment is an example of correcting design image information by using a correction model.

(3-4-3-1) Outline of Modified Example 3 An outline of Modified Example 3 of the third embodiment will be described. FIG. 28 is an explanatory diagram of an outline of a modification 3 of the third embodiment.

As shown in FIG. 28, the server 30 causes the generation model corresponding to the combination of a plurality of categories (“CATEGORY1” and “CATEGORY2”) specified by the user to output the design image information (CATEGORY1x2).
After presenting the design image information (CATEGORY1x2) to the user, the server 30 inputs the design image information (CATEGORY1x2) to the correction model based on the correction instruction specified by the user. The correction model outputs corrected image information (CATEGORY1x2).
The server 30 presents the corrected image information (CATEGORY1x2) to the user.

(3-4-3-2) Design Image Generation Process The design image generation process of Modification 3 of the third embodiment will be described.

The learned correction model is stored in the server 30. The correction model is learned by deep learning using a plurality of item image information, feature information associated with each item image information, and an image processing filter. The correction model is, for example, GAN or DCGAN.

In step S430 of FIG. 24, the server 30 corrects the design image information by using the correction model stored in the storage device 31.
Specifically, the processor 32 inputs the image correction filter selected in step S430 and the design image information generated in step S330 into the correction model. As a result, the correction model outputs the correction image information according to the user instruction included in the correction request data.

According to the third modification of the third embodiment, the correction model outputs the correction image information. As a result, the design image information corrected with higher accuracy can be presented to the user.

(4) Fourth Embodiment The fourth embodiment will be described. The fourth embodiment is an example of generating design image information based on item image information stored on the network.

(4-1) Outline of Fourth Embodiment An outline of the fourth embodiment will be described. FIG. 29 is an explanatory diagram of an outline of the fourth embodiment.

A plurality of item image information is stored in the server 30 of FIG. 29.
The server 30 acquires the user information and the user size information.
The server 30 presents the image information of the recommended item recommended to the user (hereinafter referred to as "recommended image information") based on the user information and the user size information from the plurality of item image information. For example, tops recommended image information (CATEGORY1) and bottoms recommended image information (CATEGORY2) are presented.
The server 30 acquires a user instruction regarding a desired category (CATEGORY1).
The server 30 adjusts the parameters of the generative model (CATEGORY1x2) based on the category (CATEGORY1) corresponding to the user instruction.
The parameter-adjusted generative model (CATEGORY1x2) outputs design image information (CATEGORY1x2) corresponding to the category (CATEGORY1) corresponding to the user instruction.
The server 30 presents the design image information (CATEGORY1x2) output from the generation model (CATEGORY1x2) to the user via the client device 10.

(4-2) Design image generation process The design image generation process of the fourth embodiment will be described. FIG. 30 is a sequence diagram of the design image generation process of the fourth embodiment. FIG. 31 is a diagram showing an example of a screen displayed in the information processing of FIG. 30. FIG. 32 is a detailed flowchart of the generation of the design image of FIG.

As shown in FIG. 30, the client device 10 executes the reception of the user instruction (S510).
Specifically, the processor 12 displays the screen P50 (FIG. 31) on the display.

The screen P50 includes an operation object B500 and a field object F500.
The field object F500 is an object that receives a user instruction for designating a user ID.
The operation object B500 is an object that receives a user instruction for confirming the input to the field object F500.

After step S510, the client device 10 executes the recommendation request (S511).
Specifically, when the user inputs a user instruction to the field object F500 and operates the operation object B500, the processor 12 transmits the recommendation request data to the server 30. The recommendation request data includes the user ID specified by the field object F500.

After step S511, the server 30 executes the identification of the recommended item (S530).
Specifically, the processor 32 refers to the user information database (FIG. 18) and identifies the user information associated with the user ID included in the recommendation request data.

The processor 32 identifies the item ID of the recommended item based on the specified user information with reference to the item image information database (FIG. 4) and the feature information database (FIG. 14).
As an example, the storage device 31 stores a coordination model in which a preferable combination of a plurality of items is defined. The processor 32 identifies the item ID of the owned item owned by the user by referring to the information in the "purchase history" field associated with the user ID included in the recommendation request data. The processor 32 inputs the category information and the feature information associated with the item ID of the owned item into the coordination model. The coordination model outputs the item ID of the recommended item, which is preferably combined with the owned item, from the item IDs stored in the item information database.

After step S530, the server 30 executes the recommendation response (S531).
Specifically, the processor 32 transmits the recommendation response data to the client device 10. The recommendation response data includes the following information.
-Item ID specified in step S530
-Item image information associated with the item ID (that is, recommended image information of the recommended item)

After step S531, the client device 10 executes the display of the recommended image (S512).
Specifically, the processor 12 displays the screen P51 on the display.

The screen P51 includes image objects IMG510 to IMG513, operation objects B510, and field objects F510. Item IDs of recommended items are assigned to the image objects IMG510 to IMG513.
The image object IMG510 is the recommended image information of the recommended item corresponding to the category “CATEGORY1” (for example, the type “TOPS”).
The image object IMG511 is the recommended image information of the recommended item corresponding to the category “CATEGORY2” (for example, the type “BOTOMS”).
The image object IMG512 is the recommended image information of the recommended item corresponding to the category “CATEGORY3” (for example, the type “SHOES”).
The image object IMG513 is the recommended image information of the recommended item corresponding to the category “CATEGORY4” (for example, the type “WATCH”).
The field object F510 is an object that receives a user instruction for designating a desired item type.
The operation object B510 is an object for confirming the operation on the image objects IMG510 to IMG513 and the input to the field object F510.

After step S512, the client device 10 executes the design request (S513).
Specifically, when the user specifies at least two image objects IMG510 to IMG513, specifies a desired type for the field object F510, and operates the operation object B510, the processor 12 transmits the design request data to the server 30. Send to. The design request data includes the following information.
-Item ID assigned to the image objects IMG510 to IMG513 specified by the user.
-User instruction specified by field object F510 (that is, desired type)

After step S513, the server 30 executes the generation of the design image (S530).

As shown in FIG. 32, the server 30 executes the selection of the generation model (S5300).
Specifically, the processor 32 refers to the item information database (FIG. 4) to obtain information in the "category" field (for example, information in the "brand" field) associated with the item ID included in the design request data. Identify.
The processor 32 refers to the model information database (FIG. 19) to identify the information in the "model ID" field (ie, the model ID) associated with the information in the identified category field. The identified model ID identifies the selected generative model.

After step S5300, the server 30 executes parameter adjustment (S5301).
Specifically, the processor 32 adjusts the parameters of the generative model selected in step S5300 based on the desired type contained in the design request data. This increases the probability that the generative model will generate the desired type of design image information.

After step S5301, the server 30 executes step S3302 in the same manner as in FIG. 22.

After step S530, the server 30 executes step S131 in the same manner as in FIG.
After step S131, the client device 10 executes step S210 in the same manner as in FIG.

According to the fourth embodiment, the design image information of the desired type of the user is presented based on the recommended image information of the recommended item presented to the user. As a result, it is possible to provide a novel design while retaining the individuality of the recommended item recommended by the user.

(5) Other Modification Examples Other modification examples will be described.

The storage device 11 may be connected to the client device 10 via the network NW. The storage device 31 may be connected to the server 30 via the network NW.

In the present embodiment, an example in which information processing is realized by a combination of the client device 10 and the server 30 is shown, but each step of the above information processing is one of the client device 10 and the server 30, or a plurality of steps on the network. It can also be realized in a distributed environment with the above equipment. As described above, the present embodiment can be applied to various forms such as a web service realized by the server 30 or a program installed in the client device 10.

In the present embodiment, the communication interfaces 14 and 34 may support not only communication using the Internet protocol but also communication by a wired or wireless bus connection, USB (registered trademark), or Bluetooth (registered trademark). ..

In this embodiment, an example in which the item is a fashion item is shown. However, the "item" of this embodiment may be an item other than a fashion item. That is, the "category" of this embodiment is not limited to fashion brands. Items other than fashion items include, for example, at least one of the following.
・ Products (for example, electronic devices or sports equipment)
・ Product packaging (for example, product packaging or container)

In this embodiment, an example of presenting design image information corresponding to a combination of two categories has been described. However, this embodiment is not limited to this. This embodiment is also applicable to the case of presenting design image information corresponding to a combination of three or more categories.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited to the above embodiments. Further, the above-described embodiment can be improved or modified in various ways without departing from the spirit of the present invention. Moreover, the above-described embodiment and modification can be combined.

1: Information processing system 10: Client device 11: Storage device 12: Processor 13: Input / output interface 14: Communication interface 30: Server 31: Storage device 32: Processor 33: Input / output interface 34: Communication interface

Claims (10)

A means for generating design image information corresponding to the combination using a generation model corresponding to a combination of a plurality of categories is provided.
A means for storing the design image information generated by using the generative model is provided.
It has a means to accept the specification of multiple categories from the user.
A means for presenting design image information corresponding to a combination of a plurality of categories specified by the user from a plurality of design image information stored by the storage means is provided.
Information processing device. The presenting means presents design image information corresponding to a combination of a plurality of categories designated by the user and user attribute information relating to the user's attributes from the plurality of design image information.
The information processing device according to claim 1. It has a means to accept the specification of multiple categories from the user.
A means for constructing a generation model corresponding to a combination of the plurality of categories by using the item image information corresponding to each of the plurality of categories specified by the user is provided.
A means for generating a plurality of design image information corresponding to a combination of the plurality of categories by using the generation model is provided.
A means for presenting at least one of the plurality of generated design image information is provided.
Information processing device. It is provided with a means for associating and storing the item image information of each item and the feature information regarding the characteristics of each item.
The generation means constructs the generation model by using the item image information of a plurality of categories and the feature information associated with each item image information.
The information processing device according to claim 3. The feature information is information on at least one of the target gender, usage scene, size, color, taste, and silhouette of the item.
The information processing device according to claim 4. A means for adjusting the parameters of the generative model based on the user instruction of the user.
The information processing device according to claim 4 or 5. A means for adjusting the parameters of the generative model based on the user information about the user.
The user information includes at least one of user attribute information regarding the user's attributes, user preference information regarding the user's preference, purchase history information regarding the history of items purchased by the user, and user image information of the user.
The information processing device according to any one of claims 4 to 6. After presenting the design image information, a means for receiving a correction instruction from the user is provided.
A means for generating corrected image information by correcting the design image information based on the correction instruction is provided.
The presenting means presents the generated corrected image information.
The information processing device according to any one of claims 3 to 7. The category is brand information about the brand of the item.
The information processing device according to any one of claims 1 to 8. A program for operating a computer as each means according to any one of claims 1 to 9.

Images