Information processor, information processing method and information processing program

Abstract

To propose a composition of a thumbnail image corresponding to a retrieval query.SOLUTION: An information processor includes a reception part and a provision part. The reception part accepts a designation of a target commodity and a target retrieval query from an exhibitor. The provision part provides the exhibitor with a composition of a thumbnail image of the target commodity corresponding to the target retrieval query, using the relevance between the retrieval query and a product image, which is estimated according to the user's behavioral history.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] Conventionally, a technology has been disclosed that suggests a pose for a model when taking a photo of a fashion item. For example, this technology suggests a pose based on the composition of a product photo with a high purchase rate among product photos of products similar to the product to be photographed (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2023-65909 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, no consideration has been given to providing a composition that takes into account a search query.

[0005] The present invention has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can suggest compositions of thumbnail images that correspond to a search query. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objective, the information processing device of the present invention includes a reception unit that receives a target product and a target search query from a seller, and a provision unit that provides the seller with a composition of a thumbnail image of the target product corresponding to the target search query, by utilizing the relevance between the search query and a product image estimated based on a user's behavioral history. Effect of the Invention

[0007] According to the present invention, it is possible to provide a composition of thumbnail images corresponding to a search query. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a provision system according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. [Diagram 3] FIG. 3 is a diagram showing a specific example of information processing according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of content according to the embodiment. [Diagram 5] FIG. 5 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of information stored in the image information storage unit according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of information stored in a keyword information storage unit according to the embodiment. [Figure 8] FIG. 8 is a diagram showing an example of an image transition in the information processing according to the embodiment. [Figure 9] FIG. 9 is a flowchart illustrating an example of a processing procedure of information processing according to the embodiment. [Figure 10] FIG. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0010] [Embodiment] [1.1 System] First, the provision system shown in Fig. 1 will be described. Fig. 1 is a diagram showing a configuration example of the provision system according to the embodiment. As shown in Fig. 1, the provision system includes an information processing device 1, a user terminal 10, and a seller terminal 100. The information processing device 1, the user terminal 10, and the seller terminal 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication.

[0011] The information processing device 1 provides an electronic commerce service that provides (searches, sells, etc.) products including clothing (also called fashion items, including clothes, underwear, footwear (also called shoes), headwear (caps, hats, etc.), bags, accessories (also called accessories), etc.), cosmetics (also called fashion items), etc. The information processing device 1 also provides a coordination service that accepts posts from users of content (images, videos, articles, etc.) showing outfits using multiple clothing items, content showing makeup using one or more cosmetics, etc., and provides (searches, distributes, etc.) the posted content to other users. For example, the information processing device 1 can be realized by a server device, a cloud system, etc.

[0012] Furthermore, the information processing device 1 provides various services to users by using a distributed representation space learned in advance, as described later. Moreover, images and keywords (including tags, etc.) are projected in the distributed representation space according to the embodiment, and the closeness between images, images and keywords, and keywords and keywords are projected. The closer they are, the closer they are in the distributed representation space. That is, the similarity between images, images and keywords, and keywords and keywords can be measured as a distance in the distributed representation space. Note that the closeness in the distributed representation space according to the embodiment includes, for example, closeness based on Euclidean distance and closeness based on cosine distance.

[0013] The information processing device 1 uses the distributed representation space to select thumbnail images of products corresponding to a search query specified by a user. For example, the information processing device 1 projects multiple candidate images associated with products, a search query (keyword), and user attributes into the distributed representation space, selects candidate images similar to the search query and user attributes as thumbnail images of each product, and provides them to the user.

[0014] That is, even for the same product, the information processing device 1 provides different thumbnail images depending on the search query or the user who input the search query. That is, the information processing device 1 can improve the user's purchasing motivation by providing an image corresponding to the user's search intent as a thumbnail image from multiple candidate images each associated with a product.

[0015] The information processing device 1 may also have a function as a web server that provides a website related to the service. The information processing device 1 may also be a device that distributes information to be displayed on applications related to various services installed in the user terminal 10 to the user terminal 10. The information processing device 1 may also be a device that distributes the application data itself.

[0016] Furthermore, the information processing device 1 may function as a distribution device that distributes control information to the user terminal 10. Here, the control information is described in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). Note that the application itself distributed from the information processing device 1 may be regarded as the control information.

[0017] Furthermore, in this embodiment, the information processing device 1 can also propose to each seller terminal 100 a composition of a thumbnail image of a product to be put up for sale by using the above-mentioned distributed representation space technique.

[0018] The user terminal 10 is an information processing device used by a user. The user terminal 10 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. The user terminal 10 displays information distributed by the information processing device 1, a server device that provides a predetermined service, etc., using a web browser or an application.

[0019] The seller terminal 100 is an information processing device used by a seller (store, brand) who sells a product on the online shopping mall provided by the information processing device 1. The seller terminal 100 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The seller terminal 100 also displays information distributed by the information processing device 1 or a server device that provides a predetermined service, or the like, using a web browser or an application.

[0020] [1.2 Information Processing] Next, information processing according to an embodiment will be described with reference to Fig. 2. As described above, the information processing device 1 selects and provides thumbnail images from each product corresponding to a search query or the like by using a distributed representation space. On the other hand, a problem occurs in that the seller does not know what kind of thumbnail image to prepare in advance for each search query.

[0021] Therefore, the information processing according to the embodiment supports the seller in creating thumbnail images by suggesting compositions of thumbnail images corresponding to the search query to the seller.

[0022] Fig. 2 is a diagram showing an example of information processing according to an embodiment. As shown in Fig. 2, the information processing device 1 accepts a designation of a target product and a target search query from the seller terminal 100 (step S1).

[0023] Here, the target product includes a product that the seller is considering putting up for sale in the online shopping mall provided by the information processing device 1 and a product that the seller has already put up for sale. Also, the target search query is a search query for a target product that the seller expects to sell in the online shopping mall.

[0024] The information processing device 1 proposes a composition of a thumbnail image of a target product in the online shopping mall based on a target product and a target search query specified from the seller terminal 100 (step S2).

[0025] That is, when a seller specifies a target product and a target search query, the information processing device 1 proposes a composition of a thumbnail image of the target product that matches the target search query. This makes it possible to create an appropriate thumbnail image that matches the seller and the target search query.

[0026] Next, an overview of the process of proposing a composition of a thumbnail image will be described with reference to Fig. 3. Fig. 3 is a diagram showing a specific example of information processing according to an embodiment. As shown in Fig. 3, the information processing device 1 receives a product image Is of a target product and a target search query qs from a seller.

[0027] In the example shown in the figure, the target product is a short-sleeved knitwear, and the target search query qs is "golf". Note that in the figure, the seller specifies the target product by the product image Is, but the target product may be specified by text. Also, the target search query qs may be specified by, for example, an image, in addition to text.

[0028] Next, the information processing device 1 projects the product image Is and the target search query qs into the distributed representation space S. As shown in the figure, in addition to the product image Is and the target search query qs, image vectors Ia1 to Ia3 (hereinafter also referred to as image vector Ia), which are feature vectors of the images of each product (for example, thumbnail images), are projected into the distributed representation space S.

[0029] The information processing device 1 selects an image vector Ia that is close to the product image Is and the target search query qs from among the image vectors Ia projected into the distributed representation space S. For example, the information processing device 1 selects an image vector Ia that has the smallest area of ​​space T that connects each image vector Ia, the product image Is, and the target search query qs. In the example shown in the figure, the area of ​​space T that connects the image vector Ia1 is the smallest, so the information processing device 1 selects the image vector Ia1.

[0030] Then, the information processing device 1 proposes an image corresponding to the image vector Ia1 as a composition of a thumbnail image of the product image Is in the target search query qs. In addition, as shown in Fig. 3, the information processing device 1 can generate a sample image Ic of the thumbnail image and then propose the sample image Ic.

[0031] For example, the sample image Ic is an image in which a person (model) appearing in the image corresponding to the image vector Ia1 is wearing the product (knitwear) in the product image Is, and is an image generated, for example, by an image generation AI, as described below.

[0032] Furthermore, in addition to proposing the composition of the thumbnail image, the information processing device 1 can also provide suggested content that emphasizes the symbolic part of the target search query or displays the search query corresponding to the sample image Ic.

[0033] 4 is a diagram illustrating an example of content according to an embodiment. As illustrated in the left diagram of FIG 4, in a sample image Ic, emphasis marks A1 and A2 are superimposed on symbolic portions of a target search query qs, and further, a corresponding search query qc corresponding to the sample image Ic is displayed.

[0034] The symbolic portion of the target search query qs is a portion of the sample image Ic whose feature vector is close to the feature vector of the target search query qs when the sample image Ic is divided into multiple regions and projected onto the distributed representation space S.

[0035] Moreover, the corresponding search query qc is a feature vector of a search query (keyword) close to the sample image Ic in the distributed representation space S. In this way, the information processing device 1 can allow the seller to grasp information about the search query related to the sample image Ic in more detail by proposing the symbolic part of the target search query qs together with the corresponding search query qc.

[0036] As shown in the right diagram of the figure, the information processing device 1 also provides content that visualizes statistical information related to the search query. In the example shown in the figure, the content is a histogram H. For example, the histogram H shows the number of searches for each search query in the online shopping mall, and among the search queries, a search query corresponding to a corresponding search query qc is highlighted and displayed. The number of search queries corresponding to the corresponding search query qc may be displayed. In addition, if there are already one or more candidate images of thumbnail images for the target product, the search query corresponding to the corresponding search query qc corresponding to each candidate image may be highlighted and displayed. This allows the user to understand which search query is lacking in candidate images of thumbnail images.

[0037] In the example shown in Fig. 4, the corresponding search query qc, "autumn" and "slim", are highlighted in the histogram H. For example, when a seller specifies a search query displayed in the histogram H, the seller can also specify the search query as the target search query qs.

[0038] For example, when a seller selects a search query of "denim" from the histogram H, the information processing device 1 sets the target search query qs as "denim" and proposes a sample image Ic corresponding to "denim."

[0039] In this way, the information processing device 1 accepts the designation of the target product and the target search query from the seller, and proposes the composition of the thumbnail image of the target product corresponding to the target search query. This allows the information processing device 1 to appropriately support the seller in creating thumbnail images. Note that the information processing device 1 may register the sample image Ic as a thumbnail image or a candidate image in the online shopping mall in response to an instruction from the seller.

[0040] In addition, information about users (e.g., user attributes) can also be projected into the distributed representation space S, and the information processing device 1 can accept specifications from the seller regarding target users who are the targets of the target product, and suggest thumbnail image compositions for the target users.

[0041] More specifically, the information processing device 1 may suggest, as the composition of the thumbnail image, the composition of the image vector that is close to the product image, the target search query, and the target user among the image vectors projected into the distributed representation space S.

[0042] In this way, the information processing device 1 can propose a composition of thumbnail images based on each vector projected into the distributed representation space S, thereby responding to the target search query and proposing a composition of thumbnail images of the target product that is appropriate for the target user.

[0043] [2. Information Processing Device] Next, a configuration example of the information processing device 1 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a block diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in Fig. 5, the information processing device 1 includes a communication unit 2, a storage unit 3, and a control unit 4. Note that the information processing device 1 may also include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator who uses the information processing device 1, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0044] The communication unit 2 is realized by, for example, a network interface card (NIC) etc. The communication unit 2 is connected to a communication network such as 4G (4th Generation) or 5G (5th Generation) by wire or wirelessly, and transmits and receives information to and from each of the user terminals 10 etc. via the communication network.

[0045] The storage unit 3 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 3 has an image information storage unit 31, a keyword information storage unit 32, and a model storage unit 33.

[0046] The image information storage unit 31 stores image information. The image information is information about an image to be compared with a target product, such as an image of a product exhibited in an online shopping mall (including a thumbnail image and a candidate image thereof) or an image related to a coordination posted by a user.

[0047] Fig. 6 is a diagram showing an example of information stored in the image information storage unit 31 according to the embodiment. As shown in Fig. 6, the image information storage unit 31 stores information items such as "image ID" and "image information" in association with each other.

[0048] "Image ID" indicates identification information for identifying an image. "Image information" indicates image information. In the example shown in FIG. 6, conceptual information such as "Image information #1" and "Image information #2" is stored in "Image information", but in reality, various images related to products and information such as the brand name and product name related to the corresponding products are stored.

[0049] The keyword information storage unit 32 stores keyword information. The keyword information storage unit 32 stores information related to keywords (search queries) used by users for searches in the online shopping mall provided by the information processing device 1.

[0050] Fig. 7 is a diagram showing an example of information stored in the keyword information storage unit 32 according to the embodiment. As shown in Fig. 7, the keyword information storage unit 32 stores information items such as "keyword ID", "keyword", and "number of searches" in association with each other.

[0051] "Keyword ID" indicates identification information for identifying a keyword. "Keyword" indicates a keyword. "Search count" indicates the number of searches for the corresponding keyword. The search count may be a cumulative total, or may be the number of searches within a specified period of time. The search count may also include the number of searches for each user attribute.

[0052] The model storage unit 33 stores the model. For example, the model is a model that projects each image, keyword, and user attribute into the same distributed representation space. For example, the model is a VSE model that is trained so that the closer the images are to each other, the closer the images are to each other, the closer the keywords are to each other, the more similar the feature vectors are in the distributed representation space.

[0053] The model can also project user attributes into the same distributed representation space as the images and keywords. For example, the model can be constructed using Convolutional Neural Networks (CNNs).

[0054] Next, the control unit 4 will be described. The control unit 4 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM as a working area. The control unit 4 is also, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0055] As shown in Fig. 5, the control unit 4 includes a receiving unit 41, a selecting unit 42, a generating unit 43, and a providing unit 44, and realizes or executes the functions and actions of information processing described below. The internal configuration of the control unit 4 is not limited to the configuration shown in Fig. 5, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationship between the processing units in the control unit 4 is not limited to the connection relationship shown in Fig. 5, and may be other connection relationships.

[0056] The reception unit 41 receives designation of a target product and a target search query from a seller. For example, the reception unit 41 acquires information on a product image of the target product and a target search query from the seller through the seller terminal 100. At this time, the reception unit 41 may receive designation on a target user from the seller.

[0057] Based on the target product and the target search query accepted by the accepting unit 41, the selecting unit 42 selects a reference image corresponding to the target search query from the image information stored in the image information storage unit 31.

[0058] For example, the selection unit 42 projects the product image of the target product and the target search query into a distributed representation space, respectively, using a model that has learned the relevance between the search query and an image specified by the user in the search results based on the search query.

[0059] Then, the selection unit 42 selects images corresponding to image vectors Ia similar to the product image and the target search query from among the image vectors Ia (see FIG. 3) of the images projected in advance into the distributed representation space.

[0060] That is, the selection unit 42 selects an image that is similar to an item shown in the product image of the target product and similar to the target search query by using the distributed representation space. The selection unit 42 may also project each search query into the distributed representation space and select an image that is similar to the feature vectors of multiple search queries. That is, in this case, the selection unit 42 selects images that correspond to multiple search queries.

[0061] The selection unit 42 also selects a search query related to the target search query, for example, based on the target search query. The related search query here is a search query that is frequently used simultaneously with the target search query, or a search query that combines the target search query with a keyword that has a different structure, style, season, or the like.

[0062] For example, if the target search query is "golf tops knit," the selection unit 42 selects search queries corresponding to each season, such as "spring," "summer," "autumn," and "winter," and combines each of them with the target search query.

[0063] Then, the selection unit 42 projects these target search queries and keywords combining each search query into a distributed representation space, and selects images with similar feature vectors.

[0064] The generating unit 43 generates a sample image of the thumbnail image. For example, the generating unit 43 generates a sample image in which the product of the product image of the target product is applied to the composition of the image selected by the selecting unit .

[0065] For example, the generation unit 43 generates a sample image using various image generation AIs. The generation unit 43 also superimposes an emphasis mark A1 (see FIG. 4) or the like that emphasizes a symbolic portion of the target search query on the sample image.

[0066] In addition, the generation unit 43 generates a sample image including items related to the target search query. For example, if the target search query includes "golf", the generation unit 43 selects images related to various golf equipment such as golf clubs, golf shoes, and golf gloves from the image information storage unit 31, and generates a sample image including these images.

[0067] The providing unit 44 provides (suggests) information regarding the composition of the thumbnail image of the target product corresponding to the target search query to the seller. For example, the providing unit 44 provides the image selected by the selecting unit 42 as the composition of the thumbnail image of the target product.

[0068] The providing unit 44 also provides a sample image of the thumbnail image in which the product of the product image is applied to the composition of the thumbnail image. The providing unit 44 also proposes a plurality of reference images corresponding to the target search query, and proposes a sample image corresponding to the reference image selected by the seller. The providing unit 44 may also select one reference image corresponding to the target search query (a reference image corresponding to an image vector Ia that is most similar to the product image and the target search query) and propose a sample image corresponding to the reference image.

[0069] Here, a series of processes from providing a reference image to providing a sample image will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example of an image transition in information processing according to an embodiment. As shown in Fig. 8, first, a first page P1 is displayed on the seller terminal 100, and the seller can specify a product image Is of a target product and a target search query qs on the first page P1.

[0070] The above-mentioned selection unit 42 combines a plurality of search queries with different styles and seasonal senses with the target search query qs, and then projects each combination into a distributed representation space to select reference images with similar feature vectors.

[0071] As a result, the second page P2 is displayed on the seller terminal 100. As shown in Fig. 8, the second page P2 displays the target search query qs and reference images It1 to It4 corresponding to combinations of each search query together with each search query.

[0072] The seller can select the reference image It of his / her choice from the second page P2, and the generation unit 43 generates a sample image Ic of a thumbnail image of the target product based on the reference image It specified by the seller and the product image Is specified by the seller on the first page P1.

[0073] As a result, the third page P3 including the sample image Ic generated by the generation unit 43 is displayed on the seller terminal 100. Through this series of processes, the seller can confirm the composition of the thumbnail image in the style that he or she desires. In this way, the information processing device 1 first presents the reference image It to the seller, and then generates a sample image based on the reference image It specified by the seller.

[0074] This allows the information processing device 1 to propose a more abstract thumbnail image composition for matching the target product with each search query. In addition, the providing unit 44 also provides an emphasis mark A that emphasizes the symbolic portion of the target search query, a histogram H that lists search queries that correspond to the sample image Ic, and the like, as shown in FIG.

[0075] This allows the information processing device 1 according to the embodiment to propose an appropriate composition of thumbnail images corresponding to the target search query.

[0076] The information processing device 1 may highlight the portion of the product image Is displayed on the first page P1 that does not correspond to the target search query qs. For example, the portion of the product image Is that does not correspond to the target search query qs can be determined based on the similarity between the feature vector of the target search query and the feature vector of each of the areas into which the product image Is is divided.

[0077] [3. Processing flow] Next, a processing procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 9. Fig. 9 is a flowchart showing an example of the processing procedure of the information processing according to the embodiment. The processing shown below is repeatedly executed by the information processing device 1 at a predetermined cycle each time a search query is acquired.

[0078] 9, the information processing device 1 receives a target product and a target search query from a seller (step S101). Next, the information processing device 1 projects the target product and the target search query into the same distributed representation space (step S102).

[0079] Next, the information processing device 1 selects a reference image based on the feature vectors of the target product and the target search query projected into the distributed representation space (step S103). Next, the information processing device 1 generates a sample image that serves as a sample of the composition of a thumbnail image of the target product from the product image of the target product and the reference image (step S104).

[0080] Next, the information processing device 1 proposes (provides) the generated sample image to the seller (step S105), and ends the process.

[0081] 4. Modifications In the above embodiment, the information processing device 1 proposes the composition of thumbnail images related to products, but the present invention is not limited to this. For example, the present invention may be applied to the case where thumbnail images of various web services such as SNS and video sites are proposed.

[0082] 5. Effects The information processing device 1 of the embodiment includes a receiving unit 41 that receives a target product and a target search query from a seller, and a providing unit 44 that provides the seller with a composition of a thumbnail image of the target product corresponding to the target search query, by utilizing the relevance between the search query and the product image estimated based on the user's behavioral history (search history, browsing history, purchase history).

[0083] The providing unit 44 also provides the composition of the thumbnail image by utilizing a model that has learned the relevance between the search query and an image selected by the user in the search results based on the search query. More specifically, the providing unit 44 proposes the composition of the thumbnail image by utilizing a learning model that has learned the relationship between an image (e.g., a thumbnail image) clicked by the user among images of products included in the search results based on the search query and the search query, and the relationship between an image (e.g., a thumbnail image) that led to a purchase by the user among images of products included in the search results based on the search query.

[0084] The receiving unit 41 also receives a product image of a target product from a seller, and the providing unit 44 provides a sample image of the thumbnail image in which the product of the product image is applied to the composition of the thumbnail image. The providing unit 44 also provides a plurality of reference images corresponding to the target search query, and provides a sample image corresponding to the reference image selected by the seller.

[0085] The providing unit 44 also provides the sample image with an emphasis on a symbolic portion of the target search query. The providing unit 44 also provides a list of search queries corresponding to the sample image. The providing unit 44 provides a list of search queries, and when a seller selects a search query from the list, the providing unit 44 provides a sample image corresponding to the search query.

[0086] By using any one or a combination of the above-described processes, the information processing device according to the present application can provide a composition of thumbnail images corresponding to a search query.

[0087] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 10. Fig. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0088] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0089] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0090] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 10, the output devices and the input devices are collectively referred to as "input / output devices") via an input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0091] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0092] For example, when the computer 1000 functions as an information processing device according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0093] [7. Other] Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. The above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0094] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0095] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0096] For example, the above-mentioned information processing device may be realized using multiple server computers, and depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0097] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0098] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0099] 1. Information processing device 2. Communications Department 3 Storage section 4. Control section 10 User terminal 31 Image information storage unit 32 Keyword information storage unit 33 Model Memory Section 41 Reception 42 Selection section 43 Generation part 44 Providing Department 100 seller terminals

Claims

1. A reception unit that receives a target product and a target search query from a seller; a providing unit that provides the seller with a composition of a thumbnail image of the target product corresponding to the target search query by utilizing a relevance between the search query and an image of the product estimated based on the user's behavior history; An information processing device comprising:

2. The providing unit is Providing a composition of the thumbnail image using a model that has learned associations between the search query and images selected by a user in search results for the search query.

2. The information processing apparatus according to claim 1,

3. The reception unit is receiving a product image of the target product from the seller; The providing unit is To provide a sample image of the thumbnail image in which the product of the product image is applied to the composition of the thumbnail image.

2. The information processing apparatus according to claim 1,

4. The providing unit is Providing the seller with a plurality of reference images corresponding to the target search query, and providing the example images corresponding to the reference images selected by the seller.

4. The information processing apparatus according to claim 3,

5. The providing unit is providing the sample image with an emphasis on a symbolic portion of the target search query; 5. The information processing apparatus according to claim 4,

6. The providing unit is Providing a list of the search queries corresponding to the sample images.

4. The information processing apparatus according to claim 3,

7. The providing unit is Providing a list of the search queries, and when the seller selects the search query from the list, providing the sample image corresponding to the search query.

4. The information processing apparatus according to claim 3,

8. The providing unit is providing said example images containing items related to said target search query; 4. The information processing apparatus according to claim 3,

9. 1. A computer-implemented information processing method, comprising: A receiving step of receiving a designation of a target product and a target search query from a seller; a providing step of providing the seller with a composition of thumbnail images of the target product corresponding to the target search query by utilizing a relevance between the search query estimated based on the user's behavior history and an image of the product; 13. An information processing method comprising:

10. A receiving step of receiving a target product and a target search query from a seller; a provision step of providing the seller with a composition of thumbnail images of the target product corresponding to the target search query by utilizing a relevance between the search query and a product image estimated based on the user's behavior history; An information processing program characterized by causing a computer to execute the above.

Images